US Pat. No. 11,113,701

CONSUMER PROFILING USING NETWORK CONNECTIVITY

FUJITSU LIMITED, Kawasak...


1. A method of profiling users of facilities, each facility having access points for mobile devices of the users geographically distributed within the facility, and transaction points for the users to conduct transactions, the method comprising:at the access points, detecting the mobile devices by negotiating possible connections with the mobile devices and collecting information identifying the mobile devices but not the users, and generating time-stamped location reports of the mobile devices in real time;
at the transaction points, generating time-stamped transaction reports of transactions made by the users in real time;
at a server linked to the access points and the transaction points, generating correlated reports by correlating in time the time-stamped location reports of the mobile devices with the time-stamped transaction reports and creating a probabilistic link between a specific mobile device of a specific anonymous user and a specific transaction by assuming that, based on the correlated reports, a specific transaction made at a transaction point at substantially a same time as a specific mobile device was detected in a vicinity of the transaction point was made by the specific anonymous user of the specific mobile device;
at the server, building a probabilistic personalized user profile of the specific anonymous user without access to identity information of the specific anonymous user, based on the probabilistic link;
updating the probabilistic personalized user profile when the specific anonymous user performs a transaction at a transaction point in one of the facilities; and
at the server, generating, from the probabilistic personalized user profile, a personalized offer targeted at and provided to the specific anonymous user.

US Pat. No. 11,113,700

METHOD AND APPARATUS FOR ASSOCIATING DEVICE USER IDENTIFIERS WITH CONTENT PRESENTATION AND RELATED EVENTS

Adobe Inc., San Jose, CA...


1. A method for using a mobile device to associate media content presentations with purchase-related events of a user of the mobile device, the method comprising:detecting by a software application executed by a mobile device, a plurality of presentation events, each presentation event indicating a connection between a user identifier linked to the mobile device and a presentation of a respective different media content presentation on one or more televisions, each media content presentation promoting a respective different product or service and provided by a respective different retailer, wherein the software application identifies each media content presentation by matching audio content emitted by one of the televisions and received via a microphone of the mobile device to stored audio data accessible by the software application;
transmitting, by the software application to a network server, a plurality of presentation event messages, each presentation event message identifying one of the presentation events and including the user identifier and a media content identifier of the media content presentation indicated by the presentation event;
transmitting, by the software application to the network server, a plurality of predefined event messages, each event message identifying one of a plurality of geofence areas encountered by the mobile device and the user identifier, each geofence area being at a respective different retail establishment, and wherein each geofence area is detected by a location-tracking system executed by the mobile device, and wherein each geofence area is defined by the respective different retailer;
associating, by an analytical application executed on the network server, each of the predefined event messages with one or more of the presentation event messages by matching the user identifier included in each of the predefined event messages with the user identifier included in each of the one or more presentation event messages; and
determining, by the analytical application, that an association between each of the predefined event messages and the one or more presentation event messages indicates whether the user viewing or listening to a selected one of the media content presentations visited the retail establishment of the retailer of the product or service promoted by the selected media content presentation and whether the user viewing or listening to the selected media content presentation visited one or more other retail establishment of one or more other retailers of products of services promoted by one or more others of the media content presentations.

US Pat. No. 11,113,699

OPEN REGISTRY FOR IDENTITY OF THINGS

Chronicled, Inc., San Fr...


1. A method of item identity verification using an item open registry, a mobile device, and a plurality of identity tags, the identity tags each storing a private key and a unique identifier and coupled to a separate one of a plurality of physical items, wherein the physical item is associated with a network accessible location and the network accessible location comprises a website, the method comprising: for each physical item of the plurality of physical items:storing, by the open registry, an entry of the physical item, wherein the entry comprises the unique identifier of the identity tag, a public key of the identity tag, an identifier of the network accessible location and a history of custodianship of the physical item, wherein the public key is associated with the private key stored on the identity tag coupled to the physical item;
broadcasting, by the identity tag, the unique identifier;
monitoring, by the mobile device, the identity tag and receiving, by the mobile device, the unique identifier of the identity tag;
transmitting, by the mobile device, the unique identifier to the open registry;
receiving, by the mobile device, the public key associated with the unique identifier from the open registry;
generating and transmitting, by the mobile device, a challenge message to the identity tag;
generating, by the identity tag, a digital signature by signing the challenge message with the private key;
sending, by the identity tag, the digital signature and the signed challenge message to the mobile device;
authenticating, by the mobile device, the physical item by verifying the digital signature;
retrieving, by the mobile device, the identifier of the network accessible location from the open registry using the unique identifier based on the verification of the digital signature; and
accessing and presenting, by the mobile device, the network accessible location of the physical item using the retrieved identifier of the network accessible location.

US Pat. No. 11,113,698

LINE-BASED CHIP CARD TAMPER DETECTION

Square, Inc., San Franci...


1. A payment reader for exchanging payment information with a chip card and for providing decoy data to a tamper device connected to a chip card interface of the payment reader, comprising:a chip card interface comprising at least a voltage interface, a reset interface, a clock interface,an input/output interface, a ground interface, and a programming interface;

a processing unit coupled to the chip card interface and configured to execute instructions;
a plurality of chip card lines coupled between the chip card interface and the processing unit, comprising:a voltage line coupled between the voltage interface and the processing unit;
a reset line coupled between the reset interface and the processing unit;
a clock line coupled between the clock interface and the processing unit;
an input/output line coupled between the input/output interface and the processing unit;
a ground line coupled between the ground interface and the processing unit; and
a programming line coupled between the programming interface and the processing unit; and

the input/output interface comprising:a reader communication circuit coupled to the input/output line, the reader communication circuit configured to operate at a first clock frequency;
a card communication circuit coupled to the input/output line, the card communication circuit configured to operate at a second clock frequency;

a memory having the instructions stored thereon and coupled to provide the instructions to the processing unit, wherein the instructions cause the processing unit to:transmit data over the input/output line with the card communication circuit at the second clock frequency;
read data from the input/output line with the reader communication circuit at the first clock frequency; and
transmit decoy data over the input/output line with the reader communication circuit after expiration of a first period for the first clock frequency and before an expiration of a second period for the second clock frequency.


US Pat. No. 11,113,697

METHOD AND APPARATUS FOR OFFLINE PAYMENT, SERVICE PROCESSING, AND PAYMENT PROCESSING

Advanced New Technologies...


1. A computer-implemented method for an offline service processing, comprising:establishing a communication connection between a service device and an end-user device, wherein both the service device and the end-user device are in an offline state;
receiving, by the end-user device through the communication connection established to the service device, service data sent by the service device;
generating, by the end-user device, a first service record based on the service data and account information of the end-user device;
sending, by the end-user device and through the communication connection, the first service record to the service device;
generating, by the service device, a second service record based on the first service record and the account information of the end-user device;
sending, by the end-user device, the first service record to a server when the end-user device is in an online state;
sending, by the service device, the second service record to the server when the service device is in an online state;
performing, by the server, service processing based on the first service record and the second service record; and
determining, by the server, based at least on a first amount, the account information of the end-user device, account information of the service device comprised in the first service record, a second amount, the account information of the end-user device, the account information of the service device comprised in the second service record, whether the first service record matches the second service record.

US Pat. No. 11,113,696

METHODS AND SYSTEMS FOR A VIRTUAL ASSISTANT

U.S. Bancorp, National As...


1. A method comprising:receiving, by a virtual assistant computing device, an indication that a transaction by a mobile device was completed;
determining, by the virtual assistant computing device, an event category of the transaction by:retrieving, from a database in a central server, calendar entries that are within a time frame before or after a time of the transaction or emails that contain words that match words of the transaction;
identifying parameters of the calendar entries or emails by parsing the calendar entries or the emails for key words;
determining a first potential event by feeding the parameters into a machine learning model;
transmitting the first potential event to the mobile device;
receiving, from the mobile device, an a first indication that the first potential event is incorrect;
responsive to receiving the first indication that the first potential event is incorrect, generating a training data set comprising the parameters and the first indication that the first potential event is incorrect;
training the machine learning model using the training data set;
after training the machine learning model, determining a second potential event by using the trained machine learning model;
transmitting the second potential event to the mobile device;
receiving, from the mobile device, a second indication that the second potential event is correct; and
responsive to receiving the second indication that the second potential event is correct, determining the event category of the transaction to be an event category of the second potential event;

storing, by the virtual assistant computing device, transaction data and a history of messages between the virtual assistant computing device and the mobile device in regards to the transaction in the central server;
determining, by the virtual assistant computing device and based on the determined event category, whether the transaction is in accordance with policy;
responsive to determining the transaction is in accordance with policy, generating, by the virtual assistant computing device, an expense report associated with the transaction, wherein generating the expense report includes:fetching, via an application programming interface (API) call, a template from an expense report system;
filling out the template in accordance with the stored transaction data; and
attaching the stored history of messages between the virtual assistant computing device and the mobile device in regards to the transaction and a receipt associated with the stored transaction data to the expense report; and

submitting, by the virtual assistant computing device, the generated expense report to the expense report system.

US Pat. No. 11,113,695

TOKEN-BASED DETERMINATION OF TRANSACTION PROCESSING RESOURCES

PAYPAL, INC., San Jose, ...


1. A method for token-based automatic transaction processing, the method comprising:receiving, by one or more electronic processors, a token request from a first transaction system, the token request for generating a token associated with a first user account;
in response to receiving the token request,generating, by the one or more electronic processors, the token that authorizes a use of an initial transaction resource at a second transaction system, and
generating, by the one or more electronic processors, transaction preferences that associate the token with a plurality of transaction resources at the second transaction system;

transmitting, by the one or more electronic processors, the token to the first transaction system for a use via the first transaction system;
receiving, by the one or more electronic processors, a transaction request for using the token for a first transaction;
in response to receiving the transaction request, processing, by the one or more electronic processors, the first transaction based on the token, a monetary balance of the first user account, and the transaction preferences, the processing the first transaction including determining whether to revise the use of the initial transaction resource to one or more other transaction resources;
linking, by the one or more electronic processors, a second user account at the first transaction system with the first user account at the second transaction system, wherein the linking comprises receiving an authorization, from the first transaction system, to change a default transaction resource, at the second transaction system, for a subsequent token; and
exchanging, in response to the linking and between the first transaction system and the second transaction system, registration and configuration information of the first user account and the second user account, the exchanging making the first user account and the second user account accessible at either the first transaction system or at the second transaction system.

US Pat. No. 11,113,694

AUTOMATED ANTI-MONEY LAUNDERING (AML) ALERTS INVESTIGATION AND DISPOSITION SYSTEM AND ASSOCIATED METHOD THEREOF

ENERGICA ADVISORY SERVICE...


1. A non-transitory computer readable medium comprising computer-readable instructions stored in a memory, which when executed by one or more processors enable:an alert generation unit to generate alert data representative of AML alert transactions of one or more entities through a financial institution, wherein the alert data comprise the plurality of alerts, transaction data, associated entity data, transaction scenarios, the plurality of predefined customizable rules, algorithms, risk ratings of the plurality of alerts, and meta data;
a storage server of an alert investigation system to receive the alert data from the alert generation unit;
a trigger schedule module of the alert investigation system to trigger a plurality of alerts of the alert data based on at least one of time instances and transaction events;
an alert pre-processing module of the alert investigation system to generate pre-processed alert data from the alert data, wherein the alert pre-processing module comprises a reconciliation module and a duplicate alerts removal module; and
an investigation module of the alert investigation system to receive the plurality of alerts of the pre-processed alert data, wherein the investigation module comprises a multivariate dynamic rule engine and a decision engine, wherein the multivariate dynamic rule engine is configured to execute the plurality of predefined customizable rules and the algorithms to process the plurality of alerts of the pre-processed alert data, and wherein the decision engine is configured to generate a plurality of decisions to categorize the plurality of alerts into the one or more disposition categories based on the plurality of predefined customizable rules, predefined scenarios data, and the algorithms, wherein an automated AML alerts investigation and disposition system comprises the alert generation unit and the alert investigation system.

US Pat. No. 11,113,693

SYSTEMS FOR DETECTING BIOMETRIC RESPONSE TO ATTEMPTS AT COERCION

CAPITAL ONE SERVICES, LLC...


1. A system comprising non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the system to:receive, from one or more biometric sensors of a user device, user-specific baseline stress data and user-specific baseline calm data, the user-specific baseline stress data being representative of biological information of a user being in a stressed state and the user-specific baseline calm data being representative of biological information of the user being in a calm state;
receive situational data from one or more biometric sensors including biological information associated with the user in response to detecting a trigger event associated with a potential transfer of funds;
responsive to determining that the received situational data is above a predetermined level of similarity to the user-specific baseline stress data, determine that a suspicious transaction is occurring; and
initiate one or more precautionary safety measures, the one or more precautionary safety measures comprising transmitting, to at least one of a camera and a microphone, instructions to begin recording; and confirm whether the suspicious transaction was a coerced transaction by:
transmitting a request for a confirmation of safety of the user for verification of whether a requested transfer of funds was coerced, the verification comprising user recitation of a security phrase;
receiving a received security phrase provided by the user and recorded by a microphone;
saving, via memory associated with the one or more processors, the received security phrase as recorded security data;
responsive to the recorded security data being determined to be within a predetermined level of similarity to stored voice data associated with a predetermined security phrase, determining that the requested transfer of funds is a voluntary transfer of funds, and
responsive to the recorded security data being determined to be outside the predetermined level of similarity to the stored voice data, determining that the requested transfer of funds is a coerced transfer of funds.

US Pat. No. 11,113,692

SECURE VERIFICATION OF CLAIMS

INTUIT, INC., Mountain V...


1. A computer-implemented method for verifying a claim associated with an online transaction, comprising:receiving, by operation of a processor, claim information for the claim, wherein the claim information includes an attribute characterizing a seller related to an online advertisement;
determining, by the processor, verification information associated with the claim information by accessing a plurality of accounts over a network, each account of the plurality of accounts providing an source of information characterizing the seller, wherein at least one of the plurality of accounts is associated with an application, and wherein the accessing is authorized in advance by the seller;
verifying, by the processor, the claim by confirming the claim information against the verification information;
once the claim is verified, generating, by the processor, a plurality of views of the verification information for presentation on a user interface, each view including a subset of the verification information, wherein the plurality of views includes at least a first view and a second view, wherein the subset included in the first view differs from the subset included in the second view, wherein each of the first view and the second view comprises a digitally-signed certificate
receiving, by the processor, a request from a computing device associated with a potential customer to access the verification information;
receiving, by the processor, authorization from the seller for the potential customer to access the second view but not to access the first view;
allowing, by the processor, based on the authorization, access by the potential customer to the second view; and
providing, by the processor, the second view to the computing device for display to the potential customer.

US Pat. No. 11,113,691

VOICE INTERFACE TRANSACTION SYSTEM USING AUDIO SIGNALS

American Express Travel R...


1. A method, comprising:generating, by a merchant computing device, a transaction request comprising a transaction amount and a merchant identifier;
generating, by the merchant computing device, an audio signal comprising a header soundwave configured to indicate to a transaction account holder device that the audio signal comprises an audio transaction signal, the header soundwave including a voice assistant awake word, and wherein the audio transaction signal comprises the transaction request;
playing, by the merchant computing device via a first voice assistant, the audio signal, wherein the transaction account holder device is configured to:
detect the header soundwave comprised in the audio signal, and
ingest the audio transaction signal by a second voice assistant in response to a passive listening detection of the voice assistant awake word in the header soundwave;
receiving, by the merchant computing device, a transaction authorization for the transaction request from a payment network associated with the transaction account holder device; and
completing, by the merchant computing device, the transaction request in response to receiving the transaction authorization from the payment network.

US Pat. No. 11,113,690

SYSTEMS AND METHODS FOR PROCESSING DATA MESSAGES FROM A USER VEHICLE

MASTERCARD INTERNATIONAL ...


1. A payment processor computing device for performing an electronic transaction initiated by a vehicle including a vehicle computing device, said payment processor computing device comprising one or more processors in communication with one or more memory devices, said payment processor computing device communicatively coupled to the vehicle computing device and to at least one merchant point-of-sale (POS) device, said payment processor computing device configured to:receive a registration secure token from a vehicle computing device, the registration secure token being unique to a combination of a cardholder and the vehicle associated with the cardholder and created during a registration process for initiating future electronic transactions, the vehicle computing device coupled to the vehicle, the registration secure token including:a tokenized account identifier, the cardholder having an account associated with the account identifier for use in processing electronic transactions;
a vehicle identifier unique to the vehicle associated with the cardholder; and
a biometric identifier associated with the cardholder, the biometric identifier generated by the vehicle computing device in response to receiving a first biometric input from a biometric input device connected to the vehicle computing device, wherein the first biometric input is stored in a memory device of the vehicle computing device;

store the registration secure token in the one or more memory devices;
receive an authorization request message associated with a payment transaction initiated by the cardholder using the vehicle computing device in communication with a first merchant POS device, the authorization request message sent by the vehicle computing device to said payment processor computing device via the first merchant POS device physically proximate to the vehicle computing device, the authorization request message including transaction data associated with the payment transaction and a transaction secure token, wherein the transaction secure token includes the tokenized account identifier, the vehicle identifier of the vehicle, and the biometric identifier, and wherein the transaction secure token is generated by the vehicle computing device in response to the vehicle computing device receiving a second biometric input from the biometric input device, the second biometric input substantially matching the first biometric input stored in the memory of the vehicle computing device;
authenticate the authorization request message by matching the transaction secure token to the registration secure token, the matching including (i) matching a first portion of the transaction secure token representing the tokenized account identifier and a second portion of the transaction secure token representing the vehicle identifier to a first portion of the registration secure token representing the tokenized account identifier and a second portion of the registration secure token representing the vehicle identifier to verify the payment account being used to initiate the payment transaction via the vehicle computing device is associated with the vehicle associated with the vehicle identifier and that the vehicle associated with the vehicle identifier is in proximity to the first merchant POS device at the time the payment transaction is initiated, and (ii) matching a third portion of the transaction secure token representing the biometric identifier to a third portion of the registration secure token representing the biometric identifier to verify a registered cardholder is initiating the payment transaction;
embed a matching indicator within the authorization request message, the matching indicator representing successful verification of the payment transaction based upon successful matching of the transaction secure token with the registration secure token; and
transmit the authorization request message with the embedded matching indicator to an issuer of the account for further processing, wherein, upon detection of the embedded matching indicator by the issuer, the embedded matching indicator is configured to indicate initial verification of the payment transaction has been performed by the payment processing computer device and cause expedited issuer authentication and authorization of the payment transaction.

US Pat. No. 11,113,689

TRANSACTION POLICY AUDIT

SAP SE, Walldorf (DE)


1. A computer-implemented method comprising:receiving receipt data associated with a request associated with a first policy-enforcer entity, wherein the receipt data includes tokens extracted from at least one receipt;
identifying policy questions associated with the first policy-enforcer entity, wherein each policy question is associated with at least one policy question answer, and wherein each policy question answer corresponds to a conformance or a violation of a policy selected by the first policy-enforcer entity, wherein the identified policy questions associated with the first policy-enforcer entity include a first set of policy questions specific to the first policy-enforcer entity and a second set of policy questions common to multiple policy-enforcer entities, wherein the multiple policy-enforcer entities include the first policy-enforcer entity and at least a second policy enforcer entity that is a different entity than the first-policy enforcer entity; and
for each respective policy question in the identified policy questions:identifying a machine learning policy model for the respective policy question based on a mapping associated with the first entity that maps policy questions to machine learning policy models, wherein the machine learning policy model is trained based on historical determinations of policy question answers for the respective policy question for historical receipt data, wherein the historical determinations of policy question answers includes different historical determinations for different policy-enforcer entities of the multiple policy-enforcer entities, and wherein the machine learning policy model includes, for each policy question answer, receipt data features that correspond to the policy question answer;
using the machine learning policy model to automatically determine a selected policy question answer to the respective policy question by comparing features of the extracted tokens to respective receipt data features of the policy question answers that are included in the machine learning policy model; and
in response to determining that the selected policy question answer corresponds to a policy violation, generating an audit alert.


US Pat. No. 11,113,688

SYSTEMS AND METHODS FOR MOBILE WALLET PROVISIONING

Wells Fargo Bank, N.A., ...


1. A method performed by an initiating device associated with a financial institution, the method comprising:receiving, by the initiating device associated with and coupled to a computing system of the financial institution, a request to provision a payment account to a mobile wallet associated with a mobile device that is separate and distinct from the initiating device;
receiving, by the initiating device via a short range communication with the mobile device, address information uniquely identifying the mobile wallet and authentication data regarding a user, the authentication data comprising biometric information associated with the payment account; and
in response to authenticating the biometric information, initiating, by the initiating device, provisioning of the payment account to the mobile wallet by sending the address information and account information to a token service provider that is separate from the initiating device, wherein the address information comprises a return address identifying a network location of the mobile wallet such that the return address is usable to transmit a payment token directly to the mobile device via a network different from the short range communication.

US Pat. No. 11,113,687

SYSTEM FOR PERFORMING CROSS CARD AUTHENTICATION USING WALLET TRANSACTION AUTHENTICATION HISTORY

MASTERCARD INTERNATIONAL ...


1. A method comprising:performing a first transaction using a first payment account, the first transaction including a successful authentication of a holder of the first payment account, the first transaction performed using a first digital wallet;
storing a record of the first transaction, the stored record including an indication that the successful authentication occurred;
receiving a request for a second transaction using a second payment account held by the holder of the first payment account, the second transaction different from the first transaction, the second transaction performed using a second digital wallet different from the first digital wallet;
detecting the indication of the successful authentication in the stored record of the first transaction;
applying a rule to the second transaction, the rule directing that the indication of the successful authentication is relevant to the second transaction in cases where a third payment account is held in both the first digital wallet and the second digital wallet;
determining that the rule is satisfied with respect to the second transaction; and
in response to the determining step, completing the second transaction without requiring authentication of the account holder.

US Pat. No. 11,113,686

SYSTEM AND METHOD FOR A MOBILE WALLET

Wells Fargo Bank, N.A., ...


1. A computer system comprising one or more processors storing non-transitory computer readable media containing code, which, when executed is configured to cause the computer system to:receive information related to a redemption opportunity;
store the information related to the redemption opportunity in a mobile wallet of a user;
detect a geographic location of a mobile device running the mobile wallet of the user when the mobile device is in a sleep mode of operation;
compare the detected geographic location of the mobile device to a geographic location of a merchant at which the redemption opportunity may be redeemed;
generate, on the mobile device of the user, an alert that is displayed by the mobile device while the mobile device is in the sleep mode of operation when the detected geographic location of the mobile device is within a predetermined vicinity of the geographic location of the merchant, wherein the alert includes a message comprising an image overlaid on a map indicating the geographic location of the merchant relative to the detected geographic location of the mobile device; and
provide, by the mobile device of the user, at least one of a vibration or a sound to accompany the alert while the mobile device is still in the sleep mode of operation.

US Pat. No. 11,113,685

CARD ISSUING WITH RESTRICTED VIRTUAL NUMBERS

CAPITAL ONE SERVICES, LLC...


1. A system comprising:(i) an apparatus comprising one or more processors operable to execute stored instructions that, when executed, cause the one or more processors to:
receive, via a software application, instruction or a selection from a user to generate a virtual card number;
determine whether one or more restrictions are associated with the generation of the virtual card number, wherein the one or more restrictions are input, set, or specified by the user via the software application;
establish near field communication (NFC) with a first contactless card via NFC circuitry, the first contactless card being tapped to the apparatus;
in response to the NFC established with the first contactless card, receive one or more cryptograms from the first contactless card, wherein the one or more cryptograms includes at least a first customer identifier;
send the one or more cryptograms to one or more first remote computing devices and receive an indication from the one or more first remote computing devices of successful authentication of the user;
provide, based on the successful user authentication, the one or more restrictions to the one or more remote computing devices and receive the virtual card number having the one or more restrictions from the one or more remote computing devices, the virtual card number funded with a predefined amount of money from a user account associated with the first contactless card; and
establish NFC with a second contactless card different from the first contactless card via the NFC circuitry, the second contactless card being tapped to the apparatus; and
in response to the NFC established with the second contactless card, write the virtual card number to the second contactless card by providing the card virtual number with the one or more restrictions as an NFC data exchange format (NDEF) tag only to a first applet of the second contactless card;
(ii) the one or more remote computing devices comprising one or processors operable to execute stored instructions that, when executed, cause the one or more processors to:
receive and perform decryption on the one or more cryptograms;
authenticate the user based on the first customer identifier;
send the indication of the successful authentication of the user to the apparatus;
receive the one or more restrictions; and
generate and provide the virtual card number to the apparatus; and
(iii) the second contactless card comprising NFC circuitry and memory, the memory comprising the first and second applets, and
wherein the first applet is different from a payment applet, and
wherein the first and second applets reside in a same security domain of the memory of the second contactless card and communicate with each other via a secure communication tunnel.

US Pat. No. 11,113,684

DEVICE, SYSTEM, AND METHOD FOR CREATING VIRTUAL CREDIT CARD

Tencent Technology (Shenz...


1. A social network application and exchange server for providing social network accounts to users comprising a data storage containing real-name user information, a memory containing instructions, and a processor, wherein the processer, when executing the instructions, is configured to cause the social network application and exchange server to create an exchange account bound to a social network account of a user in the social network application server and a virtual credit card bound to the exchange account by causing the social network application server to:receive, via the social network account of the user, user real-name ID information of the user from a user interface of a social network application corresponding to the social network application and exchange server and running on a client terminal device;
send the user real-name ID information to a second server, for use by the second server for detecting if a credit card account associating with the user real-name ID information was previously issued and is saved in the second server;
receive an identity of a validation terminal device sent from the second server in response to determining that a credit card account associated with the user real-name ID information was previously issued, wherein the validation terminal device is different from the client terminal device;
perform validation by sending a validation code to the validation terminal device according to the received identity of the validation terminal device, receiving a second code entered by a user into the client terminal device wherein the second code is determined by the user by obtaining the validation code from the validation terminal device, and determining that the validation is successful when the validation code matches the second code; and
upon determining that the validation is successful:send an indicator of successful validation to the second server to prompt the second server to create a virtual credit card account separate from and independent of the credit card account previously issued;
send user historical social data of the user including at least one of historical online time, historical social network chatting time, historical email data, and historical social network login data to the second server for the second server to generate a credit limit for the virtual credit card account;
receive the virtual credit card account and the credit limit;
open a new electronic exchange account associated with the received user real-name ID information, wherein the new electronic exchange account has a binding relationship with the social network account;
create a binding relationship between the virtual credit card account and the new electronic exchange account; and
conduct a transaction using the virtual credit card account via the binding relationship on behalf of the new electronic exchange account from the user interface provided by the social network application.


US Pat. No. 11,113,683

DISPLACED SCANNER STATUS INDICATOR

NCR Corporation, Atlanta...


1. A method, comprising:detecting, by a scanner, an item passing by a scan window of the scanner during a transaction;
determining, by the scanner, whether the item was identified by the scanner for processing with the transaction; and
selectively activating or deactivating, by the scanner, at least one light visible within a field-of-view of an overhead security camera as an indication for the determining, where the at least one light visible within the field-of-view of the overhead security camera is situated on a terminal status pole associated with a terminal performing the transaction and having the scanner, wherein the scanner comprises a peripheral connection to the at least one light visible within the field-of-view of the overhead security camera and the scanner controls the at least one light during the transaction, wherein the at least one light when illuminated is visible to the overhead security camera but not visible to customers from the terminal status pole, wherein the at least one light when illuminated does not interfere with existing lights associated with the terminal status pole and the existing lights are visible to the customers from the terminal status pole.

US Pat. No. 11,113,682

CLOUD-BASED TRANSACTION PROCESSING

Tempus Technologies, Inc....


