US Pat. No. 10,769,617

USING A MOBILE DEVICE IN A COMMERCIAL TRANSACTION

1. A method comprising:receiving, with a first device, information for completing a transaction between a first entity associated with the first device and a second entity associated with a second device;
the first device causing a payment to be made to the second entity by communicating with a third device;
the first device receiving a payment confirmation from the third device; and
the first device providing the payment confirmation to the second device, thereby completing the transaction.

US Pat. No. 10,769,616

METHODS AND SYSTEMS FOR DISPLAYING ACCOUNT INFORMATION

CAPITAL ONE SERVICES, LLC...

1. A system for displaying account information, comprising:a display device comprising:
a processor;
a display;
a transceiver; and
a memory having stored thereon instructions that, when executed by the processor, cause the processor to:
pair with a device configured to access account information associated with a user;
receive, using the transceiver, the account information from the device;
check a timestamp associated with the account information;
compare the timestamp with a current time to determine an age of the account information;
cause the display to display the account information with an icon to inform the user of the age of the account information when the account information is older than a predetermined threshold preconfigured by the user;
determine whether to change a content frame of the display displaying the account information; and
change the content frame of the display displaying account information at a predetermined time interval to cycle through additional account information.

US Pat. No. 10,769,615

DEVICE AND METHOD IN WIRELESS COMMUNICATION SYSTEM AND WIRELESS COMMUNICATION SYSTEM

SONY CORPORATION, Tokyo ...

1. A device, comprising:processing circuitry configured to
establish a secure communication channel between a first apparatus and a second apparatus;
extract a channel key from the secure communication channel;
generate a data security key for protecting service data based on at least the extracted channel key;
protect the service data using the generated data security key;
generate cipher text data from the protected service data using the extracted channel key; and
transmit the generated cipher text data on the secure communication channel.

US Pat. No. 10,769,614

OVER THE AIR UPDATE OF PAYMENT TRANSACTION DATA STORED IN SECURE MEMORY

Visa International Servic...

1. A data processing device, comprising:a processor;
a memory; and
a set of instructions stored in the memory, which when executed by the processor implement a method to:
receive data for a transaction on an account from a point of sale terminal, the data including an actual transaction amount of the transaction, wherein at least some of the data is provided to the point of sale terminal by a mobile device that communicates with the point of sale terminal, wherein the mobile device stores an accumulator, receives an initial transaction amount of the transaction from the point of sale terminal, and adjusts the accumulator from a first accumulator value to a second accumulator value based on the initial transaction amount;
process the received data to generate a record of the transaction, wherein the record of the transaction includes the actual transaction amount; and
synchronize the accumulator stored in the mobile device by providing the record of the transaction including the actual transaction amount to an element of a wireless communications system, thereby causing the record of the transaction to be provided to the mobile device over a wireless network, wherein the mobile device adjusts the accumulator from the second accumulator value to a third accumulator value based on a difference between the actual transaction amount of the transaction and the initial transaction amount of the transaction.

US Pat. No. 10,769,613

DELEGATE CARDS

ONDOT SYSTEMS, INC, Sant...

1. A computer-implemented method in a card management system in a data communication network for controlling ISO (International Organization for Standardization) authorization requests initiated from transaction cards over the data communication network, the method for selectively delegating control of a transaction card for improving card security of delegation and comprising:receiving, at a network interface of the card management system, from a first party with control of a transaction card managed by the card management system designation of at least one second party to whom control of the payment card is to be granted;
receiving, at the network interface of the card management system, input from the at least one second party to control the transaction card by the card management system,
wherein the at least one second party has a subset of control delegated by the first party; and
automatically asserting, by a processor unit of the card management system coupled to the network interface, control of the transaction within a transaction approval path for a specific ISO authorization request over the data communication network, based on the input received from the second party, the approval path comprising a merchant device, an acquirer processor device, a card network device, and an issuer processor device, and the control asserted at the issue processor,
wherein the card issuer affects whether or not the ISO authorization request is approved, and the card issuer is unaware of the delegated control from the first party to the at least one second party.

US Pat. No. 10,769,612

SYSTEM AND METHOD FOR CUSTOMERS INITIATED PAYMENT TRANSACTION USING CUSTOMER'S MOBILE DEVICE AND CARD

1. A system for a customer initiated payment transaction, comprising:a mobile device of a customer;
a card of the customer having card information;
a merchant device having merchant information and payment information; and
a server having a database which stores the merchant information,wherein the merchant information includes a merchant code and the payment information includes a payment amount,wherein the mobile device is operative to process a card payment transaction by the steps of:receiving the merchant information and the payment information;
activating the mobile device, for processing the card payment transaction, by the card;
creating a payment authorization request using the card information, the merchant information, and the payment information, and sending the payment authorization request to an acquirer affiliated with the customer;
deleting the card information from the mobile device after sending the payment authorization request; and
receiving a result of the payment authorization request from the acquirer,
wherein the card is a multi-function device (MFD) card or a near field communication (NFC) card having an antenna for near field communication (NFC), and the mobile device includes an NFC sensor,
wherein the mobile device is activated for processing the card payment transaction via NFC between the card and the mobile device, and wherein the mobile device receives the card information from the card via NFC between the card and the mobile device,
wherein the step of activating the mobile device, for processing the card payment transaction, by the card includes transferring a chip serial number or a card serial number of the card from the card to the mobile device via NFC or Bluetooth Light Energy (BLE) communication such that the mobile device only becomes activated for processing the card payment if the chip serial number or the card serial number matches a chip serial number or a card serial number stored in the mobile device,
wherein the card information from the card of the customer is not transferred to the merchant, and
wherein the mobile device obtains geolocation data of the merchant device using a global positioning sensor of the mobile device and sends the geolocation data to the server, and in response, the server searches for and retrieves the merchant information corresponding to the geolocation data and sends the merchant information to the mobile device.

US Pat. No. 10,769,611

LOCATION BASED SYSTEM AND METHOD FOR CALCULATING SALES AND USE TAX

GEOINVOICE, INC., Tombal...

1. A computer-implemented method for calculating a transaction tax for a mobile app stored on a mobile device, the method comprising:capturing geographic coordinate data of the location of the mobile device storing the mobile app;
determining if the captured geographic coordinate data is within a transaction tax area by:
geospatially analyzing the captured geographic coordinate data to determine if the captured geographic coordinate data is within the transaction tax area, and utilizing a feature overlay analysis of a coordinate-based data model of a legally defined tax area that represents geometry types for points, lines, polygons and represents the legal boundary of a tax area or tax areas; and
calculating a transaction tax for services and/or products offered by the mobile app based upon the transaction tax area,
wherein the transaction tax area is a non-traditional point of sale that does not have a physical human readable address.

US Pat. No. 10,769,610

ALTERNATIVE SERVICE ACCESS

PAYPAL, INC., San Jose, ...

1. A system, comprising:one of more geolocation sensors;
a non-transitory memory; and
one or more hardware processors coupled to the non-transitory memory and configured to read instructions from the non-transitory memory to cause the system to perform operations comprising:
detecting, via the one or more geolocation sensors, that the system is within a geo-fence of a merchant;
determining that a battery level of the system has dropped below a threshold; and
in response to the detecting and the determining:
generating an authentication token for authorizing a payment with the merchant using a payment provider; and
sending the authentication token to the payment provider.

US Pat. No. 10,769,609

NETWORK SECURITY BASED ON PROXIMITY WITH IP WHITELISTING

Google LLC, Mountain Vie...

1. A computer-implemented method to designate trusted service computing devices, comprising:by a payment processing computing system:
transmitting, to a beacon computing device, an encrypted random nonce, wherein the beacon computing device broadcasts the encrypted random nonce at a location;
receiving, from a service computing device at the location at a first time, a first request for first user account information associated with one or more user computing devices located at the location at the first time, the first request comprising a service computing device identifier and an unencrypted version of the encrypted random nonce;
determining that the service computing device is authorized to receive the first user account information based on determining that the received unencrypted version of the encrypted random nonce corresponds to a first random nonce associated with the service computing device;
in response to determining that the service computing device is authorized to receive the first user account information:
designating the received service computing device identifier as an approved service computing device identifier; and
transmitting, to the service computing device, first user account information;
receiving, from the service computing device at a second time after transmitting the first user account information, a second request for second user account information associated with one or more user computing devices located at the location at the second time, the second request comprising the service computing device identifier; and
in response to determining that the received service computing device identifier is designated as an approved service computing device identifier, transmitting, to the service computing device, the second user account information.

US Pat. No. 10,769,608

INTELLIGENT CHECKOUT MANAGEMENT SYSTEM

INTERNATIONAL BUSINESS MA...

1. A computer implemented method for optimizing checkout operation, comprising:obtaining, by one or more processor of a computer, shopper data and shopping cart data associated with each of at least one shopper in a store, the obtaining comprising collecting the shopper data and the shopping cart data respectively associated with each of the shopper in the store, wherein the shopper data for each of the shopper includes a shopper identification and a micro-location in the store, wherein the shopping cart data includes a number of items in one or more shopping cart associated with each of the shopper and types of items, wherein the collecting is performed by one or more monitoring devices in the store selected from the group consisting of Wi-Fi triangulation, face recognition based on images of each of the shopper as captured by in-store video cameras, tag identification, and proximity detectors utilizing at least one of remote communication technologies selected from the group consisting of radio frequency identification, Bluetooth, Wi-Fi, and near field communication;
generating a current store status by use of the shopper data and the shopping cart data from the obtaining;
determining that a current checkout configuration is not optimal according to a checkout operation rule, based on store status data, a shopper profile respective to each of the at least one shopper, and one or more store transaction records;
creating a new checkout configuration by optimizing the current checkout configuration according to the checkout operation rule, by use of the store status data, each of the shopper profile, and the store transaction records; and
communicating the new checkout configuration to one or more user at the store in order to deploy the new checkout configuration.

US Pat. No. 10,769,607

UNIVERSAL SYMBOL SYSTEM LANGUAGE-ONE WORLD LANGUAGE

JGist, Inc., Bloomington...

2. A method for symbolic communication performed by a symbol server including a server processor, a server memory and a database containing billable and non-billable symbols, the billable symbols representing products or services, each billable symbol being associated with a merchant that registers with the system, and having a billing rate associated with its use, and a communication device including a device processor and a device memory and a touch-based graphical user interface display, and including a subset of the billable and non-billable symbols obtained from the symbol server, the symbol server and the communication device configured to:initiate, by the symbol server, a population of symbols in the database of symbols using indirect symbol harvesting which allows the symbol server to search and acquire symbols from the internet, wherein each symbol populated using indirect symbol harvesting is associated with alphabetic words or phrases by a system administrator of the symbol server;
register, by the symbol server, the merchant to contract billable symbols;
populate, by the symbol server, the billable symbols submitted by the merchant in the database using commercial symbol harvesting, wherein the commercial symbol harvesting allow the merchant to contract billing information and submit a plurality of the billable symbols with respective dynamic billing rate for each of the billable symbols populated, wherein the dynamic billing rate for each billable symbol is based on a time of day, geography and store location;
populate, by the symbol server, additional symbols submitted by a user in the database using at least one method selected from a group consisting of direct symbol harvesting, blind symbol harvesting, and genius symbol harvesting, wherein each of the additional symbols populated is associated with respective alphabetic words or phrases, wherein the direct symbol harvesting allows users to submit each additional symbol with an association of the respective alphabetic words or phrases, wherein the blind symbol harvesting allows the users to participate in games that validate the association of respective alphabetic words or phrases with the additional symbol, wherein the genius symbol harvesting allows a self-identified expert user to validate the association of respective alphabetic words or phrases with the additional symbol;
compose, by a user of the communication device, the message using the alphabetic words or phrases;
request, by the user of the communication device, via the touch-based graphical user interface, consensus-popular symbols relevant to the alphabetic words or phrases used in the composition of the message;
parse, by the symbol server, alphabetic words and phrases used in the message to configure a dynamic series of symbol selection wheels for display on the communication device;
configure, by the symbol server, for display on the touch-based graphical user interface of the communication device, the dynamic series of symbol selection wheels including consensus-popular symbols which sequentially correspond to the relevant alphabetic words and phrases used in the message, wherein the consensus-popular symbols are ranked based on the usage count of each symbol across all messages previously sent by all users, wherein the consensus-popular symbols displayed on each respective wheel include the highest ranked symbols relative to the respective alphabetic word or phrase parsed in the message;
display, via the communication device, on the touch-based graphical user interface and overlaying a touch keyboard, a first symbol selection wheel, from the configured dynamic series of symbol selection wheels, which corresponds to a first alphabetic word or phrase associated with a consensus-popular symbol, wherein the user can further select additional symbols through a symbol keyboard not presented on the touch-based graphical user interface;
select, by the user of the communication device, the consensus popular symbols from the first symbol selection wheel, wherein additional symbol selection wheels are each displayed in sequential order relative to the remaining unselected consensus-popular symbols based on the configured dynamic series of symbol selection wheels;
convert, by the symbol server, the respective alphabetic words and phrases to user selected consensus-popular symbols in the message;
send, by the user of the communication device, the message from the communication device to a second communication device using either a texting application or an email application;
count, by the symbol server, each symbol used in the message,
store, by the symbol server, the count in the database, and
bill, by the symbol server, the merchant for the use of each billable symbol in a message, using the billing rate associated with the billable symbol.

US Pat. No. 10,769,606

PAYMENT REAL-TIME FUNDS AVAILABILITY

EARLY WARNING SERVICES, L...

1. A system comprising:one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:
automatically adjusting, based on a configuration of one or more other systems, a messaging algorithm comprising one or more real-time capability calls to the one or more other systems;
automatically performing the messaging algorithm, as adjusted, based on the configuration of the one or more other systems, wherein the messaging algorithm comprises:
receiving a first capability inquiry at a transaction system from an application service provider;
storing the first capability inquiry in the transaction system;
sending the one or more real-time capability calls to the one or more other systems, as adjusted based on the configuration of the one or more other systems;
receiving one or more capability responses from the one or more other systems;
storing the one or more capability responses in the transaction system; and
sending an overall capability response from the transaction system to the application service provider indicating whether the one or more other systems support real-time payment transactions;
receiving a first promise-to-pay message at the transaction system, the first promise-to-pay message being based on a successful debit of a first account maintained by a first financial institution, the successful debit of the first account being based on a payment authorization made by a sender at a payment authorization time, the first account being held by the sender;
storing the first promise-to-pay message in the transaction system;
sending a second promise-to-pay message from the transaction system to a second financial institution, the second promise-to-pay message being based on the first promise-to-pay message, such that the second financial institution credits a second account maintained by the second financial institution to make funds available in the second account in real-time after the payment authorization time, the sender being financially liable for the second account;
receiving a first response at the transaction system from the second financial institution indicating a successful credit of the second account maintained by the second financial institution;
storing the first response in the transaction system; and
sending a second response from the transaction system indicating the successful credit of the second account maintained by the second financial institution to inform at least the sender in real-time after the payment authorization time of the successful credit of the second account maintained by the second financial institution,
wherein:
the first financial institution is different from the second financial institution;
the first financial institution maintains a first settlement account;
the first settlement account is credited after the successful debit of the first account maintained by the first financial institution to account for the successful debit of the first account maintained by the first financial institution;
the second financial institution maintains a second settlement account;
the second settlement account is debited before the successful credit of the second account maintained by the second financial institution to account for the successful credit of the second account maintained by the second financial institution;
the successful credit of the second account maintained by the second financial institution involves a hard credit to the second account in real-time after the payment authorization time;
settlement funds are transferred from the first settlement account to the second settlement account in a settlement completion after the payment authorization time, after receiving the first response, and after the hard credit to the second account;
the first promise-to-pay message is sent to the transaction system from the application service provider;
the application service provider is in data communication with the transaction system;
the transaction system is in data communication with the second financial institution; and
the transaction system is maintained by an entity that is different from the application service provider, the first financial institution, and the second financial institution.

US Pat. No. 10,769,605

MODULATION FORMAT CHANGE AND LICENSE UPDATING

Infinera Corporation, Su...

1. A method comprising:generating by a network device with a digital signal processor (DSP) first signals modulated in accordance with a first quadrature amplitude modulation (QAM);
modifying by the network device a phase of a reference signal based on the first signals by modulating the reference signal output from a laser;
receiving by one or more servers, an instruction to change the first QAM modulation to a second QAM modulation;
providing by the one or more servers, the instruction to the network device;
generating by the network device with the digital signal processor (DSP), second signals modulated in accordance with the second quadrature amplitude modulation (QAM);
modifying by the network device the phase of the reference signal based on the second signals by modulating the reference signal output from the laser;
determining by one or more servers a quantity of licenses stored by a license repository associated with the second QAM modulation;
determining by one or more servers bandwidth values of each of the licenses associated with the second QAM modulation;
determining by one or more servers a first value based on determined quantity of licenses and bandwidth values;
determining by one or more servers a second value corresponding to an amount of bandwidth allocated to one or more optical channels;
determining by one or more servers that the first value is less than the second value;
determining by one or more servers, that the license repository is to be updated based on receiving the instruction to change the first QAM modulation to the second QAM modulation and determining that the first value is less than the second value;
generating by the one or more servers, a license update instruction based on determining that the license repository is to be updated; and
providing by the one or more servers the license update instruction to the license repository.

US Pat. No. 10,769,604

SYSTEM AND METHOD FOR ECOMMERCE TICKET SALES BASED ON SEAT OCCUPANCY

Mastercard International ...

1. A system for facilitating an ecommerce sale of a ticket to an individual based on a seat occupancy by the individual, the system comprising:a software application for downloading onto a mobile communications device, with the software application allowing the individual to specify an ecommerce payment method;
an initiation mechanism configured to detect a presence of the mobile communications device;
a seat occupancy determining mechanism configured to determine whether the individual has occupied a seat among a plurality of seats; and
a computing device configured to—
determine an amount owed by the individual based at least in part on the occupancy of the seat by the individual, and
execute the ecommerce sale of the ticket via the software application using the ecommerce payment method to pay the amount owed.

US Pat. No. 10,769,603

SYSTEM AND METHOD FOR STOREFRONT BANK DEPOSITS

UNITED SERVICES AUTOMOBIL...

1. A computer-implemented method of assisting remote deposits from a remote deposit system to unrelated financial institutions, the method comprising:at a processor of a third party facilitator system in communication with a mobile device of the remote deposit system, the processor:
receiving a communication from the mobile device of the remote deposit system requesting financial institution information from the third party facilitator system; the communication including identification information pertaining to a particular one of the unrelated financial institutions;
based on the received identification information, determining the financial institution information pertaining to the particular one of the unrelated financial institutions, the financial institution information including communication path information for directly submitting remote deposits from the mobile device of the remote deposit system to the particular one of the unrelated financial institutions without communicating via the third party facilitator system; and
transmitting the determined financial institution information pertaining to the identification information to the mobile device of the remote deposit system from the third party facilitator system.

US Pat. No. 10,769,602

SYSTEM AND METHOD FOR CUSTOMER INITIATED PAYMENT TRANSACTION USING CUSTOMER'S MOBILE DEVICE AND CARD

1. A customer-initiated payment transaction system for transacting customer-initiated payments, the system comprising:a mobile device of a customer, the mobile device comprising a digital wallet and a near-field communication (NFC) device;
a multi-payment gateway affiliated with the customer;
a network;
a server having a database; and
a multi-function device (MFD) card of the customer comprising a NFC antenna wherein the MFD card stores MFD card information corresponding to a plurality of payment methods, wherein a customer-initiated payment transaction comprises the steps of:
the MFD card activating the digital wallet for processing the customer-initiated payment transaction wherein the mobile device receives the MFD card information from the MFD card via NFC between the MFD card and the mobile device;
the digital wallet receiving merchant information and payment information of a merchant by the digital wallet communicating with the merchant via one of:
NFC, the merchant further comprising a NFC tag; and
quick read (QR) code scanning, the merchant further comprising a QR tag;
the digital wallet receiving a payment method selection from the customer for payment;
the digital wallet generating a payment authorization request based on the merchant information and the payment method selection;
the digital wallet sending the payment authorization request to the multi-payment gateway;
the multi-payment gateway directly or indirectly communicating to the merchant a result of the customer-initiated payment transaction; and
the digital wallet receiving a result of the payment authorization request from the multi-payment gateway, wherein activating the digital wallet by the MFD card includes transferring a chip serial number of the MFD card, or a card serial number of the MFD card, from the MFD card to the mobile device,wherein the digital wallet is activated for processing the payment transaction if the transferred chip serial number of the MFD card or the transferred card serial number of the MFD card matches the chip serial number of the MFD card or the card serial number of the MFD card stored in the mobile device,wherein the merchant information is stored in the database, and wherein the mobile device obtains geolocation data of the merchant using a global positioning sensor of the mobile device and sends the geolocation data to the server, and in response, the server searches for and retrieves the merchant information corresponding to the geolocation data and sends the merchant information to the mobile device.

US Pat. No. 10,769,601

SYSTEMS AND METHODS FOR USE IN CLEARING AND/OR SETTLING NETWORK TRANSACTIONS

MASTERCARD INTERNATIONAL ...

1. A method for use in distributing processing of transactions to a payment network, the method comprising:transmitting, by at least one computing device of a payment network, a network request, received from at least one computing device of an acquirer, to at least one computing device of an issuer;
intercepting, by the at least one computing device of the payment network, a network reply from the at least one computing device of the issuer in response to the network reply being associated with the acquirer and the acquirer being registered with the payment network for irrevocable transaction settlement services, the network reply responsive to the network request and including at least one parameter, the at least one parameter including at least one of a transaction amount and/or a merchant category code (MCC);
appending, by the at least one computing device of the payment network, an indicator to the network reply in response to a rule associated with the acquirer being satisfied by the at least one parameter of the network reply;
appending, by the at least one computing device of the payment network, a transaction associated with the network reply to a clearing and/or settlement process in response to the rule associated with the acquirer being satisfied by the at least one parameter of the network reply; and
transmitting the network reply, with the appended indicator, to the at least one computing device of the acquirer, whereby, upon identifying the indicator, the acquirer is permitted to omit the transaction from further reporting to the payment network in connection with clearing and/or settlement of the transaction.

US Pat. No. 10,769,600

CRYPTOCURRENCY TRANSACTIONS USING DEBIT AND CREDIT VALUES

INTERNATIONAL BUSINESS MA...

1. A computer implemented method for transferring cryptocurrency amounts, the method comprising:receiving, by a processing device, a request to transfer an amount of a cryptocurrency from a first storage location, the first storage location including a first wallet owned by a payer and storing an amount of cryptocurrency;
transmitting the request to a transaction module configured to perform a transfer of the amount of the cryptocurrency, the transaction module being part of a distributed ledger network including a distributed ledger maintained by the payer and a payee;
in response to the request, initiating a transaction by the transaction module, generating a credit value and a debit value as a related pair, the credit and debit value independently transferable and representing the amount of the cryptocurrency, broadcasting the transaction, the credit value and the debit value to the distributed ledger network, and transferring the debit value to the payer and transferring the credit value to the payee, each of the credit value and the debit value having an identifier that relates the credit value and the debit value to the amount of the cryptocurrency, one of the credit value and the debit value being a positive value and another of the credit value and the debit value being a negative value, at least one of the credit value and the debit value applied as an input to a transaction record in the distributed ledger network; and
transferring the amount of the cryptocurrency by the transaction module from a wallet connected to the transaction module to a second storage location, the second storage location including a second wallet owned by the payee, wherein transferring the amount includes transferring the credit value from the payer to the payee, the debit value and the credit value configured to be cancelled by the payee to complete the transaction.

US Pat. No. 10,769,599

METHOD FOR CONDUCTING MONETARY AND FINANCIAL TRANSACTIONS BY TREATING AMOUNTS AS COLLECTIONS OF DISTINCT UNITS OF ACCOUNT

1. A method comprising:mapping, by a processor of a payment system, unique identifiers to a plurality of accounts in an account identifier mapping table, wherein each unique identifier has a same predetermined conventional monetary value, wherein of each account in the plurality of accounts has a balance represented by a sum of the predetermined conventional monetary values of the unique identifiers mapped to that account, wherein each unique identifier is a unique bit sequence containing a first section of random bits and a second section of pre-arranged bits, and wherein a numerical value of the pre-arranged bits reflects a designated use for which the unique identifier is allowed to be used;
receiving, by the processor from a financial institution, a first request to record a first financial transfer of a given designated use and a given first amount from a first account to a second account among the plurality of accounts;
automatically calculating, by the processor and in response to receiving the first request, an amount of the first financial transfer as a collection of the unique identifiers currently mapped to the first account, wherein each unique identifier in the collection of the unique identifiers has the numerical value of the pre-arranged bits corresponding to the given designated use of the first financial transfer, and wherein the amount of the first financial transfer is represented by a sum of the predetermined conventional monetary values of the collection of the unique identifiers;
recording, by the processor in a memory coupled to the processor, the first financial transfer in a first entry of the account identifier mapping table, wherein the first entry includes an account identifier of the second account a first unique identifier in the collection of the unique identifiers, and a first timestamp when the collection of the unique identifiers was mapped to the second account;
receiving, by the processor from the financial institution, a second request to record a second financial transfer of the given designated use and a given second amount from the second account to a third account in the plurality of accounts;
automatically calculating, by the processor and in response to receiving the second request an amount of the second financial transfer as a subset of unique identifiers in the collection of the unique identifiers that are currently mapped to the second account and that include the first unique identifier, and that have the numerical value of the pre-arranged bits corresponding to the given designated use of the second financial transfer, wherein the amount of the second financial transfer is represented by a sum of the predetermined conventional monetary values of the subset of unique identifiers;
recording, by the processor, the second financial transfer in a second entry of the account identifier mapping table, wherein the second entry includes an account identifier of the third account, the first unique identifier in the subset of unique identifiers, and a second timestamp of when the subset of unique identifiers was mapped to the third account;
receiving, by the processor from an external source, an inquiry containing a plurality of suspected illicit user accounts, wherein the inquiry requests to determine whether the first unique identifier has a transaction history that traces back to at least one of the suspected illicit user accounts;
accessing, by the processor and in response to the inquiry, the account identifier mapping table to identify transactions involving the first unique identifier and producing an output table with the identified transactions including the first entry having the account identifier of the second account and the first timestamp, the second entry having the account identifier of the third account and the second timestamp, and a third entry having an account identifier of the first account and a third timestamp of when the first unique identifier was mapped to the first account;
comparing, by the processor, the first second, and third account identifiers in the output table with account identifiers of the plurality of suspected illicit user accounts; and
determining, by the processor and based on the comparing, that the first unique identifier has been involved in an illicit transaction when one of the first second, and third account identifiers matches an account identifier of the at least one of the suspected illicit user accounts.

