US Pat. No. 10,657,515

METHOD AND SYSTEM FOR ENABLING A PAYMENT

Parousya Technologies Pty...

1. A method of processing a payment by a wireless mobile device, comprising:monitoring by the wireless mobile device a first communication channel for receipt of a broadcast signal comprising a broadcast identifier and a first identifier corresponding to one of a plurality of wireless communication devices, wherein the first communication channel operates over a first distance;
upon receipt of the broadcast signal,
comparing by the wireless mobile device the broadcast identifier with a designated broadcast identifier to determine that the broadcast identifier corresponds to the designated broadcast identifier, and
enabling, by the wireless mobile device, a processing device to identify the one of the plurality of wireless communication devices relating to the payment by
generating an identifier notification comprising the first identifier and a second identifier corresponding to the wireless mobile device, and
in response to generating the identifier notification based on determining that the broadcast identifier corresponds to the designated broadcast identifier, automatically transmitting the identifier notification from the wireless mobile device to the processing device over a second communication channel, without storing the first identifier in the wireless mobile device, such that when the identifier notification is received by the processing device, the processing device associates the second identifier with the first identifier in the processing device, wherein the second communication channel operates over a second distance that is greater than the first distance; and
upon receipt of an input, enabling, by the wireless mobile device, the processing device to notify the one of the plurality of wireless communication devices about the payment by
generating a payment request comprising the second identifier, and
transmitting the payment request from the wireless mobile device to the processing device over the second communication channel such that when the payment request is received by the processing device, the processing device generates and transmits a payment notification in connection with the payment request to the one of the plurality of wireless communication devices corresponding to the first identifier.

US Pat. No. 10,657,514

SETTLEMENT TERMINAL DEVICE

PANASONIC INTELLECTUAL PR...

1. A settlement terminal device, comprising:a housing that is configured to be gripped by an operator, the housing including an operation display surface, the operation display surface defining a first opening and a second opening, the operation display surface including an interposed portion that is physically between the first opening and the second opening;
a first information processor that is in the housing and provided with a first user interface in the first opening of the operation display surface of the housing;
a secured second information processor that is in the housing and provided with a tamper-resistant second user interface, which is configured to perform a securable operation, in the second opening of the operation display surface of the housing; and
one light transmitting member that is disposed to continuously cover, above the operation display surface of the housing, the first user interface, the interposed portion, and the second user interface,
wherein, in a direction perpendicular to the operation display surface of the housing, a periphery of an upper surface of the light transmitting member entirely protrudes above a periphery of the housing and is continuously exposed without including a groove or a projection portion between the first user interface and the second user interface and without contacting or abutting the housing.

US Pat. No. 10,657,513

METHOD AND APPARATUS FOR USING QUICK RESPONSE CODES IN E-COMMERCE

SWOOP IP HOLDINGS LLC, W...

14. A method of improving security of an e-commerce transaction using Simple Mail Transfer Protocol) (SMTP), the method comprising:receiving, by a processor of an email payment gateway, a first email from a client device, wherein the first email identifies one or more products associated with a quick response (QR) code that is scanned to generate the first email,
sending, by the processor of the email payment gateway, a second email to the client device that includes a mailto link, a first UUID that is associated with a particular product, and a second UUID that is associated with a user, wherein the mailto link when activated by the user selects the particular product from the one or more products and generates a third email that is sent to the email payment gateway,
receiving, by the processor of the email payment gateway, the third email from the client device, wherein the third email includes the first UUID and the second UUID,
comparing, by the processor of the email payment gateway, the first UUID and the second UUID received in the third email with a plurality of UUIDs stored in a database of the email payment gateway, and
on a condition that the first UUID and the second UUID match the plurality of UUIDs:
processing, by the processor of the email payment gateway, payment and purchase of the particular product.

US Pat. No. 10,657,511

PROXIMITY-BASED TRANSACTION DEVICE SELECTION

NCR Corporation, Atlanta...

2. A mobile device comprising:at least one data communication transceiver device;
at least one processor and at least one memory device, the memory device storing instructions of a transaction processing app executable by the at least one processor to:
completing a first phase of a transaction; and
transferring the transaction to a terminal to perform a second phase of the transaction, including:
receiving a positioning signal from the terminal;
identifying the terminal based upon the positioning signal;
determining peripheral devices connected to the identified terminal including at least one peripheral device required for the second phase of the transaction;
modifying transaction processing options within the transaction processing app based on the peripheral devices determined as connected to the identified terminal, including providing an option to transfer the transaction from the transaction processing app to the identified terminal and the determining including determining whether a cash drawer is connected to the identified terminal;
when a cash drawer is connected to the terminal, enabling a transaction processing option within the transaction processing app to receive cash as a form of payment, otherwise disabling the transaction processing option within the transaction processing app to receive cash as a form of payment; and
transmitting transaction data and an instruction to take over the transaction to the identified terminal via the least one data communication transceiver device.

US Pat. No. 10,657,510

SALES DATA PROCESSING APPARATUS AND COMPUTER-READABLE STORAGE MEDIUM

CASIO COMPUTER CO., LTD.,...

1. A sales data processing apparatus comprising:a narrow area communication unit which communicates with a predetermined terminal apparatus by wireless communication limited to a narrow area;
a wide area communication unit which communicates with the terminal apparatus by wireless communication throughout a wide area; and
a mode switching unit which switches between a first mode in which wireless communication with the terminal apparatus using the narrow area communication unit is allowed but the wireless communication using the wide area communication unit is prohibited, and a second mode in which at least wireless communication using the wide area communication unit is allowed,
wherein, a report mode which outputs sales data calculating predetermined transaction data is assigned to the first mode.

US Pat. No. 10,657,509

COHORT-BASED EVENT MONITORING SYSTEM

The Toronto-Dominion Bank...

1. An event monitoring processor comprising:at least one memory storing a member profile database and a database of cohort definitions, the member profile database storing member particulars of cohort members, each said cohort definition defining a respective cohort; and
a notification processor coupled to the memory and configured to:
receive, from a POS terminal, a notification identifying a member action initiated at the POS terminal by one of the cohort members, and determine the one cohort from a correlation between the cohort definitions and the member particulars associated with the one cohort member in the member profile database;
determine, from the cohort definition of the one cohort, a correlation outcome value from a correlation between the member action and an action associated with the one cohort, and update at least one of the cohort definitions by saving in the cohort definitions database particulars of the member action in association with the at least one of the cohort definition; and
save in the cohort member database a member database record identifying the correlation outcome value, the cohort member database being associated with the cohort member.

US Pat. No. 10,657,508

PRODUCT STORAGE DEVICE AND AUTOMATIC VENDING MACHINE

FUJI ELECTRIC CO., LTD., ...

1. A product storage device comprising:a main gate that is swingably provided to advance to and move away from a product storage column for storing products in alignment, the main gate being located, in a normal state, at an advanced position which is on a dispensing slot side of a downstream-most product present at a downstream-most side in the product storage column, and moving away from the product storage column, to allow the downstream-most product to be taken out through the dispensing slot;
a sub-gate that is swingably provided in association with the main gate to advance to and move away from the product storage column, the sub-gate being arranged such that, when the main gate advances to the product storage column, the sub-gate moves away from the product storage column, and when the main gate moves away from the product storage column, sub-gate advances to the product storage column and regulates a product disposed next to an upstream side of the downstream-most product from moving toward the dispensing slot;
a sliding member that is slidable in a storing direction of the product storage column, the sliding member, when being disposed at a regulation position, regulating the main gate from moving away and retracting from the product storage column;
a lever that is swingably provided together with the main gate, the lever being arranged such that, when in a standby posture, the lever allows the sliding member to be present at the regulation position, when the sliding member slides from the regulation position, the lever switches to a regulation posture which regulates the sliding member from returning to the regulation position, and then, when the main gate moves away from the product storage column in response to a take-out operation of taking out the downstream-most product, the lever switches to the standby posture while the sub-gage advances to the product storage column to allow the sliding member to return to the regulation position; and
a switching member that is movable between a vendition position and a restocking portion, the switching member being arranged such that, when the sliding member slides from the regulation position, the switching member allows the lever to switch to the regulation posture,
wherein in the vendition position, when the main gate, which moved away from the product storage column in response to the take-out operation of taking out the downstream-most product, again advances to the product storage column, the lever is allowed to switch to the standby posture, and in the restocking position, when the sliding member slides from the regulation position, the sliding member is maintained in a state of having slid from the regulation position and the lever is regulated from switching to the standby posture.

US Pat. No. 10,657,507

MIGRATION BETWEEN DIGITAL RIGHTS MANAGEMENT SYSTEMS WITHOUT CONTENT REPACKAGING

Adobe Inc., San Jose, CA...