1. A cloud-based server to facilitate a payment transaction, the server comprising:a database having stored thereon pairing relationships between a plurality of peripheral devices and a plurality of payment user interfaces (UIs), wherein the pairing relationships comprise associations between respective peripheral devices of the plurality of peripheral devices and respective payment user UIs of the plurality of payment UIs, wherein at least a portion of the associations between respective peripheral devices of the plurality of peripheral devices and respective payment user UIs of the plurality of payment UIs are based on peripheral IDs that uniquely identify respective peripheral devices and identifiers that identify respective payment UIs;
a processor;
a memory coupled to the processor and having stored therein a plurality of instructions that, when executed, cause the server to:receive a transaction request from a requesting payment UI of the plurality of payment UIs including transaction information corresponding to a payment transaction;
determine a paired peripheral device of the plurality of peripheral devices corresponding to the requesting payment UI based on one or more pairing relationships in the database to establish a cloud-based virtual connection between the paired peripheral device and the requesting payment UI, thereby decoupling a need for a physical connection between a payment node on which the requesting payment UI is implemented and the paired peripheral device of the plurality of peripheral devices, wherein a display on which the requesting payment UI is to be displayed and paired peripheral device are local to each other, but geographically remote from the cloud-based server;
request payment information from the paired peripheral device of the plurality of peripheral devices based on the transaction information received from the requesting payment UI;
receive payment information from the paired peripheral device of the plurality of peripheral devices;
associate the transaction information with the payment information to create a payment request; and
providing the payment request to a payment processing system.


US Pat. No. 11,113,681

CLOUD-BASED TRANSACTION PROCESSING

Tempus Technologies, Inc....


1. A cloud-based server to facilitate a payment transaction, the cloud-based server comprising:a processor;
a memory coupled to the processor and having stored therein a plurality of instructions that, when executed, cause the server to:
pair a payment user interface (UI) that guides a user through payment transactions with a peripheral device to receive payment information for payment transactions, wherein to pair the payment UI with the peripheral device comprises:
registering the peripheral device in a database as a function of a peripheral ID that uniquely identifies the peripheral device;
registering the payment UI in the database as a function of a pair request that identifies the payment UI based on a one or more of a payment node identifier (ID), a payment node certificate, a payment UI type indicator, a pair identifier (UI), or a payment UI identifier (UIID); and
associating the peripheral device and the payment UI in the database; receive transaction information corresponding to a payment transaction; receive payment information from the peripheral device;
associate the transaction information with the payment information to create a payment request;
provide the payment request to a payment processing system;
wherein the cloud-based server is to pair the payment UI and the peripheral device over the Internet to establish a cloud-based virtual connection between the payment UI and the peripheral device to establish communications between the payment UI and the peripheral device, thereby decoupling a need for a physical connection between a payment node on which the payment UI is implemented and the peripheral device; and
wherein the cloud-based server is geographically remote from the peripheral device, which is in the same facility as a display on which at least a portion of the payment UI is to be presented.

US Pat. No. 11,113,680

SELF-SERVICE CHECKOUT COUNTER CHECKOUT

Advanced New Technologies...


1. A computer-implemented method for self-service checkout, comprising:obtaining, by using a camera, an image, wherein the image is of at least one product placed on a checkout counter;
performing image segmentation on the image to obtain at least one image region;
identifying a product code included in a code region in an image region of the at least one image region;
determining that a product category of a product associated with the product code fails to be identified;
in response to determining that the product category fails to be identified, determining the product category by using an object detection model obtained by pre-training using labeled training sample images, each labeled training sample image comprising a rectangle that frames the product code to label the code region, wherein the object detection model generates a candidate image region in the image, performs target identification within the candidate image region, performs bounding box regression in the candidate image region, and corrects the code region by using a perspective transformation relative to position markers to obtain a corrected code region, and determines the product category based on the corrected code region; and
determining a price of the product based on the product category.

US Pat. No. 11,113,679

METHOD AND SYSTEM FOR CARDLESS USE OF AN AUTOMATED TELLER MACHINE (ATM)

Mastercard International ...


1. A computer-implemented method for cardless use of an automated teller machine (ATM) by a user, the method implemented using a computer system comprising a server, the server including at least one processor in communication with a database, the database storing a user profile of the user and stored ATM information, the stored ATM information identifying a plurality of ATMs, the method comprising:receiving, by the server from a user device of the user, a request to log on to a computer application, the request including at least one security feature submitted by the user;
granting, by the server, access by the user device to the computer application in response to verifying that the submitted at least one security feature matches at least one profile security feature stored in the user profile;
receiving, by the server, ATM information submitted by the user device via the computer application, the ATM information identifying a candidate ATM, wherein the candidate ATM is not associated in the database with the user profile;
identifying, by the server, the candidate ATM by comparing the submitted ATM information to the stored ATM information;
receiving, by the server from the user device of the user, a control element indicating a request for a cardless service type of a plurality of cardless service types to be accessed at the candidate ATM;
determining, by the server, that the user is authorized to access the cardless service type of the plurality of cardless service types at the candidate ATM based on the control element;
generating and transmitting, by the server to the user device, a first onetime password (OTP) for the user to enter at the candidate ATM in response to determining that the user is authorized to access the cardless service type of the plurality of cardless service types at the candidate ATM;
receiving, by the server, a second OTP entered into the candidate ATM;
verifying, by the server, that the first OTP matches the second OTP; and
in response to the verification, authorizing, by the server, access by the user to at least one service associated with the cardless service type of the plurality of cardless service types available through the candidate ATM, without use of a card.

US Pat. No. 11,113,678

SYSTEMS CONFIGURED TO MANAGE USER-RELATED EXTERNAL PARTY-ACTIVITY SOFTWARE OBJECTS BY USING MACHINE-READABLE INDICIA AND METHODS OF USE THEREOF

Capital One Services, LLC...


1. A method, comprising:receiving, by a first server associated with an entity, from a computing device associated with an application end user, a first request to link a third-party digital service of a second server associated with a third-party entity to a digital profile of the application end user associated with the entity;
wherein the first request comprises at least one identifying attribute to identify the application end user and a third-party attribute to identify the third-party entity;
receiving, by the first server, from the application end user, a second request for accessing at least one user-related external party-activity software object via the first server by using machine-readable indicia;
importing, by the first server, the at least one user-related external party-activity software object associated with the machine-readable indicia from the second server to the first server;
associating, by the first server, the at least one user-related external party-activity software object with the digital profile based at least in part on the link;
recognizing, by the first server, electronic content represented by the at least one user-related external party-activity software object based at least in part on the at least one identifying attribute, the third-party attribute and the digital profile;
identifying, by the first server, data fields in the at least one user-related external party-activity software object based at least in part on the electronic content;
auto-populating, by the first server, the at least one user-related external party-activity software object with user data from the digital profile based at least in part on the data fields;
generating, by the first server, a user interface including the at least one user-related external party-activity software object based on the machine-readable indicia;
wherein the at least one user-related external party-activity software object requires the user to complete at least one activity associated with the third-party entity and is displayed within the user interface without the computing device associated with the application end user communicating with the second server associated with the third-party entity;
receiving, by the first server, from the computing device, via the user interface, input data from the application end user to add to the at least one user-related external party-activity software object; and
transmitting, by the first server, the input data and the user data from the digital profile, via the at least one user-related external party-activity software object, to the second server to complete the at least one activity.

US Pat. No. 11,113,677

DATA PROCESSING USING PROOF-OF-TRANSFER

Hiro Systems PBC, New Yo...


1. A computing device of a decentralized network for selecting a first miner device of one or more miner devices to create a new block, the computing device comprising:a network interface configured to couple the computing device to the decentralized network, wherein the decentralized network comprises a base chain and a virtual chain, and wherein blocks in the virtual chain are anchored to blocks in the base chain;
a hardware processor; and
a non-transitory computer readable storage medium storing program instructions for execution by the hardware processor in order to cause the computing device to:store data that indicates creation of a first block in the virtual chain;
in a prepare phase corresponding to a first set of blocks on the base chain:identify the first block as an anchor block in a virtual chain;

during a reward phase corresponding to a second set of blocks on the base chain, wherein the second set of blocks are created after the first set of blocks:(i) determine a set of reward addresses to receive at least some cryptocurrency in a plurality of cryptocurrency associated with the base chain, wherein the set of reward addresses are utilized in a consensus algorithm;
(ii) determine that the first miner device submitted a block commit transaction that references a second block in the virtual chain that descends from the anchor block;
(iii) store data indicating that first cryptocurrency in the plurality of cryptocurrency associated with the base chain is transferred from an address of the first miner device to at least one reward address in the set of reward addresses in response to the determination; and
(iv) perform a single-leader sortition that results in a selection of the first miner device to create the new block in the virtual chain based at least in part on the block commit transaction.



US Pat. No. 11,113,676

BLOCK MINING METHODS AND APPARATUS

Top Galore Limited, Tort...


1. A method for mining a block, comprising a block header, as a function of a predetermined hash function applied on the block header, the predetermined hash function comprising an expansion operation and a compression operation, the method comprising the steps of:retrieving, by a processing system comprising a processor and memory, a plurality of transactions associated with the block from a ledger stored on a server of a decentralized network, the processing system comprising a single shared expander and a plurality of compressor entities, each being implemented as hardware components in an application specific integrated circuit;
determining, by the processing system, a plurality of candidate roots from the received plurality of transactions associated with the block, each candidate root including a predetermined pattern;
developing, by a mid-state generator entity of the processing system, m mid-states, each mid-state being developed from a first portion of one of the plurality of candidate roots, the mid-state generator developing a new mid-state of the m mid-states every compressor entity pipe clock, with each mid-state of the m mid-states being passed down a compressor entity chain at the pipe clock rate;
distributing the determined plurality of m mid-states to a beginning stage of the plurality of compressor entities;
performing, by the single shared expander of the processing system using an input of a message and a nonce, the expansion operation on a second portion of each of the plurality of candidate roots to produce a message schedule, the message schedule comprising a plurality of message schedule elements, the single shared expander being provided by a single shared rolled message expander entity;
distributing the message schedule to the plurality of compressor entities via the single shared expander;
delaying delivery of the plurality of m mid-states to a final stage of the plurality of compressor entities using a FIFO having a number of stages, the number of stages corresponding to the plurality of message schedule elements of the message schedule;
for each of the m mid-states, performing, by one of a plurality of compressors of the processing system, the compression operation on a combination of one of the m mid-states and the message schedule, the plurality of compressors being communicatively coupled to the single shared expander and receiving the message schedule from the single shared expander, the compression for each of the m mid-states producing a respective one of m results;
identifying, by the processing system, a block solution from the m results by comparing each of the m results to a target; and
providing, by the processing system, the block solution to the ledger stored on the server.

US Pat. No. 11,113,675

UNIFIED TRANSACTION SERVICES FOR MULTI-TENANT ARCHITECTURES

PayPal, Inc., San Jose, ...


1. A method for using unified identity services in a multi-tenant architecture system, the method comprising:receiving a request, at a first service provider, to provide a first transaction service for a user;
accessing a first representation of the first service provider in a first hierarchical data structure, the first hierarchical data structure being managed by a second service provider, the second service provider managing a user identity of the user;
determining that a second hierarchical data structure, that is managed by the first transaction service, does not include one or more transaction resources that are associated with the first representation in the first hierarchical data structure;
generating the resource representation at the second service provider without linking to the first service provider;
determining, based on the first representation, that transaction resources required for completion of the first transaction service are provided at the second service provider using the resource representation; and
responsive to determining that the transaction resources are accessible at the first service provider, accessing, at the first service provider, the transaction resources via the resource representation.

US Pat. No. 11,113,674

METHOD AND USER DEVICE FOR MONITORING A USE CONDITION

Motorola Mobility LLC, C...


1. A method for monitoring a condition of a user device, the method comprising:determining a baseline level of performance for each of one or more elements of the device including a determined replacement threshold level;
triggering a running of a diagnostic in addition to an expected periodic diagnostic, which determines the current performance of at least some of the one or more elements for which a baseline level of performance has been determined, wherein the running of the diagnostic in addition to the expected periodic diagnostic includes a diagnostic determination triggered by a detected non-standard use condition; and
comparing the current performance of the at least some of the one or more elements to the determined baseline level performance for the respective ones of the one or more elements of the user device; and
wherein when the determined current performance of at least one of the one or more elements falls below the determined replacement threshold level, notifying the user of a need for service of the user device.

US Pat. No. 11,113,672

COMPUTER SUPPORT FOR MEETINGS


1. A method to provide computer support for a meeting of invitees, the method comprising:accessing one or more sensory data streams providing digitized sensory data responsive to an activity of one or more of the invitees during the meeting, the one or more sensory data streams including at least one audio stream and a video stream;
subjecting the at least one audio stream to phonetic and situational computer modeling to recognize a sequence of words in the at least one audio stream;
assigning each word of the sequence of words to an invitee based at least in part on an analysis of image data from the video stream;
subjecting the sequence of words to semantic computer modeling by a machine-learning model to recognize a sequence of directives in the sequence of words, each directive associated with at least one invitee or other individual;
releasing one or more output data streams based on the sequence of directives, the one or more output data streams including one or more notifications comprising a list of directives recognized by the machine-learning model;
receiving an edited list of directives actually discussed during the meeting; and
refining the machine-learning model based on the edited list of directives.

US Pat. No. 11,113,671

METHOD AND SYSTEM FOR UPDATING MESSAGE THREADS

BlackBerry Limited, Wate...


1. A server system, the server system comprising:a processor; and
a memory coupled to the processor, the memory including instructions which, when executed, cause the processor to:display a compose screen for composition of a reply to a message and an indicator associated with the message;
detect arrival of a new message; and
while the compose screen is displayed:in response to a determination that the new message belongs to a message thread to which the message belongs, modify the indicator based on the new message.



US Pat. No. 11,113,670

SYSTEM AND METHOD FOR AUTOMATIC PROCESS ERROR DETECTION AND CORRECTION

CONDUENT BUSINESS SERVICE...


1. A method for detecting an error in a business process via an exchange of email messages, comprising:receiving, by a processor of a business process analysis server (BPAS) that receives all email messages for analysis, an email, wherein the email includes an address of the BPAS that is automatically added to each email that is created at an endpoint device of a user and a recipient email address when the email is created at the endpoint device, wherein the address of the BPAS is included in a carbon copy field or a blind carbon copy field of the email;
analyzing, by the processor, the email to determine at least one feature, wherein the at least one feature comprises a keyword within text from the email and a role associated with each email address in the email found from a company directory;
determining, by the processor, the business process based on the role associated with each email address and the keyword within the text in the email using a logistic regression model, the logistic regression model comprising,




where P is a business process that is identified based upon a given process p and a message thread prefix m1: from a training data set of pre-defined business processes and associated features that are known, ? is a vector of learned parameters from a thread of the emails, T, used to train the logistic regression model and, ? is a fixed dimension feature vector function of the given process p and the message thread prefix m1:;
determining, by the processor, one or more variables that is associated with activities associated with the business process based on analysis of the text within the email, wherein the analysis deploys a conditional random field model for a word-label sequence of the email of an email thread;
detecting, by the processor, the error in the business process associated with the email based on at least one variable of the one or more variables associated with the business process, wherein the error comprises at least one of: a role anomaly, an information anomaly or a workflow anomaly, wherein the detecting comprises:comparing, by the processor, the activities and values of the one or more variables of the activities of the business process to known activities and associated variables of the business process; and
determining, by the processor, that a value of the at least one variable of the one or more variables of the activities is different than a value of a corresponding variable of the associated variables of the known activities; and

generating, by the processor, an alert email in response to the error that is detected, wherein the alert email requests a correction to the at least one variable to complete the business process, wherein the alert email is generated by the BPAS and addressed only to a user that has a particular role that is responsible for providing correct information for the at least one variable that caused the error in the business process, wherein the user is missing from a thread of emails associated with the business process.

US Pat. No. 11,113,669

MANAGING EMPLOYEE COMPENSATION INFORMATION

The PNC Financial Service...


1. An apparatus for managing compensation information of an employee of an organization, the apparatus comprising:a computer processor programmed for executing computer-readable instructions included within a plurality of modules and a plurality of data storage media operatively associated with the computer processor, wherein:each module is configured to generate a graphical user interface enabling at least one user to issue commands to the apparatus or to access data stored within the apparatus;
each module is provided with at least one indicia, each indicia configured to actuate a display when selected;
the apparatus is configured to provide a communication network to streamline information flow and orchestrate interaction between the computer processor and a plurality of communication devices;
the apparatus is in communication with one or more external account associated with the at least one user to receive data therefrom and transmit data thereto; and,
the apparatus is in communication with one or more research data source to provide a link to at least one article;
the plurality of modules comprises a learning center module, a compensation module, and a profile module, wherein:the learning center module is programmed to be a central location for facilitating access to the plurality of storage data media, wherein access through the learning center module generates a plurality of panels, and accessing a panel facilitates access to a specific storage data media, wherein the plurality of panels comprises a compensation panel and a notification panel;
the compensation panel is also accessed through the compensation module;
the compensation panel includes a salary graphical display illustrating salary compensation associated with a paycheck of the employee,
the salary graphical display comprising a circular display including at least:(i) a net pay sub-section identifying net pay information for the employee,
(ii) a tax deduction sub-section identifying tax deduction information for the employee, and
(iii) an additional deduction sub-section identifying additional deduction information for the employee;
wherein the salary graphical display is configured to display a dollar amount associated with a selected portion of the additional deduction sub-section that includes an employer matching amount associated with a contribution made to an investment account by the employee, wherein when the employee contribution is less than a maximum for purposes of employer matching a graphical display is generated to illustrate an amount that would be included with the matching amount had the employee contribution been set to the maximum;

the compensation panel further includes the graphical display illustrating the salary compensation associated with the paycheck, the net pay sub-section, the tax-deduction sub-section, and the additional deduction sub-section, the graphical display being shown on the display device when the compensation panel is displayed by the display device, wherein each sub-section comprises a circular sub-section portion of the circular salary graphical display, wherein at least a portion of each sub-section is programmed for highlighting in response to a selection by an access device, wherein the highlighting comprises a sub-section becoming enlarged or popping out from the graphical display;
the notification panel is configured to provide time-based notifications comprising notifications communicated from a human resource agent, each time-based notification having a status indicator and having a relative position when displayed, each time-based notification being automatically moved relative to other time-based notifications based upon a status thereof, wherein at least one time-based notification is savable and/or exportable to a Lotus Notes and/or Outlook calendar account associated with the at least one user;


wherein content is searchable via a tag cloud comprising at least one actuable term, actuating the at least one actuable term causes search results associated with the at least one actuable term to be displayed, wherein a size of the actuable term is indicative of a frequency of instantiation corresponding to the actuable term;
wherein the profile module is provided with a user profile screen enabling the at least one user to input the data and set up communication preferences, wherein the communication preferences are predetermined to facilitate communications between the apparatus and the at least one user through a medium and in a format desired by the at least one user; and,
wherein the graphical user interface is configured to discriminatorily grant access to the data and display the data base upon a status of the at least one user.

US Pat. No. 11,113,668

METHOD AND DEVICE FOR DETERMINING AN AREA CUT WITH A CUTTING ROLL BY AT LEAST ONE CONSTRUCTION MACHINE OR MINING MACHINE

Wirtgen GmbH


1. A method of determining usage of at least one construction machine including a milling drum, the milling drum having a milling width, the method comprising:(a) milling a ground surface in a plurality of milling trajectories with the at least one construction machine;
(b) determining a length of each of the milling trajectories by determining a plurality of machine positions along each trajectory;
(c) determining a partial usage corresponding to each trajectory as a function of the length of each trajectory and the milling width of each trajectory; and
(d) determining a total usage by adding the partial usage for the plurality of milling trajectories and subtracting any overlapping usage where one trajectory overlaps another trajectory.

US Pat. No. 11,113,667

SYSTEMS AND METHODS FOR PROVIDING A DASHBOARD FOR A COLLABORATION WORK MANAGEMENT PLATFORM

Asana, Inc., San Francis...


1. A system for providing a dashboard representing workflow for a collaboration work management platform, the system comprising:one or more physical computer processors configured by machine-readable instructions to:manage environment state information for maintaining a collaboration environment, the environment state information including user records and work unit records, the environment state information defining a state of the collaboration environment including user states and work unit states, wherein the user states are defined by the user records that define values of user parameters associated with users interacting with and viewing the collaboration environment, and wherein the work unit states are defined by the work unit records that define values of work unit parameters for units of work managed within the collaboration environment, created within the collaboration environment, and assigned within the collaboration environment, the work unit records defining the values of the work unit parameters for individual units of work within sets of units of work, wherein an individual user is associated with the individual units of work within a given set of units of work such that the individual user has a higher level of responsibility for the individual units of work within the given set of units of work than other users that are assigned to the units of work and responsible for performing activities and actions for the units of work within the given set of units of work;
identify a first user;
identify a first set of units of work;
determine which of the units of work within the first set of units of work the first user is associated with but not assigned to by virtue of the first user having the higher level of responsibility, such that a first subset of units of work within the first set of units of work is determined to be associated with the first user by virtue of the first user having the higher level of responsibility for the first subset of units of work, wherein the first user is not assigned to the first subset of units of work such that one or more of the other users are assigned to the first subset of units of work;
obtain work information for the first subset of units of work within the first set of units of work, wherein the work information is based on the work unit records and indicates titles for the first subset of units of work within the first set of units of work, statuses of the first subset of units of work within the first set of units of work, and user information for the one or more of the other users assigned to the first subset of units of work within the first set of units of work; and
effectuate presentation of a dashboard displaying the work information for the first subset of units of work within the first set of units of work.


US Pat. No. 11,113,666

READER MODE FOR PRESENTATION SLIDES IN A CLOUD COLLABORATION PLATFORM

salesforce.com, inc., Sa...


1. A computer-implemented method, comprising:displaying, by a cloud collaboration platform, a slide presentation in a reader mode, wherein the reader mode is configured to display visual elements in the slide presentation and navigation controls;
receiving, by the cloud collaboration platform, a comment in the reader mode via the navigation controls;
associating, by the cloud collaboration platform, the comment with a particular element in the visual elements;
displaying, by the cloud collaboration platform, the comment in the reader mode in association with the particular element;
providing, by the cloud collaboration platform, a link creation interface;
receiving, by the cloud collaboration platform, a reader-link-creation selection via the link creation interface;
in response to the reader-link-creation selection, creating, by the cloud collaboration platform, a reader link to the reader mode; and
initializing, by the cloud collaboration platform, the reader mode upon reception of an engagement with the reader link, wherein the displaying, receiving, and associating are performed by one or more computers.

US Pat. No. 11,113,665

DISTRIBUTED TERMINALS NETWORK MANAGEMENT, SYSTEMS, INTERFACES AND WORKFLOWS


1. A method comprising:managing or servicing one or more clients, wherein:each client of the one or more clients comprises a hardware terminal, node, point of sale, or kiosk;
wherein the one or more clients includes at least a first hardware terminal comprising;first components comprising:at least one display screen, touch screen, or graphical user interface (GUI);
at least one cash dispenser;
at least one keypad;
at least one bill validator;
at least one camera;

a first set of one or more processors; and
a first set of one or more computer readable media or memories, the first set of one or more computer readable media or memories storing:a first application, wherein the first application is a first internet application; and
a first set of one or more files or computer program instructions;



wherein the first hardware terminal is owned by a first owner of a plurality of hardware terminals, the plurality of hardware terminals comprising at least the first hardware terminal, the first hardware terminal at a first location, wherein the first hardware terminal comprises a cryptocurrency or virtual currency terminal or kiosk performs at least one of:one-way exchange transactions between cryptocurrency and cash currency;
two-way exchange transactions between cryptocurrency and cash currency; or
transactions that utilize virtual currency and/or cryptocurrency;

allowing access to first information associated with a first operator account and allowing selections or updates associated with the first information, wherein the first information associated with the first operator account is presented using:one or more graphical user interfaces (GUIs), the one or more GUIs displaying:first data associated with each of one or more terminals of a first set of terminals, wherein the first data includes:
first configuration preferences associated with the one or more terminals of the first set of terminals, wherein the configuration preferences include:first fee settings;



receiving first selections or updates associated with the first information associated with the first operator account;
based on the first selections or updates, updating first configuration settings associated with the one or more terminals of the first set of terminals, wherein the updating comprises:
storing first configuration data in one or more data storage devices, wherein the first configuration data reflects the first selections or updates;
the one or more graphical user interfaces (GUIs) further displaying:second data associated with one or more terminals of a second set of terminals, wherein the second data includes:
second configuration preferences associated with the one or more terminals of the second set of terminals, wherein the second configuration preferences include:second fee settings;


receiving second selections or updates associated with second information associated with the first operator account;
wherein the first selections or updates are different from the second selections or updates;
based on the second selections or updates, updating second configuration settings associated with at least one of the second set of terminals, wherein the updating comprises:storing second configuration data in the one or more data storage devices, wherein the second configuration data reflects the second selections or updates.


US Pat. No. 11,113,664

DATA PROVISIONING SYSTEM AND METHOD

Morgan Stanley Services G...


1. A computer-implemented method for provisioning data to a plurality of data consumers in an organization, the method comprising:providing a graphical user interface designed to: (a) present a data consumer in the organization with a data catalog comprising metadata that identifies a plurality of columns in a database available to the data consumer and identifies a data type of each of the plurality of columns without providing the data to the data consumer, wherein the data consists of values the plurality of columns are assigned in particular records, and wherein the data remains located on different data sources from different platforms and only the metadata for the data catalog is centralized; (b) present a data provider in the organization with options for specifying access of particular categories of data consumers to the data provider's data; (c) present a data steward in the organization with options to view and govern use of the data by the data consumers; and (d) receive input from the data consumer, provide the input to a data request module and present the data consumer with output from the data request module, wherein the data request module
receives a natural language search query and a data attribute through a drag and drop feature of the user interface;
receives a modification input from the data steward, the modification input being a SQL query to optimize the search query;
identifies in data sources an existing feed that has already been produced for another data consumer, wherein the existing feed matches the search query, the modification input and the data attribute; and
displays to the data consumer a message indicating that the existing feed is available;
providing a data preparation module, wherein the data preparation module is programmed to (a) provide an interface to the data sources, (b) provide a data entitlement module to control the types of data presented to the data consumer, and (c) provide a semantic layer that decouples a data source data structure from a data consumer data structure by associating a business name for each column with a technical name for that column, allowing a data consumer to use a query builder to build a query that acts upon technical names of columns while only knowing business names of columns;
providing a metadata module that collects and stores metadata associated with the data sources and that updates the data catalog based on the metadata; and
providing a data publishing module that receives data from the data sources in response to the request of the data consumer and provisions data to the data consumers, wherein the data publishing module uses an auto code generation module to automatically generate code to execute the data provisioning.

US Pat. No. 11,113,663

SYSTEM AND METHOD FOR AUTOMATIC INSERTION OF CALL INTELLIGENCE IN AN INFORMATION SYSTEM

Fonality, Inc., Plano, T...


1. A computer-implemented method for automatically inserting a call intelligence content into a customer relationship management (CRM) system, the computer-implemented method comprising:accessing, via a processor, a new call detail record associated with a time span from when a phone call between a first user and a second user is initiated and the phone call is terminated, wherein the new call detail record is stored in a first database within a phone system at a user site, wherein the new call detail record is associated with the phone call;
identifying, via the processor, a database record associated with the new call detail record, wherein the database record is associated with at least one of the first user or the second user, wherein the database record is stored in a second database within the CRM system at the user site, wherein the phone system is separate and distinct from the CRM system;
forming, by the processor, a copy of a portion of the new call detail record from the first database;
determining, via the processor, a most likely subject matter content associated with the copy of the portion of the new call detail record based on a series of queries to a third database and a fourth database, wherein each of the third database and the fourth database is within a data center system that is separate and distinct from the user site, wherein the series of queries include (i) a first query to the third database for information relating to a phone number associated with the phone call, a duration of the phone call, and an identification of the at least one of the first user or the second user, (ii) a second query to the fourth database for an established relationship between the first user and the second user based on the database record, and (iii) a third query to the fourth database for a most recent subject matter content associated with the established relationship, wherein the third database is associated with the first database, wherein the fourth database is associated with the second database;
generating, via the processor, a call intelligence record in the fourth database based on the at least one of the first user or the second user and the most likely subject matter content; and
inserting, via the processor, the call intelligence record from the fourth database into the second database in association with the new call detail record in the first database, in direct response to generating the call intelligence record within the fourth database.