US Pat. No. 10,769,598

SYSTEMS AND METHODS FOR REMOTE DEPOSIT OF CHECKS

United States Automobile ...

1. A method of facilitating remotely depositing funds into a user's account with a bank's computing system and without using an Automatic Teller Machine (ATM), comprising:providing a remote deposit application for download to a customer device, wherein the remote deposit application comprises computer-executable instructions that, when executed by a processor, provide a user-interface and control a camera associated with the customer device to facilitate capturing at least one electronic image of a check;
receiving at the bank's computing system, via the user-interface on the customer device: authentication data, an electronic identification of an account for receipt of a value associated with the check, an electronic indication of the value associated with the check, and the at least one electronic image of the check;
determining whether the check was previously deposited using the at least one electronic image of the check; and
initiating and/or logging a first deposit of the value to the account via the bank's computing system unless the bank's computing system determines from the at least one electronic image of the check that the check was previously deposited.

US Pat. No. 10,769,597

DATA PROCESSING METHOD AND DEVICE, AND POS TRANSACTION SYSTEM

TENDYRON CORPORATION, Be...

1. A data processing method, applied to a POS terminal, comprising:reading card information pre-stored in a chip card transacting with the POS terminal, wherein the card information comprises information of a program set for processing transaction data of the chip card, the program set at least comprises one or more transaction programs, each of the one or more transaction programs is configured to implement one or more businesses supported by the chip card;
acquiring one or more transaction programs matching with a current transaction in the program set according to the card information, which comprises:
inquiring whether the one or more transaction programs have been installed according to the card information;
if yes, reading the one or more transaction programs installed; and
if no, sending a download request of the one or more transaction programs to a POS management server communicatively connected to the POS terminal, receiving an installation package returned by the POS management server in response to the download request, and installing the one or more transaction programs by using the installation package, which comprises:
verifying a digital signature included in the installation package;
decrypting the installation package to obtain an installation data plaintext after the digital signature is verified successfully;
verifying a data format of the installation dta plaintext, and
installing the one or more transaction programs by using the installation data plaintext verified successfully; and
running the one or more transaction programs to calculate and transmit transaction data of the current transaction.

US Pat. No. 10,769,596

RESOURCE VALIDATION BASED EVENT SCHEDULING IN A SOCIAL NETWORK

INTERNATIONAL BUSINESS MA...

1. A computer-implemented method comprising:identifying, based on activity in a social network, planning of an event;
determining event parameters of the event, the determining the event parameters comprising:
determining an anticipated number of attendees of the event; and
profiling predicted attendees of the event to identify attendee preferences, wherein the event parameters comprise the determined anticipated number of attendees and attendee preferences;
soliciting resource validation information from one or more network connected smart devices providing one or more resources at a location for the event, the resource validation information indicating ability of each network connected smart device of the one or more network connected smart devices to support estimated use of the network connected smart device, the estimated use being based on the determined event parameters;
receiving from the one or more network connected smart devices the resource validation information; and
scheduling the event based on the resource validation information.

US Pat. No. 10,769,595

VERIFYING PUBLISHER SUGGESTIONS

Yext, Inc., New York, NY...

1. A system comprising:a memory to store instructions; and
a processing device, operatively coupled to the memory, to execute the instructions to:
identify an indication of a first suggested change to listing data associated with an entity at a first provider system;
determine whether the first suggested change matches previously stored information associated with the entity;
responsive to detecting a difference between the first suggested change and previously stored information, initiate a communication with a client device associated with the entity based on the suggested change;
receive input data from the client device in response to the communication, wherein the input data indicates an acceptance of the first suggested change;
responsive to the acceptance of the first suggested change, apply the first suggested change by accessing each of a plurality of additional provider systems via a respective interface and updating the listing data stored by each of the plurality of additional provider systems, wherein each of the plurality of additional provider systems stores listing data comprising the first suggested change;
receive, at a first time, an instruction to reject a second suggested change to the listing data associated with the entity at the one or more provider systems;
determine a third suggested change is a repeat of the second suggested change; and
reject the third suggested change based on a determination that a difference between the first time the second suggested change was rejected and a current time is within a threshold time period.

US Pat. No. 10,769,594

DYNAMICALLY GENERATED CONFIGURATION PROFILES BASED ON DEVICE OPERATING SYSTEM

AIRWATCH LLC, Atlanta, G...

1. A system, comprising:at least one computing device; and
program instructions executable in the at least one computing device that, when executed by the at least one computing device, cause the at least one computing device to:
maintain a database that comprises a mapping of a common field name to a plurality of variable names associated with a plurality of different operating systems, the setting being previously defined as common by an administrator of an enterprise, indicating that the setting is applicable to the plurality of different operating systems, and the common field name being used to obtain the value of the setting for the plurality of variable names;
determine that a configuration profile configured for a type of a client device has not been created in an instance in which a request for the configuration file is received from the client device of a plurality of client devices enrolled in a management service managed by the enterprise;
in response to the configuration profile having not been created for the type of the client device, identify a particular operating system of the plurality of different operating systems installed on the client device;
determine a format for the configuration profile based at least in part on the particular operating system;
identify the setting that is defined as being common to the plurality of different operating systems;
obtain the value of the setting for the particular operating system according to the common field name; and
generate the configuration profile in accordance with the format, a particular variable name of the plurality of variable names of the setting for the particular operating system as defined in the mapping, and the particular operating system, wherein the configuration profile is generated to comprise the value of the setting for the particular operating system that is previously defined for the setting according to the common field name that is mapped to the particular variable name.

US Pat. No. 10,769,593

HANDLING EMAIL FLOWS ARISING FROM TRANSACTIONS INITIATED WITH A SHARED PRIVILEGED IDENTITY AT A SERVICE PROVIDER

International Business Ma...

1. A computer-implemented method for handling email flows arising from transactions initiated with a shared privileged identity at a service provider, the method comprising:reading, by a privileged identity management (PIM) system, an email sent from a service provider to a single shared PIM email address, wherein the single shared PIM email address is associated with a shared account registered at the service provider, and wherein the email is related to a transaction initiated with the shared account;
extracting, by the PIM system, from the email, a transaction ID of the transaction, wherein the transaction ID identifies the transaction, the transaction being independent of the email;
identifying from a plurality of PIM users sharing the single shared PIM email address, by the PIM system, one or more PIM users relevant to the transaction as one or more recipients of the email, based on the transaction ID;
sending to the one or more recipients, by the PIM system, a notification of the email related to the transaction; and
wherein the PIM system comprises a machine learning module, wherein the machine learning module studies at least one of a history of emails and user feedback from the service provider so as to learn how to extract transaction IDs and keywords embedded in incoming emails.

US Pat. No. 10,769,592

METHODS, SYSTEMS AND COMPUTER PROGRAM PRODUCTS FOR GENERATING EXPLANATIONS FOR A BENEFIT QUALIFICATION CHANGE

INTUIT INC., Mountain Vi...

1. A computer-implemented method for generating an explanation for a benefit qualification status change over different benefit qualification periods, the method comprising:a computing device executing a benefit calculation engine, the benefit calculation engine operating on a first benefit completeness graph from a first benefit qualification period to perform a first benefit qualification status determination, the benefit calculation engine operating on a second benefit completeness graph from a second benefit qualification period and different in at least one respect from the first benefit completeness graph to perform a second benefit qualification status determination, the first and second benefit completeness graphs each comprising rules and regulations of its respective benefit qualification period implemented as data dependent benefit qualification operations comprising a plurality of interconnecting functional nodes connected by one of a plurality of functions;
the computing device identifying differences among nodes within the first benefit completeness graph and the second benefit completeness graph;
the computing device executing an explanation engine associated with the benefit calculation engine to generate a textual explanation identifying a difference between the first benefit qualification status determination and the second benefit qualification status determination based on one or more differences among the nodes;
the computing device presenting the textual explanation identifying the difference between the first benefit qualification status determination and the second benefit qualification status determination based the one or more differences among the nodes to a user interface along with a link allowing a user to request an additional explanation; and
in response to a request for the additional explanation, the computing device recursively traversing nodes of the completeness graphs to generate a further textual explanation regarding the difference between the first benefit qualification status determination and the second benefit qualification status determination based the one or more differences among the nodes.

US Pat. No. 10,769,591

ENABLING SERVICE FEATURES WITHIN PRODUCTIVITY APPLICATIONS

Microsoft Technology Lice...

1. A computing apparatus comprising:one or more non-transitory computer readable media;
a processing system operatively coupled with the one or more non-transitory computer readable media; and
program instructions stored on the non-transitory computer readable media that, when executed by the processing system, direct the computing apparatus to at least:
identify a user logged into a productivity application;
identify one or more online services logged into by the user;
present, through a user interface to the productivity application, a productivity feature menu that includes a plurality of productivity features;
responsive to a selection of one of the plurality of productivity features, present through the user interface a service feature menu in the productivity application that includes a plurality of service features;
enable at least one service feature of the plurality of service features corresponding to an online service logged into by the user;
disable at least one other service feature of the plurality of service features corresponding to one other online service not logged into by the user; and responsive to a selection of the at least one service feature, perform a function on content generated with the productivity application using content obtained from the online service.

US Pat. No. 10,769,590

SYSTEMS AND METHODS FOR SHARING IMAGES IN A SOCIAL NETWORK

Facebook, Inc., Menlo Pa...

1. A method comprising, by one or more computing devices of a social-networking system:determining that one or more new photographs have been captured by a client computing device of a user of the social-networking system, each photograph comprising metadata;
identifying a user account of the user within the social-networking system;
generating a fingerprint for each of the one or more new photographs, respectively, each fingerprint being based on characteristics of the respective photograph and configured to uniquely identify the respective photograph;
automatically and without user input, fetching from the client computing device one or more of the new photographs for storage in association with the user account within the social-networking system; and
determining for each photograph whether the photograph or a similar photograph has previously been uploaded to the social-networking system by comparing the fingerprint of the photograph with one or more fingerprints stored within the social-networking system and comparing the metadata of the photograph with metadata stored within the social-networking system.

US Pat. No. 10,769,589

INVENTORY SYSTEM AND METHODS OF USING THE SAME

1. A system comprising:a tagged inventory item, wherein the tagged inventory item includes a radio field tag attached to an inventory item; and
an inventory device, wherein the inventory device includes a weighing surface, an array of force sensing resistors, and at least one radio field antenna,
wherein the inventory device includes a top, a bottom, and a side, wherein the top of the inventory device includes the weighing surface, wherein the weighing surface includes a flexible material;
wherein the top, bottom, side, and weighing surface are resistant to the passage of water;
wherein the array of force sensing resistors is positioned between the weighing surface and the at least one radio field antenna; and
wherein the array of force sensing resistors and the at least one radio field antenna are configured to weigh and identify the tagged inventory item through the weighing surface.

US Pat. No. 10,769,588

SYSTEMS AND METHODS FOR GENERATING GRAPHICAL USER INTERFACES FOR ADAPTIVE DELIVERY SCHEDULING

COUPANG, CORP., Seoul (K...

1. A computerized system for delivery scheduling, comprising:at least one processor; and
at least one non-transitory storage medium comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform steps comprising:
receiving, from a remote system, an electronic request to order a product;
determining information associated with the remote system;
determining a fulfillment center associated with the information and the product;
assigning a delivery wave estimate by:
calculating an estimated arrival from the fulfillment center to a camp zone based on at least one of distance, historic trends, or delivery rotations; and
assigning the delivery wave estimate to the first wave when determining the estimated arrival is before a first wave;
generating, based on the information associated with the remote system, an electronic message comprising:
the determined fulfillment center,
the product,
a time of day, and
the delivery wave estimate; and
forwarding, to the fulfillment center, the electronic message and instructions to generate a graphical user interface displaying the product and the delivery wave estimate,
wherein determining the fulfillment center comprises:
storing in a database a plurality of previous electronic requests and associated fulfillment centers;
dividing the previous electronic requests in a training dataset and a validation dataset, the training dataset having more requests than the validation dataset;
generating a predictive model based on the training data set associating request information and fulfillment centers;
validating the predictive model using the validation dataset; and
determining the fulfillment center by applying the predictive model to the electronic request.

US Pat. No. 10,769,587

SYSTEMS AND METHODS OF STORING AND RETRIEVING RETAIL STORE PRODUCT INVENTORY

Walmart Apollo, LLC, Ben...

1. A retail store inventory storage and retrieval system, comprising:a rack system positioned above a dropdown ceiling of a retail store and extending over at least a majority of a sales floor comprising product support devices supporting products offered for sale and separated by aisles along which customers move in order to locate and select desired products for purchase from the retail store, wherein the rack system comprises: a plurality of racks, a rail system and a plurality of access passages;
a retail store inventory central control circuit;
an inventory tracking system communicatively coupled with the central control circuit;
a plurality of unmanned vehicles in wireless communication with the central control circuit, wherein each of the unmanned vehicles comprises a vehicle control circuit, at least one motor controlled by the vehicle control circuit, a propulsion system operatively coupled with the at least one motor and configured to induce movement of the unmanned vehicle in response to being driven by the motor, and a tote retrieval system;
a plurality of access stations each positioned at various different locations throughout the sales floor and an exterior of the retail store, wherein each of the access stations is physically cooperated with one of the plurality of access passages of the rack system, and each of the access stations is accessible by customers for use by customers in requesting products while at the retail store; and
a plurality of sensor systems, separate from the plurality of unmanned vehicles, communicatively coupled with at least the central control circuit and configured to detect at least totes as they are moved through the rack system;
wherein the plurality of racks are organized in a plurality of rows with each row having multiple aligned racks of the plurality of racks, wherein each rack comprises a plurality of storage cells configured to receive a reusable storage tote that is configured to receive and maintain at least one product of thousands of products offered for sale by the retail store;
wherein the rail system comprises a grid of a plurality of pairs of rails that are cooperated and extending at least vertically and horizontally between rows of racks of the plurality of racks and the storage cells of racks;
wherein each of the access passages cooperates the plurality of racks with at least one of the access stations and comprise some of the rail system enabling the unmanned vehicles to transport the totes between the racks and the access stations; and
wherein the central control circuit is configured to receive a request for a first product, identify a first access station of the plurality of access stations to which the first product is to be routed, access the inventory tracking system to identify a first storage cell in which the first product is stored within a first tote, identify an available first unmanned vehicle of the plurality of unmanned vehicles, and communicate to the first unmanned vehicle directing the first unmanned vehicle to retrieve the first tote and transport the first tote to the first access station.

US Pat. No. 10,769,586

IMPLEMENTATION OF ROLLING KEY TO IDENTIFY SYSTEMS INVENTORIES

Red Hat, Inc., Raleigh, ...

1. A method comprising:receiving, by a processing device of an inventory server from a client system, a key and a key component, wherein the key component comprises a random string of characters generated by the client system to uniquely identify the client system;
identifying, using the key as an identifier, the client system in an inventory database of the inventory server;
transmitting an acknowledgement to the client system that the client system has been identified in the inventory database and that the inventory server received the key component, the acknowledgement to cause the client system to store the key component as part of a new key used to identify the client system; and
storing the key component, wherein storing the key component causes a modification of the key used to identify the client system.

US Pat. No. 10,769,585

SYSTEMS AND METHODS FOR AUTOMATED HARMONIZED SYSTEM (HS) CODE ASSIGNMENT

Walmart Apollo, LLC, Ben...

1. An automated Harmonized System (HS) code assignment system, the system comprising:a computer-readable medium including a database configured to store a plurality of HS codes and information associated with a plurality of items, each of the plurality of items being assigned at least one HS code from the plurality of HS codes;
a computing system communicatively coupled to the computer-readable medium, the computing system configured to:
receive a first input associated with a new item;
retrieve, from the database, information associated with one or more items of the plurality of items, based on the first input;
compare the first input associated with the new item to the information associated with the one or more items;
identify at least one item of the one or more items, based on the comparison of the first input associated with the new item to the information associated with the one or more items;
execute a gap analysis to determine differences between the at least one item and the new item;
calculate a percentage representing an amount of similarity between the new item and the at least one item, in response to executing the gap analysis;
in response to determining the percentage is greater than a first threshold amount, calculate a difference between a value associated with the new item and a value associated with the at least one item;
determine whether the difference between a value associated with the new item and a value associated with the at least one items is greater than a second threshold amount;
in response to determining the difference between a value associated with the new item and a value associated with the at least one items is greater than a second threshold amount, fail to match the new item to the at least one item;
in response to determining the difference between a value associated with the new item and a value associated with the at least one items is less than a second threshold amount, retrieve, from the database, a HS code assigned to the at least one item; and
assign a HS code from the plurality of HS codes to the new item based on the retrieved HS code assigned to the at least one item.

US Pat. No. 10,769,584

INVENTORY CONTROL SYSTEM AND METHOD

THE BOEING COMPANY, Chic...

1. An inventory control system comprising:one or more memory devices storing inventory data, inventory control instructions, inventory control parameters, and historical demand data, the historical demand data indicating demand for each of a plurality of inventory items during a plurality of time periods; and
a processor configured to execute the inventory control instructions, wherein the inventory control instructions, when executed by the processor cause the processor to perform operations comprising:
generating, based on the historical demand data, an initial demand matrix including a plurality of demand value cells, each demand value cell storing a demand value indicating demand, during a respective time period, for a respective inventory item of the plurality of inventory items;
generating, based on the historical demand data, a plurality of synthetic demand matrices, each synthetic demand matrix of the plurality of synthetic demand matrices including a plurality of synthetic demand values arranged in synthetic demand value cells, each synthetic demand value determined by using a randomization process to assign a demand value for a particular inventory item and for a first historical period as a synthetic demand value for the particular inventory item and for a second historical period;
identifying sparse demand vectors for the synthetic demand matrices, each sparse demand vector including values indicating synthetic demand that satisfies a sparse demand criteria of the inventory control parameters;
modifying the synthetic demand matrices based on sparse demand vectors to generate a plurality of filtered synthetic demand matrices;
generating estimated demand for a target period for each inventory item of the plurality of inventory items, the estimated demand generated based on the filtered synthetic demand matrices and the initial demand matrix;
performing a comparison of the estimated demand and the inventory data to determine whether one or more inventory items should be acquired; and
responsive to determining that one or more inventory items should be acquired, generating and sending a demand signal to cause the one or more inventory items to be acquired.

US Pat. No. 10,769,583

INVENTORY TRACKING

WALMART APOLLO, LLC, Ben...

1. A computer-implemented method of updating an inventory cache management system, comprising:providing an e-commerce web site over an internet from a front end server to a user computing device, the e-commerce website comprising an inventory status indicator;
at a backend inventory management module, receiving and storing a first item inventory level quantity located at one or more warehouse locations;
at a store inventory database module, receiving and storing a second item inventory level quantity located at a retail store location different from the one or more warehouse locations;
at the backend inventory management module, comparing the first item inventory level quantity with a first item high threshold;
when the first item inventory level quantity is less than the first item high threshold, transmitting a first Limited Stock Alert from the backend inventory management module to a backend inventory cache;
at the backend inventory cache, storing a first inventory status corresponding to the first item inventory level quantity;
at the store inventory database module, comparing the second item inventory level quantity with a second item high threshold;
when the second item inventory level quantity is less than the second item high threshold, transmitting a second Limited Stock Alert from the store inventory database module to a store inventory cache;
at the store inventory cache, storing a second inventory status corresponding to the second item inventory level quantity;
at the front end server, receiving a data request for an item from the user computing device;
in response to receiving the data request, determining when the data request for the item is for data related to at least one of the first inventory status stored at the backend inventory cache or the second inventory status stored at the store inventory cache;
in response to determining that the data request for the item is for the data, calling the backend inventory cache or the store inventory cache for the data according to the data request;
in response to calling the backend inventory cache or the store inventory cache, receiving at least one response from the backend inventory cache or the store inventory cache to be combined into an aggregated inventory status;
transmitting the data related to the aggregated inventory status to the front end server for display at the e-commerce website on the user computing device as the inventory status indicator in response to the data request from the user computing device, wherein:
the inventory status indicator allows a user to purchase the item from a store inventory or a warehouse inventory; or
when the item is not available for purchase from the store inventory or the warehouse inventory, the inventory status indicator allows the user to place a backorder for the item based on a future inventory availability of the item in the store inventory or the warehouse inventory; and
when transmitting the data related to the aggregated inventory status to the front end server fails, when calling the backend inventory cache or the store inventory cache fails, or when receiving the at least one response from the backend inventory cache or the store inventory cache fails, at least one of (a) requesting the second item inventory level quantity from the store inventory database module, and bypassing the store inventory cache, or (b) requesting the first item inventory level quantity from the backend inventory management module, and bypassing the backend inventory cache.

US Pat. No. 10,769,582

MULTIPLE CAMERA SYSTEM FOR INVENTORY TRACKING

BOSSA NOVA ROBOTICS IP, I...

1. A robotic camera system for inventory monitoring, comprising:a movable base;
multiple cameras supported by the movable base, the multiple cameras being directable toward inventory;
a processing module connected to the multiple cameras and able to construct inventory related information, the processing module configured to:
stitch together consecutive images from the multiple cameras into a panorama,
segment the panorama to define a plurality of bounding boxes,
classify the plurality of bounding boxes into different categories,
associate bounding boxes among different categories based on geographic position of the plurality of bounding boxes, and
determine the inventory-related information based on the association of the bounding boxes;
a communication module connected to the processing module to transfer the inventory related information to remote locations; and
a navigation module connected with the movable base, the communication module, and the multiple cameras to direct the position and orientation of the robotic camera system.

US Pat. No. 10,769,581

OVERHANGING ITEM BACKGROUND SUBTRACTION

Amazon Technologies, Inc....

1. An inventory management system, comprising:inventory holders configured to store inventory items;
mobile drive devices configured to move the inventory holders;
a station configured for performance of a task related to one or more inventory items associated with an inventory holder based at least in part on the inventory holder being positioned at the station;
storage locations that are stationary and remote from the station and that facilitate storage of the inventory holders;
a sensor located at a distance from the station and configured to sense objects; and
one or more computer processors communicatively coupled with the station and the sensor and configured to:
access, from a data store associated with the inventory management system, inventory holder information describing at least an attribute of the inventory holder;
determine that an object has moved between the inventory holder and the sensor based at least in part on sensed data by the sensor about an obstruction by the object of a portion of the inventory holder;
determine a location of the obstruction by the object based at least in part on the sensed data;
identify a first inventory bin associated with the inventory holder based at least in part on the inventory holder information and the location of the obstruction;
access item information associated with an inventory item stored in the first inventory bin, the item information identifying a color or size of the inventory item;
determine that the object moved between the inventory holder and the sensor before an interaction with the inventory item at the station based at least in part on second sensed data, the second sensed data obtained from a different sensor of a different station and indicating, initially, the interaction with the inventory item and, subsequently, that the different sensor is clear of the object, the different station being one of a plurality of stations associated with the inventory management system;
based at least in part on the inventory holder information, the location of the obstruction, a comparison of the item information and the sensed data by the sensor about the obstruction by the object, and the second sensed data, determine that the object is associated with handling the inventory item at the location of the obstruction or that the object is an overhanging inventory item; and
update, at the data store associated with the inventory management system, the inventory holder information to include a relative location of the inventory item in the inventory holder based at least in part on determining that the object is associated with the handling of the inventory item or that the object is the overhanging inventory item.

US Pat. No. 10,769,580

METHOD AND APPARATUS FOR INVENTORY CONTROL IN MEDICAL TREATMENT AREAS

CareFusion 303, Inc., Sa...

1. A method of assigning a medical device to a patient, comprising:detecting, by one or more computing devices, that a medical device moved into a predefined medical treatment area currently associated with a patient of a medical facility responsive to a wireless connection being formed between a first wireless communication device of the medical device and a second wireless communication device inside the predefined medical treatment area, wherein the wireless connection is formed only when the first and second wireless devices are within a predetermined wireless range defined by the predefined medical treatment area;
automatically, in response to detecting that the medical device moved into to the medical treatment area, by the one or more computing devices, obtaining identity information identifying the medical device from the medical device over the wireless connection, retrieving, using the obtained identify information, a medical device record associated with the medical device from a storage medium, the storage medium being accessible through the medical facility, and updating a patient record of the patient currently associated with the treatment area to reflect that the medical device has been assigned to the patient currently associated with the treatment area;
detecting, by the one or more computing devices, that the medical device was removed from the treatment area based on the first wireless communication device of the medical device no longer being detected within the predetermined wireless range of the second wireless communication device; and
updating, responsive to the first wireless communication device no longer being detected within the predetermined wireless range of the second wireless communication device, the patient record to reflect that the medical device has been discharged from the patient.

US Pat. No. 10,769,579

TOTE ASSOCIATION

Amazon Technologies, Inc....

14. The computing system of claim 12, wherein the first item is located in the first tote prior to the second tote being associated with the profile item identifier list.

US Pat. No. 10,769,578

SYSTEM AND METHOD FOR FACILITATING PICK UP OF PRODUCTS ORDERED BY A CUSTOMER BY A FRIEND OR FAMILY MEMBER OF THE CUSTOMER

Walmart Apollo, LLC, Ben...