1. A method comprising:extracting, by a processing device, first license metadata from digital content, wherein the first license metadata identifies a first licensing protocol for generating a license request for accessing the digital content;
determining, by the processing device, a media player incompatibility, wherein a media player executed by the processing device cannot generate the license request using the first licensing protocol and can generate the licensing request using a second licensing protocol, wherein the media player incompatibility comprises the media player being unable to generate the license request using the first licensing protocol;
based on determining the media player incompatibility, performing, by the processing device, operations comprising:
sending the first license metadata to a server,
receiving second license metadata from the server for generating the license request using the second licensing protocol,
generating the license request based on the second license metadata, and
sending the license request based on the second license metadata to the server;
receiving, by the processing device, a license from the server; and
accessing, by the processing device, the digital content using the license received from the server.

US Pat. No. 10,657,506

MOBILE DEVICE MULTI-FEED SCANNER

CAPITAL ONE SERVICES, LLC...

1. An imaging device comprising:a platform having an upper side, a reverse side opposite the upper side, and a transparent portion; and
first and second mirrors positioned relative to the transparent portion to allow imaging of a reverse side of an object placed on the transparent portion with an image capture device while simultaneously imaging an upper side of the object, opposite the reverse side of the object, with the image capture device.

US Pat. No. 10,657,505

DUAL MODE PAYMENT AND DISPLAY SYSTEM

Clover Network, Inc., Su...

1. A system, comprising:a dual mode payment interface device having a touch screen display and storing instructions for operating in a first mode of operation and a second mode of operation;
wherein the first mode of operation provides access to a merchant system interface on the touch screen display and provides access to a customer system interface on the touch screen display;
wherein the second mode of operation provides access to the customer system interface on the touch screen display and does not provide access to the merchant system interface on the touch screen display;
a merchant display device having a second touch screen display;
wherein the merchant display device provides access to the merchant system interface on the second touch screen display;
a wire that provides a communicative connection between the dual mode payment interface device with the merchant display device;
a means for detecting the communicative connection, located on the dual mode payment interface device; and
a means for enabling the second mode of operation in response to the means for detecting the communicative connection detecting the communicative connection;
wherein the dual mode payment interface device is configured to switch from the first mode of operation to the second mode of operation and lock-in the second mode of operation upon:
(i) detecting the communicative connection with the means for detecting the communicative connection; and
(ii) enabling the second mode of operation with the means for enabling the second mode of operation in response to the means for detecting the communicative connection detecting the communicative connection.

US Pat. No. 10,657,504

SYSTEM AND METHOD FOR AUTOMATED OPTIMIZATION OF FINANCIAL ASSETS

Six Trees Capital LLC, N...

1. A method for permitting a third-party entity to gain access to an online account held by an account holder that is secured by a multi-factor authentication protocol, comprising the following steps performed by the third-party entity:(1) accessing, via one or more processors, the online account using the account holder's credentials;
(2) receiving a multi-factor authentication request from the online account, the multi-factor authentication request indicating that a response is required from the account holder before further access to the online account is granted;
(3) transmitting the request to the account holder and receiving the response thereto from the account holder;
(4) transmitting the account holder's response to the online account to satisfy the multi-factor authentication request;
(5) assigning an endpoint using one or more processors, wherein the endpoint is stored in a database and associated with the online account;
(6) adding the endpoint to the online account; and
(7) utilizing the endpoint to permit the third-party entity to respond to subsequent multi-factor authentication requests without requiring a response to the subsequent multi-factor authentication requests by the account holder.

US Pat. No. 10,657,503

SYSTEM AND METHOD OF PROVIDING A CUSTOMER WITH METHOD OF MAKING A PAYMENT TO A THIRD PARTY USING A REMOTE DISPENSING MACHINE

CAPITAL ONE SERVICES, LLC...

1. A computer-implemented method comprising:receiving, at one or more processors and from a customer device, financial transaction information for a requested financial transaction, the customer device being associated with a plurality of financial accounts and the financial transaction information comprising a payment amount, contact information corresponding to a payee device associated with a payee, and a financial account of the plurality of financial accounts from which the payment amount is requested to be debited;
determining, by the one or more processors and based on a comparison of the payment amount to an account balance of the financial account, whether the financial account has sufficient funds to complete the requested financial transaction;
responsive to determining that the financial account has insufficient funds to complete the requested financial transaction:
determining whether a combination of the plurality of financial accounts has sufficient funds to complete the requested financial transaction; and
transmitting, to the customer device, a first message indicating that the financial account has insufficient funds to complete the requested financial transaction and requesting approval to process the requested financial transaction with funds from the combination of the plurality of financial accounts;
responsive to receiving a declination to use funds from the combination of the plurality of financial accounts for the requested financial transaction, transmitting a second message to the customer device, the second message requesting an updated payment amount;
responsive to receiving the updated payment amount, determining, by the one or more processors and based on a comparison of the updated payment amount to the account balance of the financial account, whether the financial account has sufficient funds to complete an updated requested financial transaction associated with the updated payment amount; and
responsive to (i) determining that the financial account has sufficient funds to complete the requested financial transaction, (ii) receiving approval to process the requested financial transaction with the funds from the combination of the plurality of financial accounts, or (iii) determining that financial account has sufficient funds to complete the updated requested financial transaction:
generating, by the one or more processors, a security identifier and a token, the token associated with the financial transaction information and representing the payment amount and comprising a computer-implemented representation of randomly generated barcode data;
transmitting, by the one or more processors and to the payee device via a first message, the token;
transmitting, by the one or more processors and to the payee device via a second message different from the first message, the security identifier;
receiving, from the payee device and via an automatic teller machine (ATM), the token;
receiving, from the payee device and via the ATM, the security identifier;
determining, by the one or more processors and based on a comparison of the token to stored token data, whether the token is authenticated;
determining, by the one or more processors and based on a comparison of the security identifier to stored security identifier data, whether the security identifier is authenticated;
responsive to determining that at least one of the token and security identifier is not authenticated, transmitting, by the one or more processors and to the customer device and the payee device, a notification indicating that the at least one of the token and security identifier is not authenticated; and
responsive to determining that both the token and the security identifier are authenticated, transmitting, by the one or more processors and to the ATM, instructions to dispense an amount of cash equal in value to the payment amount without regard as to whether the ATM is associated with the payee or any account associated with the payee.

US Pat. No. 10,657,502

SYSTEMS AND METHODS FOR PERFORMING FINANCIAL TRANSACTIONS

FISERV, INC., Brookfield...

1. A system, comprising:one or more computers comprising:
at least one memory storing computer-executable instructions; and
at least one processor configured to access the at least one memory and to execute the computer-executable instructions to:
receive, on behalf of a requestor, a request associated with a financial transaction, wherein the request comprises first information associated with a first financial account at a first financial institution to be debited and second information associated with a second financial account at a second financial institution to be credited;
identify (i) the first financial account based at least in part on the first information and (ii) the second financial account based at least in part on the second information;
identify (i) a first payment network and (ii) a second payment network,
wherein the first financial account and the second financial account are accessible by the system via the first payment network and the second payment network, respectively,
wherein the first payment network comprises a non-real-time network,
wherein the first payment network is identified subsequent to failing to identify a third payment network capable of accessing the first account in real time, wherein attempting to identify the third payment network capable of accessing the first account in real time comprises (a) searching one or more datastores associated with the third payment network for an identifier corresponding to at least a portion of an identifier associated with the first financial account, or (b) submitting a request to a service to determine whether the first financial account is accessible in real-time via the third payment network and receiving a response from the service,
wherein the second payment network comprises a network of financial institutions, including the second financial institution, enabled by a payment processing module respectively provided at or on behalf of each of the financial institutions, and
wherein the payment processing module provided at or on behalf of the second financial institution (i) comprises a network interaction component configured to communicate with the system in real-time and an integration component configured to communicate with a core account processing system associated with the second financial institution in real-time, and (ii) enables validation of the second financial account prior to transmitting the credit instruction to the second payment network;
in response to identifying the first payment network, perform a quantitative analysis that generates a measure of a level of risk associated with the financial transaction; and
in response to a determination that the measure of the level of risk associated with the financial transaction satisfies a threshold level, transmit (i) a debit instruction to the first payment network to post a debit to the first financial account, wherein the debit to the first financial account is not performed in real-time, and (ii) a credit instruction to the second payment network to post a credit to the second financial account in real-time, wherein the debit instruction and the credit instruction are (i) associated with the financial transaction, and (ii) are transmitted substantially simultaneously, and wherein the credit instruction is received by the network interaction component of the payment processing module and the credit is transmitted for posting in the core account processing system by the integration component of the payment processing module.