US Pat. No. 11,113,662

ELECTRONIC APPARATUS FOR PROVIDING PICKING INFORMATION OF ITEM AND METHOD THEREOF

Coupang Corp., Seoul (KR...


1. A method operable by an electronic apparatus to provide information for picking an item in an item storage center, wherein the electronic apparatus is configured to communicate with a manager terminal via a network, the method comprising:identifying, by a processor of the electronic apparatus, pickup item information;
receiving, via a communication port of the electronic apparatus, location information of a tote from the manager terminal, the communication port configured to facilitate communication with the manager terminal over the network;
identifying, by the processor, at least one storage place corresponding to the pickup item information among a plurality of storage places in the item storage center based on information regarding an item group located at each of the plurality of storage places and based on the location information of the tote;
providing, via the communication port, information regarding the identified at least one storage place and the pickup item information to the manager terminal over the network; and
receiving information regarding the tote from the manager terminal over the network, the information regarding the tote generated by a scanner of the manager terminal, the scanner configured to scan a machine-readable code attached to the tote to generate the information regarding the tote,
wherein the item group comprises at least one same item corresponding to an item group, and at least a portion of a plurality of item groups comprising a same item are stored in different storage places in the item storage center,
wherein the pickup item information comprises information regarding a quantity of a first item to be picked,
wherein the identifying the at least one storage place comprises:identifying, by the processor, storage places in which the first item is located among the plurality of storage places;
identifying, by the processor, among the identified storage places, a storage place storing at least the quantity of the first item to be picked;
in response to no storage place storing at least the quantity of the first item to be picked, identifying, by the processor, a first storage place storing a quantity of the first item closest to the quantity of the first item to be picked and identifying a second storage place comprising an item group corresponding to an earliest warehousing order among the identified storage places in which the first item is located; and
identifying the first storage place and the second storage place as the at least one storage place corresponding to the pickup item information, and

wherein the item group is placed in one of the plurality of storage places based on a random stow-based arranging method.

US Pat. No. 11,113,661

INTERACTIVE INVENTORY STORAGE DEVICE, SYSTEM, AND METHOD

CareFusion 303, Inc., Sa...


1. An inventory device attachable to a first movable container, the inventory device comprising:a retainer clip for removably attaching the inventory device to a retainer slot of the first movable container;
a memory including a non-volatile data store containing a local cache storing a local inventory of the first movable container, the local inventory including an amount of an item;
a communication interface;
an audiovisual element; and
a processor configured to:output, via the audiovisual element, a visual representation of the local inventory;
receive a user input via the communication interface;
determine a change to the local inventory according to the user input;
update the local inventory in the non-volatile data store according to the change;
synchronize, via the communication interface, the local inventory with one or more other inventory devices removably attached to respective movable containers geographically remote from the first movable container;

receive, from the one or more other inventory devices, via the communication interface, periodic updates for the local cache comprising locations and inventories of the one or more respective movable containers.

US Pat. No. 11,113,660

DATABASE MODIFICATION FOR IMPROVED ON-SHELF AVAILABILITY DETERMINATION

Target Brands, Inc., Min...


1. A method comprising:identifying, based on movements of a retail item within a store, a maximum net sales floor replenishment for the retail item during a first period of time;
determining, by a processor, whether a hands-on count of the retail item has ever been negative during a second period of time;
when the hands-on count has been negative during the second period of time, determining by the processor, that the nominal capacity is incapable of being automatically corrected; and
when the hands-on count has not been negative during the second period of time:
automatically determining, by the processor, that a nominal capacity for the retail item set in a database is incorrect based on the maximum net sales floor replenishment, and automatically modifying, by the processor, the incorrect nominal capacity for the retail item in the database so that the modified nominal capacity matches the maximum net sales floor replenishment; and
using, by the processor, the modified nominal capacity to count how often the retail item is unavailable on the sales floor.

US Pat. No. 11,113,659

SYSTEMS AND METHODS FOR IMPROVING RECOMMENDATION SYSTEMS

Stitch Fix, Inc., San Fr...


1. A system, comprising:one or more data stores configured to store:client attribute data that includes a plurality of client attributes and client history data, for each of a plurality of clients, wherein the plurality of client attributes include one or more client specified attributes; and
item attribute data that includes a plurality of item attributes, for each of a plurality of items included in an item inventory;

one or more processors coupled to the one or more data stores and configured to:select, using one or more feature selection processes, from the plurality of item attributes an item attribute and from the plurality of client attributes a client specified attribute associated with a client, wherein the selected item attribute and the selected client specified attribute are selected for presentation to an entity tasked with selecting one or more items for the client;
select a subset of a plurality of different recommendation processes to use for the client, wherein each of the recommendation processes included in the subset is configured to calculate a corresponding metric between the selected item attribute and the selected client specified attribute, wherein each of the recommendation processes included in the subset is configured to weigh the corresponding metric differently than the other recommendation processes included in the subset, wherein the plurality of different recommendation processes are configured to identify corresponding subsets of the items in the item inventory that are recommended for the plurality of clients using the corresponding metric wherein each of the items selected by a recommendation process included in the subset have a corresponding common attribute, wherein the one or more processors are configured to execute each of the recommendation processes included in the subset of the plurality of different recommendation processes;
identify a plurality of different subsets of the items in the item inventory that are recommended for the client using the subset of the plurality of different recommendation processes;
provide to the entity tasked with selecting one or more items for the client the plurality of different subsets of items in the item inventory that are recommended for the client, wherein each different subset of the items in the plurality of different subsets is provided with an indication of the corresponding common attribute associated with the items included in the corresponding subset;
receive a selection feedback from the entity tasked with selecting one or more items for the client and a selection feedback from the client, wherein one or more items are selected by the entity from the plurality of different subsets of items and the one or more selected items are provided to the client, wherein the client selection feedback indicates one or more items selected by the client among the one or more items that were selected by the entity, wherein the client selection feedback is used to update the client history data; and
modify the one or more feature selection processes based on the client selection feedback, wherein a manner in which the one or more feature selection processes select item attributes and client attributes to select items for the client are modified based on the client selection feedback including by modifying a corresponding weight associated with the selected client specified attribute based on the client selection feedback, wherein the client selection feedback conflicts with the selected client specified attribute.


US Pat. No. 11,113,658

SYSTEM AND METHOD FOR GENERATING AND IMPLEMENTING A HOUSEHOLD CUSTOMER DATABASE

United States Postal Serv...


1. A method of distributing an item, the method comprising:receiving the item for distribution via a distribution system, the item having delivery point information thereon:
identifying whether the delivery point information on the item corresponds to an improper or nonexistent destination delivery point;
determining that the delivery point information comprises encrypted delivery point information based on the identifying that the delivery point information of the item corresponds to an improper or nonexistent destination delivery point;
flagging the item as comprising encrypted delivery point information based on the determination;
generating decrypted delivery point information by decrypting the encrypted delivery point information;
parsing the decrypted delivery point information to determine sorting and routing instructions;
sending sorting and routing instructions to a sorting apparatus; causing the sorting apparatus to route and sort the item according to the determined sorting and routing instructions;
wherein the encrypted delivery point information comprises one of an encrypted intelligent mail barcode or an encrypted 11-digit delivery code.

US Pat. No. 11,113,657

METHOD AND SYSTEM FOR PHYSICAL ASSET TRACKING

Lob.com, Inc., San Franc...


1. A method for tracking an asset, comprising:receiving a digital version of the asset associated with a sender;
determining an asset identifier for the asset;
generating an asset barcode based on the asset identifier;
transmitting the digital version to a printer, wherein the printer prints the asset and the asset barcode;
determining a picked-up event for the asset, wherein the picked-up event represents asset pick-up from the printer by a delivery service, wherein the picked-up event is determined based on an invoice received from the delivery service, wherein the invoice comprises a first batch identifier and a pick-up timestamp, wherein the asset is associated with a second batch identifier, and wherein determining the picked-up event comprises associating the asset with the pick-up timestamp when the first batch identifier and the second batch identifier match; and
notifying the sender of the picked-up event.

US Pat. No. 11,113,656

SYSTEM FOR AUTOMATIC SIGNATURE FOR RECEIPT VERIFICATION

Walmart Apollo, LLC, Ben...


9. A method of automatically signing for receipt verification, the method comprising:recording an authorized signature for a recipient in a database stored on memory of a delivery management server;
commissioning a secure unattended delivery smart crate to an authorized recipient located at an address of the recipient;
receiving a request for signature for a delivery at the delivery management server; automatically determining at the delivery management server that the recipient is the authorized recipient with the authorized signature stored in the delivery management server and sending confirmation the recipient is the authorized recipient and has the authorized signature stored to a delivery service prior to the delivery service shipping a package;
receiving a delivery notification at the delivery management server automatically from the secure unattended delivery smart crate in response to the secure unattended delivery smart crate being opened to receive the package and delivery of the package for the authorized recipient to the secure unattended delivery smart crate, wherein, following the delivery notification being sent, additional access by the delivery service to the delivery smart crate is restricted until the package is retrieved by the authorized recipient;
sending the stored authorized signature for the authorized recipient from the delivery management server to the delivery service in response to receiving the delivery notification; and
sending an authorized recipient notification to the secure unattended delivery smart crate, wherein the secure unattended delivery smart crate processes the authorized recipient notification and will only disengage a locking device of the secure unattended delivery smart crate in response to the authorized recipient requesting access, thereby restricting access to the secure unattended delivery smart crate to only the authorized recipient.

US Pat. No. 11,113,655

CONTROLLING INDUSTRIAL TRUCKS IN A WAREHOUSE

Locanis AG, Berlin (DE)


1. A method for controlling a plurality of industrial trucks in a warehouse, the method comprising:managing, by a server, a plurality of transport orders in a database, each of the plurality of transport orders specifying a shipment to be transported between at least two sites of a plurality of sites of the warehouse;
upon receiving, by the server, at least one new transport order, storing, by the server, the at least one new transport order as part of the plurality of transport orders in the database;
upon receiving, by the server, an indication from at least one of the plurality of industrial trucks indicating that the at least one industrial truck is available for executing driving orders, generating, by the server, a driving order based on the plurality of transport orders in the database and the at least one industrial truck from which the indication has been received, by:selecting a subset of transport orders from among the plurality of transport orders based at least in part on capabilities of the at least one industrial truck, and
selecting a subset of shipments to be transported as the driving order, the shipments to be transported being specified by the subset of transport orders;

transmitting, by the server, the generated driving order to the at least one industrial truck for execution; and
updating, by the server, the plurality of transport orders in the database by excluding the subset of the shipments specified by the generated driving order from the shipments to be transported.

US Pat. No. 11,113,654

OBJECT REGISTRATION

SAP SE, Walldorf (DE)


1. A computer-implemented method of registering custom software components, comprising:receiving a customized calculation model to replace a pre-defined calculation model, the customized calculation model sharing one or more output properties of the pre-defined calculation model, wherein the customized calculation model comprises one or more flowgraphs respectively having one or more nodes different from the pre-defined calculation model, the nodes comprising a data provider node and a data operator node, wherein the data provider node augments the pre-defined calculation model by incorporating additional information into the customized calculation model;
registering the customized calculation model by associating a first database identifier with a stored procedure and an entry in a metadata table, wherein the stored procedure and the entry in the metadata table define the customized calculation model via the first database identifier, wherein registering the customized calculation model comprises respectively binding one or more runtime objects to the respective one or more nodes of the one or more flowgraphs;
receiving a customized business rule to replace a pre-defined business rule, the customized business rule sharing one or more input properties of a pre-defined business rule;
registering the customized business rule by associating a second database identifier with a second stored procedure and a type information, wherein the second stored procedure and the type information identify the customized business rule via the second database identifier and wherein the one or more shared output properties of the registered customized calculation model corresponds to the one or more shared input properties of the registered customized business rule;
executing, based on the customized calculation model being selected in a user interface to replace the pre-defined calculation model being displayed in the user interface, the registered customized calculation model via the bound one or more runtime objects of the one or more nodes of the respective one or more flowgraphs to generate a customized calculation model output;
executing, based on the customized business rule being selected in the user interface to replace the pre-defined business rule being displayed in the user interface, the registered customized business rule, using the generated customized calculation model output as an input, to generate a second output; and
performing a resource planning operation based on the second output.

US Pat. No. 11,113,653

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING BASED INCIDENT MANAGEMENT

ACCENTURE GLOBAL SOLUTION...


1. An artificial intelligence and machine learning based incident management apparatus comprising:an incident data receiver, executed by at least one hardware processor, toascertain, for a specified time duration, incident data related to a plurality of incidents associated with organizational operations of an organization;

an incident data preprocessor, executed by the at least one hardware processor, topreprocess the incident data to remove specified features of the incident data;

an incident data analyzer, executed by the at least one hardware processor, toanalyze the preprocessed incident data to determine the organization associated with the preprocessed incident data;

a classification model generator, executed by the at least one hardware processor, toseparate the analyzed preprocessed incident data into a first part that is to be used to train a machine learning classification model, and a second part that is to be used to test the trained machine learning classification model,
train, based on the analyzed preprocessed incident data from the first part, the machine learning classification model, and
test, based on the analyzed preprocessed incident data from the second part, the trained machine learning classification model bydetermining, for the trained machine learning classification model, a precision score, and
based on a determination that the precision score is less than a specified precision score threshold, iteratively training the machine learning model until the precision score is greater than or equal to the specified precision score threshold;


a corpus generator, executed by the at least one hardware processor, togenerate, based on mapping of the organizational operations of the organization to associated organizational key performance indicators, a corpus, and
for each incident of the plurality of incidents, determine, based on the corpus, an organizational key performance indicator that is impacted by the incident;

an output generator, executed by the at least one hardware processor, toascertain, for another specified time duration, new incident data related to a further plurality of incidents associated with further organizational operations of the organization,
determine, specified organizational key performance indicators associated with the further organizational operations of the organization, and
determine, based on the corpus and the trained machine learning classification model, and from the further organizational operations of the organization, an output that includes an organizational operation impacted by an incident of the further plurality of incidents associated with the further organizational operations of the organization, and a specified organizational key performance indicator, from the specified organization key performance indicators, associated with the organizational operation; and

an organizational operation controller, executed by the at least one hardware processor, tocontrol, based on the output, an operation of a hardware system associated with the identified organization.


US Pat. No. 11,113,652

SYSTEM AND METHOD FOR A RECOMMENDATION MECHANISM REGARDING STORE REMODELS

Walmart Apollo, LLC, Ben...


1. A computer-implemented method, comprising:generating, via a processor, a trained Bayesian Structural Time Series machine learning model, wherein the trained Bayesian Structural Time Series machine learning model is iteratively trained by a first training data set comprising sales data for one or more stores;
analyzing, via the processor, a profitability impact of a remodel on a target store using the trained Bayesian Structural Time Series machine learning model;
generating, via the processor, a trained non-parametric regression machine learning model, wherein the trained non-parametric regression machine learning model is iteratively trained by a second training data set;
performing, in parallel via the processor:generating a lift classification of the target store using the profitability impact; and
generating a cost estimate for the remodel using the trained non-parametric regression machine learning model;

generating, via the processor, a remodel score for the target store based on the lift classification and the cost estimate of the remodel; and
determining, via the processor, that the remodel score is above a threshold, to yield a determination.

US Pat. No. 11,113,651

METHOD AND SYSTEM FOR ASSESSING PLAY VALUE OF A PLAYGROUND

PLAYCORE WISCONSIN, INC.,...


1. A method for designing or modifying an existing or prospective playground, the method comprising:receiving, by at least one processor, an identification of one or more categories of physical play opportunities that are present in the existing or prospective playground;
receiving, by the at least one processor, for each identified category of physical play opportunity:an identification of a total number of components in the existing or prospective playground within the identified category,
an identification of a number of unique components in the existing or prospective playground within the identified category, and
an identification of a challenge level of each unique component in the existing or prospective playground within the identified category;

assigning, by the at least one processor, a play value to the existing or prospective playground based at least in part on the total number of components, the number of unique components, and the challenge level of the components within each identified category of physical play opportunity;
determining and presenting at a display, by the at least one processor, a recommendation of one or more new components to be added to the existing or prospective playground based at least in part on an amount the new component increases the play value of the existing or prospective playground;
receiving, by the at least one processor, a selection of at least one of the one or more new components to be added to the existing or prospective playground;
building, by the at least one processor, a three-dimensional rendering of a design of the existing or prospective playground modified to include the selected at least one of the one or more new components; and
presenting in real-time at the display, by the at least one processor, (i) the three-dimensional rendering of the design of the existing or prospective playground modified to include the selected at least one of the one or more new components, (ii) the play value of the existing or prospective playground modified to include the selected at least one of the one or more new components, (iii) an increased amount in the play value of the existing or prospective playground modified to include the selected at least one of the one or more new components over the existing or prospective playground prior to the selection of the selected at least one of the one or more new components, or (iv) any combination of (i) through (iii).

US Pat. No. 11,113,650

AUTOMATED GENERATION OF ADAPTIVE POLICIES FROM ORGANIZATIONAL DATA FOR DETECTION OF RISK-RELATED EVENTS

EMC IP Holding Company LL...


1. A method, comprising:extracting a plurality of features identified in organization data of an organization for a risk analysis, wherein a given feature comprises a plurality of data values, wherein each data value for the given feature comprises one or more of a discrete value of the given feature and a range of values for the given feature;
obtaining a probability of occurrence associated with each data value based on the organization data;
identifying, using at least one processing device, a plurality of candidate anomalous data values based on the probabilities of occurrence;
determining, using at least one processing device, an intervention rate for a plurality of combinations of the candidate anomalous data values;
automatically generating, using at least one processing device, one or more policies for the organization using one or more of the combinations of candidate anomalous data values based on a corresponding intervention rate, wherein the one or more policies are used to detect one or more risk-related events associated with user transactions of the organization;
initiating, based on the one or more policies, a generation of at least one authentication challenge for at least one of the user transactions; and
transitioning from the one or more generated policies to a risk engine based on estimated risk detection rates of the risk engine and the one or more generated policies, wherein the risk engine is trained using a supervised machine learning technique.

US Pat. No. 11,113,649

METHODS AND SYSTEMS FOR RECOMMENDING AGRICULTURAL ACTIVITIES

THE CLIMATE CORPORATION, ...


1. A computer-implemented method for providing an improvement in recommending agricultural activities determined based on crop-related data and field condition data and using an agricultural intelligence computer system in communication with a processor, a memory and a database, the method comprising:receiving, from a database over an interface coupled to a processor and a memory of an agricultural intelligence computer system, a plurality of field definition data;
retrieving a plurality of input data from a plurality of data networks;
determining a plurality of field regions based on the field definition data;
identifying a subset of the plurality of input data associated with the plurality of field regions;
determining a plurality of field condition data based on the subset of the plurality of input data;
identifying a plurality of field activity options;
determining, for each of the plurality of field regions, a recommended field activity option, of the plurality of field activity options, based at least in part on the plurality of field condition data;
determining, for each of the plurality of field regions, a recommended crop type, of a plurality of recommended crop options, based at least in part on the plurality of field condition data;
determining, for each field region of the plurality of field regions, a recommendation score, of a plurality of recommendation scores, based at least in part on the plurality of field condition data;
determining, for each of the plurality of field regions, a tillage practice option, of a plurality of recommended tillage practice options, based at least in part on the plurality of field condition data;
providing, and displaying on a display device of the agricultural intelligence computer system, a graphical user interface that displays a page including:a first pull-down menu that allows selecting, for each field region of the plurality of field regions, a particular recommended field activity option from the plurality of field activity options,
a second pull-down menu that allows selecting, for each field region of the plurality of field regions, a particular recommended crop type from the plurality of recommended crop options;
a third pull-down menu that allows selecting, for each field region of the plurality of field regions, a particular recommendation score from the plurality of recommendation scores,
a fourth pull-down menu that allows selecting, for each field region of the plurality of field regions, a particular tillage practice from the plurality of recommended tillage practice options and determined based on the plurality of field activity options and associated recommendation scores;

automatically generating an update based on the particular recommended field activity option, the particular recommended crop type, the particular recommendation score and the particular tillage practice, and updating, based on the update, the graphical user interface to reflect options selected for each field region of the plurality of field regions;
transmitting the update for the plurality of field regions to one or more agricultural machines in real time, so that each agricultural machine, of the one or more agricultural machines, executes instructions, included in the update, in a field region of the plurality of field regions;
performing, by the agricultural intelligence computer system, a historical data analysis based on user's farming practices within a current season and for historical seasons;
determining, by the agricultural intelligence computer system, a relative maturity value of crops based on expected heat units over a growing season in light of a planting date, the user's farming practices, and field-specific and environmental data;
calculating, by the agricultural intelligence computer system, expected heat units for crops and determining a development of maturity of the crops as heat is a proxy for energy received by the crop.

US Pat. No. 11,113,648

MULTI-LINE SYSTEM AND METHOD FOR RETRIEVING AND FULFILLING ITEMS IN A CUSTOMER ORDER


1. A customer order fulfillment system, comprisingan order collection unit for collecting information associated with a plurality of customer orders from a plurality of customers and generating customer order data that includes data associated with each of the plurality of customer orders and the plurality of customers, wherein each of the plurality of customer order includes one or more items associated therewith,
an order generating unit for receiving the customer order data from the order collection unit and generating in response thereto consolidated order fulfillment data,
a pick tour generating subsystem for receiving the consolidated order fulfillment data from the order generating unit and in response thereto generating pick instructions associated with a pick tour or a pick tour plan from the consolidated order fulfillment data, wherein the pick tour generating subsystem comprisesa map unit for storing a map having data associated therewith that corresponds to a location for each of the items in a warehouse,
a graph generating unit for generating a value sorted tree graph by employing a value sorted tree mapping technique based on the map data and the consolidated order fulfillment data, and wherein the value sorted tree graph includes data associating one or more of the items from the plurality of a customer orders with a selected location in the warehouse, and
a pick tour generator for generating the pick tour plan having the pick instructions based on the value ordered tree graph and the map data,

a bulk pick order fulfillment unit for receiving the consolidated order fulfillment data from the order generating unit and grouping together similar ones of the items associated with the plurality of customer orders to form a plurality of bulk picks, wherein one or more of the plurality of bulk picks can form part of one or more bulk pick tours, wherein the bulk pick order fulfillment unit groups selected ones of the items of the plurality of customer orders in the consolidated order fulfillment data into the bulk picks based on a plurality of selectable predetermined logical parameters, including warehouse data and data associated with the items that are common among a selected group of items, so as to optimize a fulfillment process,
wherein the bulk pick order fulfillment unit includes processing hardware that is configured to generate one or more bulk picks having associated therewith a plurality of bulk pick recipes from the data associated with the customer orders and the warehouse data including one or more locations in the warehouse, wherein each of the bulk pick recipes includes a selected quantity of different ones of the one or more items from different ones of the plurality of customer orders that are grouped together; and
an automated fulfillment system for receiving the consolidated order fulfillment data from the order generating unit and for automatically selecting one or more of the items in the customer order that are store in one or more of a plurality of storage receptacles,
wherein the automated fulfillment system is configured for receiving the pick tour plan or the pick tour and for automatically selecting the items in the customer order set forth in the pick tour plan or the pick tour from the one or more carousels, and is configured for receiving one or more of the plurality of bulk picks for automatically selecting one or more of the items in the customer order from the one or more carousels.

US Pat. No. 11,113,647

AUTOMATIC DEMAND-DRIVEN RESOURCE SCALING FOR RELATIONAL DATABASE-AS-A-SERVICE

Microsoft Technology Lice...


1. A database-as-a-service system, comprising:an auto-scaling module configured to automatically compute container sizes of containers in database servers for subsequent billing intervals based on telemetry from the database servers by assigning specific container sizes to resource utilization values, each of the containers comprising a plurality of resources; and
at least one hardware processor configured to execute computer-executable instructions in a memory, the instructions executed to:transform the telemetry into a plurality of signals, each of the plurality of signals representing performance data for one or more of the plurality of resources in a container;
determine a state of each of the plurality of signals by applying a corresponding latency threshold to each of the plurality signals;
combine the states of each of the plurality of signals to estimate a resource demand for the container; and
scale a size of the container for a billing interval on behalf of a tenant based on a demand of the one or more of the plurality of resources in the container.


US Pat. No. 11,113,646

INTELLIGENT ROUTING CODE FOR IMPROVED PRODUCT DISTRIBUTION

ZEST LABS, INC., San Jos...


1. A computer-implemented method for managing a product delivery process, the method comprising:calculating, by a computer, a unique actual Intelligent Routing (IR) code for a good, the good being a perishable food product, the actual IR code being a single string of alphanumeric characters representing a remaining life of the good, wherein the actual IR code for the good is calculated at least in part on sensor data received from a sensor coupled to the good, wherein sensor data which is inaccessible is provided by proxy sensor data derived at least in part from a second sensor coupled to another good in proximity to the good;
updating, by the computer, the actual IR code for the good based on the sensor data associated with the good;
in response to sensor data from the sensor coupled the good being inaccessible and proxy sensor data being inaccessible, updating, by the computer, the actual IR code for the good based on inferred sensor data, wherein the inferred sensor data is based on routine temperature changes associated with historical shipments of substantially similar goods;
receiving, by the computer, a target IR code for a receiver, the target IR code being a single string of alphanumeric characters based at least in part on a minimum remaining shelf life of the good at the date of delivery;
comparing, by the computer, as the good moves along a supply chain route, the actual IR code for the good to the target IR code for the receiver, wherein the comparison determines whether the actual IR code for the good is within the target IR code;
based on the comparison of the actual IR code for the good to the target IR code for the receiver, determining, by the computer, whether the good is compliant with predefined requirements of the receiver, wherein the determination that the good is non-compliant is based at least in part on the actual IR code for the good being less than the target IR code;
outputting, by the computer, a result of the determination in response to determining that the good is non-compliant with predefined requirements of the receiver; and
redirecting, by the computer, the good to a second receiver having a second target IR code, wherein the actual IR code is greater than or equal to the second target IR code, wherein the second target IR code is a single string of alphanumeric characters.

US Pat. No. 11,113,645

INTELLIGENT ROUTING CODE FOR IMPROVED PRODUCT DISTRIBUTION

ZEST LABS, INC., San Jos...


1. A computer-implemented method for managing a product delivery process, the method comprising:calculating, by the computer, a unique actual Intelligent Routing (IR) code for a good, the good being perishable food product, the actual IR code being a single metric,wherein the actual IR code for the good is calculated based at least in part on condition data obtained from a weather information network;

receiving, by the computer, a target IR code for each of at least two receivers;
comparing, by the computer, the actual IR code for the good to the target IR codes for each of the at least two receivers, wherein each of the target IR codes is a single metric of a same type as the single metric of the actual IR code, wherein the actual IR code represents a remaining shelf life of the good and each of the target IR codes for each of the at least two receivers represents a required shelf life of the good;
based on the comparison of the actual IR code for the good to the target IR codes for each of the at least two receivers, determining, by the computer, which receiver of the at least two receivers will receive the good;
outputting, by the computer, a result of the determination;
updating, by the computer, the actual IR code based on sensor data received from a sensor coupled to the good during transportation of the good and prior to reaching a destination in response to the sensor data being accessible;
in response to sensor data from the sensor coupled to the good being inaccessible, updating, by the computer, the actual IR code based on inferred sensor data, wherein the inferred sensor data is based on routine temperature changes associated with historical shipments of substantially similar goods;
recomparing, by the computer, during the transportation of the good and prior to reaching the destination, the actual IR code for the good to the target IR codes for each of the at least two receivers;
based on the recomparison of the actual IR code for the good to the target IR codes for each of the at least two receivers, redetermining, by the computer, which receiver of the at least two receivers will receive the good; and
outputting, by the computer, a result of the redetermination.