9. A method of facilitating pick up of products purchased over a network by a customer from a retailer, the method comprising:providing an electronic customer information database configured to store electronic data associated with geographic locations of friends and family members of the customer;
processing, at an order processing server, an order for a product placed by the customer, and permitting, the customer to elect, via a computing device of the customer, to have the product ordered by the customer be picked up by a friend or a family member of the customer;
accessing, via a computing device of the retailer including a processor-based control circuit, the electronic customer information database to obtain the electronic data associated with the geographic locations of the friends and family members of the customer;
identifying, via the computing device of the retailer and based on the electronic data obtained from the customer information database, the geographic locations of the friends and family members of the customer;
analyzing, via the computing device of the retailer, the identified geographic locations of the friends and family members of the customer to determine a first friend or family member of the customer located at a geographic location closest to a geographic location of a retail facility of the retailer associated with a geographic location of the customer;
transmitting, via the computing device of the retailer, a first electronic notification to a computing device of the first friend or family member of the customer, the first electronic notification causing a first graphical interface to be displayed on the computing device of the first friend or family member, the first graphical interface requesting the first friend or family member of the customer to select at least one input field within the first graphical interface to indicate agreement to pick up, at the retail facility of the retailer, the product ordered by the customer;
in response to a selection by the customer of the at least one input field within the first graphical interface, receiving, at the computing device of the retailer, a response from the computing device of the first friend or family member of the customer indicating agreement by the first friend or family member of the customer to pick up, at the retail facility of the retailer, the product ordered by the customer; and
transmitting, from the computing device of the retailer, a second electronic notification to the computing device of the customer, the second electronic notification causing a second graphical interface to be displayed on the computing device of the customer, the second graphical interface indicating that the product ordered by the customer will be available for pick up at the geographic location of the first friend or family member of the customer.

US Pat. No. 10,769,577

ADAPTIVE LOGISTICS PLATFORM FOR DETERMINING DEMURRAGE AND DETENTION DATA

Accenture Global Solution...

1. A device, comprising:one or more processors to:
determine a predicted port congestion based on a model that maps movement of shipping vessels,
the predicted port congestion being determined based on global positioning system (GPS) readings indicating the shipping vessels are in motion or at rest outside of a port;
receive geolocation information from a location sensor of a shipping vessel that carries one or more shipping containers,
the geolocation information identifying a location of the shipping vessel,
each shipping container, of the one or more shipping containers, being associated with a GPS sensor;
alter, based on the geolocation information received from the location sensor of the shipping vessel and the predicted port congestion, an amount of computing resources used to monitor periodic GPS measurements reported by the GPS sensor associated with each shipping container,
the amount of computing resources to be altered being determined based on a predicted amount of time the shipping vessel will be motionless;
collect event information using the altered amount of computing resources used to monitor the periodic GPS measurements,
the event information identifying one or more container events associated with the one or more shipping containers,
the one or more container events indicating a time to be used to determine demurrage or detention data for the one or more shipping containers;
determine, based on the event information, baseline information associated with generating demurrage or detention data for the one or more shipping containers;
determine, based on the one or more container events and the baseline information, that demurrage or detention has been triggered in association with the one or more shipping containers;
generate the demurrage or detention data for the one or more shipping containers using the baseline information and the event information, and based on determining that demurrage or detention has been triggered in association with the one or more shipping containers,
the one or more processors, when generating the demurrage or detention data, are to:
generate the demurrage or detention data based on one or more exception events that identify an exception to demurrage or detention,
 the one or more exception events including one or more of:
 a port congestion delay, or
 a customs delay;
provide the demurrage or detention data; and
update the model using the baseline information and the event information.

US Pat. No. 10,769,576

METHOD AND SYSTEM FOR CARGO LOAD DETECTION

BlackBerry Limited, Wate...

1. A method for cargo load detection in a container by a computing device, the method comprising:capturing a first image of an interior of the container when the container is empty;
detecting a first set of edges within the first image;
capturing a second image of the interior of the container;
detecting a second set of edges within the second image; and
determining cargo loading within the container by comparing the first set of edges with the second set of edges, the comparing comprising determining that a missing portion of at least one edge within the first set is missing from the second set, wherein the determining is based on a ratio of a length of the missing portion to a length of the at least one edge.

US Pat. No. 10,769,575

DISTRIBUTION SYSTEMS AND RELATED METHODS

MASTERCARD INTERNATIONAL ...

1. A method for distributing a parcel to a recipient based on location data associated with the recipient, the method comprising:generating and storing, by at least one computing device, a shipping file for the recipient, the shipping file including an identifier for a portable communication device associated with the recipient and a defined geographic region for the recipient;
in connection with an expected shipment of the parcel to the recipient, retrieving, by the at least one computing device, location data for a location of the portable communication device, from the portable communication device, based on the identifier associated with the portable communication device;
determining, by the at least one computing device, whether the location of the portable communication device is within the defined geographic region;
directing an entity associated with the parcel to ship the parcel to the recipient when the location is determined to be within the defined geographic region; and
directing the entity to hold shipment of the parcel when the location is determined to be outside the defined geographic region, whereby the entity holds shipment of the parcel until a time when the recipient is located within the defined geographic region.

US Pat. No. 10,769,574

MAXIMIZE HUMAN RESOURCES EFFICIENCY BY REDUCING DISTRACTIONS DURING HIGH PRODUCTIVITY PERIODS

International Business Ma...

1. A processor-implemented method for reducing one or more distractions during a period of high productivity, the method comprising:receiving, by a processor, a plurality of user metadata;
in response to determining a user is in a high productivity state, analyzing the plurality of received user metadata for potential distractions to the high productivity state;
in response to identifying one or more potential distractions based on the plurality of analyzed user metadata, determining an appropriate modification to the one or more identified potential distractions; and
performing the determined appropriate modification, wherein the appropriate modification is based on a comparison of a usefulness of the identified potential distraction to the user and an amount of distraction of the identified potential distraction to the user.

US Pat. No. 10,769,573

SYSTEM AND METHOD SUPPORTING ONGOING WORKER FEEDBACK

TRANSFORM SR BRANDS LLC, ...

1. A method of operating a system that supports the ongoing communication, tracking, and management review of feedback among a population of end users of the system comprising workers and managers of the workers, the method comprising:providing, in one or more electronic memory devices, a repository for storing data comprising:
information representing working relationships of the population of end users;
information representing each request for feedback; and
information representing feedback submitted by each of the population of end users;
generating, by a processing circuitry of the system, at least one first graphical user interface (GUI) via which a first end user of the population of end users is enabled to input, using one or more input devices of the system, first information representing feedback from the first end user regarding a second end user of the population of end users;
storing the first information in the one or more electronic memory devices, and associating, in the repository of data by the processing circuitry, the first information with the first end user and the second end user;
analyzing, by the processing circuitry, information stored in the repository representing feedback regarding the second end user, to determine areas of performance behaviors for which information representing feedback is missing or which information represents feedback from less than a certain number of end users of the population of end users;
generating, by the processing circuitry, at least one second GUI via which a third end user of the population of end users is enabled to input, using one or more input devices of the system, second information representing feedback from the third end user regarding the second end user, wherein the generating comprises adjusting the second GUI for gathering third information representing feedback on areas of additional performance behaviors, based on the determined areas of performance behaviors for which information representing feedback is missing or for which feedback was received from less than the certain number of end users of the population of end users;
storing the second information in the one or more electronic memory devices, and associating, in the repository of data by the processing circuitry, the third end user and the second end user; and
generating, by the processing circuitry, at least one third GUI via which a manager of the second end user is enabled to view one or both of:
an analysis of quantitative feedback for the second end user; and
qualitative feedback for the second end user.

US Pat. No. 10,769,572

METHOD AND SYSTEM FOR DETERMINING AN OPTIMAL STRATEGY PERTAINING TO A BUSINESS OPPORTUNITY IN COGNITIVE DECISION MAKING

DIWO, LLC, Northville, M...

1. A method for determining an optimal strategy in a cognitive framework, the method comprising:storing, by a processor, a set of strategies in a system database, wherein each strategy, of the set of strategies, is associated to one or more opportunities;
filtering, by the processor, a subset of the set of strategies applicable to an opportunity of the one or more opportunities, wherein the subset is filtered based on a set of parameters associated to the opportunity;
automatically determining, by the processor, an impact for each strategy of the subset in real-time by using one or more predefined computational libraries, wherein the one or more predefined computational libraries are computed in parallel to each other on a distributed computing environment, and wherein the impact indicates a profit to be attained when the strategy is implemented for the opportunity, and wherein the computational libraries include GNU Linear Programming Kit, SCIP, CLP, LP SOLVE, SoPlex, Cplex, Xpress, and Gurobi;
automatically determining, by the processor, one or more strategies of the subset based on the impact and a set of Key Performance Indicators (KPI) associated to the opportunity, wherein the optimal strategy is determined in a cognitive framework by comparing the impact of each strategy with a predefined threshold impact, and wherein the optimal strategy has a highest impact as compared to the impact of each strategy of the one or more strategies;
implementing, by the processor, the optimal strategy in real-time on one or more activities within an organization; and
initiating, by the processor, a fault recovery mechanism for the optimal strategy when a computation of the optimal strategy is failed, wherein the fault recovery mechanism restarts the computation of the optimal strategy.

US Pat. No. 10,769,571

SECURITY AND CONTENT PROTECTION BY TEST ENVIRONMENT ANALYSIS

PEARSON EDUCATION, INC., ...

1. A system, comprising: a candidate client device including:a processor configured to implement a candidate evaluation software application,
a camera configured to record a sequence of images of an environment of the candidate client device, and
a microphone configured to record audio data in the environment of the candidate client device; and
one or more server hardware computing devices communicatively coupled to a network and in communication, via the network, with the candidate client device, and each comprising at least one processor executing specific computer-executable instructions within a memory that, when executed, cause the one or more server hardware computing devices to:
receive the sequence of images and the audio data from the candidate client device,
extract a first video attribute from the sequence of images,
extract a first audio attribute from the audio data, implement a machine learning engine to determine that the first video attribute or the first audio attribute violates a first condition by determining, based on a feature vector including a plurality of features that are extracted from the sequence of images and the audio data, that the candidate client device is in an unsuitable testing environment, and
prevent the candidate client device from performing a candidate evaluation function using the candidate evaluation software application.

US Pat. No. 10,769,570

ARTIFICIAL INTELLIGENCE BASED RISK AND KNOWLEDGE MANAGEMENT

ACCENTURE GLOBAL SOLUTION...

1. A system comprising:a data analyzer to provide entity data pertaining to an entity covered by a risk management instrument models, based on a risk control and management task to be performed, the entity data being obtained from at least one of an Internet of Things (IoT) device associated with the entity and a risk control and knowledge management database, wherein the entity data includes one or more of, entity-before-damage data and entity-post-damage data pertaining to the entity;
data pertaining to environmental attributes associated with the entity;
details pertaining to the risk control and management associated with the entity, a user associated with the entity, and external related data associated with multiple entities and multiple users;
and live data associated with covered entities, the live data being gathered using remote sensing and loT monitoring;
and an intelligent risk control and management agent in communication with the data analyzer, wherein the intelligent risk control and management agent is to process the entity data using at least one of an artificial intelligence technique and a machine learning technique to perform the risk control and knowledge management task, the intelligent risk control and management agent comprising at least one of, a claim processor to assist in claim processing pertaining to the entity, wherein the claim processor is to perform at least one of:
identify a case similar to the entity from a risk management database, using a similarity computation technique, the similar case having a case similarity score within a predefined threshold;
and compute a loss estimation, based on claims settled in the similar case;
a notification generator to generate notifications to the users, the notifications comprising one of alerts to notifying the users of existing and potential damages to the covered entities, and advice on how to react to the alerts and existing and potential damages, wherein the notification generator is to perform at least one of, identify the existing and potential damages to the entity, based on processing of the entity data with respect to reference parameters corresponding to the entity, the reference parameters influencing a computational intelligence measure of a damage to the entity by the artificial intelligence techniques;
generate the alerts to notify the user of the potential damage, when the potential damage is identified;
and provide the advices to how to react on the alerts to prevent the potential damage;
a risk control formulizer (RCF) to process the entity data to formulize the risk management instrument, based on at least one of the entity data in a plurality of domains and a relationship between various external factors associated with the risk management instrument, wherein the risk control formulizer is to identify emerging risk markets, develop new risk management instruments, and review existing risk management instruments;
and an agent assistant to process the entity data and related data to supplement the risk control and management task performed by one of an external agent, a user, and an organization providing risk management instruments.

US Pat. No. 10,769,569

SYSTEM FOR AUTOMATED RESOURCE SET MULTI-FACTOR RISK ANALYSIS

Hartford Fire Insurance C...

1. A multi-factor risk analysis system, comprising:a user device;
a resource data store containing electronic records defining, for each of a plurality of resources: a resource identifier associated with an entity, a current resource value, a resource type, and a resource location;
and
an automated back-end application computer server remote from the user device, coupled to the resource data store and the user device, including:
a communication port adapted to exchange information via a distributed communication network,
a computer processor, and
a computer memory storing instructions that, when executed by the computer processor cause the automated back-end computer server to perform a method, comprising;
receiving, from the user device via the communication port, a transmitted request for a set of index resources,
responsive to said request, establishing a set of risk parameter diversification objectives,
determining a set of eligible resources by accessing the resource data store,
calculating a value factor characteristic for each of the eligible resources,
calculating a momentum factor characteristic for each of the eligible resources,
automatically constructing the requested set of index resources from the set of eligible resources based on the risk parameter diversification objective and a risk optimization process utilizing a weighted value factor characteristic and momentum factor characteristic of each resource,
exchanging information with the remote user device via the communication port to render an interactive user interface including indications associated with the requested set of index resources, the value factor characteristics, and the momentum factor characteristics, and
automatically generating a plurality of reports including indications associated with the constructed set of index resources, the value factor characteristics, and the momentum factor characteristics,
wherein the interactive user interface further includes a circular visualization associated with risk distortions such that:
a graphical area within the circle is associated with an expected tail loss risk contribution based on resource location,
a graphical length along the circumference of the circle is associated with at least one of an overall country capital allocation and an overall currency capital allocation,
a length of a line extending outside and away from the circle is associated with an allocation to a particular equity or security, and
graphical elements of the circular visualization may be interactively adjusted by a user to automatically change resource allocations.

US Pat. No. 10,769,568

UAV ROUTING AND DATA EXTRACTION

Hartford Fire Insurance C...

1. A computer system comprising:one or more data storage devices storing data relating to a plurality of property insurance policies;
one or more computer processors in communication with the one or more data storage devices;
a communications interface in communication with the one or more computer processors and the one or more data storage device; and
a memory, coupled to the one or more computer processors, storing program instructions which, when executed by the one or more computer processors, cause the one or more computer processors to:
receive via the communications interface data, other than unmanned aerial vehicle (“UAV”) data, indicative of condition of a property related to at least one of the plurality of insurance policies;
determine, based on one or more data items, and without UAV data, whether collection of data relating to the property via an UAV is applicable in relation to the condition of the property;
responsive to a determination that collection via UAV is not applicable, forward the data indicative of the condition to an insurance workflow subsystem for investigation, without UAV data;
responsive to a determination that collection of data relating to the condition of the property via UAV is applicable, issue instructions for controlling UAV collection of information, the instructions causing an onboard computer of at least one UAV to control the UAV to autonomously navigate to a location of the property;
receive data via the communications interface from the UAV;
process the data from the UAV to determine at least one action; and
communicate via the communications interface with an insurance subsystem to initiate an insurance workflow process.

US Pat. No. 10,769,567

SYSTEM AND METHOD OF SCHEDULING WORK WITHIN A WORKFLOW WITH DEFINED PROCESS GOALS

Verint Americas Inc., Al...

1. A method of optimizing a workflow for scheduling work assignments, the method comprising:defining a plurality of work queues, each work queue representative of a task to be completed as a specific step in the workflow;
displaying the plurality of defined work queues in a graphical user interface;
receiving, through the graphical user interface, a selection of at least two work queues of the plurality of defined work queues;
presenting a graphical indication of each of the selected work queues on the graphical user interface;
creating and displaying, in the graphical user interface, at least one directional graphical link between two of the at least two selected work queues, binding the two of the at least two selected work queues;
defining, with the graphical user interface, at least one constraint associated with at least one of the selected work queues or at least one of the created graphical directional links;
creating at least one work process in the workflow by receiving, in the graphical user interface, a selection of at least two of the selected work queues, wherein the two work queues of the at least two selected work queues are connected by the at least one directional graphical link;
graphically depicting each of the work processes with a unique color;
graphically depicting each work queue and each graphical link that are not part of one of the work processes in a single unique color;
graphically depicting each work queue that is part of at least one of the work processes with the unique color assigned to each work process to which the work queue is assigned;
defining at least one work process goal for the at least one work process;
generating, using a processor adapted to optimize a work schedule, a workflow for scheduling tasks associated with the graphically depicted work queues, the generated schedule defined by the at least one constraint and the at least one work process goal;
unbinding a plurality of work queues for a predetermined number of work processes; and
randomly selecting an unbound work queue and iteratively binding another unbound work queue to the selected unbound work queue and simulate the performance of the workflow to optimize the workflow schedule until all unbound work queues are rebound and the workflow schedule is optimized such that all constrains and work process goals are met.

US Pat. No. 10,769,566

MANAGING PROCESS INSTANCES

International Business Ma...

1. A computer-implemented method, comprising:providing, by a processor, a plurality of policies for managing existing process instances of a business process management (BPM) engine, wherein each of the plurality of policies comprises:
a policy target descriptor specifying a set of process instances;
an action to be executed; and
a prerequisite condition to perform the action;
receiving, by the processor, a first status change event related to a first existing process instance, wherein the first existing process instance is defined by a first process definition, wherein the first process definition specifies a first workflow to implement a first plurality of related tasks of a first process;
matching, by the processor, the first existing process instance with a first policy of the plurality of policies, by comparing attributes of the first existing process instance to the prerequisite condition of the first policy; and
in response to determining that the attributes of the first existing process instance satisfy the prerequisite condition of the first policy:
determining, by the processor, that a plurality of existing process instances match a respective policy target descriptor of the first policy, wherein the plurality of existing process instances are defined by a second process definition that specifies a second workflow to implement a second plurality of related tasks of a second process;
executing, by the processor, a respective action of the first policy on the plurality of existing process instances; and
updating, by the processor, in an instance guarding table, a respective field of a respective row associated with each respective process instance of the plurality of existing process instances to indicate that the respective action has been performed on the respective process instance, wherein the respective row associated with each respective process instance of the plurality of existing process instances in the instance guarding table comprises:
an identifier of the first policy; and
an original status of the respective process instance that indicates whether the respective process instance was active prior to the first status change event.

US Pat. No. 10,769,565

SYSTEM AND METHOD FOR OPTIMIZED NETWORK DEVICE REPORTING

Toshiba TEC Kabushiki Kai...

1. A system comprising:a processor and associated memory; and
a network interface configured for data communication with a multifunction peripheral,
wherein the memory is configured for storing reporting schedule data corresponding to a reporting schedule of the multifunction peripheral,
wherein the processor is configured to send the reporting schedule to the multifunction peripheral via the network interface,
wherein the processor is further configured to receive a plurality of service file sets from the multifunction peripheral via the network interface,
wherein the processor is further configured to determine a timing of receipt of each of the service file sets relative to timing specified the reporting schedule data,
wherein the processor is further configured to generate updated reporting schedule data in accordance with a determined timing, and
wherein the processor is further configured to send the updated reporting schedule data to the multifunction peripheral via the network interface.

US Pat. No. 10,769,564

UNSCHEDULED BREAK COORDINATION SYSTEM

1. An unscheduled break coordination system, which is comprised of:a. one or more remote servers;
b. a plurality of mobile electronic communication devices;
wherein the plurality of mobile electronic communication devices provides a display;
c. a web-based software;
wherein the web-based software is provided on the plurality of mobile electronic communication devices;
wherein the web-based software is wirelessly connected to the one or more remote servers with the plurality of mobile electronic communication devices;
wherein the web-based software provides at least one user profile for each user;
wherein each user profile provides a user status;
wherein each user's status is further comprised of a location status and break status;
wherein each user can modify the break status;
wherein the user can modify the location status;
wherein a request for a break can be sent from one user within the plurality of users to at least one other user within the plurality of users;
wherein a user may accept another user's request for a break;
wherein the web-based application software notifies other users of the system when a status is changed;
wherein the web-based software notifies other users of the system when a request break button is engaged;
wherein each profile displays the status of at least one other user of the system;
d. a network;
wherein the network provides communication between the users.

US Pat. No. 10,769,563

METHOD AND SYSTEM FOR MANAGING BUSINESS DEALS

salesforce.com, inc., Sa...

1. A system comprising:a database system implemented using a server system comprising one or more hardware processors, the database system configurable to cause:
obtaining information identifying a plurality of past events and a plurality of future events, the past events and the future events being associated with one or more of a plurality of database records stored in a database;
providing feed data to a user device, the feed data capable of being processed by the user device, using one or more applications, to cause display or cause updating of display in a user interface of a plurality of feed items associated with the one or more database records, the feed items comprising a subset of past feed items representing the past events and a subset of future feed items representing the future events;
processing notification data regarding a first future event associated with the one or more database records, the notification data identifying a future event date, a location and a user; and
providing the notification data to the user device, the notification data capable of being processed by the user device to cause updating of the displayed feed items to represent the first future event as a designated future feed item according to the future event date, the designated future feed item configured to indicate the future event date, the location, and/or the user.

US Pat. No. 10,769,562

SENSOR BASED SYSTEM AND METHOD FOR AUTHORIZING OPERATION OF WORKSITE EQUIPMENT USING A LOCALLY STORED ACCESS CONTROL LIST

Triax Technologies, Inc.,...

1. An equipment sensor, comprising:a mechanical interface configured to attach the equipment sensor to a piece of equipment;
a processor configured to detect whether an operator is authorized to operate the piece of equipment, wherein detecting whether the operator is authorized to operate the piece of equipment comprises:
receiving, from a wearable sensor of the operator, a signal including an identifier for the wearable sensor;
retrieving, from a memory local to the equipment sensor, an access control list of operators that are authorized to operate the piece of equipment;
determining whether the identifier for the wearable sensor corresponds to an entry in the access control list; and
based on determining that the identifier for the wearable sensor corresponds to an entry in the access control list, without additional authentication, authorizing the operator to operate the piece of equipment based on detecting a presence of the operator within a range of the piece of equipment, the presence of the operator being detected within the range of the piece of equipment based on the signal received from the wearable sensor of the operator exceeding a threshold, the threshold being set differently based on a type of the piece of equipment and a location of the equipment sensor on the piece of equipment relative to a position of the operator;
at least one altimeter adapted to detect an altitude of the piece of equipment;
at least one accelerometer adapted to detect motion of the piece of equipment; and
a wireless network interface adapted to communicate data to an external system, the data comprising:
the altitude of the piece of equipment;
the presence of the operator of the piece of equipment; and
the motion of the piece of equipment.

US Pat. No. 10,769,561

ADAPTIVE LOGISTICS PLATFORM FOR GENERATING AND UPDATING SCHEDULES USING NATURAL LANGUAGE PROCESSING

Accenture Global Solution...

1. A device, comprising:a memory; and
one or more processors to:
receive user preference data and company preference data associated with one or more bookable items;
obtain external preference data associated with the one or more bookable items by extracting text, associated with the one or more bookable items, from an external source,
the external preference data being different from the user preference data and the company preference data;
parse the text using natural language processing;
determine, based on parsing the text using natural language processing, one or more scores associated with the one or more bookable items;
generate a list of schedules based on the user preference data, the company preference data, and the external preference data;
generate one or more category scores for a plurality of schedules included in the list of schedules based on the one or more scores associated with the one or more bookable items;
rank the list of schedules based on the one or more category scores;
select a first schedule, from the ranked list of schedules, based on the one or more category scores;
generate a knowledge graph based on the ranked list of schedules,
the knowledge graph including node values and edge values,
each node value, of the node values, representing a schedule of the plurality of schedules, and
each edge value, of the edge values, representing a degree of similarity between two schedules represented by two connected nodes;
monitor contextual data related to the first schedule,
the contextual data including at least one of:
information regarding one or more external events,
information regarding one or more user actions, or
user location information;
detect, based on monitoring the contextual data, a particular event that impacts a bookable item of the one or more bookable items;
modify the knowledge graph based on detecting the particular event;
select a second schedule based on modifying the knowledge graph; and
perform one or more actions based on selecting the second schedule,
the one or more actions including at least one of:
automatically displaying the second schedule on an interface of a user device,
automatically purchasing tickets,
automatically booking transportation,
automatically booking flights,
automatically booking reservations, or
automatically sending reminder notifications.

US Pat. No. 10,769,560

SYSTEMS AND METHODS FOR CHATBOT APPLICATIONS TRACKING USER STRESS LEVELS

Massachusetts Mutual Life...

1. A method comprising:reading, by a chatbot application, a plurality of email messages and a plurality of calendar entries, wherein the email messages are associated with a plurality of user profiles, wherein the calendar entries are associated with the user profiles, wherein the email messages and the calendar entries are stored remote from the chatbot application;
generating, by the chatbot application, a plurality of busyness factors based on the email messages and the calendar entries;
writing, by the chatbot application, the busyness factors into the user profiles;
reading, by the chatbot application, the busyness factors from the user profiles;
aggregating, by the chatbot application, the busyness factors into a group busyness factor;
caching, by the chatbot application, the group busyness factor;
receiving, by the chatbot application, a query from a client during a chat, wherein the client is running remote from the chatbot application, wherein the query is regarding a particular user profile not associated with the client, wherein the user profiles include the particular user profile;
reading, by the chatbot application, a particular busyness factor from the particular user profile;
retrieving, by the chatbot application, the group busyness factor;
comparing, by the chatbot application, the particular busyness factor against the group busyness factor;
tracking, by the chatbot application, the group busyness factor over a predetermined time period;
determining, by the chatbot application, how the group busyness factor changes over the predetermined time period;
generating, by the chatbot application, a baseline based on how the group busyness factor changes over the predetermined time period; and
presenting, by the chatbot application, a message to the client during the chat, wherein the message is responsive to the query, wherein the message is informative of the group busyness factor, the baseline, and the particular busyness factor relative to the group busyness factor wherein the message indicates how the group busyness factor changed over the predetermined time period.

US Pat. No. 10,769,558

SYSTEMS AND METHODS FOR MANAGING DYNAMIC TRANSPORTATION NETWORKS USING SIMULATED FUTURE SCENARIOS

Lyft, Inc., San Francisc...