US Pat. No. 10,657,501

SYSTEM AND METHOD OF PROVIDING TO-DO LIST OF USER

Samsung Electronics Co., ...

1. A device for providing a to-do list of a user, the device comprising:a display;
a transceiver;
at least one processor; and
a memory electrically connected to the at least one processor,
wherein the memory stores one or more computer programs including instructions which, when executed by the at least one processor, cause the at least one processor to control for:
controlling the transceiver to receive, from another device of another user, a part of conversation information, of a conversation between the user and the other user, which is performed by the other user on the other device;
automatically, by the device, recognizing the conversation between the user and the other user, wherein the conversation information is text of the conversation converted by the device,
collecting another part of the conversation information, of the conversation between the user and the other user, which is performed by the user on the device,
determining a meaning of the conversation information, of the conversation between the user and the other user, based on the part of the conversation information received from the other device and the other part of the conversation information performed by the user on the device, wherein the determining of the meaning of the conversation information is based on keywords corresponding to interrogatives which are identified in the text of the conversation information, and uses as least one of data mining technology or natural language processing technology,
generating the to-do list of the user based on the determined meaning of the conversation information,
determining an unperformed task not performed by the user from among at least one task in the to-do list by using log information about an operation of the device and the determined meaning of the conversation information, and
outputting notification information, to the display, in a dialogue style, along with a notification reason for notification of the determined unperformed task,
wherein the one or more computer programs further include instructions for determining the unperformed task by using the conversation information from the other user related to the at least one task in the to-do list, and
wherein the display displays the notification information and the notification reason.

US Pat. No. 10,657,500

METHOD AND COMMUNICATION NODE FOR FACILITATING PARTICIPATION IN TELEMEETINGS

Telefonaktiebolaget LM Er...

1. A method performed by a communication node in a communication network operative for facilitating participation in telemeetings, the method comprising:receiving, from an organizer communication device, a first message for invitation to a telemeeting, wherein the first message comprises a meeting agenda with a plurality of agenda items and a time schedule for each of the plurality of agenda items;
making the meeting agenda available on the communication network for a plurality of candidate participant communication devices;
receiving a second message from a first one of the plurality of candidate participant communication devices, wherein the second message comprises information of a selection of one or more individual agenda items out of the plurality of agenda items;
during the telemeeting, receiving, from the organizer communication device, a third message comprising information about which one or more of the plurality of agenda items are currently treated;
determining, based on the second and third messages received from the first candidate participant communication device and the organizer communication device, whether there is a match between the selected one or more individual agenda items and the one or more agenda items currently treated; and
when there is the match, triggering setup of a connection to the telemeeting for the first candidate participant communication device.

US Pat. No. 10,657,499

TIME TRACKING DEVICE AND METHOD

ZR Investments, LLC, Car...

1. A method of employee time management at a set of job sites on a time management server, the method comprising:authenticating, by the time management server, an employee mobile device;
receiving, by the time management server, an employee image from the employee mobile device in response to a time punch event, the employee image pertaining to the time punch event;
receiving, by the time management server, location information pertaining to the employee mobile device in response to the time punch event, the location information comprising location data of the employee mobile device at the time punch event;
comparing, by the time management server, the location information to an expected job site location to determine a location match condition;
generating, by the time management server, a set of time punch data for a work shift for the expected job site location when the set of location information matches the expected job site location;
comparing, by the time management server utilizing electronic facial recognition, the employee image to an archived image to derive an employee match condition; and
validating, by the time management server, the set of time punch data that is based on the location data of the employee mobile device at the time punch event using the employee match condition that is based on an electronic facial recognition comparison between the employee image received from the employee device and the archived image.

US Pat. No. 10,657,498

AUTOMATED RESUME SCREENING

Walmart Apollo, LLC, Ben...

1. A system for automated resume screening, the system comprising:at least one memory;
at least one processor coupled to the memory;
a text analyzer, implemented on the at least one processor, that at least:
obtains historical resumes,
isolates historical terms via a full text analysis of the historical resumes;
a weighted value calculator, implemented on the at least one processor, that at least:
obtains historical candidate selection data associated with the historical resumes,
based at least on some of the historical candidate selection data, determines weighted historical term values of at least some of the isolated historical terms;
a machine learning engine, implemented on the at least one processor, that at least machine trains a predictive model based at least on some of the weighted historical term values;
a keyword score calculator, implemented on the at least one processor, that at least:
analyzes one or more current candidate resumes associated with a role, and
based at least on some of the weighted historical term values, determines a keyword score of the one or more current candidate resumes,
wherein the text analyzer further at least extracts current terms via a full text analysis of the one or more current candidate resumes,
wherein the weighted value calculator further at least determines weighted current term values of at least some of the extracted current terms based at least on some of the historical candidate selection data,
wherein the predictive model determines a probability score of each of the one or more current candidate resumes; and
a resume screening module, implemented on the at least one processor, at least:
generates a candidate score of each of the one or more current candidate resumes based at least on the weighted current term values and the probability score of each of the one or more current candidate resumes,
generates a candidate report based at least one the candidate score, and
provides the candidate report on a user interface, and
receives new candidate selection data feedback indicating selection decisions of the one or more current candidate resumes,
wherein the weighted value calculator updates the weighted historical term values based at least on some of the new candidate selection data feedback, and
wherein the machine learning engine updates the predictive model based at least on some of the new candidate selection data feedback.

US Pat. No. 10,657,497

JIRA DATA VISUALIZATION

JPMORGAN CHASE BANK, N.A....

1. A computer implemented method for generating at least one consolidated data repository report comprising:transmitting an application request to an application server, the application request based on an application parameter;
receive application data from the application server;
transmitting a configuration data request to a configuration server, the configuration data request based on a configuration parameter;
receive configuration data from the configuration server;
generating a data repository report request based on the received application data and configuration data;
connecting to a plurality of data servers to acquire project data related to the data repository report request;
generating the at least one consolidated data repository report based on the project data; and
generating at least one data illustration based on the consolidated data repository report;
wherein the at least one data illustration is generated according to at least one dependency indicator, the dependency indicator including an alert of one or more conflicts present within the data.

US Pat. No. 10,657,496

DETERMINING TIME HISTORIES FOR FINANCIAL INFORMATION

INTUIT, INC., Mountain V...

1. A computer-executable method for determining values for a financial variable at a specified period of time by creating a dateline-based temporal object model (DTOM) in a data layer of a financial software application, comprising:receiving, for use by the financial software application at a computer having one or more processors communicatively coupled to a memory, a single command from a user to access values for a first financial variable for a specified date span;
identifying at least one second variable that is associated with the first financial variable;
querying, by the computer, at least one data source out of a plurality of data sources for a time history of the at least one identified second variable during the specified date span;
creating, based on the results of querying the at least one data source, the DTOM comprising a number of sequential non-overlapping time intervals;
converting, by the computer, the received single command into multiple queries based on the non-overlapping time intervals;
executing the multiple queries against the plurality of data sources to obtain values of the first financial variable from the plurality of data sources storing data with different time resolutions in the DTOM, wherein at least one query is destined to a data source storing data related to the first financial variable corresponding to one of the sequential non-overlapping time intervals;
applying results of the multiple queries to generate a value for a field in a document; and
populating the value to the field of the document.

US Pat. No. 10,657,495

SYSTEMS AND METHODS FOR FORMING AND OPERATING AN ECOSYSTEM FOR A CONDUCTED ELECTRICAL WEAPON

Axon Enterprise, Inc., S...

1. A system for supplementing a first log, the system comprising:a first CEW, the first CEW includes a first processing circuit, a memory, a signal generator, a first wireless short-range communication circuit, and at least one electrode, the signal generator configured to provide a current via at least one electrode through a human or animal target to impede locomotion of the target, the at least one electrode configured to be launched toward the target to provide the current through the target, the first CEW configured to be carried by an officer;
a mobile computer, the mobile computer includes a second processing circuit, a user interface, a display, a second wireless short-range communication circuit, a long-range communication circuit, and a global positioning system (“GPS”) receiver, the mobile computer configured to be carried by the officer or positioned in a vehicle; wherein:
the first processing circuit of the first CEW stores a first information as the first log in the memory, the first information related to one or more functions performed by the first CEW including providing the current through the target to impede locomotion of the target;
the first CEW transmits the first log to the mobile computer via the first wireless short-range communication circuit;
the mobile computer receives the first log from the first CEW via the second wireless short-range communication circuit;
the second processing circuit of the mobile computer combines at least a portion of a second information with the first information of the first log to form an augmented log, the second information includes at least one of an information provided by the officer via the user interface of the mobile computer and a geographic location of the mobile computer provided by the GPS receiver of the mobile computer; and
the mobile computer transmits the augmented log to a server via the long-range communication circuit.