US Pat. No. 11,113,644

INTELLIGENT ROUTING CODE FOR IMPROVED PRODUCT DISTRIBUTION

ZEST LABS, INC., San Jos...


1. A computer-implemented method for managing a product delivery process, the method comprising:calculating, by a computer, a unique actual Intelligent Routing (IR) code for each good of a plurality of goods of the same type, wherein the actual IR code for each good is based on sensor data received from a sensor coupled to each good, wherein the sensor data is continuously collected as each good moves along a respective supply chain route, wherein sensor data which is inaccessible is provided by proxy sensor data derived at least in part from a second sensor coupled to another good in proximity to the good;
updating, by the computer, the actual IR codes for the goods based on the sensor data associated with the respective goods;
in response to sensor data from the sensor coupled to one of the goods being inaccessible and proxy sensor data being inaccessible, updating, by the computer, the actual IR code for the one of the goods based on inferred sensor data, wherein the inferred sensor data is based on routine temperature changes associated with historical shipments of substantially similar goods;
receiving, by the computer, a target IR code for each of at least two receivers, wherein each of the target IR codes is calculated based at least in part on quality requirements for the same good, wherein each of the target IR code calculations is based at least in part on different quality requirements for the same good;
comparing, by the computer, as each good moves along the respective supply chain route, the actual IR code for each of the goods to the target IR codes for each of the at least two receivers;
based on the comparison of the actual IR codes for the plurality of goods to the target IR codes for each of the at least two receivers, determining, by the computer, which receiver of the at least two receivers will receive which good of the plurality of goods, wherein the comparison determines whether the actual IR code for each good is within the target IR code of the receiver determined to receive the good; and
outputting, by the computer, a result of the determination, wherein the determination is based at least in part on ranking the results of the comparison of the actual IR codes for the plurality of goods to the targets IR codes for each of the at least two receivers.

US Pat. No. 11,113,643

NOTIFICATION MANAGEMENT TO A GROUP PERFORMING A COMMON TASK

International Business Ma...


1. A computer-implemented method for managing group member notifications, the computer-implemented method comprising:contextually analyzing, by a computer, personal monitoring system inputs corresponding to each member of a defined group of members performing a common task to identify a notification sequence for each respective member of the defined group of members enabling performance of the common task by members in a synchronized manner;
analyzing, by the computer, progress of each respective member of the defined group of members while performing activities corresponding to the common task using the personal monitoring system inputs to enable dynamic modification of the notification sequence and content of notifications to the members in accordance with the analyzed progress;
identifying, by the computer, existence of any problem during performance of the activities corresponding to the common task to accordingly modify the notification sequence and the content of notifications to a set of target members in the defined group of members for mitigation of an existing problem; and
identifying, by the computer, alignment of one or more members in the defined group of members with a completion timeline for a given activity corresponding to the common task for automatic notification suppression of a planned notification upon completion of the given activity within the completion timeline.

US Pat. No. 11,113,642

MOBILE APPLICATION FOR ASSISTING A TECHNICIAN IN CARRYING OUT AN ELECTRONIC WORK ORDER

CommScope Connectivity UK...


1. A method, comprising:generating an electronic work order, the electronic work order comprising a set of steps that are to be carried out by a single technician at a particular location, wherein at least one step of the set of steps includes adding, moving, or changing a connection made at a first port of a device;
communicating the electronic work order to a mobile application executing on a smartphone;
displaying information about the at least one step of the set of steps included in the electronic work order with the mobile application executing on the smartphone;
receiving a first user input, at the mobile application executing on the smartphone, during performance of the at least one step of the set of steps included in the electronic work order, the first user input requesting that an electronic visual indicator associated with visually assisting the technician in carrying out the at least one step of the set of steps included in the electronic work order be visually actuated, wherein the electronic visual indicator is located on the device, distinct from the smartphone, having one or more ports to attach cables to the device, wherein the electronic visual indicator is associated with the first port of the one or more ports where a connection is changed as part of the at least one step of the set of steps included in the electronic work order;
in response to the received first user input requesting that the electronic visual indicator associated with visually assisting the technician in carrying out the at least one step of the set of steps included in the electronic work order be visually actuated, sending a request from the mobile application executing on the smartphone to an external entity, wherein the external entity visually actuates the electronic visual indicator in response to receiving the request from the mobile application executing on the smartphone;
receiving a second user input, at the mobile application executing on the smartphone, during performance of the at least one step of the set of steps included in the electronic work order, the second user input requesting that the electronic visual indicator associated with visually assisting the technician in carrying out the at least one step of the set of steps included in the electronic work order stop being visually actuated; and
in response to the received second user input requesting that the electronic visual indicator associated with visually assisting the technician in carrying out the at least one step of the set of steps included in the electronic work order stop being visually actuated, sending a stop request from the mobile application executing on the smartphone to the external entity, wherein the external entity is configured to stop visually actuating the electronic visual indicator in response to receiving the stop request from the mobile application executing on the smartphone; and
wherein the method further comprises at least one of:receiving an additional user input, at the mobile application executing on the smartphone, indicating that a second step of the set of steps included in the electronic work order has been completed; and
receiving a communication from the external entity, at the mobile application executing on the smartphone, verifying that the at least one step of the set of steps included in the electronic work order that includes adding, moving, or changing the connection made at the first port of the device has been correctly completed.


US Pat. No. 11,113,641

SYSTEMS AND METHODS FOR ACCESS CONTROL GOVERNANCE RECOMMENDATION

FMR LLC, Boston, MA (US)...


1. A computer-implemented method for generating an access profile for a given user in a group that includes a plurality of users with respect to access of a plurality of resources, the method comprising:generating, by a computing device, a plurality of demographic similarity scores in a demographic similarity matrix, wherein each demographic similarity score measures a degree of similarity between a pair of the users in the group with respect to a demographic metric in a plurality of demographic metrics;
generating, by the computing device, a plurality of access similarity scores in an access similarity matrix, wherein each access similarity score measures a degree of similarity between a pair of the users in the group with respect to a plurality of current access privileges to respective ones of the plurality of resources, wherein generating the plurality of access similarity scores comprises generating a subject-access matrix that includes a plurality of access vectors corresponding to the plurality of users, each access vector indicating the current access privileges of the corresponding user;
calculating, by the computing device, a plurality of group similarity scores in a group similarity matrix based on a weighted average of the demographic similarity scores and the access similarity scores, wherein each group similarity score measures a degree of similarity between a pair of the users in the group with respect to both the demographic metrics and the current access privileges;
performing, by the computing device, outlier detection on the plurality of group similarity scores to detect at least one user who is an outlier for accessing one or more of the resources;
reducing, by the computing device based on the outlier detection, the current access privilege of the outlier user corresponding to the one or more resources, thereby accounting for legacy access of the outlier user to the one or more resources, wherein the reducing comprises numerically updating the access vector in the subject-access matrix that corresponds to the outlier user;
creating, by the computing device, the access profile for the given user based on the group similarity matrix and the updated subject-access matrix, the access profile indicating access recommendations for the given user in relation to the resources; and
granting, by the computing device, the given user access to the plurality of resources based on the access recommendations in the access profile.

US Pat. No. 11,113,640

KNOWLEDGE-BASED DECISION SUPPORT SYSTEMS AND METHOD FOR PROCESS LIFECYCLE AUTOMATION

Tata Consultancy Services...


7. A knowledge-based decision support method providing process lifecycle automation, the method comprising:registering, via a hardware processor, one or more software applications and data sources, wherein the registered one or more software applications comprise at least one external software application, wherein the external software application is a predictive analytical model;
defining, via the hardware processor, one or more processes to be implemented by executing the registered one or more software applications, wherein the definition of the one or more processes span across the one or more software applications;
orchestrating, via the hardware processor, execution of the registered one or more software applications for implementing the one or more processes, wherein the orchestration facilitates users utilizing the software application or the processes to create and run instances of other processes, wherein the processes includes ad hoc processes for experimentation;
monitoring, via the hardware processor, system performance based on the execution of the registered one or more software applications by:facilitating acquisition and analysis of a process execution data using machine learning techniques;
identifying performance issues of the one or more processes; and
triggering notifications to one or more users indicating the performance issues, wherein the notifications are sent to at least one of a corresponding software application and the users utilizing the software application for implementing remedial measures;

generating, via the hardware processor, analytics data related to the monitored system performance;
updating, via the hardware processor, a database with historical data using the generated analytics data;
generating, via the hardware processor, an analytical report by analyzing, using a machine learning technique, the historical data stored in the database as well as the generated analytics data;
generating automatically, a user interface based on user inputs, wherein the user inputs comprise at least one of a layout and a specification provided by a user;
modifying, via the hardware processor, execution of the registered one or more software applications based on the generated analytical report; and
displaying, via the hardware processor, data from the generated analytical report using the automatically generated user interface.

US Pat. No. 11,113,639

SYSTEMS AND METHOD FOR MESSAGE-BASED CONTROL AND MONITORING OF A BUSINESS PROCESS

CONTROLS FORCE LTD, Herz...


1. A system for monitoring an enterprise process across disparate information technology systems, the enterprise process comprising two or more messages to create, produce and deliver an outcome of an enterprise process instance of the enterprise process, the enterprise process comprising meta-tag fields of a meta-tag spec, the enterprise process instance being uniquely identified by values of meta-tag fields of the meta-tag spec, the system comprising:at least one processor; and
at least one memory storing instructions which when executed by the at least one processor causes the at least one processor to:receive a first message of a first message type, which is created by a first disparate system, the first message type comprising a first subset of meta-tag fields of the meta-tag spec, wherein the first message comprises values arranged in the first set of meta-tag fields;
receive a second message of a second message type different than the first message type, which is created by a second disparate system, the second message type comprising a second subset of meta-tag fields of the meta-tag spec, wherein the second message comprises values arranged in a second set of meta-tag fields;
apply one or more rules to correlate between the first message and the enterprise process instance based on the values in the first set of meta-tag fields, wherein the one or more rules correlate by analyzing the first message against a plurality of triads, each triad comprising an incoming message, an entity receiving the incoming message, and an outgoing message generated by the entity in response to receiving the incoming message;
in response to a match from the correlation between the first message and the enterprise process instance, merge the values arranged in the first set of meta-tag fields to the enterprise process instance and link the first message to the enterprise process instance by adding a new triad to the plurality of triads, wherein the new triad is generated to comprise:the first message;
an identified receiving entity contained within a given one of the plurality of triads; and
an outgoing message generated by the identified receiving entity, wherein the outgoing message and the identified receiving entity are obtained from the same given triad of the plurality of triads;

in response to the merge, apply one or more validation rules to validate the first message against one or more other messages of the enterprise process instance and a data-centric process model;
apply the one or more rules to correlate between the second message and the enterprise process instance based on values in the second set of meta-tag fields, wherein the one or more rules correlate by analyzing the first second message against the incoming messages and outgoing messages contained within the plurality of triads;
in response to a match from the correlation between the second message and the enterprise process instance, merge the values arranged in the second set of meta-tag fields to the enterprise process instance and link the second message to the enterprise process instance;
in response to the merge, apply the one or more validation rules to validate the second message against one or more other messages of the enterprise process instance and the data-centric process model.


US Pat. No. 11,113,638

OPTIMIZED PARTS PICKUP LIST AND ROUTES FOR EFFICIENT MANUFACTURING USING FREQUENT PATTERN MINING AND VISUALIZATION

FUJIFILM Business Innovat...


1. A method, comprising:executing an item ordering for a plurality of lots and route optimization for each of a plurality of workers on a manufacturing floor, the manufacturing floor comprising a plurality of items disposed amongst a plurality of racks, wherein each lot of the plurality of lots comprises an itemset of the plurality of items;
determining rack placement of the plurality of racks and total travel distance for the each of the plurality of workers;
determining frequent patterns sets indicating items of the plurality of items more likely to be included in a respective itemset of the plurality of lots than other items of the plurality of items;
determining individual item frequencies within the plurality of racks and individual item priority within the plurality of racks;
generating a rack filling plan for item placement amongst the plurality of racks based on frequent patterns sets, individual item frequencies and priority within racks;
generating a deployment plan for the each of the plurality of workers from the item ordering, the route optimization, the rack placement, the rack filling plan, avoidance of collision/congestion between the plurality of workers, and the total travel distance, the deployment plan comprising an order list of pick-up items for each lot, an optimized route, and a schedule for the each of the plurality of workers;
providing the deployment plan to an interface configured to receive modifications to the deployment plan;
upon receiving instructions to deploy the deployment plan through the interface, providing the deployment plan to a device of each of the plurality of workers;
receiving feedback data of the plurality of lots from the device of each of the plurality of workers based, in part, on executing the deployment plan;
generating a visualization for display with the interface based on the deployment plan by:displaying floor map of the manufacturing floor in a first region of the visualization, the floor map comprising the plurality of racks having the plurality of items disposed therein;
displaying, in the first region, a visualization of aggregated trajectories of the plurality of workers on the floor map according to a first color scheme that assigns segments of the aggregated trajectories different colors based on a frequency of the plurality of workers in each respective segment; and

while the plurality of workers execute each deployment plan:receiving an input in the first region selecting at least one of the segments on the floor map to be blocked, and
in response to receiving the input, updating the item ordering, the route optimization, the rack placement, and the total travel distance for each of the plurality of workers to avoid the selected at least one of the segments and automatically re-generating the deployment plan based on the updates to the item ordering, the route optimization, the rack placement, and the total travel distance,

wherein the frequent patterns sets are derived from historical data of the plurality of lots received from a database intaking the feedback data from the device of each of the plurality of workers.

US Pat. No. 11,113,637

CONTENT EXCHANGE WITH A TRAVEL MANAGEMENT SYSTEM

AMADEUS S.A.S., Biot (FR...


1. A method of exchanging content with a travel management system, the method comprising:maintaining, at the travel management system, a plurality of records in an extended record data structure that includes at least one standard data container that includes standard data elements in a standard record data structure and at least one non-standard data container that includes non-standard data elements in a non-standard record data structure, wherein the non-standard data container comprises auto-serialization properties, and the non-standard data container is configured to dynamically adapt to a format of the non-standard data elements based on the auto-serialization properties;
associating each record with a respective structure description file defining a structure of attributes associated with the standard data elements or the non-standard data elements based upon predefined local mapping rules;
configuring a plurality of applications to use the standard data container to access the standard data elements or the non-standard data container to access the non-standard data elements, wherein the applications are executable by the travel management system in response to requests received by the travel management system;
associating a common record identifier with the standard data elements and the non-standard data elements, wherein the common record identifier is shared between at least one standard data element and at least one non-standard data element, the non-standard data elements are maintained in the non-standard record data structure in association with the common record identifier, and the standard data elements and the non-standard data elements are configured to be accessed by at least one of the applications based on the common record identifier;
managing access of each application to the records maintained in the extended record data structure based on the associated common record identifier; and
generating, at the travel management system, a first data exchange message including the structure description file associated with each record and a set of values corresponding to values of the attributes.

US Pat. No. 11,113,636

AUTOMATED GENERATION OF A PACKAGE DATA OBJECT

StubHub, Inc., San Franc...


1. A method comprising:receiving a filter criteria selection designating a first event and a second event at a venue;
generating a package data object by executing a first process to add a first ticket for a first seat in a section of the venue for the first event while in parallel executing a second process to add a second ticket for a second seat in the section of the venue for the second event, the first seat associated with a first listing and the second seat associated with a second listing independent of the first listing;
transmitting instructions to generate a display of the venue hosting the first event and the second event, the display of the venue including an average price for the first ticket and the second ticket;
receiving a single selection request to purchase both the first ticket and the second ticket of the package data object through the selection request;
prior to completing the purchase of both the first ticket and the second ticket, confirming availability of the first ticket and the second ticket; and
based on a received confirmation of the availability of the first ticket and the second ticket and the single selection request, purchasing both the first ticket and the second ticket.

US Pat. No. 11,113,635

SYSTEMS AND METHODS FOR RE-ISSUING TRAVEL RESERVATIONS BASED ON A SPECIFIC TRAVEL CATEGORY

AMADEUS S.A.S., Biot (FR...


1. A method comprising:determining, by a computer, that a standard record of a first travel category is unavailable for a fare component of a travel reservation, each standard record of the first travel category comprising a reissuance rule expressed as machine-readable code;
determining that the fare component of the travel reservation is associated with a second travel category corresponding to records that are incompatible with a format compatible with the first travel category;
determining, based on an evaluation of the records that are incompatible with the format compatible with the first travel category, that a coded record of the second travel category is available for the fare component of the travel reservation;
determining that at least one predetermined condition of a plurality of predetermined conditions is not satisfied;
in accordance with a determination that at least one predetermined condition of the plurality of predetermined conditions is not satisfied, generating, by the computer, a plurality of additional fields to create a non-standard record having the format compatible with the first travel category based on the evaluation of the records of the second travel category, wherein the second travel category includes coded records having reissuance rules expressed as machine-readable code and non-coded records having reissuance rules expressed as human-readable text; and
re-issuing the travel reservation, by the computer, using the non-standard record having the format compatible with the first travel category.

US Pat. No. 11,113,634

CHECK-IN SYSTEMS AND METHODS


1. A method of providing check-in information from a mobile computer device to a check-in enabled network, the method comprising:providing check-in information to the check-in enabled network, the check-in information being sent wirelessly from the mobile computer device to the check-in enabled network, the mobile computer device comprising a processor and a memory that stores the check-in information, wherein the processor:recognizes when the mobile computer device is within a sufficient physical proximity to an entity that provides goods or services in return for a payment, the entity being in communication with the check-in enabled network;
based on location of the mobile computer device, causes the mobile computer device to access the check-in enabled communications network that is in communication with the entity; and
sends the check-in information to the check-in enabled network when the mobile computer device is within the sufficient physical proximity to the check-in enabled network so as to alert the entity in communication with the check-in enabled network of an arrival of a user of the mobile computer device and to begin checking the user into the entity,

wherein the check-in information comprises a unique identifier that is sent to a third-party information repository and that is used to retrieve pre-stored medical information relating to the user from the third-party information repository,
wherein the pre-stored medical information comprises at least one of insurance information, medical information, and payment information,
wherein the third-party information repository queries the user to selectively identify at least a portion of the pre-stored medical information in response to the third-party information repository receiving the unique identifier, and
wherein the third-party information repository transfers the portion of the pre-stored medical information to the entity in response to the portion of the pre-stored medical information being identified by the user.

US Pat. No. 11,113,633

MACHINE LEARNING SYSTEM AND METHODS FOR DETERMINING CONFIDENCE LEVELS OF PERSONAL INFORMATION FINDINGS

BigID Inc., New York, NY...


1. A computer-implemented method of finding and classifying personal information in a data source, the method comprising:receiving, by a computer, an identity data source comprising:a first attribute field associated with first attribute values; and
a second attribute field associated with second attribute values;

receiving, by the computer, a scanned data source comprising a first scanned field associated with first scanned values;
determining, by the computer, a plurality of personal information findings comprising:a first set of personal information findings determined by comparing the first attribute values to the first scanned values; and
a second set of personal information findings determined by comparing the second attribute values to the first scanned values;

creating, by the computer, a plurality of personal information records from some or all of the plurality of personal information findings, the plurality of personal information records comprising:a first set of personal information records created from some or all of the first set of personal information findings; and
a second set of personal information records created from some or all of the second set of personal information findings;

calculating, by the computer, a first confidence level for the first scanned field and the first attribute field, said calculating based on a plurality of: a count of the first scanned values, a count of the first set of personal information findings, a count of the first set of personal information records, and a sum of the count of the first set of personal information records and a count of the second set of personal information records;
calculating, by the computer, a second confidence level for the first scanned field and the second attribute field, said calculating based on a plurality of: the count of the first scanned values, a count of the second set of personal information findings, a count of the second set of personal information records, and the sum of the count of the first set of personal information records and the count of the second set of personal information records;
upon determining that the first confidence level is greater than or equal to a minimum confidence threshold and that the second confidence level is less than the minimum confidence threshold, associating, by the computer, the first attribute field, but not the second attribute field, with the first scanned field in a report; and
providing the report to a user device.

US Pat. No. 11,113,632

SYSTEM AND METHOD FOR PERFORMING OPERATIONS ON MULTI-DIMENSIONAL FUNCTIONS

THE GOVERNING COUNCIL OF ...


1. A computer-implemented method for performing operations on multi-dimensional functions using a machine learning model, the method comprising:receiving a problem formulation in input space;
mapping the problem formulation from input space to one or more latent vectors or a set in latent feature space using a projection learned using the machine learning model;
splitting the one or more latent vectors or set in latent space into a plurality of lower-dimensional groupings of latent features;
performing one or more operations in latent space on each lower-dimensional groupings of latent features;
combining each of the low-dimensional groupings; and
outputting the combination for generating the prediction.

US Pat. No. 11,113,631

ENGINEERING DATA ANALYTICS PLATFORMS USING MACHINE LEARNING

Accenture Global Solution...


1. A computer-implemented method comprising:accessing, for each past data analysis provider of one or more past data analysis providers, historical information that includes (i) past characteristics of past data analyzed by the past data analysis provider, (ii) past computing loads during analysis of the past data by the past data analysis provider, (iii) past analysis techniques offered by the past data analysis provider, (iv) past access and security requirements implemented by the past data analysis provider for past users accessing the past data analyzed by the data analysis provider, and (v) past configurations of the respective data analysis provider used to analyze the past data;
training, using machine learning and using the historical information, a model that receives (i) given characteristics of given data, (ii) given computing loads of each of one or more given data analysis providers, (iii) given analysis techniques offered by each of the one or more given data analysis providers, (iv) given access and security requirements for given users accessing analyzed given data, and outputs data indicating (i) a subset of the one or more given data analysis providers to analyze the given data and (ii) a given configuration for the subset of the one or more given data analysis providers; and
providing the model to a recommendation generator, wherein the recommendation generator recommends based on the model both (i) one or more data analysis providers to analyze data and (ii) a configuration for the one or more data analysis providers.

US Pat. No. 11,113,630

COMPUTER ARCHITECTURE FOR TRAINING A CORRELITHM OBJECT PROCESSING SYSTEM

Bank of America Corporati...


1. A system configured to train a correlithm object processing system, comprising:a node linked with a node table that identifies:a plurality of source correlithm objects, wherein each source correlithm object is a point in an n-dimensional space represented by a binary string; and
a plurality of target correlithm objects, wherein:each target correlithm object is a point in the n-dimensional space represented by a binary string, and
each target correlithm object is linked with a source correlithm object from among the plurality of source correlithm objects; and


a trainer operably coupled to the memory, configured to:receive a real world input value and a real world output value;
send a node entry request to the node in response to receiving the real world input value and the real world output value;
receive a source correlithm object and a target correlithm object in response to sending the node entry request;
send the real world input value and the source correlithm object to a sensor;
send the real world output value and the target correlithm object to an actor;

the sensor operably coupled to the trainer, configured to:receive the real world input value and the source correlithm object;
generate an entry in a sensor table linking the real world input value and the source correlithm object; and

the actor operably coupled to the trainer, configured to:receive the real world output value and the target correlithm object;
generate an entry in an actor table linking the real world output value and the target correlithm object.


US Pat. No. 11,113,629

ADAPTIVE CONFIGURATION OF A HETEROGENEOUS CLUSTER ENVIRONMENT

International Business Ma...


1. A method for use in managing a system comprising one or more computers, each computer comprising at least one hardware processor coupled to at least one memory, the method comprising a computer-implemented manager:generating a plurality of potential configurations for hardware resources of the system for each of a plurality of machine learning models;
determining, for each of the plurality of machine learning models, the potential configuration of the plurality of potential configurations that exhibits a minimal execution time while satisfying accuracy and time constraints for the corresponding machine learning model, wherein the determining step comprises configuring the system according to a selected potential configuration, training the corresponding machine learning model on the configured system, and recording time required for training and accuracy reached;
sorting, based on execution time to train the corresponding machine learning model of the plurality of machine learning models, the plurality of machine learning models and corresponding plurality of potential configurations that exhibit the minimal execution time; and
configuring at least a subset of the hardware resources based on an optimal machine learning model of the plurality of sorted machine learning models.

US Pat. No. 11,113,628

SELF-LEARNING CONTEXTUAL MODALITY SELECTION FOR COGNITIVE SOLUTION DELIVERY

INTERNATIONAL BUSINESS MA...


1. A method comprising:computing, at an application executing using a processor and a memory, from an input, a problem context, the problem context comprising a set of problem factors, the input comprising a problem to be solved using a cognitive system;
computing, at the application, from the input, a user context, the user context comprising a set of user factors;
determining a type of media corresponding to a complexity of a cognitive solution received from the cognitive system, wherein the cognitive solution is responsive to the problem;
determining, using a problem factor from the set of problem factors, using a user factor in the set of user factors, and the complexity, a mode of communication;
adjusting a communication apparatus to cause a data communication to occur, wherein the data communication delivers the cognitive solution in the type of media using the mode of communication;
instrumenting the cognitive solution with an evaluation code;
receiving, after the data communication has ended, an evaluation input from the evaluation code, wherein the evaluation input has a value corresponding to a delivery performance of the cognitive solution over the data communication using the mode of communication;
changing a weight of one or more of (i) a problem factor in the set of problem factors, (ii) a user factor in the set of user factors, (iii) a second mode of communication of the input, and (iv) the complexity; and
causing, responsive to the changing, the communication apparatus to transmit a second cognitive solution responsive to a second problem in the type of media using a third mode of communication.

US Pat. No. 11,113,627

CHARACTERISATION OF DATA SETS CORRESPONDING TO DYNAMICAL STATISTICAL SYSTEMS USING MACHINE LEARNING

NOBLE ARTIFICIAL INTELLIG...


1. A method of performing machine learning on a data set representing a dynamical statistical system of entities having plural primary variables that vary with time, the entities comprising one or more species,the method treating the primary variables as dimensions in an effective configuration space, and treating secondary variables that are dependent on a rate of change of each of the primary variables as variables in an effective momentum space, and treating the effective configuration space and the effective momentum space together as a phase space,
the method comprising,
with respect to each of the one or more species of the entities:
providing a set of training feature vectors corresponding to training examples of phaseons in a plurality of classes;
training a machine learning architecture to perform classification based, at least in part, on the training feature vectors;
deriving a distribution function over time of a density of entities in the phase space;
encoding the distribution function as a sum of contour functions over time describing the contour in phase space of plural phaseons which are entities of a model of the dynamical statistical system that are localised in the phase space; and
performing, using the machine learning architecture, machine learning on the encoded distribution function or at least one field in the effective configuration space derived from the encoded distribution function, with respect to each of the one or more species of the entities;
wherein:
feature vectors are derived for the plural phaseons based, at least in part, on the encoded distribution function or the at least one field in the effective configuration space; and
the machine learning performs classification of the plural phaseons into one or more of the plurality of classes using the feature vectors.

US Pat. No. 11,113,626

SELF-LEARNING CONTEXTUAL MODALITY SELECTION FOR COGNITIVE SOLUTION DELIVERY

INTERNATIONAL BUSINESS MA...