1. A computer-implemented method comprising:receiving, by a dynamic transportation matching system, a first transport request and a second transport request;
evaluating, by the dynamic transportation matching system, a fitness of matching the first transport request with the second transport request to be fulfilled by a transport provider, based at least in part on a transportation overlap between the first transport request and the second transport request when fulfilled by the transport provider;
generating a simulated future transport request;
evaluating, by the dynamic transportation matching system, a fitness of matching the first transport request with the simulated future transport request, based at least in part on a transportation overlap between the first transport request and the simulated future transport request; and
matching, by the dynamic transportation matching system, the first transport request with the second transport request based at least in part on the fitness of matching the first transport request with the second transport request and based at least in part on the fitness of matching the first transport request with the simulated future transport request.

US Pat. No. 10,769,557

BIDDING FOR A REQUEST TO RESERVE A SERVICE

CFPH, LLC, New York, NY ...

1. A method comprising:generating, via a processor, a database that comprises data structures indicative of a plurality of table slots for on-site dining services, a plurality of table slots for off-site dining services, a plurality of time slots and a plurality of ratios of available table slots for on-site dining services to available table slots for off-site dining services;
allocating, via the processor, for a particular time slot a ratio of available table slots for on-site dining services to available table slots for off-site dining services;
receiving, via a biometric sensor, biometric data;
authenticating, via the processor, the biometric data;
in response to determining that the biometric data is authentic, permitting, via the processor, submission of a request for an off-site dining service at the particular time slot;
transmitting, to a remote device, a denial of the request for the off-site dining service at the particular time slot, in response to determining that the ratio of available table slots for on-site dining services to available table slots for off-site dining services meets a threshold;
transmitting, to a remote device, an approval of the request for the off-site dining service at the particular time slot, in response to determining that the ratio of available table slots for on-site dining services to available table slots for off-site dining services does not meet a threshold; and
adjusting, via the processor, the ratio for the particular time slot, in response to determining that a change in available table slots for on-site dining services to available table slots for off-site dining services is detected.

US Pat. No. 10,769,556

FRAMEWORKS AND METHODOLOGIES CONFIGURED TO ENABLE INTEGRATION OF BOOKING AND ACCESS CONTROL FOR SERVICE PROVIDERS

1. A computer implemented method, performed by one or more server devices, configured to selectively unlock doors at accommodations including hotel rooms, the method including:providing an interface that is configured to communicate with a plurality of client mobile devices, wherein each client mobile device executes a prescribed software application, wherein each executing instance of the prescribed software application is configured to provide a user interface that:
(i) identifies an accommodation in respect of which a time-specific booking has been made; and
(ii) provides a user interface component configured to enable a user to cause unlocking of a door of the particular accommodation in accordance with the time specific booking;
receiving a signal representative of a completion of the time-specific booking of a particular accommodation, wherein the time-specific booking is associated with a particular accommodation networked door lock device for the particular accommodation; a user account; and timing parameters; and
based on the signal received, configuring the user interface of a specific one of the client mobile devices, being a client mobile device associated with the user account, to:
(i) provide data identifying the completion of the time-specific booking of the particular accommodation; and
(ii) configure the user interface component to enable the user to submit an instruction via the user interface which is representative of a request to unlock the door for the particular accommodation;
in response to the receiving of the signal representative of the completion of the time-specific booking of the particular accommodation, wherein the time-specific booking is associated with the particular accommodation networked door lock device for particular accommodation; the user account; and the timing parameters:
setting an access permission associated with the user account for the particular accommodation networked door lock device for the particular accommodation;
receiving, from the specific one of the client mobile devices via the user interaction with the user interface component, the instruction which is representative of the request to unlock the door for the particular accommodation;
processing the request based on the access permission;
determining that the request is to be granted; and
providing a secure signal to cause the particular accommodation networked door lock device for the particular accommodation to transition into an unlocked state thereby to grant access to the particular accommodation in accordance with the time-specific booking of the accommodation;
wherein each of the client mobile device, each server device, and each particular accommodation networked door lock device are distinct devices on a common computer network.

US Pat. No. 10,769,555

PERFORMING ACTIONS IN RESPONSE TO CHARGING EVENTS

RECARGO, INC., El Segund...

1. A computerized method, comprising:determining an electric vehicle is below a battery capacity threshold;
in response to the determination that the electric vehicle is below a battery capacity threshold, sending a request to multiple charging stations to charge the electric vehicle;
obtaining from the multiple charging stations information identifying parameters associated with potential charging events provided by the multiple charging stations for charging the electric vehicle in response to the request,
wherein the parameters associated with the potential charging events are dynamically determined by the multiple charging stations after and in response to receiving the request to charge the electric vehicle, and
wherein the parameters associated with the potential charging events include parameters that identify whether one or more charging stations of the multiple charging stations have successfully charged electric vehicles having a similar make and model to the electric vehicle below the battery capacity threshold;
automatically selecting one of the multiple charging stations to charge the electric vehicle based on the information identifying the parameters associated with potential charging events provided by the multiple charging stations; and
automatically reserving the electric vehicle to charge with the selected charging station.

US Pat. No. 10,769,554

INTERACTIVE TECHNIQUE FOR USING A USER-PROVIDED IMAGE OF A DOCUMENT TO COLLECT INFORMATION

INTUIT INC., Mountain Vi...

1. A method for populating a field in a form performed by a computer, comprising:receiving a fillable form based on a description of a physical document, wherein the physical document comprises a set of fields, and wherein the fillable form comprises a fillable field for each field in the set of fields;
sending a template of the set of fields to be displayed to a user on a portable electronic device that is remotely located from the computer;
sending a unique prompt, for each field in the set of fields, to be displayed to the user at the portable electronic device, wherein each unique prompt displayed to the user requests the user to capture an image, based on the displayed template, of a region of the physical document that includes the field and data that appears in the field corresponding to that unique prompt;
receiving, for each of the one or more fields, the image of the region of the physical document that includes the field and data that appears in the field;
extracting, for each received image, the data that appears in the field from the image of the region; and
populating the extracted data into the fillable field in the fillable form that corresponds to the field from the image of the region of the physical document.

US Pat. No. 10,769,553

INTEGRATED CIRCUIT DEVICE AND CIRCUITRY

NANYA TECHNOLOGY CORPORAT...

1. An integrated circuit (IC) device, comprising:a measurement circuit configured to acquire a practical voltage; and
a classifier circuit configured to:
generate an information on an immature classification by comparing a default voltage and the practical voltage;
receive an information on a reference classification, which is acquired by manually comparing the default voltage and the practical voltage;
update the default voltage to a learned voltage based on the immature classification and the reference classification; and
generate a prediction, based on the learned voltage, for adjusting a slew rate,
wherein the measurement circuit includes:
a first sample-and-hold circuit configured to sample a first voltage of a signal; and
a second sample-and-hold circuit configured to sample a second voltage of the signal, and
wherein the practical voltage is associated with the first voltage and the second voltage.

US Pat. No. 10,769,552

JUSTIFYING PASSAGE MACHINE LEARNING FOR QUESTION AND ANSWER SYSTEMS

International Business Ma...

1. A method, in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for generating answers to an input question, comprising:receiving, in the data processing system, the input question;
generating, by the data processing system, a set of candidate answers for the input question and, for each candidate answer in the set of candidate answers, a corresponding confidence score indicating a confidence that the corresponding candidate answer is a correct answer for the input question, and a selection of one or more selected evidence portions from a corpus of information providing evidence in support of the candidate answer being a correct answer for the input question;
modifying, by the data processing system, confidence scores of one or more of the candidate answers based on relevance scores generated by an application of a justifying passage model (JPM) to the selected evidence portions for each of the candidate answers in the set of candidate answers to thereby generate a modified set of confidence scores, wherein the JPM identifies whether a candidate answer is justified by a selected evidence passage corresponding to the candidate answer, and wherein an evidence passage justifies a corresponding candidate answer in response to content of the evidence passage explicitly stating the candidate answer to be a correct answer for the input question;
ranking, by the data processing system, the candidate answers based on the modified set of confidence scores; and
outputting, by the data processing system, a candidate answer in the set of candidate answers as the correct answer for the input question based on the ranking of the candidate answers.

US Pat. No. 10,769,551

TRAINING DATA SET DETERMINATION

International Business Ma...

1. A computer program product including one or more computer readable storage media collectively having instructions embodied therewith, the instructions executable by a processor to cause the processor to perform operations comprising:selecting a first set of reference training data from a training data set based on a degree of difference between each set of reference training data in the training data set and target training data, wherein the first set of reference training data yields a smallest degree of difference from the target training data among all sets of reference training data in the training data set;
determining that a degree of difference between the target training data and the first set of reference training data is below a first threshold, wherein the degree of difference is based on a distance;
determining to include the target training data in the training data set in response to determining that an average degree of difference between the target training data and a first plurality of second sets of reference training data is larger than an average degree of difference between the first set of reference training data and a second plurality of second sets of reference training data, wherein the first and second plurality of second sets of reference training data are included in the training data set and do not include data from the first set of reference training data; and
performing machine learning using the training data set with the included target training data.

US Pat. No. 10,769,550

ENSEMBLE LEARNING PREDICTION APPARATUS AND METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM

INDUSTRIAL TECHNOLOGY RES...

1. An ensemble learning prediction apparatus, comprising:a loss module receiving a sample data and calculating a loss according to a first prediction result of the sample data and an actual result;
a diversity module receiving the sample data and calculating a diversity between at least one hypothesis according to a second prediction result of the sample data under the at least one hypothesis;
a sample weighting module calculating a correctable value of the sample data according to the first prediction result and the actual result and assigning a sample weight according to the correctable value; and
an integrating weighting module, interconnected with the loss module, the diversity module and the sample weighting module, creating an object function according to the loss, the diversity and the sample weight, and training an ensemble weight by use of the object function;
wherein an adaptive ensemble weight is calculated by integrating the ensemble weight and the ensemble weight obtained at previous time points, and the correctable value is obtained according to a function having a high point from which the function descends to both sides on which the high point no more appears.

US Pat. No. 10,769,549

MANAGEMENT AND EVALUATION OF MACHINE-LEARNED MODELS BASED ON LOCALLY LOGGED DATA

Google LLC, Mountain Vie...

1. A computer-implemented method to manage machine-learned models, the method comprising:obtaining, by a user computing device from a centralized computing system, a plurality of machine-learned models, wherein the user computing device is associated with a particular user, wherein each of the plurality of machine-learned models has been previously trained by the centralized computing system on a centralized collection of data;
prior to activation of any of the plurality of machine-learned models for use at the user computing device:
evaluating, by the user computing device, at least one performance metric for each of the plurality of machine-learned models, wherein the at least one performance metric for each machine-learned model is evaluated relative to historical data that was previously logged at the user computing device and is stored locally at the user computing device and associated with the particular user and that is not included in the centralized collection of data, wherein the at least one performance metric for each of the plurality of machine-learned models is evaluated without transmission of any of the historical data to the centralized computing system, and wherein the at least one performance metric comprises a measure of an ability of the machine-learned model to correctly predict portions of the historical data descriptive of behavior of the particular user;
comparing, by the user computing device, the measure of the ability of each of the plurality of machine-learned model to predict portions of the historical data descriptive of behavior of the particular user; and
determining, by the user computing device, a selection of a first machine-learned model from the plurality of machine-learned models for activation based at least in part on the comparison of the measure of the ability of each of the plurality of machine-learned model to predict portions of the historical data descriptive of behavior of the particular user, wherein determining the selection comprises selecting, by the user computing device, the machine-learned model with a highest measure of the ability to correctly predict portions of the historical data descriptive of behavior of the particular user among the plurality of machine-learned models;
activating, by the user computing device, the selected first machine-learned model for use at the user computing device; and
after activation of the first machine-learned model, using, by the user computing device, the first machine-learned model to obtain one or more predictions.

US Pat. No. 10,769,548

VALUE MODEL FOR SENDING NOTIFICATIONS

Facebook, Inc., Menlo Pa...

1. A system comprising: one or more processors, and a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to:send, through a communications network, sets of first notifications corresponding to a first notification type, wherein each of the sets of first notifications has a corresponding volume and is sent to a plurality of users, and the volumes corresponding to the sets of first notifications are different;
send, through the communications network, sets of second notifications corresponding to a second notification type, wherein each of the sets of second notifications has a corresponding volume and is sent to a plurality of users, and the volumes corresponding to the sets of second notifications are different;
determine visitation impacts of the sets of first and second notifications of the first and second notification types, respectively, wherein each of the visitation impacts is associated with one of the sets of first and second notifications and the volume corresponding to that set;
train, based on the visitation impacts and the associated volumes, a machine-learning model to output assessments of the first and second notification types;
determine, based on the assessments, a desired volume of a set of third notifications and a desired notification type for the set of third notifications, wherein the desired notification type is selected from the first notification type or the second notification type; and
send, through the communications network, the set of third notifications.

US Pat. No. 10,769,547

MOBILE SEARCHES UTILIZING A QUERY-GOAL-MISSION STRUCTURE

Oath Inc., New York, NY ...

1. A method for improving mobile searches, comprising:identifying a feature, generated by a user within a time period on a client device, based upon an identification of the user;
evaluating the feature to identify a goal associated with the feature;
assigning a goal identification to the feature;
calculating a user satisfaction metric associated with the goal to determine a goal satisfaction metric based upon user interaction with results associated with the goal, the results generated by a first model generated utilizing a machine learning method based upon a query-goal-mission structure,
the calculating a user satisfaction metric based upon at least one of a swipe rate through card modules associated with at least one of the goal or a mission, a number of card modules viewed associated with at least one of the goal or the mission, a card dismissal rate of the card modules associated with at least one of the goal or the mission, a number of card modules the user interacts associated with at least one of the goal or the mission, or an average scroll rate through the card modules associated with at least one of the goal or the mission;
calculating a second user satisfaction metric associated with the goal to determine a second goal satisfaction metric based upon second user interaction with second results associated with the goal, the second results generated by a second model generated utilizing the machine learning method based upon the query-goal-mission structure; and
responsive to the user satisfaction metric calculated based upon the user interaction with the results generated by the first model exceeding the second user satisfaction metric calculated based upon the second user interaction with the second results generated by the second model, selecting the first model that generated the results used to calculate the user satisfaction metric associated with the goal, but not the second model that generated the second results used to calculate the second user satisfaction metric associated with the goal, from amongst a plurality of models for subsequent use for presenting one or more results to users.

US Pat. No. 10,769,546

MICROWAVE INTEGRATED QUANTUM CIRCUITS WITH CAP WAFER AND METHODS FOR MAKING THE SAME

1. A quantum computing system comprising:a first substrate having on a first surface one or more recesses, standoff bumps, an electrically conducting layer that conforms to the one or more recesses and the standoff bumps, and bonding elements coupled with the electrically conducting layer, the bonding elements being disposed outside the one or more recesses;
a second substrate having a first surface; and
one or more quantum circuit devices disposed on the first surface of the second substrate;
wherein the first substrate and the second substrate are bonded such that the one or more recesses form enclosures that respectively house the one or more quantum circuit devices.

US Pat. No. 10,769,545

SYSTEMS AND METHODS EMPLOYING NEW EVOLUTION SCHEDULES IN AN ANALOG COMPUTER WITH APPLICATIONS TO DETERMINING ISOMORPHIC GRAPHS AND POST-PROCESSING SOLUTIONS

D-WAVE SYSTEMS INC., Bur...

1. A system for use in quantum processing, comprising:at least one non-transitory processor-readable medium that stores at least one of processor executable instructions or data; and
at least one processor communicatively coupled to the least one non-transitory processor-readable medium, and which, in response to execution of the at least one of processor executable instructions or data:
for a first computational problem defined by a problem Hamiltonian, during a first iteration on the first computational problem:
initializes the analog processor to a zeroth state via application of a local bias value to a plurality of quantum devices in the analog processor;
evolves the analog processor to a first state under an instant Hamiltonian that includes a problem Hamiltonian wherein:
the problem Hamiltonian has no local biases on the plurality of quantum devices, and
the problem Hamiltonian has no couplings between the devices in the plurality of quantum devices;
evolves the analog processor under a first non-linear evolution schedule; and
reads out a first final state of the analog processor.

US Pat. No. 10,769,544

SAMPLING SCHEMES FOR STRATEGY SEARCHING IN STRATEGIC INTERACTION BETWEEN PARTIES

Alibaba Group Holding Lim...

1. A computer-implemented method for performing counterfactual regret minimization (CFR) for strategy searching in strategic interaction between two or more parties, the method comprising:identifying N1 possible actions of a first party in a first state of the first party;
sampling a possible action out of the N1 possible actions in the first state of the first party with a first sampling probability;
identifying N2 possible actions of the first party in a second state of the first party, wherein the first state of the first party is closer to a beginning state of an imperfect information game (IIG) than the second state of the first party;
sampling a possible action out of the N2 possible actions in the second state of the first party with a second sampling probability, wherein the first sampling probability is less than the second sampling probability; and
performing the CFR based on the possible action out of the N1 possible actions in the first state of the first party and the possible action out of the N2 possible actions in the second state of the first party.

US Pat. No. 10,769,543

DOUBLE-LAYERED IMAGE CLASSIFICATION ENDPOINT SOLUTION

FORCEPOINT LLC, Austin, ...

1. A system for image classification, comprising:a central system configured to provide high reliability image data processing and recognition;
a plurality of endpoint systems, each configured to provide image data processing and recognition with a lower reliability than the central system and to generate probability data; and
a decision switch disposed at each of the plurality of endpoint systems, the decision switch configured to receive the probability data and to determine whether to deny access, grant access or generate a referral message to the central system, wherein the referral message includes at least a set of image data generated at the endpoint system.

US Pat. No. 10,769,542

GENERATING WEATHER DATA BASED ON MESSAGING SYSTEM ACTIVITY

Snap Inc., Santa Monica,...

1. A method comprising:analyzing, by a computing system, messages generated by a plurality of computing devices associated with a plurality of users in a messaging system to extract media content items from the messages and generate training data;
training, by the computing system, a machine learning model using the generated training data comprising the media content items to determine a probability that a media content item was generated inside an enclosed location or outside;
receiving, by the computing system, a media content item from a computing device;
extracting image features from the media content item;
analyzing the extracted image features of the media content item to determine objects associated with each extracted image feature;
generating a feature vector based on the determined objects associated with each extracted image feature;
analyzing the feature vector using the trained machine learning model to determine a probability that the media content item was generated inside an enclosed location or outside;
determining, based on the probability generated by the trained machine learning model, that the media content item was generated inside an enclosed location;
determining a location of the computing device when the media content item was generated;
determining a venue associated with the location of the computing device;
determining an inside temperature associated with the venue based on the messages generated by a plurality of computing devices in a messaging system comprising media content items and temperature information for the venue or a similar venue type;
generating creative functionality associated with the inside temperature and the venue or similar venue type; and
providing the creative functionality to the computing device.

US Pat. No. 10,769,541

METHOD FOR DETERMINING TACTICAL ACTIONS

THALES, Courbevoie (FR)

1. A method for determining tactical actions for protecting a reference entity with respect to a plurality of entities in a battlefield environment, the method comprising:segmenting the battlefield environment into a plurality of layers around the reference entity,
associating actable deterrent systems with each layer,
obtaining data representative of the probability, for each deterrent system, that a considered deterrent system deters an entity in an associated layer, wherein said obtaining comprises obtaining first kinematic parameters relative to each of said plurality of entities,
providing, for each entity, a level of threat of said entity, wherein said providing comprises
computing second kinematic parameters from said first kinematic parameters, for each of said plurality of entities, said second kinematic parameters presenting a monotonic relationship with regards to the level of threat,
aggregating the second kinematic parameters to obtain a threat level function giving a first level of threat,
calibrating the threat level function with a plurality of training instances to obtain a plurality of calibrated threat levels, and
computing a second threat level using the first threat level and the calibrated threat levels, and
computing a cost function for determining the deterrent systems to be engaged by the reference entity for rendering extremal the cost function, the cost function being a function depending from the level of threat and the obtained data.

US Pat. No. 10,769,540

RARE EVENT PREDICTION

HEWLETT PACKARD ENTERPRIS...

16. A non-transitory machine-readable medium storing machine-readable instructions executable by a physical processor that cause the processor to:receive a plurality of historical customer case logs, wherein each log includes at least one key variable and unstructured data;
parse the unstructured data into a plurality of parsed words;
remove stop words from the plurality of parsed words, wherein stop words are frequently used words that do not provide predictive value;
stem the plurality of parsed words into a plurality of predictors;
create an escalation prediction model based on the at least one key variable and the plurality of predictors;
receive a new customer case log;
identify at least one key variable and unstructured data from the new customer case log;
apply text mining techniques to the unstructured data from the new customer case log to obtain a corresponding plurality of predictors from the new customer case log; and
forecast an escalation to result from the new customer case log based on the escalation prediction model, the key variables from the new customer case log, and the plurality of predictors from the new customer case log.

US Pat. No. 10,769,539

AUTOMATIC EVALUATION OF A KNOWLEDGE CANVASSING APPLICATION

International Business Ma...

1. A method, comprising:generating benchmark data, each benchmark datum including a set of one or more benchmark input entities and a set of one or more benchmark output entities associated with the one or more benchmark input entities;
querying a machine-learning knowledge canvassing system with each set of benchmark input entities;
receiving a returned passage from the machine-learning knowledge canvassing system in response to the querying;
receiving, for each set of benchmark input entities queried, an output result from the machine-learning knowledge canvassing system that includes a set of zero or more knowledge canvassing system output entities;
generating an evaluation score for each set of knowledge canvassing system output entities based on a comparison of the knowledge canvassing system output entities with the set of benchmark output entities, wherein the comparison includes estimating a degree to which a knowledge canvassing system output entity in a first set of the knowledge canvassing system output entities relates to a benchmark output entity in a first set of the benchmark output entities, wherein estimating the degree to which the knowledge canvassing system output entity relates to the benchmark output entity is based on a co-occurrence, in a returned passage from the machine-learning knowledge canvassing system, of the knowledge canvassing system output entity and the benchmark output entity, and wherein the knowledge canvassing system output entity does not match any of the benchmark output entities in the first set of benchmark output entities; and
training the machine-learning knowledge canvassing system based on the evaluation scores.

US Pat. No. 10,769,538

SYSTEM AND METHOD FOR MANAGING ROUTING OF CUSTOMER CALLS TO AGENTS

Massachusetts Mutual Life...

1. A processor-based method for managing customer calls within a call center, comprising:upon receiving a customer call at a call center from an identified customer at an inbound call receiving device:
retrieving, by a processor, a set of enterprise customer data associated with the identified customer from a customer database that stores the enterprise customer data;
retrieving, by the processor, customer demographic data for the identified customer;
executing, by the processor, a predictive machine-learning model to determine a value prediction signal by inputting enterprise customer data and customer demographic data, wherein the value prediction signal is representative of a likelihood that the identified customer will accept an offer to purchase a product, the predictive machine-learning model classifying the identified customer into a first value group or a second value group, wherein a modeled value of sale of the product of the first value group is higher than a modeled value of sale of the product of the second value group;
routing, by the processor, the inbound call:
to a priority queue assignment for connection to an agent from a first group of agents in the event the processor classifies the identified customer into the first value group; and
to a subordinate queue assignment for connection to an agent from a second group of agents in the event the processor classifies the identified customer into in the second value group,
wherein the first group of agents have a higher likelihood of completing the sale of the product than the second group of agents.

US Pat. No. 10,769,537

COGNITIVE QUESTION ANSWERING PIPELINE BLENDING

International Business Ma...

1. A method comprising:generating, for a question, a first set of question answer data using a first answering pipeline, wherein the first set of question answer data comprises a first set of answers and a set of first pipeline confidence values for each answer in the first set of answers;
generating, for the question, a second set of question answer data using a second answering pipeline, wherein the second set of question answer data comprises a second set of answers and a set of second pipeline confidence values for each answer in the second set of answers;
determining, using a weighting formula and a first blending profile associated with the first answering pipeline, a first vote weight for an answer in the first set of question answer data that was assigned a first pipeline highest confidence value by the first answering pipeline;
determining, using the weighting formula and a second blending profile associated with the second answering pipeline, a second vote weight for an answer in the second set of question answer data that was assigned a second pipeline highest confidence value by the second answering pipeline; and
selecting, as a first answer to the question, the answer with an overall highest vote weight from among the answers in the first set of question answer data and in the second set of question answer data, wherein the first blending profile comprises metadata including:
a first answer accuracy value (AAV), the first AAV reflecting a first probability that the first answering pipeline will produce a first correct answer to the question;
a first answer confidence table (ACT), the first ACT reflecting a first set of confidence threshold value and probability association pairs, each first pair indicating a probability that the first answering pipeline will produce an answer with a confidence value exceeding an associated confidence threshold value; and
a first correct answer confidence table (CACT), the first CACT reflecting a second set of confidence threshold value and probability association pairs, each second pair indicating a correct answer probability that the first answering pipeline will produce a correct answer with a second confidence value equal to or greater than the associated second confidence threshold value; and
wherein the weighting formula is used to determine the first vote weight of the answer in the first set of question answer data that was assigned the highest confidence value by the first answering pipeline by:
obtaining a first CACT probability by searching the first CACT for a CACT probability, the CACT probability associated with a greatest confidence value that does not exceed the confidence value of the answer, the confidence value of the answer assigned by the first answering pipeline;
obtaining a first ACT probability by searching the first ACT for a ACT probability, the first ACT probability associated with a greatest confidence value that does not exceed the confidence value of the answer;
calculating a first ratio of the first CACT probability divided by the first ACT probability;
calculating a first product of the first ratio multiplied by the first AAV; and
assigning the first product as the first vote weight.

US Pat. No. 10,769,536

WORK SUPPORT SYSTEM AND WORK SUPPORT PROGRAM

GRACE TECHNOLOGY, INC., ...