US Pat. No. 10,657,494

AUTHORSHIP TECHNOLOGIES

Duquesne University of th...

1. A method for increasing the efficiency of a computer's verifying authorship of a first writing D, comprising computer-driven comparison of stylometrics in said first writing for which authorship verification is desired to stylometrics in at least one known authored material attributable to an author candidate for whom verification or negation of authorship of said first writing is desired, wherein only those writings of said author candidate are used for such comparison, comprising the steps of:a) compiling a set of training data known to be written by author A by selecting at least one text authored by A and inputting said text into a computer such that said text constitutes said training data;
b) compiling via computer model from said training data by extracting linguistic or token-level features from said training data to create a feature vector and labeling said feature vector M=;
c) extracting a feature set, F, from said writing D for which authorship verification is desired, in the form of F=, where fi corresponds to all mi for all i;
d) choosing a distance function, ?, such that if ?(x,y) e) assigning a threshold, t, by empirically analyzing the average ? values between writings authored by A, such that if ?(M,F)?t, we accept that d and the training data are written by the same author, A, and, wherein when a second threshold p is added, with p

US Pat. No. 10,657,493

METHOD AND SYSTEM FOR RATING A BASEBALL PLAYER'S PERFORMANCE IN PRESSURE SITUATIONS

Clutch Hitter, Inc., Eas...

1. A method for providing improved performance metrics to participants in a fantasy baseball league by rating a baseball player's performance in pressure situations, the method comprising:receiving, by a server over a computer network via an interface from at least one information source, information about at least one at bat situation associated with a player, the interface configured to receive the information from one or more of the following sources: a) game statistics provider devices, b) interactive TVs, c) mobile phones, d) text messages, e) telephones, f) websites, g) sporting organization devices, and h) fantasy sporting organization devices;
receiving in real-time, by the server from a plurality of user devices over the computer network, a plurality of fan ratings for the at least one at bat situation, each fan rating including (1) a rating whether the at least one at bat situation is a pressure at bat and (2) a rating of a performance of the player in an inning;
in a first computer process executing on a processor of the server, comparing in real-time a percentage of fan ratings deeming the at least one at bat situation to be a pressure at bat situation against a threshold to determine whether the at least one at bat situation is a pressure at bat situation;
in a second computer process executing on the processor of the server, if the at least one at bat situations is determined to be an at pressure at bat situation, updating in real-time at least one of (1) a pressure average of the player based on a number of positive pressure contributions by the player and a number of pressure at bat situations associated with the player and (2) a pressure rating of the player based on a summation of an inning rating multiplied by an average fan rating of the performance of the player in the inning for each at pressure at bat situation; and
communicating in real-time, by the server over the computer network to a plurality of servers hosting websites and application services, the websites and application services configured to be accessed by the plurality of user devices of the baseball fans, at least one of the updated pressure average or pressure rating if the at least one at bat situations is determined to be a pressure at bat situation.

US Pat. No. 10,657,492

SYSTEMS AND METHODS FOR OPTIMIZATION OF A PRODUCT INVENTORY BY AN INTELLIGENT ADJUSTMENT OF INBOUND PURCHASE ORDERS

COUPANG CORP., Seoul (KR...

1. A computer-implemented system for intelligent generation of purchase orders, the system comprising:a memory storing instructions; and
at least one processor configured to execute the instructions for:
receiving one or more demand forecast quantities of two or more products, the two or more products corresponding to one or more product identifiers, and the demand forecast quantities comprising a demand forecast quantity for each product of the two or more products for a corresponding unit of time;
receiving supplier statistics data for one or more suppliers, the one or more suppliers being associated with a portion of the two or more products;
receiving current product inventory levels and currently ordered quantities of the two or more products;
dividing the one or more product identifiers into one or more categories by assigning a subset of the one or more product identifiers with the highest demand forecast quantities to a first category and assigning subsequent portions of the one or more product identifiers with the next highest demand forecast quantities to one or more other categories;
determining preliminary order quantities for the two or more products, wherein the preliminary order quantities comprises at least one of a sum of the demand forecast quantities for the two or more products over a first period of time and a sum of safety stock quantities for the two or more products over a second period of time;
constraining the preliminary order quantities to obtain recommended order quantities based at least on the supplier statistics data, the current product inventory levels, the currently ordered quantities, and the assigned category, wherein constraining the preliminary order quantities comprises extracting from the supplier statistics data, past order quantities and actual received quantities of the two or more products, determining a fulfillment ratio of the actual received quantities and the past order quantities, and applying the fulfillment ratio to the preliminary order quantities;
generating purchase orders to the suppliers for the two or more products based on the recommended order quantities;
transmitting the purchase orders to the suppliers;
receiving one or more shipments of the two or more products in response to transmitting the purchase orders; and
updating the supplier statistics data based on the received two or more products.

US Pat. No. 10,657,491

MERCHANDISE EVENT MONITORING VIA WIRELESS TRACKING

Walmart Apollo, LLC, Ben...

1. A system for determining item movement via wireless tracking comprising:a plurality of RFID read zones in a facility;
a first RFID reader located in a first zone of the plurality of RFID read zones;
a second RFID reader located in a different non-overlapping zone of the plurality of RFID read zones from the first RFID reader;
a processing device communicatively coupled to the first RFID reader and the second RFID reader configured to:
receive first RFID data by the first RFID reader;
receive second RFID data by the second RFID reader, the second RFID data different than the first RFID data;
identify a first appearance of a first unique tag information in the first RFID data;
identify a second appearance of the first unique tag information in the second RFID data;
identify a first appearance of a second unique tag information in the second RFID data;
determine whether the second unique tag information appears in the first RFID data within a first period of time prior to the first appearance of the second unique tag information in the second RFID data;
designate, responsive to the second unique tag information appearing in the first RFID data within the first time period prior to the first appearance of the second unique tag information in the second RFID data, a group comprising the first unique tag information and the second unique tag information;
store in a memory a group designation including the first unique tag information the second unique tag information, a time corresponding to when the group is designated, and a first event indicator indicating formation of the group;
detect, during a second period of time, the first unique tag information in third RFID data, the third RFID data different than the first and second RFID data;
detect, during the second period of time, an absence of the second unique tag information in third RFID data; and
update, in the memory, the group designation including a time corresponding to the second period of time and a second event indicator indicating termination of the group.

US Pat. No. 10,657,490

INVENTORYING ITEMS USING IMAGE DATA

Esurance Insurance Servic...

1. A system, comprising:at least one data processor; and
at least one memory storing instructions, which when executed by the at least one data processor, result in operations comprising:
sending, to a device associated with a user, a request to capture image data that includes at least one image of an interior of a dwelling of the user, the device having a camera configured to capture the requested image data, and the device further having a global positioning system configured to provide a geolocation tag for the image data;
receiving, from the device associated with the user, image data including the at least one image of the interior of the dwelling of the user;
verifying, at a server, a location where the image data is captured, the location being verified based at least on the geolocation tag associated with the image data; and
in response to successfully verifying the location, processing the image data to at least identify a first consumer product item in the image data, the first consumer product item being identified by at least comparing the image data with reference image data associated with one or more reference items included in a reference database.

US Pat. No. 10,657,489

OVERSTOCK INVENTORY MANAGEMENT SYSTEM

Walmart Apollo, LLC, Ben...

1. A method of managing products at a retail sales facility, the method comprising:scanning at least one product at a stock room location of the retail sales facility using a hand-held electronic scanner including a processor;
providing a computing device at the retail sales facility in two-way communication with the hand-held electronic scanner;
providing an inventory management database in two-way communication with the computing device, the inventory management database configured to store electronic data representing consumer demand for the products within a predetermined time interval at the retail sales facility and electronic data representing total shelf space for the products at the retail sales facility;
in response to the scanning of the at least one product, transmitting a signal from the hand-held electronic scanner to the computing device, the signal including an identifier of the at least one product scanned by the hand-held electronic scanner;
in response to receiving the signal from the hand-held electronic scanner, transmitting a query from the computing device to the inventory management database to obtain, from the inventory management database, the electronic data representing the consumer demand for the at least one scanned product and the electronic data representing shelf space allocated at the retail sales facility for the at least one scanned product;
after obtaining the electronic data from the inventory management database, transmitting the electronic data obtained from the inventory management database from the computing device to the hand-held electronic scanner;
analyzing, via the processor of the hand-held electronic scanner, the electronic data received from the computing device and, based on the analyzing of the consumer demand for the at least one scanned product and the electronic data representing shelf space allocated at the retail sales facility for the at least one scanned product:
determining, via the hand-held electronic scanner, whether to generate an alert on the hand-held electronic scanner indicating that the at least one scanned product is on a pick list; and
determining, via the hand-held electronic scanner, whether to generate an alert on the hand-held electronic scanner indicating a storage bin in the stock room location of the retail sales facility in which the at least one scanned product is to be stored;
wherein the determining whether to generate the alert further comprises:
identifying at least one storage bin in the stock room location of the retail sales facility that stores at least one product identical to the scanned product; and
identifying, in the alert, the storage bin in the stock room location of the retail sales facility that stores at least one product identical to the scanned product and in which the at least one scanned product is to be stored.