1. A computer usable program product comprising one or more computer-readable storage devices, and program instructions stored on at least one of the one or more storage devices, the stored program instructions comprising:program instructions to compute, at an application executing using a processor and a memory, from an input, a problem context, the problem context comprising a set of problem factors, the input comprising a problem to be solved using a cognitive system;
program instructions to compute, at the application, from the input, a user context, the user context comprising a set of user factors;
program instructions to determine a type of media corresponding to a complexity of a cognitive solution received from the cognitive system, wherein the cognitive solution is responsive to the problem;
program instructions to determine, using a problem factor from the set of problem factors, using a user factor in the set of user factors, and the complexity, a mode of communication;
program instructions to adjust a communication apparatus to cause a data communication to occur, wherein the data communication delivers the cognitive solution in the type of media using the mode of communication;
program instructions to instrument the cognitive solution with an evaluation code;
program instructions to receive, after the data communication has ended, an evaluation input from the evaluation code, wherein the evaluation input has a value corresponding to a delivery performance of the cognitive solution over the data communication using the mode of communication;
program instructions to change a weight of one or more of (i) a problem factor in the set of problem factors, (ii) a user factor in the set of user factors, (iii) a second mode of communication of the input, and (iv) the complexity; and
program instructions to cause, responsive to the changing, the communication apparatus to transmit a second cognitive solution responsive to a second problem in the type of media using a third mode of communication.

US Pat. No. 11,113,625

ADAPTIVE CONFIGURATION OF A HETEROGENEOUS CLUSTER ENVIRONMENT

International Business Ma...


1. An apparatus, comprising:a memory; and
at least one processor coupled with the memory, the processor operative to perform operations comprising:generating a plurality of potential configurations for hardware resources of a system for each of a plurality of machine learning models;
determining, for each of the plurality of machine learning models, the potential configuration of the plurality of potential configurations that exhibits a minimal execution time while satisfying accuracy and time constraints for the corresponding machine learning model, wherein the determining step comprises configuring the system according to a selected potential configuration, training the corresponding machine learning model on the configured system, and recording time required for training and accuracy reached;
sorting, based on execution time to train the corresponding machine learning model of the plurality of machine learning models, the plurality of machine learning models and corresponding plurality of potential configurations that exhibit the minimal execution time; and
configuring at least a subset of the hardware resources based on an optimal machine learning model of the plurality of sorted machine learning models.


US Pat. No. 11,113,624

DISTRIBUTED MACHINE LEARNING ON HETEROGENEOUS DATA PLATFORMS

SAP SE, Walldorf (DE)


1. A computer-implemented method comprising:sending to a first server node of a first data platform, a first request to collect a first partial result vector regarding a first parameter of a training set;
receiving from the first server node, the first partial result vector computed by a first work node from data stored in the first data platform;
sending to a second server node of a second data platform, a second request to collect a second partial result vector regarding a second parameter of the training set;
receiving from the second server node, the second partial result vector computed by a second work node from data stored in the second data platform;
aggregating the first partial result vector and the second partial result vector to create the result vector including an updated first parameter and an updated second parameter, wherein the first partial result vector and the second partial result vector are rows or columns in the result vector;
sending back the result vector to the first server node and to the second server node for processing by the first server node and the second server node;
receiving convergence data calculated by the first server node from the updated first parameter, and calculated by the second server node from the updated second parameter;
a first in-memory database engine of a first in-memory database determining a convergence from the convergence data; and
where the convergence is found, the first in-memory database engine storing in a persistence component of the first in-memory database, a model trained according to the result vector.

US Pat. No. 11,113,623

MULTI-SAMPLE SYSTEM FOR EMULATING A QUANTUM COMPUTER AND METHODS FOR USE THEREWITH

BEIT Inc., Millbrae, CA ...


1. A system for emulating sampling of a quantum computer having a plurality of qubits arranged in a grid topology with N columns, the system comprising:a memory that stores operational instructions;
at least one classical processor that is configured by the operational instructions to perform operations, the operations including:
producing final weights and variable assignments for the N columns based on N iterative passes through the grid topology, wherein each of the N iterative passes generates preliminary weights and variable assignments for a number of columns of the N columns based on preliminary weights and variable assignments generated for an adjacent column for each of the number of columns, wherein final weights and variable assignments are generated for a final column of the N columns for each of the N iterative passes based on the preliminary weights and variable assignments generated for a column of the N columns adjacent to the final column of the N columns, wherein the final weights and variable assignments for the final column of the N columns are used in a next successive pass of the N iterative passes to reduce the number of columns of the N columns where the preliminary weights and variable assignments are regenerated until the N iterative passes are complete and final weights and variable assignments for each of the N columns have been generated;
wherein the sampling of the quantum computer having the plurality of qubits is emulated by producing a plurality of samples from the N iterative passes based on the final weights and variable assignments for each of the N columns.

US Pat. No. 11,113,622

PHONONIC QUANTUM NETWORKS OF SOLID-STATE SPINS WITH ALTERNATING AND FREQUENCY-SELECTIVE WAVEGUIDES

University of Oregon, Eu...


19. A quantum circuit, comprising:a plurality of spin-mechanical resonators (SMRs);
a plurality of acoustic waveguides coupled to the SMRs so that each SMR is coupled to a first other SMR in a first frequency band and a second other SMR in a second frequency band that is different than the first frequency band; and
a phononic crystal situated about the SMRs, wherein a bandgap of the phononic crystal includes frequencies of the first frequency band and the second frequency band.

US Pat. No. 11,113,621

SYSTEM AND TECHNIQUE FOR LOADING CLASSICAL DATA INTO A QUANTUM COMPUTER

Massachusetts Institute o...


1. A circuit for entangling quantum states of a plurality of at most 2n input data qubits that are initially unentangled, the circuit comprising:a plurality of ancilla qubits having an initially unentangled quantum state, the plurality of ancilla qubits being divided into first and second non-empty subsets, wherein the circuit provides as output qubits the second subset of ancilla qubits and a subset of the input data qubits;
a first stage of quantum gates configured to entangle the quantum states of the plurality of ancilla qubits according to a given entangled state;
a second stage of quantum gates configured to entangle, in parallel, the quantum state of each of the plurality of ancilla qubits with the quantum state of a corresponding pair of the data qubits; and
a third stage of quantum gates configured to disentangle the first subset of ancilla qubits from the output qubits.

US Pat. No. 11,113,620

ENHANCING SIMULATED ANNEALING WITH QUANTUM ANNEALING

Google LLC, Mountain Vie...


1. A method for performing thermal annealing with quantum fluctuations, the method comprising:obtaining an initial input state;
performing simulated annealing and quantum annealing on the initial input state and subsequent input states until a completion of a first event; and
determining that the completion of the first event has occurred
wherein the quantum annealing comprises:
creating a list of connected subgraphs;
computing a lowest achievable energy value for each connected subgraph;
computing the difference between a current energy value and the lowest achievable energy value for each connected subgraph;
determining that at least one difference is positive;
selecting the subgraph and corresponding transition that achieves an overall largest positive difference; and
performing the corresponding transition that achieves the overall largest positive difference.

US Pat. No. 11,113,619

DETERMINING ACTION SELECTION POLICIES OF AN EXECUTION DEVICE

Alipay (Hangzhou) Informa...


1. A computer-implemented method of an execution device for generating an action selection policy for completing a task in an environment that includes the execution device and one or more other devices, the method comprising:identifying, by the execution device, a plurality of possible actions in a state, wherein the state corresponds to a vector of information sets, and each information set in the vector of information sets comprises a sequence of actions taken by the execution device that leads to the state;
identifying, by the execution device, a vector of current action selection policies in the state, wherein each current action selection policy in the vector of current action selection policies corresponds to an information set in the vector of information sets, and the action selection policy specifies a respective probability of selecting an action among the plurality of possible actions in the state;
computing, by the execution device, a sampling policy based on the vector of current action selection policies in the state, wherein the sampling policy specifies a respective sampling probability corresponding to each of the plurality of possible actions in the state;
sampling, by the execution device, an action among the plurality of possible actions in the state according to a sampling probability of the action specified in the sampling policy; and
updating, by the execution device, the each current action selection policy in the vector of current action selection policies of the execution device in the state based on the action.

US Pat. No. 11,113,618

DETECTING THE BOUNDS OF BORDERLESS TABLES IN FIXED-FORMAT STRUCTURED DOCUMENTS USING MACHINE LEARNING

Adobe Inc., San Jose, CA...


1. A computer implemented method for detecting borderless tables in a fixed-format structured document, the method comprising:generating a sorted list of a plurality of text lines within a document, wherein the list is sorted based upon a vertical position and a horizontal position of each text line in the list;
determining a first respective probability that a first text line belongs to a borderless table that comprises first and second borderless table objects;
determining a second respective probability that a second text line belongs to the borderless table, wherein the first and second text lines have different probabilities of belonging to the borderless table;
making a first determination that the first respective probability is greater than a threshold probability, and in response to making the first determination, designating the first text line as belonging to the borderless table, associating the first text line with the first borderless table object, and updating a boundary of the borderless table;
making a second determination that (a) the second respective probability is less than the threshold probability, and (b) the second text line intersects the second borderless table object, and in response to making the second determination, designating the second text line as belonging to the borderless table and associating the second text line with the second borderless table object; and
in response to making the second determination, updating the boundary of the borderless table to reflect the second text line as belonging to the borderless table, wherein the borderless table includes at least one line having a probability greater than the threshold, and at least one line having a probability less than the threshold.

US Pat. No. 11,113,617

RANKING OF USER CONTACTS TO FACILITATE EFFICIENT USER INTERFACES

Facebook, Inc., Menlo Pa...


1. A method comprising:receiving, from a client device associated with a user, a request for a ranked list of contacts of the user, the request identifying a purpose for the ranked list of contacts;
retrieving a list of the user's contacts from a data store;
identifying a subset of the user's contacts that are likely to interact with the user in a specified future time period, identifying the subset comprising:identifying an initial subset of the user's contacts;
identifying a message thread associated with a contact in the initial subset;
obtaining a set of features associated with the message thread;
applying a machine-learned global ranking model to the set of features to generate a likelihood that the contact will interact with the user in the specified future time period; and
refining the initial subset to identify the subset based on the likelihood;

calculating ranking scores for the subset of the user's contacts, each ranking score indicating a probability that the user will interact with a corresponding one of the subset of the user's contacts in a manner consistent with the purpose; and
sending the ranked list of contacts to the client device, the ranked list of contacts based on the ranking scores.

US Pat. No. 11,113,616

SYSTEMS AND METHODS FOR AUTOMATED BAYESIAN-NETWORK BASED MASTERY DETERMINATION

PEARSON EDUCATION, INC., ...


1. A system for determining mastery in a Bayesian network, the system comprising:memory comprising: a content library database comprising content for delivery to a user; and
at least one processor configured to:receive an assertion, comprising a response to a prompt or a question, from a user device;
identify one or several nodes relevant to the received assertion;
evaluate the assertion;
calculate a node mastery probability for the identified one or several relevant nodes;
identify related nodes, comprising a plurality of connected nodes connecting, either directly or via at least one additional node, to a common learning objective, wherein the related nodes are connected to the relevant nodes via conditional dependencies, which identify the likelihood of the relevant nodes being mastered if the related nodes are likewise mastered or unmastered;
calculate mastery of the related nodes according to the node mastery probability and the conditional dependencies;
determine mastery of an objective based on the mastery of the relevant nodes and the related nodes;
generate a mastery bar in a user interface, wherein the mastery bar provides a visual indicator of progress through content and a visual indicator of mastery of the objective; and
update the mastery bar with the determined mastery of the objective.


US Pat. No. 11,113,615

REAL-TIME EVENT ANALYSIS UTILIZING RELEVANCE AND SEQUENCING

ZineOne, Inc., Milpitas,...


1. A computing system implementing predictive intent for network latency reduction in connection with an enterprise resource, the computing system comprising:one or more processors;
a memory to store a set of instructions;
wherein the one or more processors access the instructions to:detect, over one or more networks, real-time activity data from a computing device of a given user during a current application session with the enterprise resource, the real-time activity data corresponding to a series of activities performed by the given user using one or more user interface components of the enterprise resource presented on the computing device of the given user;
access a historical data store, storing event records corresponding to vector representations of historical activity data of users of the enterprise resource, to determine a matching sequence of events for the real-time activity data of the given user, each event of the matching sequence of events corresponding to one more activities of the series of activities performed by the user using the one or more interface components of the enterprise resource;
in connection with the real-time activity data of the given user, select a relevant portion of the matching sequence of events;
execute a predictive model to determine a user intent probability that the given user will engage with selected content that corresponds to the relevant portion of the matching sequence of events during the current application session;

based on the user intent probability exceeding a threshold, generate an intervention element on a user interface of the computing device of the given user, the intervention element enabling presentation of the selected content on the computing device of the given user to reduce network latency for the enterprise resource;
wherein each event of the matching sequence of events is associated with a corresponding set of parameters, and wherein the one or more processors access the instructions to determine a value for at least one parameter of the corresponding set of para meters for the associated event;
wherein the corresponding set of para meters for at least a first event of the matching sequence of events includes a set of related activity parameters, the set of related activity parameters including a first related activity parameter that identifies information about one or more activities of a particular type that preceded or followed the first event; and
wherein the first related activity parameter identifies (i) a number of page views in the current application session, or (ii) a product.

US Pat. No. 11,113,614

ENTERPRISE HYPOTHESIS ORCHESTRATION

PARSONS CORPORATION, Cen...


1. A computer implemented method for hypothesis orchestration wherein a computer includes one or more processors configured to execute instructions to perform the method and wherein the computer is communicatively coupled to one or more data repositories, the method comprising:receiving, by the one or more processors via a user interface, a situation characterized by a set of linked inquiries;
searching, by the one or more processors, the one or more data repositories to identify one or more pieces of evidence relevant to the set of linked inquiries, wherein the one or more pieces of evidence are amassed by one or more collection resources and wherein searching includes forming a semantic graph describing the set of linked inquiries for the one or more pieces of evidence;
forming, by the one or more processors, a plurality of hypotheses based on evidence identified as relevant to the set of linked inquiries, wherein each hypothesis is a proposed solution of the situation representing a unique path through the sematic graph of linked pieces of evidence, answering one or more of the set of linked inquiries;
collecting, by the one or more processors, evidence identified as relevant and linked to one or more of the plurality of hypotheses from the one or more data repositories forming, for each hypothesis, a set of collected pieces of evidence;
evaluating, by the one or more processors using fuzzy logic, each of the plurality of hypotheses based on the set of collected pieces of evidence for that hypothesis thereby determining for each hypothesis a confidence value based on a degree on which the set of collected pieces of evidence align with the situation; and
responsive to the confidence value for one or more of the plurality of hypotheses failing to exceed a predefined threshold value,identifying, by the one or more processors, one or more missing pieces of evidence by comparing the set of collected pieces of evidence with the amassed one or more pieces of evidence relevant to the situation,
isolating, by the one or more processors, one or more common missing pieces of evidence from the one or more missing pieces of evidence that is relevant to two or more of the plurality of hypotheses that failed to exceed the predefined threshold value,
forming, by the one or more processors, a value of information metric of missing information to the situation provided by each common missing piece of evidence,
selecting, by the one or more processors, at least one common missing piece of evidence from the one or more common missing pieces of evidence based on the respective value of information metric of the missing information to address the situation;
initiating, by the one or more processors, an information request to the one or more collection resources directing the one or more collection resources to seek information related to the situation based on the at least one common missing piece of evidence and the value of information metric to reduce uncertainty associated with the plurality of hypotheses;
receiving, by the one or more processors, the information related to the at least one common missing piece of evidence from the one or more collection resources; and
refining, by the one or more processors, the plurality of hypotheses relevant to the situation based on the received information related to the at least one common missing piece of evidence.


US Pat. No. 11,113,613

DETERMINING MODEL PARAMETERS USING SECRET SHARING

Advanced New Technologies...


1. A computer-implemented method, comprising:obtaining, by a first data party device, a first share of a Hessian matrix for a data processing model, wherein the Hessian matrix is secretly shared between the first data party device and a second data party device of a cooperation partner such that the first data party device and the second data party device have respective shares of the Hessian matrix, and wherein the Hessian matrix is based on feature data for the data processing model and an activation function for the data processing model;
obtaining, by the first data party device and using secret sharing with the second data party device, a first share of a product of a random number matrix and the Hessian matrix;
determining, by the first data party device and using secret sharing with the second data party device, a first share of a product of a first inverse matrix and a gradient of a loss function of the data processing model, wherein the first inverse matrix is an inverse of the Hessian matrix; and
determining a first share of a new model parameter for the data processing model based on an original model parameter of the data processing model and the first share of the product of the first inverse matrix and the gradient of the loss function.

US Pat. No. 11,113,612

PREDICTIVE ASSET OPTIMIZATION FOR COMPUTER RESOURCES

MORGAN STANLEY SERVICES G...


1. A computer-implemented method of forecasting network resource needs for an enterprise computer system, wherein the enterprise computer system comprises a plurality of network servers that host computer resources for users of the enterprise computer system, the method comprising:receiving, by a computer database system, a multivariate time-series (MTS) of performance data for the plurality of network servers, wherein the performance data comprise data for a plurality of d performance variables for the plurality of network servers for a series of m prior sampling times, such that there are m-histories of the MTS;

grouping, by a programmed computer system that is in communication with the computer database system, each of the performance variables of the MTS into two or more performance variable groups, such that each of the performance variables of the MTS belongs to a variable group, wherein the step of grouping the performance variables comprises:computing, by the programmed computer system, a correlation matrix indicating a strength of correlation between each pair of performance variables; and
determining, by the programmed computer system, the variable groups based on the strength of correlation using a clustering algorithm;

computing, by a programmed computer system, predictions of future workloads of the network servers of the enterprise computer system by computing predictions for the variables at one or more future time horizon steps, wherein computing the predictions comprises:finding the k nearest neighbors to a reference state of the MTS using a k-nearest neighbor searching algorithm applied to the two or more variable groups, wherein finding the k nearest neighbors comprises:computing distances between a target feature matrix representing a reference state of the MTS and target feature matrices for each of the m-histories, respectively; and
determining the k target feature matrices for prior sampling times that have the smallest distance to the target feature matrix representing the reference state of the MTS, wherein each of the k target feature matrices comprises d vectors of m sampling time observations; and

computing a weighted average of subsequent values of the MTS at a horizon time step h of the k nearest neighbors such that the weighted average yields a cumulative user resource requests for the enterprise computer system at the horizon time step h; and

determining, by a programmed computer system, a recommended number of network servers needed by the enterprise to be in operational modes to handle resource requests by the users of the enterprise computer system at each of the one or more future time horizon steps based on the computed cumulative user resource requests.

US Pat. No. 11,113,611

METHOD AND ELECTRONIC APPARATUS FOR PREDICTING ELECTRONIC STRUCTURE OF MATERIAL

Korea Institute of Scienc...


1. A method of predicting an electronic structure of a material by an electronic apparatus, the method comprising:receiving a user's input data about elements constituting the material;
applying the received user's input data to a trained model for estimating a state density of the material; and
outputting a first graph representing energy level-by-level state densities of the material output from the trained model,
wherein the trained model is trained to generate the first graph based on a plurality of second graphs representing pre-calculated energy level-by-level state densities respectively corresponding to a plurality of pre-input data about elements of various materials and the plurality of pre-input data by converting the plurality of second graphs into recognition data,
wherein the converting the plurality of second graphs comprises:
converting the plurality of second graphs into a plurality of lattice images, respectively;
converting the plurality of lattice images into a plurality of matrixes, respectively;
calculating a covariance of the plurality of matrixes;
calculating at least one eigenvector and at least one eigenvalue based on the calculated covariance; and
determining at least one principal component representing a characteristic of the first graph based on the at least one eigenvector and the at least one eigenvalue; and
wherein the trained model is trained to generate the first graph based on the at least one principal component.

US Pat. No. 11,113,610

SYSTEM FOR BUILDING AND DEPLOYING INFERENCE MODEL

GE AVIATION SYSTEMS LIMIT...


1. A computer-implemented system for building and deploying one or more inference models for use in remote condition monitoring of one or more first assets of a first fleet, the computer-implemented system comprising:a memory module;
a processor communicatively coupled with the memory module; a server module communicatively coupled with the processor;
at least one of a configuration file stored in the memory module, and a compiled configuration database stored within the server module, both the at least one of the configuration file and the compiled configuration database (i) being directly editable and readable by a user and (ii) comprising a model configuration data containing information and being customized to the one or more first assets and the one or more inference models;
wherein the model configuration data is defined as a plurality of structural and performance characteristics of the one or more first assets; and
a model builder application being an executable computer application configured to (i) execute one or more tasks when run on the processor (ii) receive the model configuration data and (iii) operate in a learning mode;
wherein during operation of the learning mode:
the model builder application (i) receives historical operational data corresponding to a plurality of operating states of the one or more first assets (ii) calls one or more processing algorithms, the one or more processing algorithms being determined by the model configuration data and (iii) constructs the one or more inference models based on the received model configuration data, the received historical operational data and the called for one or more processing algorithms; and
the information is contained within the model configuration data, and the processing algorithms are integrated within the model builder application, the information and the processing algorithms thereby being separate from each other.

US Pat. No. 11,113,609

MACHINE-LEARNING SYSTEM AND METHOD FOR IDENTIFYING SAME PERSON IN GENEALOGICAL DATABASES

ANCESTRY.COM OPERATIONS I...


1. A computer-implemented method comprising:identifying a first tree person from a first genealogical tree and a second tree person from a second genealogical tree, wherein both the first genealogical tree and the second genealogical tree comprise a plurality of interconnected tree persons corresponding to individuals that are related to each other;
extracting a plurality of features from both the first tree person and the second tree person to generate a first feature vector and a second feature vector;
after extracting the plurality of features from both the first tree person and the second tree person, calculating a plurality of metrics between the first feature vector and the second feature vector to generate a metric function containing a plurality of values, wherein each of the plurality of metrics corresponds to a similarity between a first feature from the first feature vector and a second feature from the second feature vector that corresponds to the first feature;
generating feature weights having a plurality of values by inputting the plurality of features into a machine-learning model, wherein the machine-learning model is configured to output the feature weights based on receiving an input comprising the plurality of features, wherein, prior to generating the feature weights, the machine-learning model was trained by:providing training data comprising pairs of tree persons to the machine-learning model; and
modifying the machine-learning model using an error computed based on an output of the machine-learning model when provided with the training data; and
generating a score by calculating a weighted sum of the plurality of values of the metric function being weighted by the plurality of values of the feature weights, wherein the weighted sum is calculated by weighting each of the plurality of values of the metric function by a corresponding value from the plurality of values of the feature weights.


US Pat. No. 11,113,608

HYBRID BOT FRAMEWORK FOR ENTERPRISES

Accenture Global Solution...


21. A system, comprising:one or more processors; and
a computer-readable storage device coupled to the one or more processors and having instructions stored thereon which, when executed by the one or more processors, cause the one or more processors to perform operations for managing interactions with an artificial intelligence (AI) assistant on a hybrid framework, the operations comprising:receiving communication data from a device, the communication data comprising data input by a user of the device;
determining a context based on an extended finite state machine that defines contexts and transitions between contexts, each state of the extended finite state machine comprising a context, transitions in a set of transitions between states comprising tuples of intent, entity, and action, a first transition comprising a first tuple comprising a first populated intent, a first populated entity, and a first populated action, and a second transition comprising a second tuple comprising a second populated intent, an unpopulated entity, and an unpopulated action;
transmitting a service request to at least one cloud-hosted service, the service request being provided at least partially based on masking sensitive information included in the communication data;
receiving a service response from the at least one cloud-hosted service, the service response comprising one or more of an intent, and an entity;
determining at least one action that is to be performed by at least one back-end source system based on the service response;
providing a user response at least partially based on an action results received from the at least one back-end source system; and
transmitting the user response to the device.


US Pat. No. 11,113,607

COMPUTER AND RESPONSE GENERATION METHOD

HITACHI, LTD., Tokyo (JP...


1. A computer comprising:a processor;
a storage device connected to the processor; and
an interface connected to the processor,
the storage device including a graph type knowledge database that stores graph type knowledges each representing a relevance among elements constituting a sentence that defines a knowledge using a node and an edge,
the graph type knowledge database includes graph data that manages a structure of each of the graph type knowledges,
the processor generating a response to an input document including a plurality of sentences using the graph type knowledge database, and
the processor being configured to:generate a first graph type knowledge from each of the sentences included in the input document;
search a second graph type knowledge similar to each of the plurality of first graph type knowledges while referring to the graph data on the basis of the plurality of first graph type knowledges, and the second graph type knowledges include a plurality of matching portions, each of the plurality of matching portions includes a plurality of the elements;
identify the plurality of second graph type knowledges included in a dense location where a density of the plurality of second graph type knowledges is high in a graph space corresponding to the graph type knowledge database as the second graph type knowledge used to generate the response;
calculate each distance between the plurality of elements in each of the plurality of matching portions in the dense location, for each of the plurality of matching portions calculate a total of the distances;
assign one of the plurality of matching portions with a smallest distance a first score and all of the other plurality of matching portions a second score;
calculate a value based on a plurality of different scores for each of a plurality of candidate responses, the plurality of candidate responses including the plurality of elements in the one of the plurality matching portions assigned the first score;
select one of the plurality of candidate responses having the calculated value above a threshold as the selected response; and
generate the response using the selected candidate response.


US Pat. No. 11,113,606

LEARNING METHOD, LEARNING DEVICE, PROGRAM, AND RECORDING MEDIUM

Konica Minolta, Inc., To...


1. A learning method, comprising:generating learning data that contains a composite image, including a computer graphics (CG) model of an object, and contains a training signal of the object; and
learning a recognition function of recognizing information regarding the object from the composite image by neuro computation using the learning data,
wherein the learning data is generated by generating new learning data on the basis of a gradient of error for each pixel of the composite image calculated from the composite image and the training signal by backpropagation, and
wherein the learning includes learning the recognition function by using the new learning data.

US Pat. No. 11,113,605

REINFORCEMENT LEARNING USING AGENT CURRICULA

DeepMind Technologies Lim...


1. A method of training a final agent policy neural network that is used to select actions to be performed by an agent interacting with an environment to perform a reinforcement learning task, the method comprising:maintaining data specifying a plurality of candidate agent policy neural networks, wherein each candidate agent policy neural network is configured to process a network input to generate a policy output, wherein the plurality of candidate agent policy neural networks includes the final agent policy neural network, and wherein the final agent policy neural network defines an action selection policy for the agent that is more complex than an action selection policy defined by at least one other candidate agent policy neural network in the plurality of candidate agent policy neural networks;
initializing mixing data that assigns respective weights to each of the candidate agent policy neural networks that define how policy outputs generated by the candidate agent policy neural networks are combined to generate combined policy outputs that are used to select actions to be performed by the agent;
training the plurality of candidate agent policy neural networks jointly to perform the reinforcement learning task, comprising:during the training, repeatedly generating training data for the plurality of candidate agent policy neural networks by controlling the agent using combined policy outputs generated in accordance with the respective weights for each of the candidate agent policy neural networks in the mixing data, and
at each of a plurality of training iterations:
obtaining, from the training data, a reinforcement learning training network input comprising a first observation of the environment,
generating, using the candidate agent policy neural networks and in accordance with the weights in the mixing data as of the training iteration, a first combined action selection policy for controlling the agent using the reinforcement learning training network input,
determining a reinforcement learning parameter update for the candidate agent policy neural networks using a reinforcement learning technique to generate combined action selection policies that result in improved performance of the agent on the reinforcement learning task, comprising determining a gradient with respect to parameters of the candidate agent policy neural networks of a reinforcement learning loss function that encourages the combined action selection policies to show improved performance on the reinforcement learning task,
obtaining, from the training data, a matching training network input comprising a second observation of the environment,
generating, using the candidate agent policy neural networks and in accordance with the weights in the mixing data as of the training iteration, a respective second policy output for each candidate agent policy neural network, and
determining a matching parameter update for the candidate agent policy neural networks that encourages the candidate agent policy neural networks to generate policy outputs that are aligned with other action policy outputs that generated by the other candidate agent policy neural networks by processing the same training network input, comprising computing a gradient of a matching loss function that measures differences in the respective second policy outputs generated by the candidate agent policy neural networks, and includes one or more terms that decrease an impact of the matching loss function on the training as the respective weight assigned to the final agent policy neural network in the mixing data increases during training; and

during the training, repeatedly adjusting the weights in the mixing data to, when generating combined policy outputs that are used to control the agent during the generating of the training data, favor higher-performing candidate agent policy neural networks.