1. A work support system that is communicably connected to a device having a sensor and a notification means that is worn or carried by a worker, for supporting work of the worker, the work support system comprising:a rule generation means that generates a rule describing a determination condition of a work object or work situation by, based on a manual describing procedures, contents, points of attention, or other matters of the work, associating elements that are terms, headings, texts, items, charts, figures, images, videos, or others included in the manual;
an element change recording means that records changes in the elements using a model case;
a learning means that optimizes the rule such that the model case gains the highest evaluation based on a recording result of the element change recording means;
a sensor information acquisition means that acquires sensor information of the sensor;
a recognition means that recognizes the work object and the work situation based on the sensor information acquired by the sensor information acquisition means; and
a work support information output means that outputs work support information to the notification means based on the rule generated by the rule generation means and a recognition result of the recognition means.

US Pat. No. 10,769,535

INGESTION PIPELINE FOR UNIVERSAL COGNITIVE GRAPH

Cognitive Scale, Inc., A...

1. A system comprising:a processor;
a data bus coupled to the processor; and
a non-transitory, computer-readable storage medium embodying computer program code, the non-transitory, computer-readable storage medium being coupled to the data bus, the computer program code interacting with a plurality of computer operations and comprising instructions executable by the processor and configured for:
receiving data from a data source;
determining whether the data comprises text;
processing the data, the processing comprising performing a natural language processing operation on the data, the processing the data identifying a plurality of knowledge elements based upon the natural language processing operation;
storing at least some of the knowledge elements within a cognitive graph as a collection of knowledge elements, the storing universally representing knowledge obtained from the data, the cognitive graph comprising integrated machine learning functionality, the integrated machine learning functionality using extracted features of newly-observed data from user feedback received during a learning phase to improve accuracy of knowledge stored within the cognitive graph, the cognitive graph being implemented with an ontology, the ontology universally representing knowledge and comprising a representation of entities along with properties and relations of the entities according to a system of categories, the ontology storing a knowledge element within the cognitive graph based upon a set of categories of the knowledge element and a set of attributes of the knowledge element;
performing a parsing operation, the parsing operation generating a set of parse trees using a parse rule set, the parsing operation comprising a mapping operation, the mapping operation comprising mapping structural elements to resolve ambiguity, the mapping operation comprising mapping structural elements of the text around a verb of the text, the mapping of the structural elements transforming the structural elements into words higher up an inheritance chain within the cognitive graph, the parse trees being ranked by a conceptualization ranking rule set, the parse trees representing ambiguous portions of the text; and,
performing a conceptualization operation, the conceptualization operation identifying relationships of concepts identified from ranking the set of parse trees using the conceptualization ranking rule set, the conceptualization operations generating a set of conceptualization ambiguity options, the set of conceptualization ambiguity options being ranked using the conceptualization ranking rule set, top-ranked conceptualization options being stored in the cognitive graph.

US Pat. No. 10,769,534

EVALUATION TARGET OF INTEREST EXTRACTION APPARATUS AND PROGRAM

Kabushiki Kaisha Toshiba,...

1. An evaluation target of interest extraction apparatus configured to discover a pattern before an evaluation target of interest is extracted based on the pattern from a plurality of pieces of text information which are given along a time series and are related to a plurality of evaluation targets, comprising a computer configured to:collect text time series data including text information delivered among the plurality of pieces of text information, information which shows evaluation targets contained in the text information delivered among the plurality of evaluation targets, and first time information which shows timing at which each text information is delivered via a network;
collect numeric time series data including numeric information which are given along a time series for each evaluation target and individually related to each evaluation target and time information individually related to each numeric information via the network, wherein the time information includes the first time information and second time information which shows timing after timing shown by the first time information in the same time series;
store, in a storage, an evaluation target expression which individually expresses each evaluation target, and a related expression which expresses a target individually related to each evaluation target in association with each other;
extract a plurality of noun expressions for each piece of text information included in the collected text time series data;
allocate the evaluation target expression or an evaluation target expression associated with the related expression in the storage to the text information related to extracted noun expressions as an evaluation target noun expression, when the noun expressions include a noun expression that matches the stored evaluation target expression or the related expression;
obtain first numeric information as numeric information related to a first timing as a delivery timing corresponding to text information to which the evaluation target noun expression is allocated and second numeric information as the numeric information related to a second timing after the first timing in the same time series from numeric time series data corresponding to the evaluation target noun expression, wherein the first timing is shown by the first time information and the second timing is shown by the second time information;
calculate a change in numeric information related to the evaluation target between the first and second timing based on the first and second numeric information which is obtained;
distinguish a class related to the change in the numeric information, and allocate the class to the text information to which the evaluation target noun expression is allocated;
generate, for each piece of collected text information, a class attached transaction including the allocated evaluation target noun expression, the extracted noun expressions, and the allocated class; and
discover the pattern indicating a combination of characteristic noun expressions from each of the transactions, the combination of characteristic noun expressions having high frequencies of occurrence.

US Pat. No. 10,769,533

SYSTEMS AND METHODS FOR EFFICIENT NEURAL NETWORK DEPLOYMENTS

Baidu USA LLC, Sunnyvale...

1. A batching method for increasing throughput of data processing requests, the method comprising:receiving data associated with requests to be processed by using a neural network model, each request of at least some of the requests being subject to one or more constraints and at least some of the requests being received asynchronously;
dynamically assembling at least some of the data into a batch using at least one of the one or more constraints by performing steps comprising:
for each request of at least some of the requests, using at least one of the one or more constraints associated with the request to select whether the request should be included in a batch; and
assembling data associated with the selected requests into a batch; and
processing the batch using a single thread that orchestrates a plurality of threads to share a burden of loading the neural network model from memory to increase data throughput.

US Pat. No. 10,769,532

NETWORK RATING PREDICTION ENGINE

Accenture Global Solution...

1. A computer-implemented method performed by at least one processor, the method comprising:receiving, by the at least one processor, first review data that includes a plurality of rated reviews;
determining, by the at least one processor, a plurality of model building transactions to be executed to build at least one prediction model based on the first review data;
building, by the at least one processor, the at least one prediction model through use of at least one deep convolutional neural network (CNN), including distributing the plurality of model building transactions for parallel execution on a plurality of compute nodes, the building comprising a heuristic unsupervised pre-training that employs a heuristic formula that includes an absolute difference factor and a distribution difference factor;
receiving, by the at least one processor, second review data that includes a plurality of unrated reviews; and
predicting, by the at least one processor, a rating for each of the plurality of unrated reviews using the at least one prediction model.

US Pat. No. 10,769,531

METHODS AND SYSTEMS FOR COUNTING PEOPLE

Cisco Technology, Inc., ...

1. A method comprising:pre-training an analytics system, wherein
the pre-training comprises
generating an augmented data set, wherein
the generating the augmented data set comprises injecting one or more modifications into a ground truth data set, and
the one or more modifications are selected by a domain expert,
generating a semantic fingerprint that comprises a probability distribution, and
utilizing the augmented data set and the semantic fingerprint to perform an unsupervised generative pre-training process and a supervised discriminative fine-tuning process;
receiving input data at a processor of the analytics system, wherein
the input data comprises a representation of an environment at a first point in time,
the representation of the environment is based, at least in part, on data captured by one or more sensors configured to capture visual data,
the representation of the environment comprises a plurality of representations of persons, and
the analytics system comprises an artificial neural network; and
subsequent to the pre-training, using the analytics system to perform operations comprising:
pre-processing the input data, wherein
the pre-processing comprises whitening the input data, wherein
whitening the input data comprises transforming the input data to uncorrelated values,
identifying, using the processor, a representation of a person of the plurality of representations of persons, wherein
the identifying comprises
generating a feature vector using a generative process, wherein
 the feature vector comprises a sparse distributed representation of the input data, and
applying a discriminative process to the feature vector to identify the representation of the person,
generating a count of a number of persons identified as being present within the input data, wherein
the count is generated, at least in part, by using the representation of the person, and
updating a value, based, at least in part, on the count, wherein
the value indicates the number of persons identified as being present within the input data.

US Pat. No. 10,769,530

METHOD FOR TRAINING ARTIFICIAL NEURAL NETWORK USING HISTOGRAMS AND DISTRIBUTIONS TO DEACTIVATE AT LEAST ONE HIDDEN NODE

SUALAB CO., LTD., Seoul ...

1. A method of training at least a part of a neural network including a plurality of layers, the method being performed by a computing device, the method comprising:inputting training data including normal data and abnormal data to an input layer of the neural network;
making a feature value output from each of one or more hidden nodes of a hidden layer of the neural network for each training data into a histogram and generating a distribution of the feature value for each of the one or more hidden nodes;
calculating an error between each distribution of the feature value and a predetermined probability distribution; and
updating a weight of at least one hidden node to deactivate the at least one hidden node of the one or more hidden nodes of the hidden layer based on the error.

US Pat. No. 10,769,529

CONTROLLED ADAPTIVE OPTIMIZATION

Google LLC, Mountain Vie...

1. A computer-implemented method for optimizing machine-learned models that provides improved convergence properties, the method comprising:for each of a plurality of iterations:
determining, by one or more computing devices, a gradient of a loss function that evaluates a performance of a machine-learned model that comprises a plurality of parameters;
determining, by the one or more computing devices, a current learning rate control value based on the gradient of the loss function, wherein the current learning rate control value equals a most recent learning rate control value minus an update value, wherein a magnitude of the update value is a function of the gradient of the loss function but not the most recent learning rate control value, and wherein a polarity of the update value is a function of both the gradient of the loss function and the most recent learning rate control value;
determining, by the one or more computing devices, a current effective learning rate based at least in part on the current learning rate control value; and
determining, by the one or more computing devices, an updated set of values for the plurality of parameters of the machine-learned model based at least in part on the gradient of the loss function and according to the current effective learning rate; and
providing, by the one or more computing devices, an optimized version of the machine-learned model as an output, the optimized version of the machine-learned model comprising a final set of values for the plurality of parameters;
wherein, for at least one of the plurality of iterations, the polarity of the update value is positive such that the current learning rate control value is less than the most recent learning rate control value, whereby the current effective learning rate is greater than a most recent effective learning rate.

US Pat. No. 10,769,528

DEEP LEARNING MODEL TRAINING SYSTEM

SAS Institute Inc., Cary...

1. A non-transitory computer-readable medium having stored thereon computer-readable instructions that when executed by a computing device cause the computing device to:(A) select a batch of observation vectors, wherein the batch of observation vectors includes a mini-batch size value number of observation vectors selected from a plurality of observation vectors, wherein each observation vector of the plurality of observation vectors includes a value for each variable of a plurality of variables;
(B) execute a neural network to compute a post-iteration gradient vector and a current iteration weight vector using the selected batch of observation vectors, wherein the neural network includes a layer type for each layer of a plurality of neural network layers;
(C) compute a search direction vector using a Hessian approximation matrix and the post-iteration gradient vector;
(D) initialize a step size value with a predefined step size value;
(E) compute an objective function value that indicates an error measure of the executed neural network given the current iteration weight vector, the step size value, and the computed search direction vector;
(F) when the computed objective function value is greater than an upper bound value, update the step size value using a predefined backtracking factor value, wherein the upper bound value is computed as a sliding average of a predefined upper bound updating interval value number of previous upper bound values;
(G) repeat (E) and (F) until the computed objective function value is not greater than the upper bound value;
(H) compute an updated weight vector as a function of the current iteration weight vector, the updated step size value, and the computed search direction vector;
(I) repeat (A) to (H) until a convergence parameter value indicates training of the neural network is complete, wherein the current iteration weight vector for a next iteration is the computed updated weight vector; and
output the computed updated weight vector to describe a trained neural network model.

US Pat. No. 10,769,527

ACCELERATING ARTIFICIAL NEURAL NETWORK COMPUTATIONS BY SKIPPING INPUT VALUES

Mipsology SAS, (FR)

1. A system for accelerating artificial neural network (ANN) computations, the system comprising:a controller;
a selector communicatively coupled to the controller; and
an arithmetic unit communicatively coupled to the controller and the selector; and wherein:
the controller is configured to:
select an input value, based on a criterion, from a subset of input values of a neuron, wherein the criterion is based on a comparison of the input value to a further value, the further value being different from the input value and being dynamically provided to the controller, the further value being related to one of the following: the neuron, a layer of the ANN, the ANN, weights of the ANN, and an operation carried by the arithmetic unit;
cause, based on the further value, the selector to provide dynamically the selected input value to the arithmetic unit; and
provide, to the arithmetic unit, an offset of an index of the selected input value in the subset of input values, wherein the offset is based on the further value, the further value being indeterminable based on the offset; and
the arithmetic unit is configured to:
acquire, based on the offset of the index of the selected input value, a weight from a set of weights, the weight corresponding to the selected input value; and
perform a mathematical operation on the selected input value and the weight to obtain a result, wherein the result is to be used to compute an output of the neuron.

US Pat. No. 10,769,526

MACHINE LEARNING ACCELERATOR ARCHITECTURE

Intel Corporation, Santa...

1. An apparatus to facilitate acceleration of machine learning operations, comprising accelerator circuitry, including:a first set of processing elements to perform first computations including matrix multiplication operations;
a second set of processing elements to perform second computations including sum of elements of weights and offset multiply operations; and
a third set of processing elements to perform third computations including sum of elements of inputs and offset multiply operations, wherein the second and third computations are performed in parallel with the first computations.

US Pat. No. 10,769,525

DECISION MAKING FOR AUTONOMOUS VEHICLE MOTION CONTROL

Apple Inc., Cupertino, C...

1. A system, comprising:a behavior planner implemented using one or more computing devices; and
a motion selector of a vehicle, wherein the vehicle comprises one or more motion control subsystems;
wherein the behavior planner is configured to:
generate, using a combination of (a) a Monte Carlo Tree Search (MCTS) algorithm and (b) heuristics obtained from one or more machine learning models for the MCTS algorithm, a plurality of conditional action sequences corresponding to the vehicle, including a first conditional action sequence and a second conditional action sequence, wherein the first conditional action sequence corresponds to a first set of anticipated states of the vehicle, and wherein the second conditional action sequence corresponds to a second set of anticipated states of the vehicle;
provide, at a first transmission rate, at least some conditional action sequences of the plurality of conditional action sequences to the motion selector; and
wherein the motion selector is configured to:
generate, based at least in part on (a) one or more conditional action sequences provided by the behavior planner and (b) sensor data obtained at a second transmission rate, one or more motion-control directives, wherein the second rate exceeds the first rate; and
transmit the one or more motion-control directives to the one or more motion control subsystems.

US Pat. No. 10,769,524

NON-BINARY GENDER FILTER

A9.COM, INC., Palo Alto,...

1. A computing system, comprising:at least one computing device processor;
a memory device including instructions that, when executed by the at least one computing device processor, cause the computing system to:
train a neural network using training data comprising images of a plurality of apparel items with respective gender designations to generate a trained neural network, the trained neural network operable to assign a gender score to an apparel item, the gender score corresponding to a position on a gender scale;
assign, using the neural network, respective gender scores to a collection of apparel items offered for consumption in an electronic marketplace;
receive an apparel search query;
receive a gender input value, the gender input value selected from a non-binary range of values and corresponding to one or more acceptable gender scores;
execute the apparel search query and the acceptable gender scores against the collection of apparel items; and
determine, from the collection of apparel items, a set of apparel items responsive to the apparel search query and having gender scores included in the one or more acceptable gender scores.

US Pat. No. 10,769,523

USING ANALYTICS TO DETERMINE DINING VENUE BASED ON GROUP PREFERENCES

International Business Ma...

1. A method for choosing a dining venue for a group of people comprising:receiving a plurality of individual flavor profiles wherein each individual flavor profile contains information pertaining to flavor preferences of a respective individual, and each individual flavor profile includes respective numerical values associated with at least five different flavor types of savory, salty, sweet, bitter and sour, by executing first instructions in a computer system, wherein at least one of the individual flavor profiles is created by receiving an input for one of the individuals indicative of a flavor type and determining the flavor type using a deep-learning neural network;
receiving a plurality of venue flavor profiles wherein each venue flavor profile contains information pertaining to available items including multiple menu entries at a respective dining venue, and each venue flavor profile includes respective numerical values associated with the at least five different flavor types, by executing second instructions in the computer system;
receiving a request to choose a dining venue for a group consisting of a plurality of the individuals, by executing third instructions in the computer system;
creating a group flavor profile based on a subset of the individual flavor profiles corresponding to the plurality of individuals, by executing fourth instructions in the computer system, wherein the group flavor profile includes respective numerical values associated with the at least five different flavor types which are a function of respective numerical values from the subset of the individual flavor profiles; and
selecting a dining venue based on the group flavor profiles and the venue flavor profiles, by executing fifth instructions in the computer system, wherein said selecting includes performing a least-squares analysis to quantitatively determine a deviation of the numerical values for a given one of the venue flavor profiles compared to respective numerical values for the group flavor profile.

US Pat. No. 10,769,522

METHOD AND SYSTEM FOR DETERMINING CLASSIFICATION OF TEXT

Wipro Limited, Bangalore...

1. A method for determining classification of text, comprising:receiving, by a text classification system; a text from a plurality of texts;
training the text classification system using a plurality of similar pair of texts and a plurality of dissimilar pair of texts from the plurality of texts to obtain first trained model parameters of a first Long Short Term Memory (LSTM) program and second trained model parameters of a second LSTM program;
generating, by the text classification system, a first vector representation of the text using the first trained model parameters of the first LSTM unit and a second vector representation of the text using the second trained model parameters of the second LSTM unit;
combining, by the text classification system, the first vector representation and the second vector representation using a combiner operator to obtain a combined vector representation, wherein the combiner operator is selected from a plurality of combiner operators based on the training using an accuracy value of a classifier of the text classification system, wherein the accuracy value of the classifier is determined by comparing a classification performed by the classifier with a predefined classification stored in a data source associated with the text classification system; and
providing, by the text classification system, the combined vector representation to the classifier for determining a classification of the text.

US Pat. No. 10,769,521

PROCESSING LOOPS IN COMPUTATIONAL GRAPHS

Google LLC, Mountain Vie...

1. A method comprising:obtaining data representing a computational graph, the computational graph comprising a plurality of nodes and directed edges, wherein each node represents a respective operation, and wherein each directed edge connects a respective first node to a respective second node that represents an operation that receives, as input, an output of an operation represented by the respective first node;
obtaining data identifying an allocation of the computational graph across a plurality of devices, wherein the allocation assigns each node in the computational graph to a respective device of the plurality of devices;
identifying a set of nodes in the computational graph that:
(i) represents a control flow statement,
(ii) includes one or more first nodes assigned to a first device that represent one or more first operations of the control flow statement that are to be conditionally executed, and
(iii) includes one or more second nodes assigned to a second device that represent one or more second operations that determine how many times the one or more first operations are to be recursively or iteratively executed;
generating a control flow state structure of nodes and directed edges, wherein generating the control flow state structure comprises:
generating nodes representing the one or more second operations that determine how many times the one or more first operations are to be recursively or iteratively executed, and that are assigned to the second device, and
adding the nodes into the control flow state structure;
inserting the control flow state structure between the one or more first nodes and the one or more second nodes in the computational graph; and
modifying the allocation to assign the one or more first nodes and the control flow state structure to the first device while still assigning the one or more second nodes that represent the one or more second operations to the second device.

US Pat. No. 10,769,520

SEMICONDUCTOR DEVICE AND SYSTEM USING THE SAME

Semiconductor Energy Labo...

1. A semiconductor device comprising:an artificial neural network comprising a product-sum operation circuit,
wherein the product-sum operation circuit comprises a first memory cell, a second memory cell, and an offset circuit,
wherein the first memory cell is configured to store a first analog data,
wherein the second memory cell is configured to store a reference analog data,
wherein the first memory cell and the second memory cell are configured to supply a first current and a second current, respectively, when a reference potential is applied as a selection signal,
wherein the offset circuit is configured to supply a third current corresponding to a differential current between the first current and the second current to the first memory cell,
wherein the first memory cell and the second memory cell are configured to supply a fourth current and a fifth current, respectively, when a potential corresponding to a second analog data is applied as the selection signal, and
wherein the product-sum operation circuit is configured to obtain a current that depends on the sum of products of the first analog data and the second analog data by subtracting the third current from a differential current between the fourth current and the fifth current.

US Pat. No. 10,769,519

CONVERTING DIGITAL NUMERIC DATA TO SPIKE EVENT DATA

International Business Ma...

15. A method comprising:at a data-to-spike converter unit supporting different spike coding schemes:
converting external input data into one or more spike event packets encoded in a spike coding scheme of the different spike coding schemes by processing the external input data in accordance with an equation corresponding to the spike coding scheme; and
outputting the one or more spike event packets to an output bus configured to transmit the one or more spike event packets to a plurality of neurosynaptic core circuits for processing;
wherein a first spike event packet, encoded in a first spike coding scheme of the different spike coding schemes, is converted from first external input data by processing the first external input data in accordance with a first equation corresponding to the first spike coding scheme; and
wherein a second spike event packet, encoded in a second spike coding scheme of the different spike coding schemes, is converted from second external input data received by processing the second external input data in accordance with a second equation corresponding to the second spike coding scheme that is different from the first equation.

US Pat. No. 10,769,518

METHOD OF CONTROLLING FOR UNDESIRED FACTORS IN MACHINE LEARNING MODELS

State Farm Mutual Automob...

1. A computer-implemented method of training and using a machine learning model that controls for consideration of one or more undesired factors which might otherwise be considered by the machine learning model when analyzing new data, the method comprising, via one or more processors:training the machine learning model using a training data set that contains information including the one or more undesired factors;
identifying the one or more undesired factors and one or more relevant interaction terms between the one or more undesired factors; and
causing the trained machine learning model to not consider the identified one or more undesired factors when analyzing the new data to control for undesired prejudice or discrimination in machine learning models,
wherein identifying the one or more undesired factors and the one or more relevant interaction terms between the one or more undesired factors includes training a second machine learning model using a second training data set that contains only the one or more undesired factors and one or more relevant interaction terms between the one or more undesired factors.

US Pat. No. 10,769,517

NEURAL NETWORK ANALYSIS

FUJITSU LIMITED, Kawasak...

1. A method of neural network analysis, the method comprising:receiving a first electronic message from a previous neural network layer and storing the first electronic message in a storage device;
decoding the first electronic message to output a first data structure, the first electronic message referencing a first dictionary entry that correlates the first electronic message to the first data structure in a first dictionary, the first data structure including more bits than the first electronic message, the first data structure part of a previous sample data set representative of potential results of previous data structure analysis of the previous network layer;
providing the first data structure to a processing element to perform a data structure analysis in a neural network on the first data structure, the data structure analysis yielding a second data structure including more bits than the first electronic message, the second data structure part of a sample data set, the sample data set representative of potential results of the data structure analysis, the second data structure also part of the previous sample data set;
matching the second data structure to a second dictionary entry that correlates the second data structure to a second electronic message, the second electronic message including fewer bits than the second data structure;
transmitting the second electronic message instead of the second data structure to a next neural network layer;
testing performance of a second dictionary that includes the second dictionary entry by testing the neural network using the second dictionary to obtain a neural network performance;
determining that the neural network performance exceeds a predetermined threshold; and
based on the neural network performance exceeding the predetermined threshold, adjusting the size of the second dictionary such that the first dictionary used to communicate with the previous neural network layer is different in size than the second dictionary used to communicate with the next neural network layer, the adjustment to the size of the second dictionary occurring despite the second data structure being in both the previous sample data set and the sample data set.

US Pat. No. 10,769,516

INFORMATION PROCESSING APPARATUS, PROGRAM AND INFORMATION PROCESSING METHOD

INTERNATIONAL BUSINESS MA...

1. An information processing apparatus, comprising:a processor; and
a computer readable storage medium storing instructions which, when executed by the processor, cause the processor to perform operations comprising:
performing a first simulation that involves a plurality of agents under a first simulation condition;
sorting the plurality of agents into a plurality of predefined states, wherein the plurality of predefined states comprises a plurality of different states;
counting a number of the plurality of agents that is sorted into each state of the plurality of predefined states at a midpoint of the first simulation, wherein the number of the plurality of agents that is sorted into each state of the plurality of states is represented by a smaller amount of data than states of the plurality of agents; and
generating characteristic data, wherein the characteristic data comprises the first simulation condition at the midpoint and a plurality of matrices, wherein each matrix of the plurality of matrices corresponds to one state of the plurality of predefined states, wherein elements of the each matrix comprise the number of the plurality of agents that is sorted into the one state of the plurality of predefined states; and
predicting and outputting a result at an end point of the first simulation at the midpoint of the first simulation based on the characteristic data and the number of the plurality of agents that is sorted into the one state at the midpoint of the first simulation.

US Pat. No. 10,769,515

COMPOSITE LAMINATE ASSEMBLY USED TO FORM PLURAL INDIVIDUAL CARDS AND METHOD OF MANUFACTURING THE SAME

ILLINOIS TOOL WORKS INC.,...

1. A laminated core stock sheet for use in a composite laminate assembly configured for being separated into plural individual cards, the laminated core stock sheet comprising:a core substrate layer; and
an intermediate filmic layer coupled to the core substrate layer, the intermediate filmic layer including a conductive material that provides at least one of a security feature, a decorative feature, or other functional feature of the individual cards, wherein the core substrate layer and the intermediate filmic layer are configured to be coupled with another laminated core stock sheet that may or may not include the intermediate filmic layer to form the composite laminate assembly configured for being separated into the individual cards,
wherein the conductive material has a small thickness within the intermediate filmic layer such that the intermediate filmic layer prevents conduction of electrostatic discharge (ESD) through the intermediate filmic layer and outside of the individual cards,
wherein the conductive material forms a layer that extends across the intermediate filmic layer, the layer of the conductive material extending continuously such that the layer of the conductive material is essentially devoid of visibly spaced-apart bodies of the conductive material.

US Pat. No. 10,769,514

PERSONAL SOUND METER AND BROADCASTING/REPORTING SYSTEM

COVIDIEN LP, Mansfield, ...

1. A sound monitoring system comprising:an identification card holder wearable on a body of a user, the identification card holder including a microphone for receiving sound and a visual sound indicator for displaying a noise level of the sound received through the microphone; and
a central processing and monitoring system in wireless communication with the identification card holder for processing sound data received from the identification card holder and transmitting the processed sound data back to the identification card holder for display of the noise level represented by the processed sound data.