US Pat. No. 10,657,488

PORTABLE INVENTORY TRACKING SYSTEM

CareFusion 303, Inc., Sa...

1. A system for tracking a quantity of an item comprising:a dispensing station cabinet comprising a plurality of containers and a controller, wherein the dispensing station cabinet is configured to provide and restrict access to each of the plurality of containers, and the controller is configured to store a first supply record and a first location record for a first item supply of a first type of item and to store a second supply record and a second location record for a second item supply of a second type of item;
a first portable terminal comprising a transceiver configured to transmit information indicating a change in a quantity of an item; and
a client device configured to:
associate the first portable terminal with the first type of item based on a first unique identifier of the first portable terminal;
determine, while a first container and a second container of the plurality of containers are open, that the first portable terminal is placed at the first container and then moved to the second container of the plurality of containers;
determine that the first container is closed and, after the first container is closed, that the second container is the only currently accessible container of the plurality of containers;
receive, from the transceiver of the first portable terminal after the first portable terminal is placed at the second container, a first change in quantity of the first type of item from the first portable terminal; and
update the first supply record and the first location record associated with the first type of item to reflect that an amount of the first type of item decreased in the first container, and that an amount of the first type of item increased in the second container, in response to receiving the first change in quantity from the first portable terminal and determining that the first portable terminal moved from first selected container to the second container and the second container is the only currently accessible container of the plurality of containers.

US Pat. No. 10,657,487

CUSTOMIZING ITEM SEARCH AND NAVIGATION BASED ON USER PREFERENCES

AMAZON TECHNOLOGIES, INC....

1. A non-transitory computer-readable medium embodying a program executable in at least one computing device, wherein the program includes instructions that cause the at least one computing device to at least:determine a location reported by a location system of a client device, the location system comprising at least one of: a global positioning system (GPS) device, a cellular radio triangulation system, or a WiFi access point reporting system;
determine a current address from a plurality of addresses associated with a user account based at least in part on the location reported by the location system;
dynamically generate a plurality of delivery speed options for the client device for items in a data set based at least in part on a current time of day and the current address;
send a listing of the plurality of delivery speed options to the client device for rendering on a display;
receive a user selection of a particular delivery speed option of the plurality of delivery speed options from the client device;
receive an item query from the client device;
determine item availability via the particular delivery speed option for items in an electronic item database;
generate a listing of items selected from the electronic item database based at least in part on the item query and the item availability via the particular delivery speed option, wherein items available via the particular delivery speed option are ranked higher in the listing of items than items not available via the particular delivery speed option; and
send data encoding the listing of items to the client device for rendering on the display.

US Pat. No. 10,657,486

CONTAINERS FOR CROWDSOURCED DELIVERY

DOORDASH, INC., San Fran...

1. A system comprising:a container including a plurality of compartments for containing a plurality of respective items during transport of the items from a sender to a plurality of respective recipients, the container including a container communication interface for communicating over one or more networks and a container GPS receiver;
a plurality of recipient devices associated with the plurality of respective recipients, each recipient device including a respective recipient device processor and a respective recipient device communication interface coupled to the respective recipient device processor for communicating over the one or more networks;
a plurality of courier devices associated with a plurality of respective couriers, each courier device including a respective courier device processor, a respective courier device GPS receiver coupled to the respective courier device processor, and a respective courier device communication interface coupled to the respective courier device processor for communicating over the one or more networks, each courier device programmed to determine, based at least in part on information from its respective courier device GPS receiver, a geographic location of the courier device;
a sender device including a sender device processor and a sender device communication interface coupled to the sender device processor for communicating over the one or more networks; and
a service computing device including a service computing device processor and a service computing device communication interface coupled to the service computing device processor for communicating over the one or more networks with the container, the plurality of recipient devices, the plurality of courier devices, and the sender device, the service computing device programmed to:
receive, by the service computing device, from the sender device, an indication of a pickup location, an indication of a first delivery location associated with a first recipient, an indication of a second delivery location associated with a second recipient, and an indication that the container, having a first item contained in a first compartment for delivery to the first recipient at the first delivery location and a second item contained in a second compartment for delivery to the second recipient at the second delivery location, is ready for pickup at the pickup location;
determine, by the service computing device, based on public transportation routing information, a route of a public transport vehicle in a geographic region between the pickup location and the first delivery location;
receive, by the service computing device, from the plurality of courier devices, indications of respective geographic locations of the plurality of courier devices;
send, by the service computing device, to a first courier device, based at least in part on the indicated geographic location of the first courier device, a request for a first courier associated with the first courier device to pick up the container from the pickup location and deliver the container to the public transport vehicle;
send, by the service computing device, to a second courier device, based at least in part on the indicated geographic location of the second courier device, a request for a second courier associated with the second courier device to pick up the container from the public transport vehicle at a vehicle location and deliver the container to the first delivery location;
send, by the service computing device, to the container, courier information to cause the container to send, based on the second courier device being within a threshold distance of the container, a signal to the second courier device, the signal providing a notification of the container on the second courier device;
receive, by the service computing device, a first plurality of communications from the container indicating locations of the container during transport of the container between the pickup location and the first delivery location;
receive, by the service computing device, from at least one of the second courier device, the container, or a first recipient device associated with the first recipient, an electronic communication indicating that the container is at the first delivery location;
send, by the service computing device, information to at least one of the second courier device, the container, or the first recipient device for opening a first closure of the first compartment containing the first item, wherein the first item is removed from the container and received by the first recipient;
send, by the service computing device, to the first recipient device, a request to deliver the container to the second delivery location within a threshold time in exchange for an incentive;
receive, by the service computing device, a second plurality of communications from the container indicating locations of the container during transport of the container from the first delivery location to the second delivery location;
receive, by the service computing device, from at least one of the first recipient device, the container, or a second recipient device associated with the second recipient, an electronic communication indicating that the first recipient delivered the container to the second delivery location; and
send, by the service computing device, information to at least one of the container or the second recipient device for opening a second closure of the second compartment containing the second item, wherein the second item is removed from the container and received by the second recipient.

US Pat. No. 10,657,485

PAIRED DRONE-BASED SYSTEMS AND METHODS FOR CONDUCTING A MODIFIED INSPECTION OF A DELIVERY VEHICLE

FEDERAL EXPRESS CORPORATI...

1. A drone-based system for conducting a modified inspection of a delivery vehicle, comprising:an inspection drone paired to the delivery vehicle and operative to aerially inspect the delivery vehicle, the paired inspection drone further comprising:
a main housing,
an onboard controller disposed within the main housing,
a memory storage coupled to the onboard controller and maintaining an inspection profile record corresponding to the delivery vehicle,
a plurality of lifting engines coupled with respective lifting rotors, each of the lifting engines being fixed to a different portion of the main housing and responsive to flight control input generated by the onboard controller as part of maintaining a desired flight profile,
at least one sensor coupled to the onboard controller, the sensor being operative to (a) detect sensor-based inspection information while the paired inspection drone is airborne, and (b) provide the detected sensor-based inspection information to the onboard controller, and
a communication interface coupled to the onboard controller, the communication interface being operative to receive an inspection update message related to the modified inspection of the delivery vehicle; and
a delivery vehicle transceiver comprising
a user interface for accepting input that identifies at least one or more additional inspection points related to the delivery vehicle, and
a wireless radio operative to transmit the inspection update message to the communication interface of the paired inspection drone, the inspection update message identifying the at least one or more additional inspection points accepted as input on the user interface; and
wherein the onboard controller of the paired inspection drone is operative to
access the memory storage to identify a plurality of existing delivery vehicle inspection points from the inspection profile record stored in the memory storage,
receive the inspection update message from the communication interface,
update the existing delivery vehicle inspection points with the at least one or more additional inspection points to yield a plurality of targeted inspection points corresponding to respective parts of the delivery vehicle, wherein the onboard controller of the paired inspection drone is operative to update the existing delivery vehicle inspection points by being further operative to generate a modified inspection profile record that identifies the targeted inspection points as a first plurality of designated inspection areas specific to the delivery vehicle as the existing delivery vehicle inspection points and identifies a second plurality of designated inspection areas specific to the delivery vehicle as the one or more additional inspection points, and
conduct the modified inspection of the delivery vehicle by gathering the detected sensor-based inspection information related to each of the targeted inspection points.