US Pat. No. 11,113,604

TRAINING AND/OR UTILIZING AN INTERACTION PREDICTION MODEL TO DETERMINE WHEN TO INTERACT, AND/OR PROMPT FOR INTERACTION, WITH AN APPLICATION ON THE BASIS OF AN ELECTRONIC COMMUNICATION

GOOGLE LLC, Mountain Vie...


1. A method, comprising:identifying, by a client device, an electronic communication,the electronic communication including content that comprises natural language content, and
the electronic communication being received at the client device via a network interface of the client device, or being formulated at the client device via at least one user interface input device of the client device;

applying, by the client device, as at least part of first input to a first portion of a trained machine learning model that is stored locally at the client device:at least part of the natural language content of the electronic communication;

determining, by the client device, one or more additional input features;
applying, by the client device, as at least part of second input to a second portion of the trained machine learning model stored locally at the client device:at least one of the one or more additional input features;

processing, by the client device, the first and second input using the trained machine learning model to generate a predicted interaction value,the predicted interaction value indicating a likelihood of interaction with a second application accessible to the client device, the interaction with the second application being on the basis of the electronic communication,wherein the second application is in addition to an electronic communication application via which the electronic communication is formulated, or via which the electronic communication is rendered after being received;


determining, by the client device and based on the predicted interaction value, whether to present a selectable interface element via a display of the client device,wherein the selectable interface element, when selected via user interface input at the client device, causes interaction with the second application to provide at least part of the content of the electronic communication to the second application;

determining, by the client device, whether any interaction, with the second application and on the basis of the electronic communication, occurs in response to selection of the selectable interface element or in response to other user interface input provided at the client device;
updating, by the client device, trained parameters of at least part of the trained machine learning model based on whether any interaction occurred with the second application on the basis of the electronic communication, wherein updating the trained parameters comprises:determining a gradient based on whether any interaction occurred with the second application on the basis of the electronic communication, and based on the predicted interaction value, and
backpropagating the gradient over at least a portion of the trained machine learning model; and

using, by the client device, the trained machine learning model with the updated trained parameters in determining whether to present an additional selectable interface element for an additional electronic communication received or formulated at the client device.

US Pat. No. 11,113,603

TRAINING NETWORK WITH DISCRETE WEIGHT VALUES

PERCEIVE CORPORATION, Sa...


1. A method for configuring a machine-trained (MT) network comprising input nodes, output nodes, and interior nodes between the input and output nodes, wherein each node produces an output value and each interior node and output node receives as input values a set of output values of other nodes and applies weights to each received input value, wherein the weights are configurable parameters for training, the method comprising:propagating a set of inputs through the MT network to generate a set of outputs, each input having a corresponding expected output;
calculating a value of a continuously-differentiable augmented loss function that combines (i) a measurement of a difference between each output and its corresponding expected output and (ii) a term that biases training of the weights towards a set of discrete values, the set of discrete values for each weight comprising zero, a positive value for the weight, and a negation of the positive value for the weight, the term comprising a function of each of the weights that is (i) continuously differentiable and (ii) equal to zero for a particular weight when the particular weight equals any one of the discrete values for the weight; and
training the weights by back propagating a gradient of the continuously-differentiable augmented loss function at the calculated value.

US Pat. No. 11,113,602

ATTENTION-BASED SEQUENCE TRANSDUCTION NEURAL NETWORKS

Google LLC, Mountain Vie...


1. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to implement a neural network for generating a network output by processing an input sequence having a respective network input at each of a plurality of input positions in an input order, the neural network comprising:a first neural network comprising a sequence of one or more subnetworks, each subnetwork configured to, at each of a plurality of time steps, (i) receive a respective subnetwork input for each of a plurality of preceding input positions that precede a current input position corresponding to the time step, and (ii) generate a respective subnetwork output for each preceding input position, and wherein each subnetwork comprises:a self-attention sub-layer that is configured to, at each time step, receive the respective subnetwork input for each of the plurality of preceding input positions and, for each particular input position of the preceding input positions:apply a self-attention mechanism over the subnetwork inputs at the preceding input positions to generate a respective output for the particular input position, wherein applying a self-attention mechanism comprises: determining a query according to the subnetwork input at the particular input position, determining keys according to the subnetwork inputs at the preceding input positions, determining values according to the subnetwork inputs at the preceding input positions, and using the determined query, keys, and values to generate the respective output for the particular input position.



US Pat. No. 11,113,601

METHOD AND SYSTEM FOR BALANCED-WEIGHT SPARSE CONVOLUTION PROCESSING

MOFFETT TECHNOLOGIES CO.,...


1. A computer-implemented method, comprising:obtaining an input tensor and a plurality of filters, wherein the input tensor and the plurality of filters have a same number of channels;
segmenting the input tensor into a plurality of sub-tensors according to a number of available processors;
pruning each of the plurality of filters so that every predetermined number of channels comprise a fixed number of non-zero weights;
segmenting each of the plurality of filters into a plurality of the sub-filters, wherein each of the plurality of the sub-filters comprises the same number of non-zero weights;
respectively assigning the plurality of sub-tensors and the plurality of sub-filters to the available processors, wherein each of the plurality of sub-filters is represented in a compact memory layout storing the non-zero weights of the sub-filter as index-value pairs, each of the index-value pairs comprising a channel-dimension index, a width-dimension index, and a corresponding non-zero weight;
for each of the available processors, iterating each of the index-value pairs in the compact memory layout of the assigned plurality of sub-filters, and identifying a corresponding input value in the assigned sub-tensor at a location identified by the channel-dimension index and the width-dimension index of the index-value pair to perform a multiply-and-accumulate (MAC) operation to generate a partial sum;
reassigning the plurality of sub-filters to the available processors by rotating the plurality of sub-filters among the plurality of processors; and
accumulating a plurality of the partial sums generated from each of the plurality of processors to obtain an output tensor.

US Pat. No. 11,113,600

TRANSLATING SENSOR INPUT INTO EXPERTISE

Bsquare Corp., Bellevue,...


1. A method comprising:receiving sensor input data from a plurality of sensors and machine insights, the machine insights comprising one or more states, with a trainer, the trainer generating a selection signal;
operating a selector with the selection signal to select a classification scheme, the classification scheme specifying a classifier;
transforming the machine insights and the sensor input data into training data utilizing the classifier;
transforming the sensor input data into a class prediction with the classifier;
applying the machine insights and the sensor input data to a machine learner to generate a machine learner prediction; and
comparing the class prediction and the machine learner prediction with a tester and altering a machine state of one or more machines if the difference between the class prediction and the machine learner prediction is less than a threshold value and updating the machine learner if the difference between the class prediction and the machine learner prediction is not less than the threshold value.

US Pat. No. 11,113,599

IMAGE CAPTIONING UTILIZING SEMANTIC TEXT MODELING AND ADVERSARIAL LEARNING

Adobe Inc., San Jose, CA...


1. A non-transitory computer-readable storage medium having stored thereon computer-executable instructions that, when executed by at least one processor, cause a computing device to:train a sentence encoder neural network utilizing an adversarial classifier by:generating, utilizing the sentence encoder neural network, a predicted feature vector of a training sentence in a semantic space; and
applying the adversarial classifier to the predicted feature vector to constrain the sentence encoder neural network to a region of the semantic space that can be decoded to viable sentences; and

training an image encoder neural network and the sentence encoder neural network utilizing a semantic similarity constraint by:generating, utilizing the image encoder neural network, a predicted image feature vector in the semantic space from a training image, wherein the training image corresponds to a plurality of training captions;
generating, utilizing the sentence encoder neural network, a plurality of predicted caption feature vectors in the semantic space based on the plurality of training captions; and
applying the semantic similarity constraint by:comparing the plurality of predicted caption feature vectors with the predicted image feature vector within the semantic space to determine a semantic similarity loss representing a difference in semantic meaning between the plurality of predicted caption feature vectors and the predicted image feature vector; and
modifying parameters of the image encoder neural network and the sentence encoder neural network based on the semantic similarity loss.



US Pat. No. 11,113,598

DYNAMIC MEMORY NETWORK

salesforce.com, inc., Sa...


1. A method of using a question-answering model embedded in a process machine to answer questions, the method including:receiving, at a question module configured to compute a representation of a question, a question posed against one or more input facts stored as vector representations of input facts at one or more input fact memories in an input encoding module, wherein the one or more input fact memories are sequentially connected, and at least one input fact memory stores an end-of-passes representation;
accessing at least one question memory that stores a vector representation of the question at hand and a plurality of episodic memories to which attention gate weights are assigned;in a first pass sequentially traversing the one or more input fact memories:
applying a gating function to the input facts and contents received directly from the question memory,
calculating updated attention gate weights by iterating the input facts from the one or more input fact memories in the first pass, and
assigning the updated attention gate weights to a first episodic memory in the input encoding module;
in one or more subsequent passes each sequentially re-traversing the one or more input fact memories:
applying the gating function to the input facts and contents received directly from the question memory and the updated attention gate weights from an episodic memory that has been updated from a most recent previous pass,
re-calculating attention gate weights by re-iterating the input facts from the one or more input fact memories in each respective pass, and
assigning the newly re-calculated attention gate weights to a most recent episodic memory in the input encoding module;
updating a final hidden state of a gated recurrent unit (GRU) based on the newly re-calculated attention gate weights;
computing an updated episodic memory vector for the respective episodic memory based on the newly re-calculated attention gate weights and a contextual vector generated by the updated final hidden state of the GRU during the respective pass; and
completing the one or more subsequent passes when the end-of-passes representation is chosen as a most relevant fact during the respective pass; and

outputting, upon completion of the one or more subsequent passes, a final outcome from the most recent episodic memory in the input encoding module to an answer module that is separate from the input encoding module, and that iteratively generates a sequence of one or more output labels responsive to the question.

US Pat. No. 11,113,597

ARTIFICIAL NEURAL NETWORK AND METHOD OF TRAINING AN ARTIFICIAL NEURAL NETWORK WITH EPIGENETIC NEUROGENESIS

HRL Laboratories, LLC, M...


1. A method for retraining an artificial neural network trained on data from an old task, the artificial neural network comprising an input layer having a plurality of input layer nodes, a plurality of hidden layers comprising at least a first hidden layer and a second hidden layer each having a plurality of hidden layer nodes, an output layer having a plurality of output layer nodes, and a plurality of old connections connecting the plurality of input layer nodes, the plurality of hidden layer nodes, and the output layer nodes, the method comprising:training the artificial neural network on data from the old task and data from a new task different than the old task;
calculating a drift, utilizing Sliced Wasserstein Distance, in activation distributions of the plurality of hidden layer nodes during training of the artificial neural network with the data from the old task and data from the new task;
calculating a number of additional nodes to add to at least one of the plurality of hidden layers based on the drift in the activation distributions;
resetting connection weights between the plurality of input layer nodes, the plurality of hidden layer nodes, and the plurality of output layer nodes to values before the training of the artificial neural network on the data from the new task;
adding a first set of additional nodes of the number of additional nodes to the first hidden layer of the plurality of hidden layers, connecting the first set of additional nodes with new connections, and not connecting the first set of additional nodes added to the first hidden layer to the plurality of hidden layer nodes in the second hidden layer; and
training both the old connections and the new connections of the artificial neural network on data from the new task,
wherein the calculating the number of additional nodes is calculated according to Equation 1:Nnodes=c*log(D)+b??(Equation 1)

wherein Nnodes is the number of additional nodes, c and b are user-specified constants and D is the drift in the activation distributions.

US Pat. No. 11,113,596

SELECT ONE OF PLURALITY OF NEURAL NETWORKS

Longsand Limited


1. A device, comprising:an input unit that provides input data to one of a plurality of neural networks, each of the plurality of neural networks to be of a different size;
a propagation unit that determines a propagation time for the input data, the propagation time to relate to a time for the input data to propagate through one of the plurality of neural networks; and
a select unit that selects the one of the plurality of neural networks based on a comparison of the propagation time to a second time that comprises an amount of time used to transcribe the input data after the input data has propagated through the one of the plurality of neural networks.

US Pat. No. 11,113,595

ON-DEMAND INTELLIGENT ASSISTANT

THE TRAVELERS INDEMNIFY C...


1. An on-demand intelligent data retrieval system, the system comprising:one or more sensors;
an input/output interface device;
a processor; and
one or more computer-readable data storage devices storing program instructions that when executed by the processor, control the on-demand intelligent data retrieval system to perform operations comprising:obtaining one or more physical identifiers of a target individual using information received from the one or more sensors;
determining an identity of the target individual using the one or more physical identifiers;
caching the one or more physical identifiers of the target individual and the identity of the target individual in the one or more computer-readable data storage devices as baseline information of the target individual;
detecting keywords used in communications of a user with the target individual using speech recognition;
determining that the user desires additional information of the target individual based on the keywords;
determining, based on one or more of a frequency and a distance of the keywords, a confidence score that the additional information desired by the user corresponds to a predetermined type of information;
determining a query for the additional information of the target individual when the confidence score equals or exceeds a predetermined threshold, using the baseline information of the target individual and the keywords;
retrieving the additional information of the target individual from a remote database system using the query; and
providing, using the input/output interface device, the additional information of the target individual to the user.


US Pat. No. 11,113,594

MICROWAVE DIAGNOSTICS AND PASSIVE SENSORS FOR PIPELINE, WELL-BORE, AND BOILER-TUBE MONITORING

U.S. Department of Energy...


1. An integrated wireless detector for interrogating one or more metallic tubular structures, said integrated wireless detector comprising:a metallic tubular structure, wherein the cross section of said metallic tubular structure is approximately uniform;
an antenna, wherein said antenna is configured to operate in a radio or microwave frequency range, wherein said antenna propagates electromagnetic radiation within said metallic tubular structure;
a sensor comprising a surface acoustic wave sensor at the interior of said metallic tubular structure wherein said sensor is passive and wireless, wherein said electromagnetic radiation excites and interrogates said sensor, wherein said sensor re-emits electromagnetic radiation, wherein said antenna receives said re-emitted electromagnetic radiation; and
an interrogator, wherein said interrogator receives data from said antenna, wherein said interrogator processes said data.

US Pat. No. 11,113,593

CONTACTLESS METAL CARDS WITH FINGERPRINT SENSOR AND DISPLAY

Federal Card Services LLC...


1. A smartcard (SC) comprising:one or more modules (TCM, DM, FS, FSM), each having a module antenna (MA); and
a metal layer (ML) or metal card body (MCB) having one or more module openings (MO) for accepting the one or more modules, and further having one or more slits (S) or notches (N) extending from a periphery of the layer towards an interior position of the metal layer;
wherein:
at least one of the slits or notches do not extend to the one or more module openings (MO); and
further comprising:
a coupling structure (CLS, CS) comprising (i) one or more antenna structures (AS, PA, SeC, AP) (PA) overlying or fitting into at least one of the slits or notches, and (ii) a coupling loop structure (CLS) overlying the module antenna (MA) of at least one of the modules.

US Pat. No. 11,113,592

DATA-BEARING MEDIUM

Hewlett-Packard Developme...


13. A non-transitory computer readable medium to store computer executable instructions to control a processor to:apply to the data-bearing medium at a first section of a plurality of cells of a set of first opposite-shifted clusters representing a first value of the payload, the first section of the plurality of cells including shifts of the first opposite-shifted cluster; and
apply to the data-bearing medium at a second section of the plurality of cells of a set of second opposite-shifted clusters representing a second value of the payload, the second section of the plurality of cells including shifts of the second opposite-shifted cluster.

US Pat. No. 11,113,591

INFORMATION CONTROL APPARATUS, INFORMATION CONTROL SYSTEM, AND NON-TRANSITORY COMPUTER READABLE MEDIUM

FUJIFILM Business Innovat...


1. An information control apparatus comprising:a controller that controls a printer including a postprocessing unit that performs postprocessing on sheets of paper printed in units of copies and an accumulation unit comprising a plurality of trays, the accumulation unit accumulating the sheets of paper that have been subjected to the postprocessing such that the sheets of paper are stacked in units of copies,
wherein the controller controls the printer such that in a case where printing is stopped and then resumed in a process of the printing by the printer, an indicator indicating a copy that is being ejected at a time when the printing is stopped is inserted, and
wherein the controller performs control such that as the indicator, a copy that is first ejected after the printing is resumed is ejected offset or ejected in an orientation different from a transport direction of a sheet of paper that has been used until the printing is stopped.

US Pat. No. 11,113,590

DEVICE AND METHOD FOR OPTIMISING TRANSFORMATION BY DIGITAL PROCESSING OF A SUBSTRATE

MGI Digital Technology, ...


1. A method in a transformation device for printing on a pre-processed substrate by digital processing comprising:a step for printing by digital processing of a pre-processed substrate in a transformation station of the transformation device,
a step for the control of the transformation station by a means of control,
a recording step in the means of control of a digital source FN1 file representing the pre-processed substrate,
a recording step in the means of control of a digital FN3 file representing the printing to carry out on the pre-processed substrate by digital processing,
a step for the analysis of the pre-processed substrate by means of a X device in order to assign numerical values to it, the said X device configured to capture image data representing a surface of the pre-processed substrate and assign numerical values based on the image data, the said X device being located in the transformation device,
a recording step in the means of control of a digital FN2 file representing the pre-processed substrate analyzed by means of the X device and the acquisition of the corresponding digital data,
a step for comparison and recording in the means of control of the differences between the FN1 file and the FN2 file,
a step for the correction, by a means of correction that is part of the means of control, of the FN3 file by the differences between the FN1 file and the FN2 file, and
a recording step in the means of control of a digital FN3-CORR file supplied by the means of correction of the FN3 file, the step for printing by digital processing of the pre-processed substrate in a transformation station being the last step, the said last step being controlled by the means of control by means of the FN3-CORR file;
wherein the distance dE which corresponds to the distance between that point on the pre-processed substrate that at time “t” undergoes the printing in the transformation station and the point upstream of the analysis and acquisition zone at the same time “t” of the X device is greater than 1 mm.

US Pat. No. 11,113,589

SYSTEM AND METHOD FOR PRINTING CUSTOMIZED ITEMS

CCL LABEL, INC., Framing...


10. A printing system, comprising:a processor coupled to a memory storing computer-executable instructions, the processor executes or facilitates execution of the computer-executable instructions to perform operations comprising:
identifying a user-generated design arranged in a first template associated with a first type of print-receptive medium, the user-generated design having multiple visual elements;
initiating, based on user input, printing of the design to a second type of print-receptive medium based on a second template, wherein the first template and the second template comprise different parameters;
automatically repositioning and resizing the multiple visual elements according to the second template, wherein the second template defines locations, absolute positons, and print boundaries for each of the multiple visual elements,
wherein the first template is associated with a first label sheet, the second template is associated with a second label sheet, and the first label sheet comprises a different number of labels as the second label sheet; and
creating and storing a first printable file based on the first template format and a second printable file based on the second template format.

US Pat. No. 11,113,588

RANDOMIZATION-BASED HIERARCHICAL AND ASSOCIATIVELY ASSISTED VECTOR LEARNING FOR MACHINE VISION

United States of America ...


1. A method comprising:automatically recognizing an object in a digital image by:obtaining the digital image;
generating a first vector representation of a plurality of pixels of the obtained digital image;
randomizing the first vector representation to generate a first generalized vector representation of the digital image that is substantially an order of magnitude smaller than the first vector representation; and
searching a repository of hierarchically generalized vector representations of previously recognized digital images, to determine whether the first generalized vector representation of the digital image matches one or more of the previously recognized digital images, within a predetermined threshold value, based on determining a focus area within the obtained digital image, using associative memory.


US Pat. No. 11,113,587

SYSTEM AND METHOD FOR APPEARANCE SEARCH

AVIGILON CORPORATION, Va...


1. An appearance search system comprising:one or more cameras configured to capture video of a scene, the video having images of objects;
one or more processors and memory comprising computer program code stored on the memory and configured when executed by the one or more processors to cause the one or more processors to perform a method comprising:identifying one or more of the objects within the images of the objects, wherein the identifying comprises:identifying multiple ones of the objects within at least one of the images; and
dividing the at least one of the images into multiple divided images, each divided image of the multiple divided images comprising at least a portion of one of the identified objects; and

implementing a learning machine configured to generate signatures of the identified objects and generate a signature of an object of interest; and

a network configured to send the images of the objects from the camera to the one or more processors,
wherein the method further comprises:
comparing the signatures of the identified objects with the signature of the object of interest to generate similarity scores for the identified objects; and
transmitting an instruction for presenting on a display one or more of the images of the objects based on the similarity scores.

US Pat. No. 11,113,586

METHOD AND ELECTRONIC DEVICE FOR RETRIEVING AN IMAGE AND COMPUTER READABLE STORAGE MEDIUM

BOE TECHNOLOGY GROUP CO.,...


1. A method for retrieving an image, comprising:processing an image to be retrieved using a first neural network to determine a local feature vector of the image to be retrieved;
processing the image to be retrieved using a second neural network to determine a global feature vector of the image to be retrieved; and
determining, based on the local feature vector and the global feature vector, an image having a similarity to the image to be retrieved which is higher than a similarity threshold;
wherein the first neural network is trained by using a loss function as follows:Lt(ya,yp,yn)=max(?ya?yp?22??ya?yn?22+?,0),

where Lt represents a loss function for the first neural network, ya is a feature vector of a standard image, yp is a feature vector of a positive sample, yn is a feature vector of a negative sample, ???22 represents a square of 2-norm of a vector, max( ) represents a maximum value solving function, and ? is margin value.

US Pat. No. 11,113,585

ARTIFICIALLY INTELLIGENT SYSTEMS, DEVICES, AND METHODS FOR LEARNING AND/OR USING VISUAL SURROUNDING FOR AUTONOMOUS OBJECT OPERATION


1. A system comprising:one or more processors; and
one or more memories that store at least a first one or more digital pictures correlated with a first one or more instruction sets for operating a first object of a first application program, wherein the one or more processors are configured to perform at least:
receiving or generating a new one or more digital pictures that depict at least a portion of a surrounding of: the first object of the first application program, a second object of the first application program, or a first object of a second application program;
determining the first one or more instruction sets for operating the first object of the first application program based on at least partial match between the new one or more digital pictures and the first one or more digital pictures; and
at least in response to the determining, executing the first one or more instruction sets for operating the first object of the first application program, wherein the first object of the first application program, the second object of the first application program, or the first object of the second application program autonomously performs one or more operations defined by the first one or more instruction sets for operating the first object of the first application program.

US Pat. No. 11,113,584

SINGLE FRAME 4D DETECTION USING DEEP FUSION OF CAMERA IMAGE, IMAGING RADAR AND LIDAR POINT CLOUD

NIO USA, Inc., San Jose,...


1. A method for object detection, the method comprising:receiving, by a processor, sensor data indicative of one or more objects for each of a camera subsystem, a LiDAR subsystem, and an imaging RADAR subsystem,
wherein the sensor data includes camera image data, LiDAR point cloud data and imaging RADAR point cloud data and the sensor data is received simultaneously and within one frame for each of the camera subsystem, the LiDAR subsystem, and the imaging RADAR subsystem;
extracting, by the processor, one or more feature representations of the objects from the camera image data, LiDAR point cloud data and imaging RADAR point cloud data;
generating, by the processor, image feature maps from the extracted one or more feature representations of the objects from the camera image data, LiDAR feature maps from the LiDAR point cloud data, and imaging RADAR feature maps from the image RADAR point cloud data;
combining, by the processor, the image feature maps, the LiDAR feature maps, and the imaging RADAR feature maps to generate merged feature maps; and
generating, by the processor, object classification, object position, object dimensions, object heading and object velocity from the merged feature maps.

US Pat. No. 11,113,583

OBJECT DETECTION APPARATUS, OBJECT DETECTION METHOD, COMPUTER PROGRAM PRODUCT, AND MOVING OBJECT

Kabushiki Kaisha Toshiba,...


1. An object detection apparatus comprising:a hardware processor configured to:calculate a plurality of first feature maps from an image, at least one feature map having a different amount of an element included in an input image than at least one other feature map from the plurality of first feature maps;
generates a plurality of first combination maps by subjecting each element group of the first feature maps to a linear embedding process;
generate a spatial attention map for which a higher first weighted value is defined for a spatial attention map element comprising a higher direction relation in terms of a first space defined by a positional direction in the first feature maps and a relational direction between the first feature maps than a weighted value defined for another spatial attention map element, based at least in part on the first feature maps and the plurality of first combination maps;
generate a plurality of second feature maps by performing weighting on each of the first feature maps in accordance with a first weighted value indicated for the spatial attention map; and
detect an object included in the input image by using the second feature maps.


US Pat. No. 11,113,582

METHOD AND SYSTEM FOR FACILITATING DETECTION AND IDENTIFICATION OF VEHICLE PARTS

ADVANCED NEW TECHNOLOGIES...


1. A computer-implemented method for facilitating detection and identification of vehicle parts, the method comprising:storing a captured image of a vehicle, wherein the captured image includes a plurality of parts of the vehicle;
training a first algorithm based on at least images with pre-marked areas indicating final locations for multiple parts of the vehicle;
detecting, based on the trained first algorithm, a first area of the captured image in which a first part of the vehicle is located;
identifying, from a plurality of predetermined classes, a class corresponding to the first part in the detected first area, wherein the class indicates a location of the first part in relation to the vehicle; and
generating a result which indicates a list including an insurance claim item and corresponding damages based on the first area, the first part, and the class corresponding to the first part.

US Pat. No. 11,113,581

INFORMATION PROCESSING METHOD AND INFORMATION PROCESSING APPARATUS

FUJITSU LIMITED, Kawasak...


1. An information processing method by a network of computer implemented processes to perform training on a classification model by using a plurality of training samples, the method comprising:adjusting a distribution of feature vectors of the plurality of training samples in a feature space based on a typical sample in the plurality of training samples; and
performing training on the classification model by using the adjusted feature vectors of the plurality of training samples,
wherein,the typical sample is a training sample having a most typical feature of a class in the classification model, the most typical feature of the class is to cause the classification model not to classify the typical sample into another class, and
the adjusting includes causing feature vectors of other training samples other than the typical sample to aggregate towards a feature vector of the typical sample.


US Pat. No. 11,113,580

IMAGE CLASSIFICATION SYSTEM AND METHOD

INDUSTRIAL TECHNOLOGY RES...


1. An image classification system, comprising:a non-transitory storage device, configured to store a plurality of pseudo-centroid datasets, wherein the pseudo-centroid datasets correspond to a plurality of units of first image dataset, and the number of pseudo-centroid data points of each of the pseudo-centroid datasets is much smaller than the number of data points of each of the units of first image dataset;
a computing device, configured to receive second image data and compute a plurality of feature values of the second image data; and
a first processing device, configured to receive the feature values and the pseudo-centroid datasets, and compare the feature values with the pseudo-centroid data points to identify and classify the second image data.

US Pat. No. 11,113,578

LEARNED MODEL-BASED IMAGE RENDERING

Adobe, Inc., San Jose, C...