US Pat. No. 10,769,513

DEVICE AND METHOD FOR MANAGING THE CURRENT CONSUMPTION OF AN INTEGRATED MODULE

STMICROELECTRONICS (ROUSS...

1. A method for managing current consumption of a logic circuit coupled between a first supply terminal and a second supply terminal, the method comprising:receiving an input signal at an input terminal of the logic circuit;
producing an output signal at an output terminal of the logic circuit;
at a first time, causing the output signal to transition from a first state to a second state while generating an additional current between the first supply terminal and the second supply terminal; and
at a second time, causing the output signal to transition from the first state to the second state without generating the additional current.

US Pat. No. 10,769,512

DEVICE AND METHOD TO FACILITATE ENROLLMENT OF A BIOMETRIC TEMPLATE

IDEX BIOMETRICS ASA, Osl...

1. A device to facilitate enrollment of a verification template of biometric data in a biometric sensor-enabled smart card, the device comprising:a non-data transmitting power source comprising a receptacle configured to be removably coupled to the smart card and a power element supported on the receptacle that provides power to a smart card to which the receptacle is coupled;
at least one status indicator located on the receptacle and configured to indicate a state of an enrollment process; and
a detector circuit configured to detect a signal in the smart card and to activate the status indicator according to the detected signal.

US Pat. No. 10,769,511

LOW ENERGY TRANSMITTER

Wiliot, Ltd, Caesarea (I...

1. A low energy transmitter, comprising:an oscillator circuit; and
a reference voltage generator adapted to supply a voltage to the oscillator circuit, wherein the oscillator circuit includes two pairs of semiconductor devices, wherein each pair of a semiconductor device includes a device with a gate node coupled to an antenna positive node interface (Vop) via a capacitor and a drain connected to an antenna negative node interface (Von) and a device with a gate node coupled to an antenna positive node interface (Von) via a capacitor and a drain connected to an antenna negative node interface (Vop), wherein the oscillator circuit is connected to a common mode feedback circuit;
wherein an antenna is coupled between the antenna positive node interface and the antenna negative node interface, the antenna being an oscillating inlay antenna, and wherein an input and output of the oscillating inlay antenna is maintained at a low voltage.

US Pat. No. 10,769,510

UNIVERSAL TRANSPONDER

NEOLOGY, INC., San Diego...

1. A system comprising:a wearable mobile device comprising a metal casing and a radio frequency identification (RFID) tag having a transponder, the transponder comprising a plurality of antennas, wherein the metal casing comprises a body casing and wherein the body casing is at least one of the plurality of antennas, the transponder configured to:
communicate via the plurality of antennas and corresponding plurality of frequencies, and
store information related to an account of a user of the wearable mobile device,
wherein the RFID tag is configured to:
communicate at least a first portion of the information related to the account and stored on the RFID tag to a first device using a first RFID reader included the first device operating at a first frequency of the plurality of frequencies, and
communicate at least a second portion of the information related to the account and stored on the RFID tag to a second device using a second RFID reader included the second device operating at a second frequency of the plurality of frequencies,
wherein the first device is configured to launch an application in response to receiving the at least the first portion of the information read from the RFID tag, the application comprising a plurality of instructions stored on a memory of the first device, the plurality of instructions causing a processor of the first device to access the account based on the first portion of the information related to the account and update an account balance of the account through interactions with a virtual wallet, and
wherein the second device is configured to apply a charge to the account based, in part, on the at least a second portion of the information related to the account.

US Pat. No. 10,769,509

DETERMINING AN ACTION ASSOCIATED WITH AN APPARATUS USING A COMBINED BAR CODE IMAGE

KONINKLIJKE PHILIPS N.V.,...

1. A method of determining an action associated with an apparatus, the apparatus having a disposable component, the method comprising:obtaining, by means of a camera, data representing a visual code and a visual symbol;
comparing, by means of a processor, the visual code represented by said data with a reference code, the reference code indicating an identity of a disposable component of the apparatus, and comparing, by means of said processor, the visual symbol represented by said data with a reference symbol, to obtain comparison results; and
determining the action in response to the comparison results,
wherein the action to be taken in response to the comparison of the visual code with the reference code and the visual symbol with the reference symbol results in one of four unique actions as determined by the comparison results.

US Pat. No. 10,769,508

RADIO FREQUENCY YARN MODULE

TAIWAN TEXTILE RESEARCH I...

1. A radio frequency yarn module, comprising:a first flexible substrate that is strip shaped and has a thickness ranging from 40 ?m to 60 ?m;
a radio frequency assembly disposed on the first flexible substrate and comprising:
a first conductive layer disposed on the first flexible substrate and having a thickness ranging from 3 ?m to 10 ?m, wherein an extending path of the first conductive layer is the same as an extending path of a first portion of the first flexible substrate;
a second conductive layer disposed on the first flexible substrate and having a thickness ranging from 3 ?m to 10 ?m, wherein an extending path of the second conductive layer is the same as an extending path of a second portion of the first flexible substrate; and
a radio frequency chip disposed on the first and the second conductive layers and having a first pin and a second pin, wherein the first pin is electrically connected to the first conductive layer, and the second pin is electrically connected to the second conductive layer; and
a first packaging adhesive covering the radio frequency assembly, so as to make the radio frequency assembly be disposed between the first flexible substrate and the first packaging adhesive.

US Pat. No. 10,769,507

IMAGE FORMING APPARATUS AND IMAGE FORMING METHOD FOR PROHIBITING OR ALLOWING RECOVERY PRINTING BASED ON NUMBER OF TIMES OF PRINTING IN CASE OF DISCREPANCY BETWEEN SIZES OF SHEET

Ricoh Company, Ltd., Tok...

1. An image forming apparatus comprising:a conveyor configured to convey a sheet;
a sensor configured to detect the sheet conveyed by the conveyor; and
control circuitry configured to:
cause the conveyor to eject the sheet without stopping conveyance of the sheet and prohibit recovery printing when a size of the sheet determined based on detection of the sheet by the sensor is different from a setting size in a first operation mode; and
cause the conveyor to stop conveyance of the sheet and allow recovery printing when the size of the sheet is different from the setting size in a second operation mode in which a number of times of printing is larger than a number of times of printing in the first operation mode.

US Pat. No. 10,769,506

IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD QUANTIZING GRADATION DATA TO HAVE A SMALLER NUMBER OF GRADATIONS

CANON KABUSHIKI KAISHA, ...

1. An image processing apparatus, comprising:one or more processors; and
one or more non-transitory computer-readable media storing computer-executable instructions that cause the one or more processors to function as:
a gradation data obtainment unit configured to obtain first gradation data corresponding to a gradation value of a first color and second gradation data corresponding to a gradation value of a second color for a processing-target pixel;
a threshold obtainment unit configured to obtain a first threshold for the processing-target pixel from a first threshold matrix including a plurality of arrayed thresholds for pixels and obtain a second threshold for the processing-target pixel from a second threshold matrix in which the thresholds for the pixels are arrayed at such pixel positions that order of the pixel positions is inverse to order of pixel positions in the first threshold matrix in a case where the pixel positions are arranged in ascending order of the thresholds; and
a quantization processing unit configured to quantize the first gradation data, and the second gradation data to generate first quantization data and second quantization data that have a smaller number of gradations than the number of gradations of the first gradation data and the second gradation data based on the first threshold, the second threshold, the first gradation data, and the second gradation data:
the image processing apparatus performing image processing to print a color material of the first color based on the first quantization data and to print a color material of the second color based on the second quantization data,
wherein
the quantization processing unit,
in a case where a sum of the first gradation data and the second gradation data is equal to or smaller than the maximum value of the thresholds arrayed in the first threshold matrix,
generates the first quantization data based on a result of comparing the first gradation data with the first threshold and generates the second quantization data based on a result of comparing the second gradation data with the second threshold, and
in a case where the sum is greater than the maximum value,
generates first overlapping gradation data and second overlapping gradation data by dividing a value that is obtained by subtracting the maximum value from the sum into two,
generates the first quantization data based on a result of comparing the first overlapping gradation data with the second threshold or a result of comparing a difference between the first gradation data and the first overlapping gradation data with the first threshold, and
generates the second quantization data based on a result of comparing the second overlapping gradation data with the first threshold or a result of comparing a difference between the second gradation data and the second overlapping gradation data with the second threshold.

US Pat. No. 10,769,505

OPTICAL SENSOR DEVICE PERFORMING COLOR CORRECTION USING LIGHT ADJUSTMENT

Ricoh Company, Ltd., Tok...

1. An optical sensor device comprising:a first light source having a plurality of peak wavelengths in a wavelength range of from 400 nm to 780 nm;
a second light source to emit ultraviolet light;
a sensor to receive light emitted by the first light source or the second light source and reflected by an object; and
control circuitry to:
adjust a light amount of the first light source based on an output of the sensor in a state where the first light source is turned on and the second light source is turned off;
adjust a light amount of the second light source based on an output of the sensor in a state where the second light source is turned on and the first light source is turned off; and
acquire a correction value of data output by the sensor, based on an output of the sensor in a state where each of the first light source and the second light source is turned on with the light amount adjusted by the control circuitry.

US Pat. No. 10,769,504

EXPANDING APPLIANCE FOR IMAGE IDENTIFYING MODULES AND EXPANDING METHOD FOR EXPANDING APPLIANCE

CHICONY POWER TECHNOLOGY ...

1. An expanding appliance for image identifying modules, for expanding identification function of an image input device, comprising:a connect port, connected with the image input device which is configured to capture an image data;
an image register;
an image capturing module, connected with the connect port and the image register, configured to sample the image data captured by the image input device for producing samples and to quantize the samples as at least one computation data, and configured to store the computation data to the image register;
an image transmitting module, connected with the image register and at least one function module, wherein the function module has an independent computing unit and is configured to execute a unique image identification procedure;
an intelligent control module, connected with the image capturing module and the image transmitting module, configured to generate at least one demanding command corresponding to the at least one function module connected to the image transmitting module, and configured to control the image capturing module to obtain the image data satisfying at least an image requirement of the at least one function module according to the at least one demanding command; and
a result displaying module, connected with the intelligent control module;
wherein the image transmitting module is configured to receive an identified result generated by the function module via executing the image identification procedure according to the computation data, and the image transmitting module is configured to convey the identified result to the intelligent control module for the intelligent control module to trigger the result displaying module for displaying the identified result;
wherein the image capturing module is configured to sample the image data according to the at least one demanding command and to perform an image pre-process on the image data for quantizing the samples as the at least one computation data required by the at least one function module, wherein the at least one computation data is able to be directly identified by the image identification procedure of the at least one function module.

US Pat. No. 10,769,502

SEMANTIC IMAGE RETRIEVAL

Dropbox, Inc., San Franc...

1. A computer-implemented method for semantic image search, the method comprising:obtaining a word vector representing an input keyword unit, the word vector generated according to an embedding function that projects keyword units in a vector space as N-dimensional vectors and in which distances between vectors in the vector space correspond to semantic similarities between the keyword units;
obtaining a plurality of word vectors representing a plurality of image content class keyword units; wherein each image content class keyword unit, of the plurality of image content class keyword units, describes a respective image content class of a plurality of image content classes; wherein each word vector, of the plurality of words vectors, is generated according to the embedding function;
generating an image match vector comprising a plurality of vector similarity measurements, each vector similarity measurement of the plurality of vector similarity measurements based on a computed vector similarity between (a) the word vector representing the input keyword unit and (b) a respective word vector of the plurality of word vectors;
computing a vector similarity measurement between the image match vector and a particular image vector, the particular image vector being for a particular digital image, the particular image vector for the particular digital image comprising a plurality of probability values for the plurality of image content classes, each probability value of the plurality of probability values reflecting a probability that the particular digital image belongs to a respective image content class of the plurality of image content classes; and
identifying the particular digital image as relevant to the input keyword unit based on the vector similarity measurement between the image match vector and the particular image vector.

US Pat. No. 10,769,501

ANALYSIS OF PERTURBED SUBJECTS USING SEMANTIC EMBEDDINGS

Google LLC, Mountain Vie...

1. A method comprising:applying a respective perturbation to each of a plurality of subjects in a controlled environment;
producing a respective visual representation for each of the perturbed subjects using at least one imaging modality;
obtaining, by a computing device for each of the respective visual representations, a corresponding semantic embedding associated with the respective visual representation,
wherein the semantic embedding associated with the respective visual representation is generated using a machine-learned, deep metric network model,
wherein obtaining the corresponding semantic embedding associated with the respective visual representations comprises incorporating data captured during one or more respective supplementary measurements of a given measurement type,
wherein the machine-learned, deep metric network model was trained using training data that includes data of the given measurement type, and
wherein incorporating data captured during one or more respective supplementary measurements comprises:
generating a first preliminary semantic embedding for the respective visual representation using the machine-learned, deep metric network model;
generating a second preliminary semantic embedding for the data captured during one or more respective supplementary measurements using the machine-learned, deep metric network model; and
generating a composite semantic embedding:
(i) using an additional machine-learned model, wherein the composite semantic embedding comprises a hybrid of the first preliminary semantic embedding and the second preliminary semantic embedding; or
(ii) by applying a mathematical operation to corresponding dimensions of the first preliminary semantic embedding and the second preliminary semantic embedding; and
classifying, by the computing device based on the corresponding semantic embedding, each of the visual representations into one or more groups.

US Pat. No. 10,769,500

LOCALIZATION-AWARE ACTIVE LEARNING FOR OBJECT DETECTION

Mitsubishi Electric Resea...

1. An active learning system, comprising:an input interface to receive a set of images of a scene from a sensor;
a memory to store active learning data that includes an object detector trained for detecting objects in images;
a processor in communication with the input interface and the memory, is configured to:
detect a semantic class and a location of at least one object in an image selected from the set of images using the object detector to produce a detection metric as a combination of an uncertainty of the object detector about the semantic class of the object in the image and an uncertainty of the object detector about the location of the object in the image, wherein the uncertainty for object localization is based on two quantitative measurements of the localization uncertainty, a first quantitative measurement is a Localization Tightness (LT) metric that estimates an amount of how tight detected bounding boxes enclose true objects, and a second quantitative measurement that is a Localization Stability (LS) metric based on whether the detected bounding boxes are sensitive to changes in the input image; and
an output interface in communication with the processor, to display the image for human labeling when the detection metric is above a threshold.

US Pat. No. 10,769,499

METHOD AND APPARATUS FOR TRAINING FACE RECOGNITION MODEL

FUJITSU LIMITED, Kawasak...

1. A method for training a face recognition model, comprising:removing black eyepits and sunglasses in first actual scenario data composed of an image containing a face which is acquired from an actual scenario, to obtain second actual scenario data;
counting a proportion wearing glasses in the second actual scenario data;
dividing original training data composed of an image containing the face into wearing-glasses first training data and not-wearing-glasses second training data, where a proportion of wearing glasses in the original training data is lower than a proportion of wearing glasses in the second actual scenario data;
generating wearing-glasses third training data based on glasses data and the second training data;
generating fourth training data in which a proportion wearing glasses is equal to the proportion of wearing glasses in the second actual scenario data, based on the third training data and the original training data; and
training the face recognition model based on the fourth training data.

US Pat. No. 10,769,498

IMAGE DATA PRE-PROCESSING

KONINKLIJKE PHILIPS N.V.,...

1. A computer-implemented method of reducing processing time of an application for visualizing image data, wherein the application is one of a plurality of applications selectable by a user, wherein each of the plurality of applications comprises a pre-processing algorithm of a plurality of pre-processing algorithms for pre-processing the image data before image processing the selected application has started, wherein the method comprises predicting which one of the plurality of pre-processing algorithms is to be performed in response to a selection of one of the applications by the user by:extracting a feature vector from the image data, metadata, and/or additional data associated with the image data,
supplying the feature vector as input to a machine learned model,
receiving an algorithm identifier as output from the machine learned model, the algorithm identifier identifying the pre-processing algorithm,
using the algorithm identifier to select the pre-processing algorithm, thereby obtaining a selected pre-processing algorithm, and
pre-processing the image data using the selected pre-processing algorithm.

US Pat. No. 10,769,497

LEARNING DEVICE, IMAGING DEVICE, AND LEARNING METHOD

Olympus Corporation, Tok...

1. An imaging device, comprising:an image input section that generates image data;
a setting circuit that sets a request including a target third party evaluator profile specified based on a user input;
a transmission circuit that transmits the request to an external machine learning device;
a reception circuit that receives at least one inference model that was transmitted directly or indirectly from the external machine leaning device, wherein the at least one inference model was generated by the external machine learning device using image training data which was retrieved from a database using the third party evaluator profile included in the request;
an inference engine that provides an inference result using the received at least one inference model and the image data generated by the image input section; and
a display that displays the inference result that was provided by the inference engine.

US Pat. No. 10,769,496

LOGO DETECTION

Adobe Inc., San Jose, CA...

1. A method comprising: receiving a source image at one or more computing devices;detecting, in the source image and using a first logo detection model implemented by the one or more computing devices, a candidate region for determining a logo in the source image; extracting, from the candidate region and by a neural network implemented using the one or more computing devices, a feature vector of the candidate region; determining, for each reference feature vector from a set of reference feature vectors stored in a database, a respective matching score between the reference feature vector and the feature vector of the candidate region, wherein each reference feature vector in the set of reference feature vectors is extracted from a respective image of a respective target logo in a set of target logos; selecting a first reference feature vector associated with a highest matching score among the set of reference feature vectors, the first reference feature vector extracted from a first image of a first target logo in the set of target logos; determining that the candidate region includes an image of the first target logo based on determining that the highest matching score is greater than a threshold value; receiving an image of a new target logo to be added to the set of target logos; extracting, using the neural network implemented using the one or more computing devices, a new reference feature vector from the image of the new target logo; and storing the new reference feature vector in the database.

US Pat. No. 10,769,494

ENHANCED TRAINING INFORMATION GENERATION

Pony AI Inc., Grand Caym...

1. A system comprising:one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining training information, the training information characterizing behaviors of moving objects, the training information determined based on observations of the behaviors of the moving objects;
obtaining behavior information, the behavior information characterizing a behavior of a given object; and
generating enhanced training information at least in part by inserting the behavior information into the training information, wherein inserting the behavior information into the training information comprises inserting the behavior information based at least in part on a frequency of occurrence of the behavior of the given object.

US Pat. No. 10,769,493

METHOD AND APPARATUS FOR NEURAL NETWORK TRAINING AND CONSTRUCTION AND METHOD AND APPARATUS FOR OBJECT DETECTION

BEIJING KUANGSHI TECHNOLO...

1. A training method of a neural network for object detection, comprising:inputting a training image including a training object to the neural network to obtain a predicted bounding box of the training object;
acquiring a first loss function according to a ratio of an intersection area to a union area of the predicted bounding box and a true bounding box, wherein the true bounding box is a bounding box of the training object marked in advance in the training image; and
adjusting parameters of the neural network by utilizing at least the first loss function to train the neural network;
wherein the first loss function is a negative value of a natural logarithm of the ratio of the intersection area to the union area of the predicted bounding box and the true bounding box;
wherein the method further comprising:
selecting a second loss function reflecting a difference between a predicted confidence and a true confidence of each pixel point in the training image, the predicted confidence being the confidence, predicted by employing the neural network, that a certain pixel point in the training image belongs to the training object, and the true confidence representing the confidence, marked in advance in the training image, that the certain pixel point belongs to the training object,
wherein said adjusting the parameters of the neural network by utilizing at least the first loss function to train the neural network comprises:
adjusting the parameters of the neural network by utilizing the first loss function and the second loss function to maximize a ratio of an intersection area to an union area of the predicted bounding box and the true bounding box and to minimize the second loss function so as to obtain the trained neural network.

US Pat. No. 10,769,492

UNSUPERVISED VISUAL ATTRIBUTE TRANSFER THROUGH RECONFIGURABLE IMAGE TRANSLATION

SK TELECOM CO., LTD., Se...

1. A system for learning an attribute transfer that conveys at least one attribute value of a reference image to a source image, the system comprising:an encoder configured to encode an original source image to generate a plurality of attribute values that specify the original source image, and to encode an original reference image to generate a plurality of attribute values that specify the original reference image;
a converter configured to replace at least one attribute value of a target attribute of the attribute values of the original source image with at least one corresponding attribute value of the original reference image, to obtain a plurality of attribute values that specify a target image of interest; and
a generator configured to generate a target image based on the attribute values of the target image of interest,
wherein during training the system,
the encoder encodes the generated target image to generate a plurality of attribute values that specify the generated target image,
the converter replaces at least one attribute value corresponding to the target attribute among the attribute values of the generated target image with at least one attribute value corresponding to the target attribute of the original source image, to generate a plurality of attribute values for a source image reconstruction,
the generator generates a reconstructed source image based on the attribute values of the source image reconstruction,
the converter replaces at least one attribute value corresponding to the target attribute among the attribute values of the original reference image with at least one attribute value corresponding to the target attribute of the target image, to generate a plurality of attribute values for a reference image reconstruction, and
the generator generates a reconstructed reference image based on the attribute values for the reference image reconstruction,
wherein, during training the system, parameters of the encoder and the generator are updated by using,
a reconstruction loss that represents a difference between the reconstructed source image and the original source image,
a reconstruction loss that represents a difference between the reconstructed reference image and the original reference image, and
a generative adversarial loss of the generated target image.

US Pat. No. 10,769,491

MACHINE LEARNING SYSTEM FOR GENERATING CLASSIFICATION DATA AND PART LOCALIZATION DATA FOR OBJECTS DEPICTED IN IMAGES

SRI International, Menlo...

1. A system for identifying discriminative, fine-grained features of an object in an image, comprising:an input device configured to receive the image of the object;
a computation engine comprising processing circuitry for executing a machine learning system; and
an output device configured to output part localization data for the object and classification data for the object,
wherein the machine learning system comprises a model comprising a first set of filters, a second set of filters, and a third set of filters,
wherein the machine learning system is further configured to apply the first set of filters to the received image to generate an intermediate representation of the received image suitable as an input to both the second set of filters and third set of filters,
wherein the machine learning system is further configured to apply the second set of filters to the intermediate representation of the received image to generate the part localization data for the object, wherein the part localization data for the object comprises data identifying one or more sub-parts of the object and one or more regions of the received image in which the one or more sub-parts of the object are located, and
wherein the machine learning system is further configured to apply the third set of filters to the intermediate representation of the received image to generate the classification data for the object,
wherein the data identifying one or more sub-parts of the object and one or more regions of the received image in which the one or more sub-parts of the object are located along with the classification data for the object results in a more discriminative, fine-grained identification of one or more features of the object in the image.

US Pat. No. 10,769,490

IMAGE PROCESSING METHODS AND DEVICES

Alibaba Group Holding Lim...

1. An image processing method, comprising:acquiring features of multiple images of a first target object and a standard feature of the first target object;
determining trusted images of the first target object from the multiple images according to similarities between the features of the multiple images and the standard feature, wherein similarities between features of the trusted images and the standard feature meet a first preset similarity requirement;
determining similarities between the trusted images of the first target object and trusted images of a second target object to obtain multiple pieces of similarity data; and
determining, according to the multiple pieces of similarity data, whether the first target object is similar to the second target object.

US Pat. No. 10,769,489

READING TEST CARDS USING A MOBILE DEVICE

Bio-Rad Laboratories (Isr...

1. A computing device for interpreting test cards, the device comprising:a template matching subsystem configured to receive an input image from a mobile device and determine that a portion of the input image corresponds to a test card, the test card having a class of a plurality of test card classes, wherein the template matching subsystem is further configured to identify the class of the test card in the input image by comparing potential features in the input image to templates corresponding to each of the plurality of test card classes;
an image processing subsystem, operably connected to the template matching subsystem, configured to apply an image transformation to rectify the portion of the input image that corresponds to the test card;
a test identification subsystem configured to identify a test type for which the test card includes a test result, where the test type corresponds to a plurality of possible result indicators for tests of the test type, wherein the test type is identified based on the identified test card class and the rectified portion of the input image; and
a result identification subsystem configured to determine the test result included on the test card based on the rectified portion of the input image and the possible result indicators corresponding to the identified test type.

US Pat. No. 10,769,488

ITEM VARIATION MANAGEMENT

Amazon Technologies, Inc....

1. A computing system, comprising:an item images data store;
one or more processors; and
a memory coupled to the one or more processors and storing program instructions that when executed by the one or more processors cause the one or more processors to at least:
receive an image of an item as the item is received into a materials handling facility;
process the image of the item to generate first item image information that includes an arrangement of a first plurality of features;
determine a correlation score between the first item image information and a second item image information, wherein the second item image information is accessible from an item images data store;
determine that the correlation score exceeds a threshold;
determine distinctive features of the first item image information that are different than features of the second item image information;
associate at least one of the distinctive features or the first item image information with the second item image information to form a cluster corresponding to an item type of the item; and
store the association, first item image information and the distinctive features in the item images data store.

US Pat. No. 10,769,487

METHOD AND DEVICE FOR EXTRACTING INFORMATION FROM PIE CHART

ABC FINTECH CO, LTD., Be...

1. A method for extracting information from a pie chart for display performed by an electronic device having a processor and memory for storing instruction to be executed by the processor, the method comprising:detecting, by the electronic device, each element in a pie chart to be processed and position information thereof, the elements comprising text elements and legend elements;
performing, by the electronic device, text recognition on the detected text elements and legend elements to obtain text information corresponding to the text elements and legend texts included in the legend elements respectively; and
obtaining, by the electronic device, sector information and legend information according to each detected element and position information thereof and the legend texts, and enabling, by the electronic device, the sector information to correspond to the legend information one by one, wherein the sector information comprises a sector color and a proportion of the sector in the pie chart, and the legend information comprises a legend color and a corresponding legend text thereof,
wherein each element in the pie chart to be processed is detected by the electronic device by adopting a target detection method of a Faster R-CNN model and the Faster R-CNN model is pre-stored in the electronic device and derived via the following training method:
step 1. randomly initializing learning parameters in the Faster R-CNN model;
step 2. inputting a batch of training samples to the Faster R-CNN model to obtain a predicted classification probability pi and a predicted bounding box coordinate vector ti of the ith element box in the training samples under the current model parameters;
step 3. performing loss calculation on the output result in step 2 by adopting the following formula, and solving the average loss L of all the element boxes in the batch of training samples,
in which L({pi},{ti}) is the loss of the ith element box, Ncls is the value of mini-batch, Nreg is the number of anchor positions, ? is weight,is the logarithmic loss of a target and a non-target, andis a regression loss function;step 4. solving the minimum L, and updating all the learning parameters in the Faster R-CNN model; and
step 5. repeatedly executing steps 2 to 4 until reaching a set number of iterations.