US Pat. No. 10,657,484

DISTRIBUTION MANAGEMENT SYSTEM, DISTRIBUTION MANAGEMENT METHOD, AND DEVICE, LABEL AND PROGRAM USED BY SAME

NEC CORPORATION, Minato-...

1. A collation server for collating an agricultural, forest and fishery product produced or shipped by a producer or distributor with the agricultural, forest and fishery product, being a collation target, comprising:a storage in which image characteristics of epidermal patterns in a predetermined collation area of the agricultural, forest and fishery product are stored, wherein the collation area is an area of which a location and a direction are set relative to a reference of the agricultural, forest and fishery product;
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
receive an image of an epidermal pattern in the collation area of the agricultural, forest and fishery product, being a collation target, determine the collation area relative to the reference in the received image, extract an image characteristic of the epidermal pattern in said collation area from the received image, the image characteristic including at least one of a luminance value and characteristic points, the characteristic points including an endpoint, an intersection point, and an angle of a line of the epidermal pattern in the collation area of said agricultural, forest and fishery product, being a collation target,
collate said image characteristic of the epidermal pattern stored in the storage with the image characteristic of the epidermal pattern in the collation area of said agricultural, forest and fishery product, being a collation target, and determine, by comparing the at least one of the luminance value and the characteristic points of the image characteristic in the received image with at least one of a luminance value and characteristic points of the image characteristic of the epidermal pattern stored in the storage, whether or not said agricultural, forest and fishery product, being a collation target, is the agricultural, forest and fishery product produced or shipped by said producer or distributor.

US Pat. No. 10,657,483

SYSTEMS AND METHODS FOR SECURE PACKAGE DELIVERY

Vivint, Inc., Provo, UT ...

12. A computing device configured for enabling secure delivery of a package to a delivery area, comprising:a processor;
memory in electronic communication with the processor; and
instructions stored in the memory, the instructions being executable by the processor to:
receive information regarding a delivery of the package to a premises;
detect a pattern associated with the delivery of the package, wherein the pattern is based at least in part on one or more previous deliveries;
determine a location of an occupant of the premises and whether the occupant is beyond a predefined distance from the premises;
select the delivery area within the premises based at least in part on the detected pattern and the location of the occupant;
detect a delivery person arriving at the premises by a delivery vehicle associated with a delivery company;
receive information relating to an identity of the delivery person including at least the delivery company;
query an external server of the delivery company to determine a location of the delivery vehicle and authenticate a location of the delivery person based at least in part on determining the location of the delivery vehicle;
upon authenticating the location of the delivery person, wirelessly actuate unlocking of the selected delivery area within the premises and verify that a remaining area within the premises is locked; and
provide instructions to the delivery person regarding how to deliver the package to the selected delivery area within the premises.

US Pat. No. 10,657,482

DYNAMIC ORGANIZATION STRUCTURE MODEL

ADP, LLC, Roseland, NJ (...

1. A method comprising:modeling multiple relationship dimensions among a set of entities using a relationship modeling environment including a relationship modeling system including a computer system:
identifying, using the relationship modeling system, a configuration corresponding to a relationship structure wherein the configuration comprises metadata about supported aspects of the configuration and wherein each entity of the set of entities is an organization unit of an organization;
identifying, using a relationship modeler of the computer system, an entity from among the set of entities, wherein the entity comprises metadata about entity aspects of the entity;
comparing the entity aspects of the entity to the supported aspects of the configuration, using the relationship modeling system, to determine whether the entity aspects meet one or more rules in a policy for the configuration;
when the entity aspects meet the one or more rules in the policy for the configuration, determining, using the relationship modeler, a relationship of the entity to the set of entities, and dynamically attaching, using a structure configurator of the relationship modeler, the entity to the set of entities according to the determined relationship to dynamically form the relationship structure;
after dynamically forming the relationship structure, displaying, using a graphical user interface of a display system, the relationship structure to a user; and
performing, using the relationship modeling environment, an operation for the organization based on display of the relationship structure to the user, wherein the operation is at least one of hiring, benefits administration, payroll, performance reviews, forming teams for new products, or assigning research projects,
wherein the relationship structure includes a relationship graph including a plurality of nodes in node-to-node relationship and a plurality of roles corresponding to a structure context, wherein each of the plurality of nodes corresponds to a different one of the set of entities.

US Pat. No. 10,657,481

EVALUATION OF OUTPUT-PRODUCING ASSET PRODUCTIVITY

SPENCERMETRICS LLC, Melv...

1. An output-producing asset productivity evaluation device system comprising:a first data processing device system;
a first input-output device system communicatively connected to the first data processing device system and including a first display device system; and
a first processor-accessible memory device system communicatively connected to the first data processing device system and storing a first program set executable by the first data processing device system,
wherein the first data processing device system is configured at least by the first program set at least to:
access, via the first input-output device system, first asset input indicating occurrence of a non-operational event in which a first output-producing asset was not operational;
cause storage of information about the occurrence of the non-operational event, including time and an identification of the first output-producing asset with an associated first particular software key of a plurality of software keys;
cause the first display device system to visually present a user interface linked to the first output-producing asset, the user interface including the plurality of software keys, each software key of the plurality of software keys associated with providing an event description;
receive a user-selection of the first particular software key of the plurality of software keys, the first particular software key associated with providing a particular event description;
associate, with the non-operational event in which the first output-producing asset was not operational, information pertaining to the particular event description at least in response to receiving the user-selection of the first particular software key;
cause storage, in a processor-accessible memory device system, of output-producing asset productivity information based at least on the information pertaining to the particular event description associated with the non-operational event in which the first output-producing asset was not operational;
facilitate log in of a first operator indicating operation of the first output-producing asset by the first operator;
link, in a state in which the first operator is logged in, the user interface to the logged-in first operator and the first output-producing asset, including associating each software key of the plurality of software keys with one or more events associated with both the logged-in first operator and the first output-producing asset;
facilitate log in of a second operator different than the first operator indicating operation of the first output-producing asset by the second operator;
link, in a state in which the second operator is logged in, the user interface to the logged-in second operator and the first output-producing asset, including associating each software key of the plurality of software keys with one or more events associated with both the logged-in second operator and the first output-producing asset;
receive, in the state in which the first operator is logged in, an instruction from the logged-in first operator to associate the user interface with a second output-producing asset other than the first output-producing asset; and
link, in response to receiving the instruction and in the state in which the first operator is logged in, the user interface to the logged-in first operator and the second output-producing asset other than the first output-producing asset, including associating each software key of the plurality of software keys with one or more events associated with both the logged-in first operator and the second output-producing asset.

US Pat. No. 10,657,480

METHODS AND SYSTEMS FOR PHARMACY MODELING

Express Scripts Strategic...

1. A method comprising:developing a pharmacy predictive model for a pharmacy based on member data, claims data, and population data stored in one or more databases, the pharmacy predictive model including a plurality of model covariates;
selecting at least one model covariate from the plurality of model covariates in the pharmacy predictive model that are related to the pharmacy;
determining an expected performance measure of the pharmacy based on the at least one model covariate that is selected;
determining a performance measure of the pharmacy using the pharmacy predictive model;
determining a quality measure of the pharmacy by comparing the performance measure of the pharmacy with the expected performance measure of the pharmacy; and
adjusting the plurality of model covariates of the pharmacy predictive model based on the quality measure,
wherein the performance measure is a calculated adherence percentage for a therapy class of medications at the pharmacy and the expected performance measure of the pharmacy is the calculated adherence percentage for the therapy class of medications at the pharmacy.

US Pat. No. 10,657,479

SYSTEM AND METHOD FOR INTEGRATING EMPLOYEE FEEDBACK WITH AN ELECTRONIC TIME CLOCK OR COMPUTER LOGIN

1. A method for integrating employee feedback with an electronic time clock, the method comprising:using a unique employee identification (ID), logging into the electronic time clock on a display screen, the electronic time clock associated with an organization employing an employee, the electronic time clock having a mechanism for an employee to input the unique employee ID, the mechanism selected from the group comprising: a card having an RFID chip containing the unique employee ID, a card having a magnetic strip containing the unique employee ID, and a log-in screen prompting the employee to input the unique employee ID,
receiving a prompt on the display screen where the employee logged into the electronic time clock to answer one or more survey questions, the one or more survey questions generated based on the unique employee ID;
answering the one or more survey questions on the display screen to provide employee feedback while still logged into the electronic time clock;
generating one or more alerts when answers provided in response to the one or more survey questions constituting employee feedback integrated with the electronic time clock identify discrimination, harassment, and/or illegal pay practices; and
sending the one or more alerts to one or more persons within the organization associated with the electronic time clock,
wherein the employee cannot log out of the electronic time clock until the employee provides answers to each of the one or more survey questions using the display screen and the answers are recorded, and
wherein the one or more alerts create management action to improve key performance indicators (KPIs) associated with employees in the organization relating to discrimination, harassment, and/or illegal pay practices.