1. A method for rendering non-photorealistic images, comprising:generating, using machine learning system, a painting agent for reproducing images in accordance with a painting style, wherein the painting agent is configured to reproduce an image by determining brushstrokes of the painting style that correspond to features of the images, the brushstrokes being determined from an action space including a set of brushstrokes the painting agent is configured to render within a user interface;
determining a constraint limiting at least one brushstroke corresponding to a feature of the image; and
generating a constrained version of the painting agent for reproducing images in accordance with the painting style and the constraint, wherein the constrained version of the painting agent determines brushstrokes within a subspace of the action space of the painting agent, the subspace of the action space including a subset of the set of brushstrokes that correspond to the constraint.

US Pat. No. 11,113,577

SYSTEMS AND METHODS FOR DETECTING LATERALITY OF A MEDICAL IMAGE

GE PRECISION HEALTHCARE L...


1. An x-ray image laterality detection system, comprising:a detection computing device comprising at least one processor in communication with at least one memory device, wherein said at least one processor is programmed to:execute a neural network model for analyzing x-ray images, wherein the neural network model is trained with training x-ray images as inputs and observed laterality classes associated with the training x-ray images as outputs;
receive an unclassified x-ray image;
analyze the unclassified x-ray image using the neural network model;
assign a laterality class to the unclassified x-ray image based on the analysis;
if the assigned laterality class is not target laterality, the at least one processor is programmed to:adjust the unclassified x-ray image to derive a corrected x-ray image having the target laterality; and
output the corrected x-ray image; and

if the assigned laterality class is the target laterality, the at least one processor is programmed to output the unclassified x-ray image.


US Pat. No. 11,113,576

INFORMATION PROCESSING APPARATUS FOR TRAINING NEURAL NETWORK FOR RECOGNITION TASK AND METHOD THEREOF

CANON KABUSHIKI KAISHA, ...


1. An apparatus comprising:a processor; and
a memory coupled to the processor storing instructions that, when executed by the processor, cause the processor to function as:
a task setting unit configured to set a plurality of recognition tasks for which a neural network or a classifier is trained, wherein the plurality of recognition tasks is to recognize targets different from each other;
a training unit configured to train the neural network or the classifier for the plurality of tasks based on training data and a teaching value for the plurality of recognition tasks;
an evaluation unit configured to evaluate a training result of the neural network or of the classifier; and
a parameter setting unit configured to set a training parameter including weight assigned to errors in the plurality of recognition tasks in training the neural network or the classifier for the plurality of recognition tasks, based on a result of evaluation by the evaluation unit,
wherein the training unit performs second training on the neural network or the classifier according to the training parameter set by the parameter setting unit based on the result of evaluation of first training by the evaluation unit.

US Pat. No. 11,113,575

AUTOMATIC IMAGE SELECTION FOR ONLINE PRODUCT CATALOGS

eBay Inc., San Jose, CA ...


1. A method comprising:gathering, a first set of feature data for a first image included as part of a first listing for a first item, the first set of feature data including image features describing the first image and user features describing a first user that posted the first listing for the first item;
determining a first probability score for the first image by using the first set of feature data as input in a machine learning model, the first probability score indicating an estimated probability that the first image is suitable to represent the first item, the machine learning model having been trained based on a set of training images of the first item and sets of feature data associated with the set of training images;
gathering, a second set of feature data for a second image included as part of a second listing for the first item, the second set of feature data including image features describing the second image and user features describing a second user that posted the second listing for the first item;
determining a second probability score for the second image by using the second set of feature data as input in the machine learning model, the second probability score indicating an estimated probability that the second image is suitable to represent the first item; and
selecting, based on a comparison of at least the first probability score and the second probability score, the first image to represent the first item.

US Pat. No. 11,113,574

METHODS FOR PERFORMING SELF-SUPERVISED LEARNING OF DEEP-LEARNING BASED DETECTION NETWORK BY USING DEEP Q-NETWORK AND DEVICES USING THE SAME

Stradvision, Inc., Gyeon...


1. A method for performing self-supervised learning of a deep-learning based detection network by using a deep Q-network, comprising steps of:(a) on condition that a detection network capable of performing an object detection has been trained with at least one training data stored in a training database, a learning device, upon acquiring at least one first unlabeled image from an unlabeled database, performing or supporting another device to perform processes of (i) inputting the first unlabeled image into the detection network, to thereby allow the detection network to perform the object detection on the first unlabeled image and thus to generate first object detection information, (ii) generating a first state set by referring to the first object detection information, wherein the first state set includes a (1_1)-st classification confidence to a (1_k1)-th classification confidence, a (1_1)-st regression uncertainty to a (1_k1)-th regression uncertainty, and a (1_1)-st pooled feature map to a (1_k1)-th pooled feature map, respectively corresponding to a (1_1)-st bounding box indicating a 1st object included in the first unlabeled image to a (1_k1)-th bounding box indicating a k1th object included in the first unlabeled image, and wherein k1 is an integer bigger than or equal to 1, (iii) inputting the first state set into a deep Q-network, to thereby allow the deep Q-network to perform a learning operation on the first state set and thus to generate a Q-value including an acceptance score and a rejection score, and (iv) generating an action by applying an argMax function to the Q-value;
(b) the learning device performing or supporting another device to perform processes of (i) (i-1) if the action is determined as corresponding to an acceptance of the first unlabeled image, adding a labeled image to the training database as the training data wherein the labeled image is generated by inserting the first object detection information into the first unlabeled image, deleting the first unlabeled image from the unlabeled database, retraining the detection network by using at least one of the training data included in the training database, and thus generating a reward by referring to a first accuracy wherein the first accuracy is obtained from a result of testing the detection network by using a validation database, (i-2) if the action is determined as corresponding to a rejection of the first unlabeled image, deleting the first unlabeled image from the unlabeled database and generating the reward by referring to a second accuracy wherein the second accuracy is obtained from a result of testing the detection network by using the validation database, and (ii) upon acquiring at least one second unlabeled image from the unlabeled database, (ii-1) inputting the second unlabeled image into the detection network, to thereby allow the detection network to perform the object detection on the second unlabeled image and thus to generate second object detection information, (ii-2) generating a second state set by referring to the second object detection information, wherein the second state set includes a (2_1)-st classification confidence to a (2_k2)-th classification confidence, a (2_1)-st regression uncertainty to a (2_k2)-th regression uncertainty, and a (2_1)-st pooled feature map to a (2_k2)-th pooled feature map, respectively corresponding to a (2_1)-st bounding box indicating a 1st object included in the second unlabeled image to a (2_k2)-th bounding box indicating a k2th object included in the second unlabeled image, and wherein k2 refers to an integer bigger than or equal to 1, and (ii-3) storing the first state set, the action, the reward, and the second state set as elements of a transition vector in a memory; and
(c) the learning device performing or supporting another device to perform a process of generating a minibatch by sampling at least one specific transition vector to be used as at least one transition vector for training from the memory and then training the deep Q-network by using the minibatch such that the deep Q-network outputs the action for increasing the reward according to the first state set and the second state set.

US Pat. No. 11,113,573

METHOD FOR GENERATING TRAINING DATA TO BE USED FOR TRAINING DEEP LEARNING NETWORK CAPABLE OF ANALYZING IMAGES AND AUTO LABELING DEVICE USING THE SAME

Superb AI Co., Ltd., Seo...


1. A method for generating training data to be used for training a deep learning network capable of analyzing images, comprising steps of:(a) if one or more test images are acquired, an auto labeling device performing or supporting another device to perform (i) a process of allowing a labeling network to label each of the test images and thus to generate each of labeled test images including primary labeling information and primary confidence scores, on one or more primary objects in each of the test images wherein each of the primary confidence scores is a value ranging from 0 to 1 representing a probability that each of the primary objects is present in its corresponding each of primary labeled regions included in the primary labeling information, (ii) a process of allowing at least one labeler to verify each piece of the primary labeling information for each of the labeled test images, to thereby generate correction-related class information, wherein the correction-related class information includes information on a first verification class representing a class of a first primary label, among primary labels of the primary labeling information, required to be corrected or having been corrected and a second verification class representing a class of a second primary label, among the primary labels of the primary labeling information, not required to be corrected or not having been corrected, for each piece of the primary labeling information, (iii) a process of setting a first threshold confidence score to be used for determining whether it becomes unnecessary for the labeler to verify the primary labeling information by referring to the primary confidence scores and the correction-related class information, respectively corresponding to the primary labeling information, and (iv) a process of setting a second threshold confidence score as a preset maximal allowed error, wherein the preset maximal allowed error is less than the first threshold confidence score;
(b) if one or more unlabeled images are acquired, the auto labeling device performing or supporting another device to perform (i) a process of allowing the labeling network to label each of the unlabeled images and thus to generate labeled images including secondary labeling information and secondary confidence scores, on one or more secondary objects in each of the unlabeled images wherein each of the secondary confidence scores is a value ranging from 0 to 1 representing a probability that each of the secondary objects is present in its corresponding each of secondary labeled regions included in the secondary labeling information, (ii) a process of allowing an object difficulty estimation module to (ii-1) generate each of object difficulty scores on each piece of the secondary labeling information by using (1) each of the secondary confidence scores corresponding to each piece of the secondary labeling information and (2) the first threshold confidence score, wherein each of the object difficulty scores is a value ranging from 0 to 1 representing a probability of necessity for verifying each piece of the secondary labeling information, and (ii-2) determine each of object difficulty classes on each piece of the secondary labeling information by using (1) each of the secondary confidence scores corresponding to each piece of the secondary labeling information and (2) the second threshold confidence score, wherein the object difficulty classes include a hard object class representing a first part, among the secondary labeling information, required to be verified by the labeler and an easy object class representing a second part, among the secondary labeling information, not required to be verified by the labeler, (iii) a process of allowing an image difficulty estimation module to (iii-1) generate each of image difficulty scores on each of the labeled images by referring to each of the object difficulty scores on each piece of the secondary labeling information, wherein each of the image difficulty scores is a value ranging from 0 to 1 representing a probability of necessity for verifying each of the labeled images, and (iii-2) determine each of image difficulty classes on each of the labeled images by referring to the image difficulty scores, wherein the image difficulty classes include a hard image class representing a class of one or more first labeled images, among the labeled images, required to be verified by the labeler and an easy image class representing a class of one or more second labeled images, among the labeled images, not required to be verified by the labeler; and
(c) the auto labeling device performing or supporting another device to perform (i) a process of transmitting, to the labeler, the first labeled images which are labeled as the hard image class by referring to each of the image difficulty classes on each of the labeled images, to thereby allow the labeler to verify the first labeled images and thus to generate verified labeled images, and (ii) a process of generating the training data comprised of (1) the second labeled images which are labeled as the easy image class and (2) the verified labeled images.

US Pat. No. 11,113,572

SYSTEMS, METHODS, AND STORAGE MEDIA FOR EVALUATING IMAGES

Vizit Labs, Inc., Boston...


1. A system comprising:one or more hardware processors including machine-readable instructions to:identify a first image;
extract a first set of features from the first image to generate a first feature tensor for the first image;
extract a second set of features from the first image to generate a second feature tensor for the first image;
identify a second image;
extract a third set of features from the second image to generate a third feature tensor for the second image;
extract a fourth set of features from the second image to generate a fourth feature tensor for the second image;
apply a first regression analysis to determine a first geometrical distance between the first feature tensor of the first image and the third feature tensor of the second image;
apply a second regression analysis to determine a second geometrical distance between the second feature tensor of the first image and the fourth feature tensor of the second image; and
determine a similarity between the first image and the second image based on the first geometrical distance and the second geometrical distance.


US Pat. No. 11,113,571

TARGET OBJECT POSITION PREDICTION AND MOTION TRACKING

Kognition LLC, Philadelp...


1. A computer-implemented method for target object position prediction, the method comprising:receiving, via a RGB camera a plurality of images depicting one or more persons positioned on a floor;
assigning one of a plurality of person location labels to each image indicating where the one or more persons are located relative to the floor;
training a foot position (FP) classifier to classify the images into the person location labels, wherein the FP classifier is configured according to a multi-layer architecture and the training results in determination of a plurality of weights for connecting layers in the multi-layer architecture;
creating a deployment of the FP classifier based on the multi-layer architecture, the plurality of weights, and the plurality of person location labels.

US Pat. No. 11,113,570

SYSTEMS AND METHODS FOR AUTOMATICALLY GENERATING TRAINING IMAGE SETS FOR AN ENVIRONMENT

THE BOEING COMPANY, Chic...


1. A method for generating a training set of images and labels for a native environment, the method implemented on a computing system comprising at least one processor in communication with at least one memory device, the method comprising using the at least one processor to:receive a plurality of physical coordinate sets;
retrieve, from the at least one memory device, environmental model data corresponding to a georeferenced model of the native environment, the environmental model data defining a plurality of environmental features;
create a plurality of two-dimensional (2-D) rendered images from the environmental model data, each of the 2-D rendered images corresponding to a view from one of the physical coordinate sets, the plurality of 2-D rendered images including one or more of the environmental features;
calculate, for each 2-D rendered image, metadata based on the environmental model data, the metadata including a spatial relationship from the corresponding physical coordinate set to at least one of the one or more environmental features;
generate linking data associating each of the 2-D rendered images with (i) labels for the one or more included environmental features, (ii) a corresponding native image, and (iii) the metadata; and
store the training set including the 2-D rendered images, the labels, the corresponding native images, the metadata, and the linking data.

US Pat. No. 11,113,569

INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING METHOD, AND COMPUTER PROGRAM PRODUCT

Kabushiki Kaisha Toshiba,...


1. An information processing device, comprising:processing circuitry configured todetermine whether unlabeled data whose class label is unknown is non-targeted data that is not targeted for pattern recognition to be performed by a first classifier, the determination being performed by a second classifier;
train the first classifier through semi-supervised learning using a first training dataset including a piece of the unlabeled data determined not to be the non-targeted data and not including a piece of the unlabeled data determined to be the non-targeted data;
cut apiece of portion data out of a piece of the unlabeled data;
generate a piece of pseudo-non-targeted data by assigning, to the piece of portion data, a non-targeted label indicating the non-targeted data; and
train the second classifier by using a second training dataset including the generated pseudo-non-targeted data.


US Pat. No. 11,113,568

DEVICES, SYSTEMS, AND METHODS FOR DEVICE-ERROR ANALYSIS USING COMPUTER VISION AND MACHINE LEARNING

Canon Kabushiki Kaisha, ...


1. An apparatus comprising:one or more computer-readable storage media; and
one or more processors that are configured to cause the apparatus to perform operations including:obtaining a video of a device, wherein the device includes one or more light emitters that are visible in the video;
inputting the video to a first machine-learning model and executing the first machine-learning model, wherein the first machine-learning model outputs a time series of light-emitting states that indicates respective light-emitting states of the light emitters at respective times in the time series; and
inputting the time series of light-emitting states to a second machine-learning model and executing the second machine-learning model, wherein the second machine-learning model outputs a status indicator of the device.


US Pat. No. 11,113,567

PRODUCING TRAINING DATA FOR MACHINE LEARNING

Amazon Technologies, Inc....


1. A system to generate training data for machine learning, comprising:a target vehicle, including:a first position tracking component that determines a position of the target vehicle as the target vehicle navigates a route and generates position data for the target vehicle; and
a transmitter configured to transmit the position data;

a station, including:an antenna configured to receive the position data from the target vehicle;
a camera at a known position and orientation, the camera configured to generate image data that includes a representation of the target vehicle when the target vehicle is within a field of view of the camera;
one or more processors; and
a memory storing program instructions that when executed by the one or more processors cause the one or more processors to at least:correlate the position data and the image data;
determine, based at least in part on the correlated position data and the image data, one or more pixels of the image data corresponding to the target vehicle; and
label the one or more pixels as the target vehicle to produce training data that includes the image data and the label of the one or more pixels.



US Pat. No. 11,113,566

IMAGE PROCESSING SYSTEM, METHOD, AND APPARATUS SPECIFYING AN OBJECT INCLUDED IN A CAPTURED IMAGE OUTSIDE A VEHICLE

TOYOTA JIDOSHA KABUSHIKI ...


1. An image processing system comprising:an image acquisition unit configured to acquire a captured image obtained by imaging a vehicle outside;
a dictionary storage memory configured to store dictionary data to be referred to in specifying an object included in the captured image;
a specification unit configured to specify the object based on the dictionary data, the specification unit determining the object to be an unspecifiable object when the object cannot be specified based on the dictionary data;
a behavior information acquisition unit configured to acquire behavior information indicating a behavior state of the vehicle; and
a classification unit configured to, based on the behavior information of the vehicle with respect to the unspecifiable object, classify whether or not the vehicle needs to avoid the unspecifiable object based on whether the vehicle shows a behavior for (i) avoiding the unspecifiable object or (ii) passing through the unspecifiable object without avoiding the unspecifiable object,
wherein image data of the unspecifiable object along with a classification result of the classification unit are used for creating the dictionary data for the unspecifiable object.

US Pat. No. 11,113,565

SYSTEMS AND METHODS FOR INTELLIGENT AND INTERPRETIVE ANALYSIS OF SENSOR DATA AND GENERATING SPATIAL INTELLIGENCE USING MACHINE LEARNING

Ambient AI, Inc., Palo A...


1. An enterprise video surveillance system comprising:a plurality of video cameras positioned within a building, each camera having a different field-of-view (FOV), at least two cameras having overlapping FOVs;
a network switch coupled to the plurality of video cameras;
a comprehension system that is communicatively coupled to the plurality of video cameras via the network switch and that includes a rendering of the building, a knowledge graph that stores contextual information for the rendering, and a user interface that includes a visual representation of the rendering superimposed with visual representations of at least a portion of the contextual information and semantic information generated by the comprehension system from image data of the plurality of cameras; and
a user interface system that receives the user interface from the comprehension system via the network switch and displays the user interface.

US Pat. No. 11,113,564

PERFORMING DISTANCE-BASED FEATURE SUPPRESSION

Texas Instruments Incorpo...


1. An automobile driver-assistance system comprising:an image processing system operable to receive an image from an image capture device, wherein the image processing system includes:a feature list generator operable to produce a list of features of the image, wherein each feature of the list of features has a respective measure of a property; and
a suppression component operable to:identify a subset of features of the list of features that are located within a distance of a first feature of the list of features;
compare the measures of the property of each feature of the subset of features; and
in response to the measure of the property of a second feature of the subset of features being greater than each of the measures of the property of a remainder of the subset of features:
mark the second feature as valid; and
mark the remainder of the subset of features as suppressed.



US Pat. No. 11,113,563

APPARATUS FOR DETECTING OBJECT AND METHOD THEREOF

Hyundai Motor Company, S...


1. An apparatus for detecting an object, the apparatus comprising:at least one processor configured to extract information for object detection from image data frames based on a hierarchical structure of a convolutional neural network (CNN) and transmit information for object detection extracted from an uppermost layer of the hierarchical structure to a lower layer to detect an object based on information received at each layer; and
storage configured to store the information for object detection and detected object information,
wherein the at least one processor further includes a hidden state top-down structure for receiving the feature information and the contextual information extracted for each layer of each image data frame; and
wherein the hidden state top-down structure includes a plurality of hidden state layers corresponding to a layer of the backbone network, and an uppermost hidden state layer sequentially transmits the contextual information received from the layer of the backbone network to a hidden state layer of the lower layer.

US Pat. No. 11,113,562

INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND PROGRAM

NEC Solution Innovators, ...


1. An information processing apparatus comprising:a determining unit that computes determination accuracy representing a probability that it is correct to use a first result as a result of a predefined determination on a determination target, and performs the predefined determination on the determination target based on the computed determination accuracy, the determining unit outputting the first result as the result of the predefined determination in a case where the determination accuracy is greater than a first threshold value, and outputting a second result as the result of the predefined determination in a case where the determination accuracy is smaller than a second threshold value (the first threshold value >the second threshold value);
a requesting unit that transmits a first request for requesting the predefined determination on the determination target to a first other apparatus in a case where the determination accuracy is equal to or greater than the second threshold value and is equal to or smaller than the first threshold value; and
an updating unit that updates at least one of the first threshold value and the second threshold value based on the result of the predefined determination performed by the first other apparatus,
wherein the first other apparatus performs the predefined determination by a method different from the determining unit.

US Pat. No. 11,113,561

METHOD, ARTIFICIAL NEURAL NETWORK, DEVICE, COMPUTER PROGRAM AND MACHINE-READABLE MEMORY MEDIUM FOR THE SEMANTIC SEGMENTATION OF IMAGE DATA

Robert Bosch GmbH, Stutt...


1. A method for providing calculation resource-saving semantic segmentation of image data of an imaging sensor with an artificial neural network, the method comprising:performing the following in a discriminative path of the artificial neural network, which includes an encoder path, a decoder path, the encoder path transitioning into the decoder path, the transition taking place via the discriminative path:dividing an input tensor as a function of a division function into at least one first slice tensor and at least one second slice tensor, the input tensor originating from the encoder path;
connecting the at least one first slice tensor to the at least one second slice tensor as a function of a first connection function to obtain at least one concatenated tensor;
connecting the at least one first slice tensor to a class tensor as a function of a second connection function to obtain a decoder tensor, the class tensor being of the at least one concatenated tensor; and
outputting the decoder tensor to the decoder path of the neural network.


US Pat. No. 11,113,560

BODY CONTOUR KEY POINT DETECTION METHODS, APPARATUSES, AND DEVICES

BEIJING SENSETIME TECHNOL...


1. A body contour key point detection method, performed by an electronic device, comprising:obtaining an image feature of an image block comprising a body;
obtaining, by means of a first neural network, a body contour key point prediction result of the body according to the image feature; and
obtaining, according to the body contour key point prediction result, a body contour key point in the image block, wherein the body contour key point is used for representing an outer contour of the body,
wherein the first neural network is trained in advance by means of a training image set comprising body contour key point marking information, wherein the training of the first neural network comprises:
obtaining an image feature of a sample image block comprising a body;
obtaining, by means of a first neural network to be trained, a body contour key point prediction result of the body according to the image feature of the sample image block; and
using a difference between the body contour key point prediction result and the body contour key point marking information as guidance information to perform supervised learning on the first neural network to be trained.

US Pat. No. 11,113,559

INFORMATION PROCESSING APPARATUS FOR IMPROVING TEXT DATA RECOGNITION, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY RECORDING MEDIUM

Ricoh Company, Ltd., Tok...


1. An information processing apparatus comprising:processing circuitry configured toacquire an electronic file containing first text data, and
determine, based on conversion tool information included in attribute information of the acquired electronic file, whether to use the first text data or second text data to perform a process, the second text data being generated through character recognition performed on an image contained in the acquired electronic file, and the conversion tool information representing a conversion tool used to convert an electronic file that contains no text data into the acquired electronic file.


US Pat. No. 11,113,558

INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING INFORMATION PROCESSING PROGRAM FOR CHARACTER STRING EXTRACTION

FUJIFILM Business Innovat...


1. An information processing apparatus comprising:a processor, configured to:extract a character string corresponding to a keyword from character strings including the keyword described across a plurality of lines, in accordance with an extraction condition of the character string corresponding to the keyword,wherein an extraction direction of the character string corresponding to the keyword, which is viewed from a description position of the keyword, is determined as the extraction condition, and
wherein in a case where the character string corresponding to the keyword is extracted from the plurality of lines, the extraction direction represents a direction of transition from a description line of the keyword toward a previous line or a direction of transition from the description line of the keyword toward a subsequent line;

combine extracted character strings in accordance with a line sequence; and
output the combined character strings as the character string corresponding to the keyword.


US Pat. No. 11,113,557

SYSTEM AND METHOD FOR GENERATING AN ELECTRONIC TEMPLATE CORRESPONDING TO AN IMAGE OF AN EVIDENCE

Vatbox, LTD., Herzeliya ...


1. A method for generating an electronic template corresponding to an image of an evidence, comprising:generating an unlabeled template corresponding to the image, the unlabeled template formatted to include a plurality of data elements organized in an array, wherein the generating includes segmenting the image into a first plurality of regions of interest (ROIs);
selecting a first labeled template from a plurality of labeled templates with a second plurality of ROIs and matching with the unlabeled template;
analyzing each of the plurality ROIs to identify at least a portion of a content within the ROI and a position of each of the plurality of ROIs within the image;
generating a label for each of the plurality of ROIs corresponding to the analysis, wherein the label is indicative of the at least a portion of the content and the position of the ROI within the image; and
classifying and storing the unlabeled template and the generated label for the evidence based on the matching, wherein the unlabeled template includes the plurality of ROIs and the labels corresponding to each ROI.

US Pat. No. 11,113,556

INFORMATION PROCESSING APPARATUS, PROGRAM, AND METHOD THAT DISPLAY CORRECTION CANDIDATE CHARACTER FOR SELECTED CHARACTER BASED ON FOUND CHARACTER STRING FROM MASTER DATA

CANON KABUSHIKI KAISHA, ...


1. An information processing apparatus comprising:a memory that stores a program of instructions; and
at least one processor in communication with the memory, wherein by executing the program of instructions, the at least one processor performs:
executing character recognition processing on a character string image including a plurality of characters;
displaying a character string as a result of the character recognition processing on the character string image;
in a case where one character in the character string displayed as the result of the character recognition processing is selected by a user, finding a first character string and a second character string from a plurality of character strings managed in a database
wherein the found first character string is different from the displayed character string in the selected one character,
wherein the found second character string is different from the displayed character string in a predetermined number of characters that include the selected one character and another character, and
wherein the predetermined number is two or three;
displaying at least one correction candidate character for the selected one character based on the found first character string and the found second character string; and
correcting, when one of the displayed at least one correction candidate character is selected by the user, the character string displayed as the result of the character recognition processing using the selected correction candidate character.

US Pat. No. 11,113,555

OBJECT DETECTION APPARATUS, TRAFFIC MONITORING SYSTEM, METHOD OF CONTROLLING AN OBJECT DETECTION APPARATUS AND PROGRAM

NEC CORPORATION, Tokyo (...


1. An object detection apparatus comprising:at least a processor; and
a memory in circuit communication with the processor,
wherein the processor is configured to execute program instructions stored in the memory to implement:
a discriminator applier configured to apply a discriminator which detects an object to images acquired in past and calculate object detection information which include at least location information of the object detected by the discriminator, in a learning phase; and
a candidate area calculator configured to perform a machine-learning by use of the object detection information and calculate an object candidate area information which includes at least information specifying a candidate area in which the object may appear in an image,
wherein the discriminator applier changes a parameter within a predetermined range at a time of applying the discriminator, in the learning phase, and calculates the object detection information including a parameter at a time of the detection of the object, and
wherein the candidate area calculator performs a machine-learning related to object detection information including the parameter at a time of the calculation of the object and calculates the object candidate area information including information specifying parameters at a time of applying the candidate area to the discriminator.

US Pat. No. 11,113,554

SYSTEMS AND METHODS FOR IDENTIFYING AND AUTHENTICATING ARTISTIC WORKS

Great Masters Art Authent...


15. A system for identifying and authenticating an object, comprising:an image data acquisition platform to acquire image data from an object in multiple electromagnetic (EM) spectrums along a coordinated array of sample regions of the object;
a data processing device, in communication with the image data acquisition platform; to analyze the acquired image data of the object and produce a quantitative data set that represents specific characteristics of the object associated with the multiple EM spectrums for each sample region,
wherein the data processing device is configured to (i) identify the object by creating a digital fingerprint that solely corresponds to the object and includes the quantitative data set, and generate an identification corresponding to the digital fingerprint, wherein the identification includes an alphanumeric string that is displayable as text, graphic, or audio to identify the object, or (ii) authenticate the object by evaluating the quantitative data set produced for the object by comparing with previously-generated quantitative data sets corresponding to other objects in order to determine an authenticity of the object to be the same object as one of the other objects; and
one or more data storage devices, in communication with the data processing device; to store the acquired data and analyzed data.