US Pat. No. 10,769,486

IMAGE PROCESSING APPARATUS, BINARY IMAGE PRODUCTION METHOD, AND IMAGE PROCESSING PROGRAM

Seiko Epson Corporation, ...

1. An image processing apparatus comprising:an acquisition unit configured to acquire a multi-valued image; and
a binarization unit configured to generate a binary image obtained by binarizing the multi-valued image,
wherein the binarization unit detects a plurality of closed regions that forms the multi-valued image, with the closed regions each having a plurality of pixels, and
the binarization unit performs binarization of the closed regions to generate the binary image, with the binarization of the closed regions including binarizing a plurality of pixels of at least one of the closed regions by a threshold which is based on both luminance inside the at least one of the closed regions and luminance inside different one of the closed regions that is different from the at least one of the closed regions and in which the pixels of the at least one of the closed regions do not belong.

US Pat. No. 10,769,485

FRAMEBUFFER-LESS SYSTEM AND METHOD OF CONVOLUTIONAL NEURAL NETWORK

Himax Technologies Limite...

1. A framebuffer-less system of convolutional neural network (CNN), comprising:a region of interest (ROI) unit that extracts features, according to which a region of interest in an input image frame is generated;
a convolutional neural network (CNN) unit that processes the region of interest of the input image frame to detect an object;
a tracking unit that compares features extracted at different times, according to which the CNN unit selectively processes the input image frame; and
a temporary storage for storing the features extracted by the ROI unit;
wherein the ROI unit adopts scan-line based technique and block-based scheme to find the region of interest in the input image frame, which is divided into a plurality of blocks of image;
wherein the ROI unit comprises:
a feature extractor that extracts the features from the input image frame; and
a classifier that makes decision whether to perform CNN for each block of image, thus generating a decision map, according to which the region of interest is determined.

US Pat. No. 10,769,484

CHARACTER DETECTION METHOD AND APPARATUS

Baidu Online Network Tech...

1. A character detection method, comprising:using an image including an annotated word as an input to a machine learning model, comprising: using a word level annotated image in a word level annotated dataset as the image including the annotated word, the word level annotated image comprising an annotation box surrounding the word for annotating the position of the word;
selecting, based on a predicted result for characters being inside an annotation region of the annotated word and predicted by the machine learning model and annotation information of the annotated word, characters for training the machine learning model from the characters being inside the annotation region of the annotated word and predicted by the machine learning model, wherein the predicted result comprises: bounding boxes corresponding to the characters being inside the annotation region of the annotated word and confidence levels corresponding to the characters being inside the annotation region of the annotated word, and the annotation information comprises a bounding box corresponding to the annotated word;
training the machine learning model based on features of the selected characters; and
detecting characters in an image by using the trained machine learning model,
wherein the selecting characters for training the machine learning model from the characters being inside the annotation region of the annotated word and predicted by the machine learning model comprises:
calculating k neighbors for the bounding boxes corresponding to the characters being inside the annotation region of the annotated word and predicted by the machine learning model, to obtain a connection relationship between the characters, wherein each of the characters is connected to k other characters;
calculating a weight wij between two connected characters by using the following formula:

wherein the two connected characters constitute a character connection pair, d(i, j) represents a distance between the two connected characters, d represents an average distance between characters in all character connection pairs, and ti and tj represent respective confidence levels corresponding to the two connected characters;
finding a maximum spanning tree, wherein the maximum spanning tree comprises sequentially connected characters predicted by the machine learning model, and the sum of the weights between the characters is the greatest;
executing the following selection operation:
pruning each character connection pair in a current tree to obtain multiple subtrees, wherein when the selection operation is executed for the first time, the current tree is the maximum spanning tree;
calculating a score s of a subtree or the current tree by using the following formula:

wherein Bchars represents a bounding box corresponding to a character in the subtree or the current tree, Banno represents the bounding box corresponding to the annotated word, area(Bchars) represents the area of the bounding boxes corresponding to the characters in the subtree or the current tree, area(Banno) represents the area of the bounding box corresponding to the annotated word, ?1 and ?2 respectively represent the greatest feature value and the second greatest feature value of a covariance matrix of the center coordinates of Bchars, w is a preset weight when the selection operation is executed for the first time, and w is the weight between the two characters in the character connection pair corresponding to the subtree when the selection operation is not executed for the first time;
determining whether the greatest of the scores of the subtrees is greater than the score of the current tree; and
if yes, using the subtree with the greatest score as the current tree, and executing the selection operation again; or
if not, using the characters in the current tree as the characters for training the machine learning model.

US Pat. No. 10,769,483

RETINAL ENCODER FOR MACHINE VISION

CORNELL UNIVERSITY, Itha...

1. A method including:applying, by an encoding module, a spatiotemporal transformation to image data to generate retinal output cell response values;
generating, by the encoding module, encoded data based on the retinal output cell response values;
applying, by a machine vision module, a machine vision algorithm to the encoded data;
monitoring, by a controller, performance of the machine vision algorithm, wherein monitoring the performance of the machine vision algorithm comprises:
calculating an error rate of the machine vision algorithm; and
comparing the error rate to a threshold level; and
adjusting, by the controller, the machine vision algorithm based on the monitored performance.

US Pat. No. 10,769,482

SYSTEMS AND METHODS FOR USING IMAGE ANALYSIS TO AUTOMATICALLY DETERMINE VEHICLE INFORMATION

STATE FARM MUTUAL AUTOMOB...

1. A computer-implemented method of analyzing image data, the method comprising:generating, by a computer processor from a digital image depicting an alphanumeric string, at least two filtered digital images;
generating, by the computer processor using an image analysis technique, at least two results respectively associated with the at least two filtered digital images and respectively indicating a set of machine-encoded strings; and
analyzing the at least two results to identify a set of common elements indicating a machine-encoded alphanumeric string representative of the alphanumeric string depicted in the digital image.

US Pat. No. 10,769,481

SYSTEM AND METHOD FOR EXTRACTION OF DESIGN ELEMENTS OF FASHION PRODUCTS

MYNTRA DESIGN PRIVATE LIM...

1. A system for extraction of design elements of a fashion product, the system comprising:a memory having computer-readable instructions stored therein; and
a processor configured to execute the computer-readable instructions to:
access a catalogue image of a fashion product;
segment the catalogue image of the fashion product to determine an article of interest of the fashion product;
generate an outer contour of the article of interest using a contour tracing technique;
analyze coordinates of the outer contour generated based upon convexity defects of the outer contour to identify one or more design points;
extract one or more design elements of the fashion product using the one or more design points identified;
determine a plurality of convex hull points of the outer contour generated;
select a subset of convex hull points from the plurality of convex hull points determined, based upon a contour length between adjacent convex hull points;
determine one or more convexity defect points on the contour by using the subset of convex hull points selected; and
extract the one or more design elements of the fashion product using the one or more convexity defect points determined and the subset of convex hull points selected.

US Pat. No. 10,769,480

OBJECT DETECTION METHOD AND SYSTEM

SAMSUNG ELECTRONICS CO., ...

1. An object detection method, comprising:executing, by at least one processor, operations comprising:
acquiring a current frame of a sequence of event frames representing an image sequence and obtained from an event camera;
extracting a feature map of the current frame;
pooling the feature map of the current frame with information of a pooled feature map of a previous frame to thereby obtain a pooled feature map of the current frame; and
detecting an object from the pooled feature map of the current frame,.
wherein,
the at least one processor is part of a neural network system that determines object movement speed based on the event frames;
the object detection method further comprising:
providing the event frames to a long and short term memory (LSTM) network or a sequence non-maximum suppression (Seq-NMS) network; and
using object detection results of the LSTM or Seq-NMS network as a final object detection result if the object movement speed is above a threshold, otherwise using the object detection of the at least one processor of the neural network system as the final object detection result.

US Pat. No. 10,769,479

RECOGNITION SYSTEM, GENERIC-FEATURE EXTRACTION UNIT, AND RECOGNITION SYSTEM CONFIGURATION METHOD

DENSO IT LABORATORY, INC....

1. A recognition system comprising:a sensing unit configured to perform sensing to output a sensor value;
a task-specific unit including a first recognition processing part that performs a first recognition task based on the sensor value and a second recognition processing part that performs a second recognition task based on the sensor value; and
a generic-feature extraction unit including a generic neural network disposed between the sensing unit and the task-specific unit, the generic neural network being configured to receive the sensor value as an input to extract a generic feature to be input in common into the first recognition processing part and the second recognition processing part,
wherein the generic-feature extraction unit is connected to both the first recognition processing part and the second recognition processing part, and
the generic feature is commonly used in both the first recognition processing part and the second recognition processing part.

US Pat. No. 10,769,478

CONVOLUTIONAL NEUTRAL NETWORK IDENTIFICATION EFFICIENCY INCREASING METHOD AND RELATED CONVOLUTIONAL NEUTRAL NETWORK IDENTIFICATION EFFICIENCY INCREASING DEVICE

VIVOTEK INC., New Taipei...

1. A convolutional neutral network identification efficiency increasing method, comprising:analyzing an input image to acquire foreground information;
computing a histogram of the foreground information;
dividing the histogram into at least one first group and at least one second group via its pixel value ranges, wherein a pixel value range of the first group is smaller than a pixel value range of the second group;
comparing a pixel amount of the second group with a predetermined parameter; and
generating a foreground mask according to a comparison result; and
transforming the input image into an output image via the foreground mask, wherein the output image is used to be an input of convolutional neutral network identification for increasing object identification efficiency;
wherein generating the foreground mask comprises: setting a foreground threshold when the pixel amount of the second group is greater than the predetermined parameter, defining pixels of the foreground information having pixel values greater than the foreground threshold as a first set of pixels, defining pixels of the foreground information having pixel values smaller than the foreground threshold as a second set of pixels, and setting pixels of the foreground mask which corresponds to the first set of pixels having pixel values as a first numeral, and setting pixels of the foreground mask which corresponds to the second set of pixels having pixel values as a second numeral;
wherein generating the foreground mask further comprises: determining whether the first group conforms to a specific condition when the pixel amount of the second group is smaller than the predetermined parameter, and setting pixels values of all pixels inside the foreground mask as a first numeral when the first group conforms to the specific condition.

US Pat. No. 10,769,477

METHOD, APPARATUS, DEVICE AND STORAGE MEDIUM FOR EXTRACTING A CARDIOVISCERAL VESSEL FROM A CTA IMAGE

SHENZHEN INSTITUTES OF AD...

1. A method for extracting a cardiovisceral vessel from a CTA image, comprising the steps of:performing a corrosion operation and an expansion operation on an image data successively via a preset structural element to obtain a structure template, wherein the image data is a coronary angiography image after a downsampling processing, and the structure template is a structure excluding a pulmonary region;
performing a transformation in layer-by-layer on slice images of the structure template to acquire a first ascending aorta structure in the structure template, and acquiring an aorta center coordinate and an aorta radius in the last layer of slice image of the structure template; and
establishing a binarized spherical structure according to the aorta center coordinate and the aorta radius, and synthesizing a second ascending aorta structure by combining the first ascending aorta structure with the structure template and the binarized spherical structure.

US Pat. No. 10,769,476

LICENSE PLATE DETECTION METHOD AND DEVICE

Hangzhou Hikvision Digita...

1. A method for detecting a license plate, comprising:obtaining, according to pixel values of pixels in an image to be detected, a candidate license plate area M1 in the image to be detected;
calculating an aspect ratio of the candidate license plate area M1 and determining whether the aspect ratio is greater than a first predefined threshold;
if the aspect ratio is greater than the first predefined threshold, determining a new candidate license plate area M2 from the candidate license plate area M1 according to a predefined machine learning-based regression algorithm, wherein the candidate license plate area M2 is an area whose aspect ratio is no greater than the first predefined threshold;
determining, according to a first predefined classification model, whether the candidate license plate area M2 is a license plate area, wherein, the first predefined classification model is a classification model obtained by learning sample license plate areas through a machine learning algorithm, and wherein, in constructing of the first classification model, a lame amount of sample license plate areas previously found are learned through the machine learning algorithm so as to obtain a classification model, by means of which an area of the candidate license plate area is classified into a license plate area and non-license plate area;
if the candidate license plate area M2 is a license plate area, determining the candidate license plate area M2 as a license plate area, and generating a detection result based on the candidate license plate area M2,
wherein, determining a new candidate license plate area M2 from the candidate license plate area M1 according to a predefined machine learning-based regression algorithm comprises:
determining a position of a suspected character string in the candidate license plate area M1;
determining, through the predefined machine learning-based regression algorithm, a new boundary of the candidate license plate area according to the determined position; and
obtaining the candidate license plate area M2 according to the new boundary.

US Pat. No. 10,769,475

METHOD OF IDENTIFYING OBJECTS BASED ON REGION OF INTEREST AND ELECTRONIC DEVICE SUPPORTING THE SAME

Samsung Electronics Co., ...

1. An electronic device comprising:a display; and
a processor functionally connected with the display,
wherein the processor is configured to:
output content including one or more objects through the display;
receive user input for specifying at least one point in an entire region of the content;
determine a portion of the entire region with respect to the at least one point as a search region;
obtain a saliency map associated with the content based on the search region;
obtain an index map associated with the content by dividing the entire region of the content into similar regions according to a preset criterion; and
determine a region of interest of a user based on the saliency map and the index map.

US Pat. No. 10,769,474

KEYPOINT DETECTION CIRCUIT FOR PROCESSING IMAGE PYRAMID IN RECURSIVE MANNER

Apple Inc., Cupertino, C...

1. A keypoint detection circuit, comprising:a first keypoint generation circuit configured to, for a first octave of an image pyramid:
receive a first parameter indicating a first blur level;
receive image data from a memory;
generate a first set of keypoints from a first response map generated by blurring the image data to the first blur level in the first octave of an image pyramid;
a second keypoint generation circuit configured to, for the first octave of the image pyramid:
receive a second parameter indicating a second blur level;
receive the image data from the memory;
generate a second set of keypoints from a second response map generated by blurring the image data to the second blur level in the first octave; and
a filter and decimation circuit configured to, for the first octave of the image pyramid, generate a second octave of the image pyramid by generating a downscaled version of the image data from the image data, and transmit the downscaled version of the image data to the memory;
wherein the first keypoint generation circuit is further configured to, for at least a second octave of the image pyramid:
receive a third parameter indicating a third blur level;
receive the downscaled version of the image data from the memory;
generate a third set of keypoints from a third response map generated by blurring the downscaled version of the image data to a third blur level in the second octave of the image pyramid; and
wherein the second keypoint generation circuit is further configured to, for at least the second octave of the image pyramid:
receive a fourth parameter indicating a fourth blur level;
receive the downscaled image data from the memory; and
generate a fourth set of keypoints from a fourth response map generated by blurring the downscaled version of the image data to a fourth blur level in the second octave.

US Pat. No. 10,769,473

IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM

Canon Kabushiki Kaisha, ...

1. An image processing apparatus comprising:an acquisition unit configured to acquire a plurality of recognition positions each recognized by a recognizer as a position of a target object on an input image;
a calculation unit configured to obtain at least one representative position by performing clustering for the plurality of recognition positions;
an editing unit configured to edit the representative position in accordance with an editing instruction from a user for the representative position; and
a saving unit configured to save the input image and the representative position as learning data to be used for learning of the recognizer.

US Pat. No. 10,769,472

METHOD AND SYSTEM COUNTING PLURALITY OF OBJECTS PLACED IN A REGION

Wipro Limited, Bangalore...

1. A method for counting plurality of objects placed in a region, the method comprising:partitioning, by an object counting system, an image of the region, comprising the plurality of objects, into one or more segments based on depth of each of the plurality of objects, wherein the image of the region is received from an image capturing unit associated with the object counting system;
identifying, by the object counting system, one or more object regions in each of the one or more segments;
determining, by the object counting system, shape of each of the plurality of objects in each of the one or more object regions of each of the one or more segments, wherein determining the shape of each of the plurality of objects comprises:
obtaining spatial frequencies of each of the one or more object regions comprising the plurality of objects;
generating a magnitude spectrum histogram of the spatial frequencies of each of the one or more object regions; and
associating a peak value of the magnitude spectrum histogram with a predetermined scaling factor for obtaining pixel coordinates corresponding to the plurality of objects, thereby determining the shape of the plurality of objects;
validating, by the object counting system, the shape of each of the plurality of objects based on comparison of the shape of each of the plurality of objects with predetermined shapes; and
aggregating, by the object counting system, count of the plurality of objects of each shape in each of the one or more segments for determining count of the plurality of objects in the region.

US Pat. No. 10,769,471

SYSTEM AND METHOD FOR HOLDING AN IMAGE DISPLAY APPARATUS

1. A system for holding an image display apparatus for displaying an image captured by means of an image capturing apparatus, comprising:a movable holding apparatus for an alterable hold of the image display apparatus;
a controllable drive device for moving the holding apparatus, comprising a control signal input for receiving a control signal;
a controller comprising a signal input for receiving a signal that represents an orientation or a change in the orientation of the viewing direction of the image capturing apparatus in space or that facilitates a determination of the orientation or the change in the orientation of the viewing direction of the image capturing apparatus, and comprising a control signal output, couplable to the control signal input of the controllable drive device, for providing a control signal for controlling the controllable drive device,
wherein the controller is embodied and provided to control the controllable drive device in such a way that, within a predetermined range of possible orientations of the viewing direction of the image capturing apparatus in space, the orientation of the image display apparatus in space is a predetermined function of the orientation of the viewing direction of the image capturing apparatus in space.

US Pat. No. 10,769,470

METHOD AND SYSTEM FOR OPTIMIZING AN IMAGE CAPTURING BOUNDARY IN A PROPOSED IMAGE

Samsung Electronics Co., ...

1. A method for optimizing a boundary of a first image, the method comprising:obtaining the first image;
identifying at least one characteristic of the first image;
determining an optimized image boundary of the first image to be captured, the optimized image boundary including at least one object included in the first image, based on the at least one characteristic;
determining a zoom level, based on the optimized image boundary; and
obtaining a second image based on the zoom level.

US Pat. No. 10,769,469

ERROR PROMPTING METHOD, DEVICE, AND ELECTRONIC APPARATUS

BEIJING XIAOMI MOBILE SOF...

1. A method of prompting a failure or error applicable to a terminal apparatus comprising a fingerprint recognizer having a sensor array, the method comprising:obtaining electrical signals containing fingerprint information through the sensor array upon a fingerprint recognition being triggered;
generating a fingerprint image according to the electrical signals containing the fingerprint information;
determining a number of sensors with abnormally-changing electrical signals in the sensor array; by:
determining, for each sensor in the sensor array, an electrical signal changing value by taking a difference between a current electrical signal value and an initial electrical signal value of the sensor; and
determining the number of sensors with electrical signal changing values exceeding a changing value threshold in the sensor array as the number of the sensors with abnormally-changing electrical signals;
outputting prompt information upon the determined number of sensors with abnormally-changing electrical signals in the sensor array exceeding a number threshold;
obtaining a corrected fingerprint image by removing abnormal pixels from the fingerprint image when it is determined that the number of sensors with abnormally-changing electrical signals in the sensor array does not exceed the number threshold, wherein the abnormal pixels are pixels corresponding to the number of sensors with abnormally-changing electrical signals in the sensor array; and
performing the fingerprint recognition based on the corrected fingerprint image.

US Pat. No. 10,769,468

MOBILE SURVEILLANCE APPARATUS, PROGRAM, AND CONTROL METHOD

NEC CORPORATION, Minato-...

1. A mobile surveillance apparatus comprising:a touch panel display configured to display a surveillance image;
at least one processor configured to:
perform a first process that is to set an event detection region with respect to the surveillance image or a second process that is to change a display range of the surveillance image, in accordance with a slide operation performed with respect to the surveillance image displayed on the touch panel display; and
switch between the first process and the second process when a touch operation is performed at a plurality of places on the touch panel display in a predetermined order.

US Pat. No. 10,769,467

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING SYSTEM, AND COMPUTER PROGRAM PRODUCT

KABUSHIKI KAISHA TOSHIBA,...

1. An information processing apparatus comprising:a processor configured to:
control to display, on a display, two or more templates included in a plurality of templates that are related to a shape of a marker inside a subject;
control to receive an input operation of a user which is a user's selection operation of selecting one or more templates out of the two or more templates displayed on the display;
control to specify at least one template out of the plurality of templates based on the input operation; and
control to track the marker in an image including the marker by using the at least one template.

US Pat. No. 10,769,466

PRECISION AWARE DRONE-BASED OBJECT MAPPING BASED ON SPATIAL PATTERN RECOGNITION

International Business Ma...

1. A method of controlling an unmanned aerial vehicle, the method executed by at least one hardware processor coupled to the unmanned aerial vehicle and a storage device, the method comprising:receiving an image of a region captured by the unmanned aerial vehicle flying at a current altitude;
executing a computer vision algorithm with the image as an input to the computer vision algorithm, the computer vision algorithm computing an overall confidence score associated with detecting one or more candidate objects in the image;
responsive to determining that the overall confidence score is below a predefined minimum threshold, controlling the unmanned aerial vehicle to reduce the current altitude and recapture the image of the region at the reduced altitude;
responsive to determining that the overall confidence score is not below the predefined minimum threshold, storing on a storage device the image, the one or more objects detected in the image, the confidence score, location coordinates of the unmanned aerial vehicle, and the current altitude;
repeating the receiving, the executing, the triggering and the storing while the region is not fully mapped with images and the unmanned aerial vehicle has energy capacity above a level needed to return to a designated base location.

US Pat. No. 10,769,465

METHOD FOR BIOMETRIC RECOGNITION AND TERMINAL DEVICE

GUANGDONG OPPO MOBILE TEL...

1. A terminal device, comprising:a distance sensor configured to detect a target distance between the terminal device and a human face;
an iris camera coupled to the distance sensor and configured to capture an iris image when the target distance falls within an iris recognition distance range;
a front camera coupled to the distance sensor and configured to capture a human face image when the target distance falls within a human face recognition distance range; and
an application processor (AP) coupled to the distance sensor, the iris camera, and the front camera, the AP configured to:
detect, through the distance sensor, the target distance between the terminal device and the human face;
detect, through the front camera, an included angle between the terminal device and the human face, when the target distance falls within at least one of the iris recognition distance range and the human face recognition distance range;
capture an iris image through the iris camera and implement a secure authentication by performing an iris recognition based on the iris image, when the target distance falls within the iris recognition distance range and the included angle falls within an iris recognition included angle range; and
capture a human face image through the front camera and implement the secure authentication by performing a face recognition based on the human face image when the target distance falls within the human face recognition distance range and the included angle falls within a face recognition included angle range.

US Pat. No. 10,769,464

FACIAL RECOGNITION METHOD AND RELATED PRODUCT

GUANGDONG OPPO MOBILE TEL...

1. A facial recognition method, comprising:acquiring a face image by a mobile terminal;
extracting face feature information from the face image and matching the face feature information with a predetermined face feature template by a central processing unit of the mobile terminal;
performing liveness detection according to the face image by a graphics processing unit of the mobile terminal, when the central processing unit extracts the face feature information from the face image and matches the face feature information with the predetermined face feature template;
wherein a length of time required for extracting and matching the face feature information is less than a length of time required for the liveness detection, and a length of time required for facial recognition is equal to the length of time required for the liveness detection.

US Pat. No. 10,769,463

TRAINING OF VEHICLES TO IMPROVE AUTONOMOUS CAPABILITIES

1. A system comprising:at least one imaging device configured to acquire images of at least one eye of a human subject operating a vehicle;
one or more processing units configured to process the acquired images to extract eye data from said images, the eye data corresponding to one or both of:
(a) movement of the at least one eye,
(b) position of the at least one eye;
the vehicle having a brake pedal and an accelerator pedal controlled by a foot of the human;
a sensing system configured to acquire foot data relating to one or more of:
(i) distance of the foot from the brake pedal,
(ii) distance of the foot from the accelerator pedal,
(iii) amount of displacement of the brake pedal when depressed by the foot,
(iv) amount of displacement of the accelerator pedal when depressed by the foot;
the one or more processing units configured to process the eye data and foot data to extract eye events and foot events;
the one or more processing units configured to make a determination that an event outside the vehicle has occurred if:
(i) both an eye event as well as a foot event has occurred, and
(ii) neither the eye event that has occurred nor the foot event that has occurred correlates with an associated map;
wherein the data related to the event that has occurred outside the vehicle is used to train vehicles to become partially or fully autonomous or to improve their autonomous functioning.

US Pat. No. 10,769,462

INFORMATION PROCESSING APPARATUS AND NON-TRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM

FUJI XEROX CO., LTD., To...

1. An information processing apparatus comprising:a processor configured to
specify a position of each member of an assembly;
acquire biometric information from members of which the number is smaller than the number of all members;
specify, from the biometric information acquired by the processor, an activeness degree of the member from which the biometric information is acquired by the processor, and specify, from the activeness degree and the position specified by the processor, an activeness degree of a member other than the member from which the biometric information is acquired by the processor among the members; and
determine a state of the assembly from the activeness degree specified by the processor.

US Pat. No. 10,769,461

DISTRACTED DRIVER DETECTION

COM-IoT Technologies, Du...