US Pat. No. 10,657,478

AGGREGATED ENTITY RESOURCE TOOL

BANK OF AMERICA CORPORATI...

1. A system for aggregated resource application, the system comprising:a memory device with computer-readable program code stored thereon;
a communication device;
a processing device operatively coupled to the memory device and the communication device, wherein the processing device is configured to execute the computer-readable program code to:
implement within a user system, wherein the user system communicates with a third party exchange system;
request authorization for uplink of the user system and the third party exchange system for extraction of resource flows;
uplink, upon receiving authorization, the user system and third party exchange system for extraction of resource flows of the user, wherein the uplink comprises generating a communicable linkage to extract resource flow data from the user system and the third party systems and the communicable linkage further comprises an internal communication linkage to an entity system sponsoring the aggregated resource application;
process competitor sales and inventory and aggregate the competitor sales and inventory;
generate, via artificial intelligence engine, a predicted future resource flow comparison, wherein generating the predicted future resource flow comparison comprises receiving real-time data from the user system and third party systems and correlating the real-time data with historic data for predictive analysis of future resource flows;
generate an interactive dashboard for visualization of categories, wherein the categories include a use of third party resources, system resources, and aggregation data across from aggregation of the competitor sales and inventory in an industry;
perform a trend analysis, via artificial intelligence engine, on the aggregated competitor sales and inventory to identify underpenetrated customer populations;
calculate, using extracted resource flow data from the user system and the third party systems, predicted inventory requirements for targeting the underpenetrated customer populations, wherein the predicted inventory are calculated by analyzing market changes in inventory, past orders for the inventory, and a recommended time frame and resource type to purchase additional inventory;
extract, via data received over the communicable linkage, information regarding third party exchange products comprising payments, lending, and merchant services that the user utilizes from the third party exchange system;
allow access to the user system, the third party systems, and the system resources for inventory and resource distribution;
present the interactive dashboard on display of the user system with overlaid multi-source data comprising predicted future resource flow comparison, third party exchange products, and predicted inventory requirements from the artificial intelligence engine; and
convert the multi-source data into an incorporated multi-source converted data platform via overlay for user manipulation and communication with sources via the communicable linkage.

US Pat. No. 10,657,477

WORK DATA MANAGEMENT SYSTEM AND WORK DATA MANAGEMENT METHOD

Hitachi, Ltd., Tokyo (JP...

1. A work data management system, comprising:a first camera configured to capture first image data of a movement of a worker in a work site;
a second camera configured to capture second image data of movement of the worker in the work site;
barcode reader configured to read information from a barcode attached to an object in a work site;
a processor connected to the barcode reader, first camera and the second camera, programmed to:
extract first feature quantity data from the first image data and determines positions of a head of the worker in a first period of time using coordinates based on the first image data;
extract second feature quantity data from the second image data and determines positions of a hand of the worker in a second period of time using coordinates based on the second image data;
determine that the worker is performing two or more first work events performed by the worker in the work site based on the determined coordinate positions of the head and the hand of the worker within a predetermined period of time,
determine a type of work performed by the worker in the work site based on the read information from the barcode reader,
determine, based on predefined combinations of the type of work performed by the worker and two or more first work events occurring within a predetermined amount of time, that the worker is performing one of a plurality of predefined second work events in the work site,
generate time-series of visualization data based on the determined predefined second work events that the worker is performing, the first feature quantities and the second feature quantities, the determined coordinate positions of the head, the determined coordinate positions of the hand, and
display the generated time-series visualization data on a display including visual representations of respective positions of the head and the hand of the worker.

US Pat. No. 10,657,476

JUST IN TIME COMPILATION (JIT) FOR BUSINESS PROCESS EXECUTION

TIBCO SOFTWARE INC., Pal...

1. A method of providing a business process, comprising:receiving, by a processor, a business process source file stored in a memory, wherein the business process is associated with the business process source file and the business process includes one or more related, structured activities or tasks;
determining, by the processor, based at least in part on the business process source file a virtual file system that does not rely on a native file system of a computer system, wherein the virtual file system includes a hierarchical namespace;
providing, by the processor, the business process source file as an input to a compiler during runtime;
receiving, by the processor, from the compiler as output a business process compilation output file stored in the memory, wherein the business process compilation output file is stored in the memory based at least in part on the hierarchical namespace of the virtual file system, wherein the business process compilation output_file outputted by the compiler includes a new or updated version of the business process; and
providing, by the processor, the business process compilation output file to a business process engine.

US Pat. No. 10,657,475

COST EFFECTIVE DATA STORAGE

International Business Ma...

1. A method for cost effective data management, the method comprising:storing data in data storage resources arranged in tiers;
determining a percentage of data stored per tier for an uncompressed arrangement of data in the data storage resources;
determining a compression factor for data stored in the data storage resources based on compressing a sample subset of data stored in the data storage resources;
determining a percentage of data stored per tier for a compressed arrangement of data in the data storage resources;
accessing information defining a cost per tier of the compressed arrangement of data and a cost per tier of the uncompressed arrangement of data;
determining a volume skew of the stored data, wherein the volume skew is a relative cumulative amount of extents generating all of the inputs and outputs minus one divided by the compression factor;
calculating a cost for the uncompressed arrangement of data based on the determined percentage of data stored per tier for an uncompressed arrangement of data in the data storage resources and the accessed information defining cost per tier of the uncompressed arrangement of data;
calculating a cost for the compressed arrangement of data based on the determined percentage of data stored per tier for a compressed arrangement of data in the data storage resources, the determined compression factor, the determine volume skew, and the accessed information defining cost per tier of the compressed arrangement of data; and
based on the calculated cost of the compressed arrangement of data being less than the calculated cost of the uncompressed arrangement of data and the data being stored in an uncompressed arrangement, switching the stored data to a compressed arrangement of data,
wherein one or more steps of the above method are performed using one or more computers.

US Pat. No. 10,657,474

COLLABORATIVE DESIGN SYSTEMS, APPARATUSES, AND METHODS

SOURCECODE TECHNOLOGY HOL...

1. A collaborative design apparatus comprising:a persistent memory configured to store an executable version of a workflow project, the workflow project including at least one executable version of an the object-orientated process having attributes and properties,
a model processing server configured to compile and execute the workflow project based on the attributes and properties of the executable version of the object-orientated process;
an abstraction interface configured to define a mapping between
(i) the executable version of the object-orientated process and a typescript version of the object-orientated process including related attributes and properties, and
(ii) the executable version of the workflow project and a typescript version of the workflow project,
the typescript version of the object-orientated process and the typescript version of the workflow project being compatible to be displayed in a web browser; and
an intermediary processing engine configured to:
transmit the typescript version of the object-orientated process and the typescript version of the workflow project to a first client device for display in the web browser of the first client device and a second client device for display in the web browser of the second client device,
transmit a toolset file to the first client device and the second client device, the toolset file specifying a user interface to enable modification of the typescript version of the object-orientated process and the typescript version of the workflow project,
receive, from the first client device, a modify instruction to modify at least one of the attributes or properties of the typescript version of the object-orientated process,
store the modify instruction in conjunction with the typescript version of the object-orientated process, and
transmit the modify instruction to the second client device causing the user interface to modify the at least one of the attributes or properties of the typescript version of the object-orientated process displayed within the user interface at the second client device,
wherein the typescript version of the object-orientated process is concurrently displayed, at the first client device and the second client device, with the modification of the at least one of the attributes or properties.

US Pat. No. 10,657,473

ROLE-BASED FRAMEWORK AND MECHANISMS FOR CONFIGURATION OF COLLABORATIVE APPLICATIONS

Oracle International Corp...