US Pat. No. 11,113,553

IRIS RECOGNITION USING FULLY CONVOLUTIONAL NETWORKS

Brown University, Provid...


2. A method of accelerated iris recognition comprising:exploring fully convolutional network (FCN) architectures for iris segmentation;
evaluating a performance versus a complexity trade-off for each FCN architecture by executing a full end-to-end iris recognition pipeline;
performing FCN selection based on its complexity and its end-to-end iris recognition performance such as equal error rate and receiver operating characteristics;
evaluating FCN complexity by measuring parameter counts and execution latency on an accelerator running on an embedded field programmable gate array (FPGA) platform; and
executing a full pipeline implementation on an embedded field programmable gate array (FPGA) platform.

US Pat. No. 11,113,552

ELECTRONIC DEVICE AND METHOD FOR DISPLAYING IMAGE FOR IRIS RECOGNITION IN ELECTRONIC DEVICE

Samsung Electronics Co., ...


1. An electronic device, comprising:a camera;
a display;
a memory storing an iris image and a plurality of images; and
a processor configured to:select an image for representing eyes from the memory;
activate an iris recognition function;
in response to activating the iris recognition function, control the camera to capture an eye image;
identify an eye included in the eye image captured by the camera;
identify a first image corresponding to a first distance among the plurality of images when a distance between the eye and the electronic device is the first distance;
control the display to display the first image, the first image being different from the eye included in the eye image, when the distance between the electronic device and the eye is a first distance;
identify a second image corresponding to a second distance among the plurality of images when the distance between the eye and the electronic device is the second distance;
change the first image into the second image obtained by differently processing at least one or more of a shape, clarity, transparency, brightness, color, or object size of the first image and control the display to display the second image associated with the first image when the distance between the electronic device and the eye is a second distance different from the first distance; and
perform authentication using the iris image and the eye included in the eye image when the distance between the electronic device and the eye included in the eye image captured by the camera is a distance within an iris-recognizable range.


US Pat. No. 11,113,551

SYSTEMS AND METHODS FOR DETERMINING LIKELIHOOD OF TRAFFIC INCIDENT INFORMATION

United Services Automobil...


1. A data acquisition system for injury analysis, comprising:a controller comprising memory and one or more processors, wherein the memory includes instructions that cause the one or more processors to:
perform a first analysis of movement of an occupant of a vehicle by determining a first positional change of a biomechanical point of the occupant between a first image and a second image;
receive an indication that a traffic incident has occurred;
perform a second analysis of movement of the occupant by determining a second positional change of the biomechanical point of the occupant between a third image and a fourth image in response to receiving the indication that the traffic incident has occurred;
determine a likelihood of injury, a severity of injury, or a combination thereof, to the occupant based on the first analysis and the second analysis; and
provide an indication of the likelihood of injury, the severity of injury, or the combination thereof.

US Pat. No. 11,113,550

METHOD AND DEVICE FOR REMINDING A DRIVER TO START AT A LIGHT SIGNAL DEVICE WITH VARIABLE OUTPUT FUNCTION

Bayerische Motoren Werke ...


1. A method for reminding a driver of a motor vehicle to start at a light signal device, the method comprising the acts of:detecting a light signal of a light signal device;
generating a stop signal when a stop light signal is detected as the light signal while the motor vehicle is at a standstill;
when the stop signal is present, generating a start signal when the light signal is detected as changing over to a drive light signal; and
transmitting the start signal to an output appliance via an interface, whereina line of vision of a driver of the motor vehicle and a position of the output appliance are detected and evaluated, and
the start signal is transmitted to the output appliance only if the output appliance is at a position in the line of vision of the driver.


US Pat. No. 11,113,549

METHOD AND DEVICE FOR ANALYZING AN IMAGE AND PROVIDING THE ANALYSIS FOR A DRIVING ASSISTANCE SYSTEM OF A VEHICLE

Robert Bosch GmbH, Stutt...


1. A method of an image analysis system of a vehicle for analyzing an image and providing the analysis for a driving assistance system of the vehicle, a plurality of operating states of the vehicle being predefined in the image analysis system and a plurality of image analysis processes being predefined in the image analysis system, the method comprising:recording the image;
identifying which one of the predefined plurality of operating states is a current operating state of the vehicle;
based on the one of the predefined plurality of operating states having been identified as being the current operating state of the vehicle, selecting, from the plurality of image analysis processes, at least one of the plurality of image analysis processes that is predefined in the image analysis system as corresponding to the one of the predefined plurality of operating states that has been identified as being the current operating state of the vehicle;
based on the selection, analyzing the image selectively using the at least one image analysis process that has been selected, without use of others of the plurality of image analysis processes; and
providing the analysis of the image as data values for the driving assistance system.

US Pat. No. 11,113,548

OBJECT DETECTION NEURAL NETWORKS

Waymo LLC, Mountain View...


1. A method comprising:processing, by one or more computers, a first input generated from first sensor data collected by one or more first sensors of a vehicle using a first high-recall object detection neural network, wherein the first sensor data characterizes an environment in a vicinity of the vehicle, and wherein the first high-recall object detection neural network is configured to:receive the first input; and
process the first input to generate:for each of a plurality of bounding boxes that each correspond to a respective region of the environment, a respective first confidence score that represents a probability that an object is present in the region of the environment corresponding to the bounding box;


selecting, based at least on the respective first confidence scores, a first region of the environment corresponding to a first bounding box of the plurality of bounding boxes;
in response to selecting the first region:obtaining, by the one or more computers, a second input characterizing the first region of the environment, wherein the second input is different from the first input and is generated from second sensor data collected by a different, second set of sensors than the first input, the different, second set of sensors comprising the one or more first sensors and at least one additional sensor that is of a different type than that of the one or more first sensors; and
processing, by the one or more computers, the second input using a high precision object detection neural network to generate a respective object score for each object category in a set of one or more object categories, wherein each object score represents a respective probability that an object belonging to the object category is present in the first region of the environment.


US Pat. No. 11,113,547

PLANNING CONTROL IN RESPONSE TO A DRIVING OBSTRUCTION DURING OPERATION OF AN AUTONOMOUS DRIVING VEHICLE (ADV)

BAIDU USA LLC, Sunnyvale...


1. A computer-implemented method for providing autonomous driving control for a vehicle, comprising:providing autonomous driving control for the vehicle using a first route plan based on a first set of driving rules, wherein the first set of driving rules include traffic rules providing guidance on traffic rules in jurisdictions, route rules providing guidance on preferences for routes, and ride comfort rules having preferences for speed or terrain;
recognizing, using one or more sensors of the vehicle, an occurrence of a driving obstruction, wherein recognizing the occurrence of a driving obstruction includes perceiving objects indicative of a potential obstruction and determining whether one or more other vehicles are at standstill or crossing over a median line;
in response to recognizing the driving obstruction, detecting a traffic flow pattern of the one or more other vehicles, including analyzing traffic flow pattern data by determining whether a number of vehicles within the one or more vehicles performing a maneuver exceeds a predetermined threshold related to the maneuver and converting a speed and direction of the one or more other vehicles within the detected traffic flow pattern into vectors;
determining a second route plan based on the detected traffic flow pattern, includingdetermining a trajectory for the vehicle to follow as the maneuver in response to the driving obstruction, wherein the determined trajectory is based on the speed and direction of the other vehicles,
determining a detour for the vehicle to follow in response to the driving obstruction,
comparing the detour to the maneuver based on one or more factors, and
determining to perform the maneuver over the detour based on the comparison of factors, wherein comparing the detour to the maneuver includes determining a traffic flow speed factor of the other vehicles maneuvering in response to the driving obstruction, wherein the traffic flow speed factor is used to determine an estimated time for the vehicle to maneuver around the driving obstruction, and determining an estimated time factor for the vehicle to complete the detour based on real-time traffic information; and

updating the first route plan with the second route plan utilizing the first set of driving rules to continue providing the autonomous driving control for the vehicle.

US Pat. No. 11,113,546

LANE LINE PROCESSING METHOD AND DEVICE

Baidu Online Network Tech...


1. A lane line processing method, comprising:obtaining distances between lane line points in a first image;
determining direction densities of the individual lane line points by using the distances between the lane line points, each direction density indicating the probability that an individual lane line point approaches other lane line points in a direction;
dividing the lane line points into groups corresponding to lane lines by using the direction densities of the individual lane line points; and
obtaining representation information of the lane lines corresponding to the groups by using the lane line points in the groups.

US Pat. No. 11,113,545

ROAD DETECTION USING TRAFFIC SIGN INFORMATION

HITACHI AUTOMOTIVE SYSTEM...


1. A system comprising:one or more processors; and
one or more non-transitory computer-readable media storing a database including sign information for a plurality of different sign types of traffic signs, the sign information including, for each sign type of the plurality of sign types, a predefined lateral distance from the sign type to a road edge, wherein the sign information in the database is initially generated at least using information specified by a jurisdictional entity, wherein the sign information in the database is subsequently updated using empirical data received from a plurality of vehicles over time;
the one or more non-transitory computer-readable media further including executable instructions, which, when executed by the one or more processors, configure the one or more processors to:receive at least one image from at least one sensor;
recognize the sign type of a traffic sign in the at least one image; and
determine a likely location of the road edge in relation to a vehicle based at least partially on the recognized sign type and the predefined lateral distance specified by the sign information in the database, wherein determining the likely location of the road edge includes applying a first weight to the information specified by the jurisdictional entity in the database, and a second weight to the empirical data in the database.


US Pat. No. 11,113,544

METHOD AND APPARATUS PROVIDING INFORMATION FOR DRIVING VEHICLE

SAMSUNG ELECTRONICS CO., ...


1. A method comprising:detecting a lane region including lane demarcation lines from a driving image;
determining curvature information of a road on which a vehicle is driving based on map information;
estimating a lateral offset of the vehicle based on the lane region and a reference line having the curvature information; and
outputting a signal including information for driving the vehicle based on the curvature information and the lateral offset,
wherein the determining curvature information comprises:performing a linear regression analysis on a plurality of waypoints located on an edge of the road, wherein the plurality of waypoints are located within a point adjacent to a current location of the vehicle and another point away from the point adjacent to the current location of the vehicle by a look-ahead distance;
obtaining a regression function corresponding to a shape of the road based on the linear regression analysis; and
determining the curvature information corresponding to coefficients of the regression function, using the regression function.


US Pat. No. 11,113,543

FACILITY INSPECTION SYSTEM AND FACILITY INSPECTION METHOD

HITACHI HIGH-TECH FINE SY...


1. A facility inspection system comprising:a photographing device that photographs an image of a surrounding environment of a vehicle moving on a track;
a storage device that stores a reference alignment point cloud and a reference difference-extraction point cloud for each position on the track;
an alignment area separation unit that separates an alignment point cloud from a three-dimensional point cloud obtained from the image;
an alignment unit that performs an alignment of the reference alignment point cloud and the alignment point cloud, the alignment unit outputting alignment information;
a difference extraction unit that extracts a difference between the three-dimensional point cloud deformed based on the alignment information and the reference difference-extraction point cloud; and
an alignment area choosing unit that determines an area among a plurality of candidate areas as an alignment area, the area including a predetermined count or more of three-dimensional points detected via the photographing device, determining the area bydetermining whether a count of three-dimensional points in a first area of the plurality of candidate areas is equal to or greater than a threshold,
selecting the first area as the alignment area when the count of three-dimensional points on the first area is equal to or greater than the threshold, and
selecting a different area of the plurality of candidate areas to be the alignment area when the count of three-dimensional points on the first area is less than the threshold,

wherein the alignment point cloud is present in the alignment area, and
wherein the plurality of candidate areas each have a different priority order.

US Pat. No. 11,113,541

DETECTION OF OBJECT REMOVAL AND REPLACEMENT FROM A SHELF

7-ELEVEN, INC., Irving, ...


1. A system, comprising:a rack comprising shelves configured to store items;
an image sensor positioned such that a field-of-view of the image sensor encompasses at least a portion of the rack, wherein the image sensor is configured to generate angled-view images of the items stored on the shelves of the rack; and
a tracking subsystem coupled to the image sensor, the tracking subsystem comprising at least one processor configured to:determine that a person has interacted with the rack;
receive an image feed comprising frames of the angled-view images generated by the image sensor after the person has interacted with the rack;
determine, based on at least one angled-view image of the image feed, that the person interacted with a first item stored on the rack;
select a first image from the image feed associated with a first time before the person interacted with the first item, and a second image from the image feed associated with a second time after the person interacted with the first item;
over a period of time, track a pixel position of a wrist of the person in the image feed;
determine, based on the tracked pixel position of the wrist, a region-of interest defining a portion of the first image and a portion of the second image;
determine, based on a comparison of the portion of the first image defined by the region-of-interest to the portion of the second image defined by the region-of-interest, whether the first item was removed from the rack or the item was placed on the rack;
if it is determined that the first item was removed from the rack, assign the first item to the person; and
if it is determined that the item was placed on the rack, unassign the first item from the person.


US Pat. No. 11,113,540

VEHICLE MONITORING SYSTEM AND VEHICLE MONITORING METHOD

PANASONIC I-PRO SENSING S...


1. A vehicle monitoring system comprising:at least one camera; and
a server that is communicably connected to a client terminal,
wherein the cameraperforms capturing video data of a vehicle while sequentially switching between a first capturing condition and a second capturing condition, the first capturing condition including an image parameter for capturing a number provided on the vehicle entering an angle of view of the camera, and the second capturing condition including an image parameter for capturing a face of an occupant in the vehicle, and
transmits, to the server, a first captured video under the first capturing condition and a second captured video under the second capturing condition, and

wherein the serverarranges reproduction screens for the first captured video and the second captured video that are reproduceable in the client terminal, and
displays the reproduction screens on the client terminal based on the first captured video and the second captured video, and

wherein the image parameter in the first capturing condition is an exposure time equal to or less than a first reference value or a gain value equal to or smaller than a second reference value, and
the image parameter in the second capturing condition is an exposure time more than the first reference value or a gain value greater than the second reference value.

US Pat. No. 11,113,539

FISH MEASUREMENT STATION KEEPING

X Development LLC, Mount...


1. A computer-implemented method comprising:obtaining data that reflects present, sensed, environmental conditions that are associated with a fish pen;
providing, to a model that is trained to output, for given, input parameters that reflect sensed environmental conditions that are associated with the fish pen, a given set of output parameters for generating images of fish that are contained within the fish pen using one or more underwater cameras, particular parameters that reflect the present, sensed, environmental conditions that are associated with the fish pen;
obtaining, from the model, a particular set of output parameters; and
adjusting a position of one or more underwater cameras based on the particular set of output parameters.

US Pat. No. 11,113,538

OBJECT TRACKING APPARATUS, OBJECT TRACKING SYSTEM, OBJECT TRACKING METHOD, DISPLAY CONTROL DEVICE, OBJECT DETECTION DEVICE, AND COMPUTER-READABLE MEDIUM

NEC CORPORATION, Tokyo (...


1. An object tracking system comprising:at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform:generating, via a first detector, a first detection result of an object from a first image;
generating, via a second detector, a second detection result of the object from a second image, the second image being different from the first image;
calculating first position information of the object represented in a common coordinate system based on the first and second detection results;
transforming the first position information of the object represented in the common coordinate system to first transformed position information of the object represented in an individual coordinate system for the first detector;
transforming the first position information of the object represented in the common coordinate system to second transformed position information of the object represented in an individual coordinate system for the second detector;
generating, via the first detector, a third detection result of the object from a third image based on the first transformed position information of the object; and
generating, via the second detector, a fourth detection result of the object from a fourth image based on the second transformed position information of the object.


US Pat. No. 11,113,537

IMAGE DETECTION USING MULTIPLE DETECTION PROCESSES

HULU, LLC, Santa Monica,...


20. An apparatus comprising:one or more computer processors; and
a non-transitory computer-readable storage medium comprising instructions, that when executed, control the one or more computer processors to be operable for:
generating, using a first detector, a first output based on a first probability that an image was inserted in a video;
generating, using a second detector, a second output based on a second probability that an image was inserted in the video;
analyzing the first output from the first detector based on the first probability that the image was inserted in the video to determine whether the first output indicates whether the image is detected in the video;
analyzing the second output from the second detector based on the second probability that the image was inserted in the video to determine whether the second output indicates whether the image is detected in the video;
when either of the first output or the second output determines that the image exists in the video, outputting an indication that the image exists in the video; and
when the first output and the second output determines that the image does not exist in the video, outputting the indication that the image does not exist in the video to allow for another image to be inserted into the video.

US Pat. No. 11,113,536

VIDEO IDENTIFICATION METHOD, VIDEO IDENTIFICATION DEVICE, AND STORAGE MEDIUM

BOE Technology Group Co.,...


10. A video identification device, comprising:a memory configured to store instructions;
a processor coupled to the memory, wherein based on the instructions stored in the memory, the processor is configured to:
extract an image and an optical flow from a video;
classify the image by using a first machine learning model to obtain a first classification result, wherein the first machine learning model comprises a first machine learning submodel, a second machine learning submodel, a first fully connected layer, and a first classifier; and the processor is configured to:
input the image into the first machine learning submodel to obtain first feature information;
input the first feature information into the second machine learning submodel to obtain second feature information;
input the second feature information into the first fully connected layer to obtain third feature information; and
input the third feature information into the first classifier to obtain the first classification result;
classify the optical flow by using a second machine learning model to obtain a second classification result, wherein a depth of the first machine learning model is larger than a depth of the second machine learning model; and
fuse the first classification result and the second classification result to obtain an identification result of the video.

US Pat. No. 11,113,535

DETERMINING TACTICAL RELEVANCE AND SIMILARITY OF VIDEO SEQUENCES

Second Spectrum, Inc., L...


1. A method comprising:receiving a first video feed, capturing a first filmed occurrence, the first video feed comprising a sequence of video frames captured by a camera, wherein the first video feed is a video feed that is consumable by a client device;
detecting at least one game chance sequence from the sequence of video frames based on spatiotemporal analysis that identifies game chance boundary events;
determining at least one semantic label and associated location data of at least one tactically relevant event in the at least one game chance sequence;
concatenating the at least one semantic label and the associated location data as a first labeled tactical sequence; and
identifying from a library of stored game chance sequences at least one stored game chance sequence that is similar to the at least one game chance sequence from the first video feed based on a tactical similarity of a stored labeled tactical sequence of the at least one stored game chance sequence with the first labeled tactical sequence.

US Pat. No. 11,113,534

DETERMINING LOCALIZED WEATHER BY MEDIA CLASSIFICATION

Alarm.com Incorporated, ...


1. A computer-implemented method, comprising:obtaining images from a camera located at a monitored property;
determining that the monitored property is located within a particular geographic region;
obtaining, for each of the images from the camera at the monitored property and based on the particular geographic region, an expected weather forecast for the geographic region at a time the image was captured, and an actual weather condition at the monitored property at the time the image was captured;
generating a training set that includes each of the images labeled with both (i) an indication of the expected weather forecast for the geographic region at the time the image was captured and (ii) an indication of the actual weather condition at the monitored property at the time the image was captured;
training a machine-learning model to classify a current weather condition for the monitored property using the training set that includes the images from the camera, the indications of expected weather forecast for the geographic region at the time the images were captured, and the actual weather condition at the monitored property at the time the images were captured;
obtaining a subsequent image from the camera and a subsequent expected local weather forecast for the monitored property at the time the subsequent image was captured;
providing the subsequent image from the camera and the subsequent expected local weather for the monitored property at the time the subsequent image was captured as inputs to the machine-learning model; and
receiving, in response to providing the subsequent image from the camera and the subsequent expected local weather for the monitored property at the time the subsequent image was captured as inputs to the machine-learning model, a weather condition from the trained machine-learning model that indicates a particular weather condition at the monitored property based on the subsequent image from the camera and the subsequent expected local weather forecast for the monitored property at the time the subsequent image was captured.

US Pat. No. 11,113,533

SMART DISPLAY APPARATUS AND CONTROL SYSTEM

International Business Ma...


1. A computer-implemented method executed by a processor for reducing exposure of a plurality of objects to environmental conditions by employing a smart room tracking system, the method comprising:counting a number of individuals within a space including the plurality of objects via one or more image capture devices;
determining whether each individual makes direct eye contact with any of the plurality of objects;
shielding, via an object viewing controller associated with each object of the plurality of objects, an object of the plurality of objects from view when no direct eye contact is determined; and
evaluating each object of the plurality of objects to determine a total amount of time the object is exposed during a predetermined time period.

US Pat. No. 11,113,532

ARTIFICIAL INTELLIGENCE APPARATUS FOR RECOGNIZING OBJECT AND METHOD THEREFOR

LG ELECTRONICS INC., Seo...


13. A machine-readable non-transitory medium having stored thereon machine-executable instructions for recognizing at least one or more objects, the instructions comprising:obtaining image data for the at least one or more objects;
generating first identification information corresponding to the at least one or more objects from the image data using a default recognition model composed of at least one or more of the plurality of recognition models for generating identification information corresponding to the at least one or more objects from the image data;
measuring a confidence level for generation of the first identification information;
obtaining the first identification information as a recognition result of the at least one or more objects if the measured confidence level is equal to or greater than a first reference value; and
obtaining the second identification information corresponding to the at least one or more objects from the image data as a recognition result of the at least one or more objects using a compound recognition model composed of one or more of the plurality of recognition models if the measured confidence level is less than a first reference value,
wherein the default recognition model is a model defined by first weights for each of the plurality of recognition models,
wherein the compound recognition model is a model defined by second weights for each of the plurality of recognition models,
wherein the obtaining of the second identification information comprises:
determining the second weights corresponding to each of the plurality of recognition models based on the image feature vector extracted from the image data and construct the compound recognition model using the second weights if the measured confidence level is less than the first reference value.

US Pat. No. 11,113,531

ANNOTATION DEVICE, ANNOTATION METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM

PANASONIC INTELLECTUAL PR...


1. An annotation device, comprising:a similarity information obtainer that obtains similarity information indicating whether or not a plurality of labels to be added as annotation data to an image are similar to each other;
a determiner that determines a layout of the plurality of labels to be displayed on an operation screen for an annotation operation based on the similarity information;
a data obtainer that obtains the annotation data added to the images using the operation screen; and
an inspector that inspects the annotation data obtained by the data obtainer for an erroneously added label.

US Pat. No. 11,113,530

SYSTEM AND METHOD FOR DYNAMIC THREE DIMENSIONAL COMMAND AND CONTROL

BOOZ ALLEN HAMILTON INC.,...


1. A system for monitoring an operational area, the system comprising:a sensor arrangement including two or more sensors, wherein:
each sensor includes a processor configured to receive plural data streams from the sensor arrangement, each data stream including a different spatial characteristic of the operational area; and
each sensor is configured to:generate a three-dimensional (3D) virtual visualization of the operational area based on observational perspectives associated with the data streams and their associated spatial characteristics;
dynamically prioritize operational sub-regions within the operational area based on the spatial characteristics; and
generate a signal encoded with data for verifying the 3D virtual visualization of the operational area including the prioritized operational sub-regions.


US Pat. No. 11,113,529

PHOTOVOLTAIC PANEL RECOGNITION METHOD, GROUND STATION, CONTROL APPARATUS, AND UNMANNED AERIAL VEHICLE

SZ DJI TECHNOLOGY CO., LT...


1. A method for identifying a photovoltaic panel, comprising:acquiring a grayscale image of an infrared image captured by a camera mounted on a UAV, the grayscale image including an image of a photovoltaic panel;
performing edge extraction processing on an image in the grayscale image to obtain a monochrome image including a plurality of horizontal lines and a plurality of vertical lines, the horizontal lines being lines in a first direction, an average length of the lines in the first direction being greater than a preset length, the vertical lines being lines in a second direction, and an average length of the lines in the second direction being less than the preset length; and
identifying the photovoltaic panel in the monochrome image based on a relative positional relationship between the horizontal lines and the vertical lines in the monochrome image.

US Pat. No. 11,113,528

SYSTEM AND METHOD FOR VALIDATING GEOSPATIAL DATA COLLECTION WITH MEDIATED REALITY


1. A computer-implemented method of positioning a geospatial object with a mediated reality device, the method comprising:collecting a geospatial object comprising:receiving, from a global navigation satellite systems (GNSS) receiver, GNSS position data based on wireless signals received from a GNSS satellite;
determining, based on the GNSS position data, a position of a geospatial object;
generating an object definition associated with the geospatial object, the object definition comprising the position of the geospatial object and a type of the geospatial object; and
storing the object definition in a data storage; and

immediately after collecting the geospatial object, displaying and verifying the position of the geospatial object, by:determining an orientation of the mediated reality device in a physical scene;
determining relative positioning of the geospatial object in the physical scene based on the position of the geospatial object relative to the orientation of the mediated reality device;
displaying a visual representation of the geospatial object to a user on the mediated reality device using the relative positioning of the geospatial object in the physical scene for the user to verify positioning of the geospatial object; and
receiving input confirming a placement of the visual representation relative to the corresponding geospatial object located in the physical scene.


US Pat. No. 11,113,526

TRAINING METHODS FOR DEEP NETWORKS

TOYOTA RESEARCH INSTITUTE...


1. A method for training a deep neural network of a robotic device, comprising:constructing a 3D model using images captured via a 3D camera of the robotic device in a training environment;
generating pairs of 3D images from the 3D model by artificially adjusting parameters of the training environment to form manipulated images using the deep neural network;
processing the pairs of 3D images to form a reference image including embedded descriptors of common objects between the pairs of 3D images; and
using the reference image from training of the neural network to determine correlations to identify detected objects in future images by:overlaying the corresponding reference image over a captured image of a scene, and
determining an identity of the detected object based on a point correspondence between the corresponding reference image and the captured image and the embedded descriptors of the corresponding reference image, in which the embedded descriptors encode information into a series of numbers to provide a numerical fingerprint to differentiate one feature from another.


US Pat. No. 11,113,525

USING EMPIRICAL EVIDENCE TO GENERATE SYNTHETIC TRAINING DATA FOR PLANT DETECTION

X DEVELOPMENT LLC, Mount...


1. A method for generating a synthetic training image, the method implemented using one or more processors and comprising:obtaining a digital image that captures an area, wherein the digital image depicts the area under a lighting condition that existed in the area when a camera captured the digital image;
based at least in part on an agricultural history of the area, generating a plurality of three-dimensional synthetic plants; and
generating the synthetic training image to depict the plurality of three-dimensional synthetic plants in the area, wherein the generating includes graphically incorporating the plurality of three-dimensional synthetic plants with the digital image based on the lighting condition.

US Pat. No. 11,113,524

SCHEMES FOR RETRIEVING AND ASSOCIATING CONTENT ITEMS WITH REAL-WORLD OBJECTS USING AUGMENTED REALITY AND OBJECT RECOGNITION

Sony Interactive Entertai...


1. A method comprising:identifying a real-world object in a scene viewed by a camera of a user device;
matching the real-world object with a tagged object based at least in part on image recognition and a sharing setting that has been assigned to the tagged object, the tagged object having been tagged with a content item that is distinct from the sharing setting;
providing a notification to a user of the user device that the content item is associated with the real-world object;
receiving a request from the user for the content item; and
providing the content item to the user.

US Pat. No. 11,113,523

METHOD FOR RECOGNIZING A SPECIFIC OBJECT INSIDE AN IMAGE AND ELECTRONIC DEVICE THEREOF

Samsung Electronics Co., ...


1. A portable communication device comprising:a display; and
a processor configured to:display a photographic image including an object via the display, the displayed object including first information corresponding to a first information type and second information corresponding to a second information type;
receive, via the display, a user input with respect to the displayed object;
based at least in part on a determination that the user input is received with respect to the first information, display, via the display, a first recognition outcome generated using a first recognition function corresponding to the first information type; and
based at least in part on a determination that the user input is received with respect to the second information, display, via the display, a second recognition outcome generated using a second recognition function corresponding to the second information type.