1. A method comprising:capturing a video frame from a near-infrared video camera, the video frame comprising a motor vehicle depicted within the video frame;
capturing position information of the motor vehicle with a light detection and ranging (LIDAR) device;
providing the video frame and position information to a trained classifier at a remote server via a network, wherein the provided video frame is compressed for transmission via the network and is selected to minimize data usage of the network based on how much of a motor vehicle is contained therein and the distance of the motor vehicle from the near-infrared video camera;
determining, from the trained classifier, a type of the motor vehicle depicted within the video frame;
determining, from the trained classifier, a location and a velocity of the motor vehicle depicted within the video frame, the velocity having a magnitude and a direction of travel;
determining from the trained classifier a presence of a predetermined action by the motor vehicle; and
based on the determined location, the velocity with the magnitude and direction of travel, and the predetermined action, sending an alert via the network indicating the presence of the predetermined action and at least one identifier associated with the motor vehicle.

US Pat. No. 10,769,460

DRIVER CONDITION DETECTION SYSTEM

Toyota Jidosha Kabushiki ...

1. A driver condition detection system comprising:a driver monitor camera capturing a face of a driver of a vehicle and generating a facial image of the driver, and
a driver condition detection part configured to detect a condition of the driver based on the facial image, wherein
when a part of face parts of the driver is hidden in the facial image, the driver condition detection part is configured to detect a condition of the driver based on each of face parts of the driver not hidden in the facial image, the face parts of the driver being a mouth, nose, right eye, and left eye of the driver,
the condition of the driver is a facial direction of the driver,
when a part of the face parts of the driver is hidden in the facial image, the driver condition detection part is configured to detect the facial direction of the driver based on the face parts of the driver not hidden in the facial image and the facial image before a part of the face parts of the driver is hidden, and
the driver condition detection part is configured to judge that the facial direction of the driver has not changed from before a part of the face parts of the driver was hidden when an amount of change of a condition of the face parts of the driver not hidden in the facial image is a threshold value or less, and not detect the facial direction of the driver when the amount of change is larger than the threshold value.

US Pat. No. 10,769,459

METHOD AND SYSTEM FOR MONITORING DRIVING BEHAVIORS

SRI International, Menlo...

4. A method of monitoring driving conditions via a monitoring module comprising program instructions stored in memory and causing one or more processors to execute the steps of:receiving video data comprising video frames from one or more sensors, wherein the video frames represent an interior or exterior of a vehicle;
detecting and recognizing one or more features from the video data, wherein each feature is associated with at least one driving condition;
extracting the one or more features from the video data;
developing intermediate features by running regressions on the one or more extracted features and correlating at least two of the extracted features; and
developing a semantic meaning for the at least one driving condition by utilizing at least the intermediate features.

US Pat. No. 10,769,458

DETERMINATION PROCEDURE OF THE LUMINANCE OF TRAFFIC SIGNS AND DEVICE FOR ITS EMBODIMENT

1. A luminance detection system connectable to a vehicle and operable while the vehicle is moving along a roadway, the luminance detection system comprising:a light source configured to illuminate a road marking positioned along the roadway, the light source being separate and distinct from a pair of headlights of the vehicle;
a first camera configured to obtain first image data, the first image data including the road marking, the first image data having first color characteristics;
a second camera configured to obtain second image data, the second image data including the road marking also included in the first image data, the second image data having second color characteristics, wherein the first color characteristics are separate and distinct from the second color characteristics;
a processor configured to:
calculate a distance between the vehicle and the road marking based on the first image data and the second image data;
apply one or more luminance transforms to convert one or more pixel values of the first image data and the second image data to obtain corresponding luminance levels representative of at least a portion of the road marking;
after applying the one or more luminance transforms, compare the first image data, and the second image data to minimize ambient light information; and
calculate a luminance value representative of a luminance of the road marking based on (i) the distance between the vehicle and the road marking (ii) the luminance levels representative of the road marking and (iii) the comparison of the first image data, after applying the luminance transform, and the second image data to minimize ambient light information.

US Pat. No. 10,769,457

SYSTEM AND METHOD FOR DETECTING AIRBORNE OBJECTS

Pony Al Inc., Grand Caym...

1. A system comprising:one or more sensors;
one or more processors; and
a memory storing instructions that, when executed by the one or more processors, cause the system to perform:
detecting an airborne object within a detection radius of a vehicle;
in response to detecting the airborne object, tracking the airborne object to obtain 3-D coordinate information of the airborne object at distinct times;
determining a probability that the airborne object will collide with the one or more sensors based on the 3-D coordinate information;
determining a driving action of a vehicle based on the determined probability, the determining the driving action comprising:
if the probability is less than a first threshold, determining the driving action to be maintaining a same navigation route;
if the probability is between the first threshold and a second threshold higher than the first threshold, determining the driving action to be swerving or changing lanes to move away from a predicted position of the airborne object;
if the probability is between the second threshold and a third threshold higher than the second threshold, determining the driving action to be stopping the vehicle; and
if the probability is between the third threshold and a fourth threshold higher than the third threshold, determining the driving action to be changing the navigation route; and
A performing the driving action.

US Pat. No. 10,769,456

SYSTEMS AND METHODS FOR NEAR-CRASH DETERMINATION

Nauto, Inc., Palo Alto, ...

1. A method comprising:capturing an external video with an external-facing camera of an on-board system mounted on a vehicle;
determining an obstacle parameter for an obstacle detected from the external video;
capturing an internal video with a driver-facing camera of the on-board system;
generating a risk score for a spatial position relative to the vehicle, the risk score being determined based on a parametric model, the obstacle parameter, and a driver parameter based on the internal video; and
detecting a near-collision event when the risk score exceeds a risk threshold.

US Pat. No. 10,769,455

SYSTEM AND METHOD OF COMPENSATING FOR POSITION OF VEHICLE USING DETERMINED ROAD-LINE OFFSETS

MANDO CORPORATION, Pyeon...

1. A system of compensating for a position of a vehicle, the system comprising:one or more camera modules disposed on the vehicle so as to have fields of view of the front area, the rear area, or the side area of the vehicle, respectively, and configured to capture image data and process the captured image data; and
a controller configured to perform control based at least in part on the processing of the image data,
wherein the controller is configured to:
detect a front road-line and a rear road-line of a driving lane of the vehicle based on the image data on the front and rear areas of the vehicle, which is processed by the one or more camera modules;
calculate an offset of the front road-line and an offset of the rear road-line;
compare the offset of the front road-line with the offset of the rear road-line; and
determine a final road-line offset of the vehicle according to a result of the comparison, and
wherein the controller is further configured to:
when a difference between the offset of the front road-line and the offset of the rear road-line is greater than a predetermined threshold value, set the offset of the rear road-line as the final road-line offset of the vehicle; and
when the difference between the offset of the front road-line and the offset of the rear road-line is not greater than the predetermined threshold value, set the offset of the front road-line as the final road-line offset of the vehicle.

US Pat. No. 10,769,454

CAMERA BLOCKAGE DETECTION FOR AUTONOMOUS DRIVING SYSTEMS

NVIDIA CORPORATION, Sant...

1. A method for detecting blockages in images, the method comprising:receiving, by a blockage detection module, a plurality of images captured by a camera installed on a vehicle;
identifying, by the blockage detection module, one or more candidate blocked regions in the plurality of images, wherein each of the candidate blocked regions contains image data caused by blockages in the camera's field-of-view;
assigning, by the blockage detection module, blockage scores to the one or more candidate blocked regions based on region-associations among the one or more candidate blocked regions in the plurality of images; and
in response to a determination that one of the blockage scores is above a predetermined blockage threshold, transmitting, by the blockage detection module, a blockage alarm signal to the vehicle.

US Pat. No. 10,769,453

ELECTRONIC DEVICE AND METHOD OF CONTROLLING OPERATION OF VEHICLE

Samsung Electronics Co., ...

1. An electronic device configured to control an operation of a vehicle, the electronic device comprising:a memory configured to store at least one program; and
at least one processor configured to provide a notification message by executing the at least one program,
wherein the at least one program includes instructions, which when executed by the processor, cause the electronic device to perform at least one operation comprising:
obtaining a video sequence comprising a plurality of frames from a camera installed on the vehicle;
detecting, from the plurality of frames, an object included in the plurality of frames via a first learning model;
obtaining position information regarding the detected object with respect to each of the plurality of frames via the first learning model;
determining whether an event related to driving of the vehicle has occurred by analyzing time-series changes in positions of the detected object in the plurality of frames via a second learning model;
generating a notification message about the event based on a result of the determining via the second learning model; and
outputting the generated notification message,
wherein an input to the second learning model includes an output of the first learning model, the output of the first learning model including the position information regarding the detected object with respect to each of the plurality of frames.

US Pat. No. 10,769,452

EVALUATING AND PRESENTING PICK-UP AND DROP-OFF LOCATIONS IN A SITUATIONAL-AWARENESS VIEW OF AN AUTONOMOUS VEHICLE

Lyft, Inc., San Francisc...

1. A method comprising, by one or more computing devices:identifying, based on map data, an area for pick-up or drop-off of a user by a vehicle;
determining, based on the map data and a location of the vehicle, that the vehicle is within a threshold distance of the area for pick-up or drop-off of the user;
in response to the determination that the vehicle is within the threshold distance of the area, determining, based on vehicle sensor data that represents an external environment of the vehicle, one or more potential pick-up or drop-off locations within the area;
calculating, based at least in part on the vehicle sensor data and historical data including past pick-up or drop-off events involving one or more past users for each potential pick-up or drop-off location, a viability score for each of the potential pick-up or drop-off locations; and
providing for display a visual representation of at least a portion of the area for pick-up or drop-off that indicates at least one of the one or more potential pick-up or drop-off locations.

US Pat. No. 10,769,451

SENSOR MAPPING TO A GLOBAL COORDINATE SYSTEM USING A MARKER GRID

7-Eleven, Inc., Irving, ...

1. An object tracking system, comprising:a first sensor configured to capture a first frame of a global plane for at least a portion of a marker grid in a space, wherein:
the global plane represents (x,y) coordinates for the at least a portion of the space;
the marker grid comprises a first marker and a second marker;
the first marker is a first object that identifies a first location on the marker grid;
the second marker is a second object that identifies a second location on the marker grid;
the first frame comprises a plurality of pixels; and
each pixel from the plurality of pixels is associated with a pixel location comprising a pixel row and a pixel column; and
a tracking system operably coupled to the first sensor, comprising:
one or more memories operable to store marker grid information that identifies:
a first offset between a first corner of the marker grid and the first marker; and
a second offset between the first corner of the marker grid and the second marker; and
one or more processors operably coupled to the one or more memories, configured to:
receive a first (x,y) coordinate identifying a first x-value and a first y-value in the global plane where a first corner of a marker grid is located in the space;
determine a second (x,y) coordinate identifying a second x-value and a second y-value in the global plane where the first marker is located based on the first offset from the first (x,y) coordinate for the first corner of the marker grid;
determine a third (x,y) coordinate identifying a third x-value and a third y-value in the global plane where the second marker is located based on the second offset from the first (x,y) coordinate for the first corner of the marker grid;
receive the first frame;
identify a first pixel within the first frame corresponding with the first marker;
identify a second pixel within the first frame corresponding with the second marker;
determine a first pixel location for the first pixel, wherein the first pixel location comprises a first pixel row and a first pixel column of the first frame;
determine a second pixel location for the second pixel, wherein the second pixel location comprises a second pixel row and a second pixel column of the first frame; and
generate a first homography based on the second (x,y) coordinate for the first marker, the third (x,y) coordinate for the second marker, the first pixel location, and the second pixel location, wherein the first homography maps between pixel locations in the first frame and (x,y) coordinates in the global plane.

US Pat. No. 10,769,450

TRACKING POSITIONS USING A SCALABLE POSITION TRACKING SYSTEM

7-Eleven, Inc., Irving, ...

1. A system comprising:an array of cameras positioned above a space, each camera of the array of cameras configured to capture a video of a portion of the space, the space containing a person;
a first camera client configured to:
receive a first plurality of frames of a first video from a first camera of the array of cameras, each frame of the first plurality of frames showing the person within the space;
for a first frame of the first plurality of frames:
determine a first bounding area around the person shown in the first frame; and
generate a first timestamp of when the first frame was received by the first camera client;
for a second frame of the first plurality of frames:
determine a second bounding area around the person shown in the second frame; and
generate a second timestamp of when the second frame was received by the first camera client; and
for a third frame of the first plurality of frames:
determine a third bounding area around the person shown in the third frame; and
generate a third timestamp of when the third frame was received by the first camera client;
a second camera client configured to:
receive a second plurality of frames of a second video from a second camera of the array of cameras, each frame of the second plurality of frames showing the person within the space;
for a fourth frame of the second plurality of frames:
determine a fourth bounding area around the person shown in the fourth frame; and
generate a fourth timestamp of when the fourth frame was received by the second camera client; and
for a fifth frame of the second plurality of frames:
determine a fifth bounding area around the person shown in the fifth frame; and
generate a fifth timestamp of when the fifth frame was received by the second camera client; and
a camera server separate from the first and second camera clients, the camera server configured to:
determine that the first timestamp falls within a first time window;
in response to determining that the first timestamp falls within the first time window, assign coordinates defining the first bounding area to the first time window;
determine that the second timestamp falls within the first time window;
in response to determining that the second timestamp falls within the first time window, assign coordinates defining the second bounding area to the first time window;
determine that the third timestamp falls within a second time window that follows the first time window;
in response to determining that the third timestamp falls within the second time window, assign coordinates defining the third bounding area to the second time window;
determine that the fourth timestamp falls within the first time window;
in response to determining that the fourth timestamp falls within the first time window, assign coordinates defining the fourth bounding area to the first time window;
determine that the fifth timestamp falls within the second time window;
in response to determining that the fifth timestamp falls within the second time window, assign coordinates defining the fifth bounding area to the second time window;
process the coordinates assigned to the first time window by:
calculating, based at least on the coordinates defining the first bounding area and the coordinates defining the second bounding area, a combined coordinate for the person during the first time window for the first video from the first camera; and
calculating, based at least on the coordinates defining the fourth bounding area, a combined coordinate for the person during the first time window for the second video from the second camera;
after processing the coordinates assigned to the first time window, process the coordinates assigned to the second time window by:
calculating, based at least on the coordinates defining the third bounding area, a combined coordinate for the person during the second time window for the first video from the first camera; and
calculating, based at least on the coordinates defining the fifth bounding area, a combined coordinate for the person during the second time window for the second video from the second camera.

US Pat. No. 10,769,449

DYNAMIC METHOD AND SYSTEM FOR MONITORING AN ENVIRONMENT

RECO3.26 S.R.L., Cavalli...

1. A dynamic monitoring method of an environment, comprising steps of:(a) providing a plurality of functional nodes comprising:
(a1) at least one context node configured for interfacing with the environment to be monitored;
(a2) one or more application nodes comprising one or more nodes selected from a processing application node configured for processing data of the environment to be monitored;
a notifying application node configured for notifying alarm situations of the environment to be monitored to further application nodes; and
an action application node configured for sorting alarms to a control room,
(b) detecting input data of the environment, representative of a significant event in the environment;
(c) analysing the input data of the environment;
(d) extracting representative data of the significant event as a function of the input data;
(e) comparing the representative data with a group of comparative data;
(f) calculating a deviation between the representative data and a most similar comparative data among the comparative data,
wherein the steps (c), (d), (e) and (f) are carried out by i) one of the at least one context nodes or ii) one or more of the application nodes;
(g) notifying by the notifying node an alarm as a function of the deviation; and
(h) implementing a monitoring network of the environment as a function of the plurality of functional nodes,
wherein the monitoring network is topologically variable as a function of the environment to be monitored, functions of the functional nodes and of the deviation, and
wherein the monitoring of the environment is performed as a function of the topology of the monitoring network implemented.

US Pat. No. 10,769,448

SURVEILLANCE SYSTEM AND SURVEILLANCE METHOD

Panasonic i-PRO Sensing S...

1. A surveillance system comprising:a server; and
a plurality of cameras provided in a surveillance area,
wherein the server and the cameras are communicably connected to each other,
wherein the server includes a memory that stores information regarding a processing capability of each of the cameras, information regarding an amount of free resources of each of the cameras, and a plurality of captured images obtained by capturing the surveillance area by each of the cameras,
wherein the server includes a processor and the memory stores a program that, when executed by the processor, causes the server to:
determine a first one of the cameras having at least a predetermined amount of free resources based on the information regarding the amount of free resources of each of the cameras,
transmit, to the first one of the cameras, an instruction to execute a learning process that learns at least one parameter used for detecting at least one object, wherein the first one of the cameras executes the learning process that learns the at least one parameter used for detecting the at least one object, based on the instruction transmitted from the server,
receive, from the first one of the cameras, the at least one parameter used for detecting the at least one object,
calculate, based on the information regarding the amount of free resources of each of the cameras, a feedback amount of the at least one parameter used for detecting the at least one object, and
transmit, to a second one of the cameras, data of a parameter corresponding to the feedback amount of the at least one parameter used for detecting the at least one object.

US Pat. No. 10,769,447

SYNCHRONOUS CONVERGENT PULSES REDUCE DIMENSIONS OF SERIAL SURFACES

1. A system comprised of at least one of a pulses selectively propagated through a set of serial 2 dimensional (2D) arrays implemented as an electrical network, the system comprising at least one of a sensors in a first array that emit the pulses due to at least one of visual and haptic stimulation, via links connecting to at least one of a nodes in the serial arrays, the pulses serially propagating by a temporal synchrony of at least one of the input pulses to at least one the nodes in the serial nodes, with a summation number of the pulses and a temporal summation duration configured as a parameter, adjustable to emit at least one output pulses, which pulses in turn, converge as inputs to at least one nodes in downstream arrays, thereby serially propagating pulses to at least one nodes in the last serial array;wherein, stimulation comprising at least one of a) a 2D feature pattern and b) a sequential moving event, empirically determined as a target from previous application of the variably similar stimuli, sustains the emission of pulses from sensors that selectively propagate in serially linked nodes, which sustained pulses thereby operationally connect, at least one the stimulated sensors of the first array and at least one said nodes in the last array;
wherein input pulses, which emit output pulses from at least one nodes configured by the adjustable parameter of the at least one nodes, emit an output pulse latency required for pulses to travel a linkage distance between at least one the nodes and at least one the downstream serial nodes, which pulse latencies summate to the maximal temporal duration of at least one nodes, which duration is adjustable as the parameter necessary to emit at least one the output pulses at a pulse frequency from at least one the nodes from temporally synchronous input pulses;
wherein the pulses emitted by stimulated sensors, by the selective propagation of said pulses reemitted through the serial nodes to at least one the nodes in the last array, operationally connect the target stimulated sensors in the first array with at least one nodes in the last array, in which at least one of a maximally stimulated 2D sensor locations are measured from a concurrent position of a prosthetic or robotic implement, whereby a minimized measurement, makes coincident the concurrent 2D sensor locations of the target stimulated pulses and the position of the prosthetic or robotic implement.

US Pat. No. 10,769,446

METHODS AND SYSTEMS OF COMBINING VIDEO CONTENT WITH ONE OR MORE AUGMENTATIONS

Second Spectrum, Inc., L...

1. A computer-implemented data processing method for displaying augmented content on a client device, the method comprising:receiving, from an external server by one or more processors, video data corresponding to an event, the video data comprising video content and a plurality of definitions of a plurality of bounding boxes;
presenting, by one or more processors on a graphical user interface, the video content;
detecting, by one or more processors, a user selection of a portion of the graphical user interface;
determining, by one or more processors, a red, green, blue, alpha (RGBA) value associated with the user selection of the portion of the graphical user interface;
determining, by one or more processors, a bounding box RGBA value that corresponds to the RGBA value associated with the user selection of a portion of the graphical user interface, wherein the bounding box RGBA value is associated with a particular bounding box from among the plurality of bounding boxes;
transmitting, by one or more processors, an indication of the particular bounding box to a renderer;
receiving, by one or more processors from the renderer, augmentation data associated with the bounding box associated with the portion of the graphical user interface selected by the user;
generating, by one or more processors, augmented video content based on the video data and the augmentation data associated with the bounding box associated with the portion of the graphical user interface selected by the user; and
presenting, by one or more processors on the graphical user interface, the augmented video content.

US Pat. No. 10,769,445

DETERMINING AN ACTION OF A CUSTOMER IN RELATION TO A PRODUCT

Capital One Services, LLC...

1. A method, comprising:receiving, by a device, video data associated with a video of a physical retail location associated with a product;
processing, by the device, the video data to identify one or more body parts of a customer associated with the physical retail location;
tracking, by the device, movement of the one or more body parts;
determining, by the device, an activity of the customer in relation to the product based on the movement;
determining, by the device, a duration of time associated with the activity;
determining, by the device and based on the activity and the duration of time, a category associated with the customer, the category indicating a type of interest the customer has in the product; and
performing, by the device, actions based on the category, actions including:
determining an amount of interest the customer has in the product; and
providing a client device with data indicating the amount of interest.

US Pat. No. 10,769,444

OBJECT DETECTION FROM VISUAL SEARCH QUERIES

GOH SOO SIAH, Singapore ...

1. A method of detecting an object in video and matching the object to one or more products comprising the steps of:a) obtaining video and automatically extracting metadata and attributes of objects in frames and/or portions of frames in the video;
b) segmenting the video based on depicted settings and/or events by comparing contents of consecutive frames for similarities and differences, wherein the video is traversed sequentially to detect a pair of frames or sequence of frames which breach a similarity threshold, wherein a key frame is identified for each segment;
c) compiling segments of same or similar settings and/or events, wherein each segment is tagged with a segment identifier;
d) analysing one or more segments to detect one or more objects, wherein frames and/or portions of frames are compared with defined content in a database populated by aligning known objects and metadata clusters, wherein the metadata is linked to the frames and/or portions of frames by the segment identifier, wherein the location of the detected one or more objects are obtained in each key frame, wherein an object-wise feature vector is generated for each segment;
e) comparing the one or more objects to products;
f) identifying products associated with the one or more objects, wherein a convolutional neural network (CNN) is used;
g) notifying one or more viewers of the products;
wherein a second screen augmentation is used for live or streaming video.

US Pat. No. 10,769,443

DOMINANT TOOL DETECTION SYSTEM FOR SURGICAL VIDEOS

SONY CORPORATION, Tokyo ...

1. A system comprising:one or more processors; and
logic encoded in one or more non-transitory computer-readable storage media for execution by the one or more processors and when executed operable to perform operations comprising:
receiving at least one image frame;
detecting one or more objects in the at least one image frame;
classifying the one or more objects into one or more tool classifications, wherein the one or more objects are one or more tools;
determining if each tool of the one or more tools is non-assistive based on the one or more tool classifications;
determining a handedness of the one or more tools; and
determining a dominant tool from the one or more tools based at least in part on the dominant tool being determined as non-assistive and based at least in part on the handedness of the one or more tools.

US Pat. No. 10,769,442

SCENE CHANGE DETECTION IN IMAGE DATA

AMAZON TECHNOLOGIES, INC....

1. A method comprising:determining a Euclidean distance between a first histogram of a first frame of video data representing an environment and a second histogram of a second frame of the video data;
determining that the Euclidean distance exceeds a threshold value;
determining, in response to the Euclidean distance exceeding the threshold value, a flow value representing changes in the environment represented in a third frame of the video data and a fourth frame of the video data, wherein the flow value is determined based at least in part on a motion vector between a first block of pixels of the third frame of the video data and a second block of pixels of the fourth frame of the video data, and a sum of absolute differences (SAD) between the first block of pixels and the second block of pixels;
determining that the flow value exceeds a flow threshold value; and
transmitting to a remote computing device at least a first portion of the video data subsequent to the first frame based at least in part on the flow value exceeding the flow threshold value.

US Pat. No. 10,769,441

CLUSTER BASED PHOTO NAVIGATION

Google LLC, Mountain Vie...

1. A method for organizing and navigating image clusters comprising:accessing, by one or more processing devices, a set of captured images;
detecting, by the one or more processing devices, whether images within the set of captured images satisfy a predetermined pattern;
grouping, by the one or more processing devices, the images in the set of captured images into one or more clusters according to the detected predetermined pattern;
receiving, by the one or more processing devices, a request to display a first cluster of the one or more clusters of captured images;
determining, by the one or more processing devices, from the images within the first cluster, a set of neighboring captured images that are within a predetermined proximity to the first captured image;
assigning, by the one or more processing devices, one or more neighboring images of the first captured image from the set of neighboring captured images;
selecting, by the one or more processing devices in response to the request, a first captured image from the first cluster to display; and
providing the first captured image from the first cluster for display.

US Pat. No. 10,769,440

VISUAL-INERTIAL POSITIONAL AWARENESS FOR AUTONOMOUS AND NON-AUTONOMOUS TRACKING

Trifo, Inc., Santa Clara...

1. A system including:two or more mobile autonomous units, including a first autonomous unit and a second autonomous unit, each having a mobile platform and disposed thereon:
a visual sensor comprising cameras providing capturing images including at least two frames, thereby providing a 360-degrees view about a centerline of the mobile platform; and at least one of:
a multi-axis inertial measuring unit (IMU) sensor capable of providing measurement of at least acceleration using one or more accelerometers; and
a global positioning system (GPS) receiver; and
a map server, including a processor and a coupled memory storing instructions to build 3D maps of surrounding scenery encountered by the autonomous units using information sourced by the autonomous units, which instructions when executed by the processor perform:
receiving a set of keyrigs from a first autonomous unit, each keyrig comprising visual information of surrounding scenery captured by the visual sensor of the first autonomous unit and a position of the first autonomous unit where the visual information was captured, the position of the autonomous unit generated using combinations of global positioning system (GPS) receiver, the multi-axis inertial measurement unit (IMU), and visual information of the surrounding scenery by the first autonomous unit during travel from a starting point to an end point;
classifying at least one of one or more objects from the visual information of the surrounding scenery from the set of keyrigs into a set of moving objects and a set of non-moving objects;
selecting a subset of keyrig from the set of keyrigs and determining a sparse 3D mapping of object feature points taken from the visual information of the surrounding scenery from the subset of keyrigs for the set of non-moving objects;
building a 3D map of object feature points from the sparse 3D mapping of object feature points using visual information of the surrounding scenery from the set of keyrigs for the set of non-moving objects, wherein the 3D map is accurate within 20 centimeters; and
providing the 3D map via a communications link to one or more additional autonomous units to guide the one or more additional autonomous units at a future time.