1. A non-transitory computer-readable storage memory storing a plurality of instructions which, when executed by one or more processors, cause the one or more processors to perform operations comprising:receiving, from a client device, first network credentials corresponding to a first user;
validating the first network credentials;
initiating a first network session with the client device based on the validation of the first network credentials;
determining a first role associated with the first user, wherein the first role is one of a plurality of roles;
retrieving a first data mapping defining a first set of interactions that are permitted for the first role with respect to a first object type;
generating a programmatic control component for the first object type;
customizing, based on the first data mapping, the programmatic control component to support the first set of interactions;
availing the customized programmatic control component to the client device during the first network session within an interface, the interface including:
one or more user-interface objects including at least a first user-interface object of the first object type, the first user-interface object corresponding to at least one of hyperlink object, a button control object, or a data field object;
for each user-interface object of the one or more user-interface objects, an object type indicator configured to indicate an object type associated with the user-interface object, wherein an object type indicator corresponding to the first user-interface object identifies the first object type;
one or more selection controls, each selection control of the one or more selection controls being associated with a particular user-interface object of the one or more user-interface objects, and each selection control of the one or more selection controls providing one or more selectable options relating to potential interactions that are permitted for the first role relative to the particular user-interface object, wherein a first selection control of the one or more selection controls is associated with the customized programmatic control component of the first user-interface object and visually indicates a first set of selectable options corresponding to the first set of interactions;
detecting, through the interface and during the first network session, user input corresponding to a selection of a first option from the first set of selectable options, wherein the first option corresponds to an interaction of the first set of interactions permitted for the first role; and
in response to the selection of the first option, causing the customized programmatic control component to initiate a transaction of a first transaction type that corresponds to the first option.

US Pat. No. 10,657,472

IT SERVICES INTEGRATED WORK MANAGEMENT

International Business Ma...

1. An information technology (IT) services based integrated work management method comprising:identifying, by a computer processor of a work management computing system via integrated computer sensor devices, work types associated with a plurality of computer and non-human resource based work functions executed by multiple work execution computing systems connected to said work management computing system;
defining within said work management system, by said computer processor, specified work functions of said plurality of computer and non-human resource-based based work functions;
identifying, by said computer processor, multiple interfaces connected between said multiple work execution computing systems and said work management computing system, wherein said multiple interfaces enable access to said multiple work execution computing systems and said work management computing system;
enabling, by said processor, system tasks of said work management computing system without assistance from an operating system of said work management computing system;
transferring, by said processor from said multiple work execution computing systems, monitoring tasks and preventative maintenance tasks for said multiple work execution computing systems;
consolidating, by said computer processor, groups of said specified work functions with respect to said monitoring tasks and preventative maintenance tasks and based on associated work types, work groups, or competencies related to work elements;
modifying, by said computer processor based on update data, each group of said groups of said specified work functions;
optimizing, by said computing system, staffing resources associated with execution of each said group by:
calculating allocations associated with each said group;
determining consolidated non-human resource capacity and utilization bandwidth associated with computer implemented work areas of each said group; and
generating forecasts associated with said computer implemented work areas; and
generating, by said computer processor based on results of said optimizing, a resource staffing plan associated with said staffing resources.

US Pat. No. 10,657,471

INTELLIGENT ASSIGNMENT OF AGENTS

1. A computer-implemented process for balancing load among a plurality of active agents within an agent group, comprising:distinguishing, by a load balancing server, an active conversation from an inactive conversation;
for the active conversation,
determining, by the load balancing server, whether a user has replied to an agent's message, and
when the user fails to reply to the agent's message within the predefined period of time, marking, by the load balancing server, the active conversation as inactive while allowing the user and the agent assigned to the now inactive conversation to remain connected until the now inactive conversation is marked as active and until the agent is reassigned to another active conversation or until another agent is reassigned to the active conversation; and
for the inactive conversation,
marking, by the load balancing server, the inactive conversation as active when the user replies to the agent's message or when the agent sends a subsequent message; and
assigning, by the load balancing server, the active conversation from one active agent to another active agent depending on a number of active conversations assigned to each of the plurality of active agents within the agent group.

US Pat. No. 10,657,470

JOINT USE UTILITY MANAGEMENT SYSTEM

CenturyLink Intellectual ...

1. A system for joint use utility management comprising:a joint use utility database maintaining entries for a plurality of joint use utilities, each of the entries respectively having joint use information regarding an associated joint use utility of the plurality of joint use utilities, the joint use information indicating at least each member of a joint use agreement having an attachment at the associated joint use utility, and location information of the associated joint use utility;
an end device associated with a first member of the joint use agreement, the joint use agreement having a plurality of members including the first member, the end device being communicatively coupled to a communications network;
a smart attachment located at the associated joint use utility, the smart attachment comprising:
at least one first processor;
a first non-transitory computer readable media having encoded thereon computer software comprising a first set of instructions executable by the at least one first processor to:
determine whether there is a first open job ticket associated with the associated joint use utility;
determine whether the end device associated with the first member of the joint use agreement is within a pre-defined range of the associated joint use utility; and
based on a determination that there is the first open job ticket associated with the associated joint use utility and that the end device associated with the first member of the joint use agreement is within the pre-defined range of the associated joint use utility, transmit the first open job ticket associated with the associated joint use utility to the end device associated with the first member of the joint use agreement;
a joint use utility manager in communication with the joint use utility database and the end device over the communications network, the joint use utility manager comprising:
at least one second processor;
a second non-transitory computer readable media having encoded thereon computer software comprising a second set of instructions executable by the at least one second processor to:
receive, from the end device, a request for one or more second open job tickets associated with the first member;
retrieve, from the joint use utility database, a list of joint use utilities use utilities associated with the first member having a second open job ticket, and respectively associated joint use information for each of the joint use utilities;
generate an interactive map populated with an indicator of each of the joint use utilities having the second open job ticket and associated with the first member based on the location information of each respective joint use utility in the list of joint use utilities, wherein job ticket information associated with each respective joint use utility is accessible through the interactive map;
transmit, via the communications network, the interactive map to the end device;
receive, from the end device, a first job ticket notification indicating a status of a first job ticket for a particular joint use utility in the list of joint use utilities;
update, at the joint use utility database, the status of the first job ticket for the particular joint use utility in a respective entry for the particular joint use utility;
receive, from the end device, a second job ticket notification indicating that the first job ticket has been completed;
based on receiving the second job ticket notification indicating that the first job ticket has been completed, identify a second member of the joint use agreement to perform work for the particular joint use utility; and
based on the identification of the second member, generate and transmit a second job ticket to the second member of the joint use agreement.

US Pat. No. 10,657,469

AUTOMATED SECURITY INCIDENT HANDLING IN A DYNAMIC ENVIRONMENT

International Business Ma...

1. A method for taking an immediate responsive action to a current security incident, the method comprising the steps of:receiving an incident report from a customer in a public cloud environment for a first virtual machine instance, the customer seeking an incident response from one or more administrators, the incident report identifying a current security incident affecting the first virtual machine instance;
receiving, from the one or more administrators, a plurality of incident information datasets respectively corresponding to a plurality of actual severities for a plurality of prior security incidents reported for the virtual machine instance and customer information collected prior to receiving the incident report;
generating a security score for the virtual machine instance based at least in part on:
the plurality of actual severities for the plurality of prior security incidents, wherein a high actual severity of a prior security incident supports an estimate of a high security score for the virtual machine instance,
the plurality of incident information datasets, wherein a basis for the incident report being from a third party image supports a high security score for the virtual machine instance, and
the customer information, wherein the customer being associated with a current customer engagement via an account representative supports a higher security score than the customer being associated with a web-based engagement by a new customer;
determining, by a processor, a severity level of the current security incident based on the security score for the virtual machine instance;
responsive to the security level indicating an immediate responsive action, shutting down the virtual machine instance while retaining a historical dataset of the security incidents for the virtual machine instance; and
reporting, to the one or more administrators, by the processor, the estimated severity level of the current security incident and the immediate responsive;
wherein:
the customer information is data available independent of the current security incident including: length of customer engagement and basis of billing schedule with the customer.

US Pat. No. 10,657,468

SYSTEM AND METHODS FOR VERIFYING THAT ONE OR MORE DIRECTIVES THAT DIRECT TRANSPORT OF A SECOND END USER DOES NOT CONFLICT WITH ONE OR MORE OBLIGATIONS TO TRANSPORT A FIRST END USER

UBER TECHNOLOGIES, INC., ...

1. A system, comprising:circuitry for receiving one or more directives that direct a transportation vehicle unit to a first location, the transportation vehicle unit traveling toward a second location and having been determined to be able to travel to the first location while the transportation vehicle unit is traveling toward the second location; and
circuitry for confirming that compliance with the one or more directives will not conflict with one or more obligations to travel to the second location by the transportation vehicle unit.

US Pat. No. 10,657,467

MULTISTAGE CONFIGURATION TREES FOR MANAGING PRODUCT FAMILY TREES

BIGLEVER SOFTWARE, INC., ...

1. A product line management system comprising:a product family tree computer data structure, wherein the nodes of the product family tree are feature profiles and each node defines a subfamily;
one or more partially bound feature profiles in the product family tree, the one or more partially bound feature profiles having some feature decisions that have been made and other feature decisions have not been made, and wherein the one or more partially bound feature profiles are present either as internal nodes or leaf nodes of the product family tree;
one or more child nodes in the product family tree, wherein the one or more child nodes must inherit, must honor, and may not override feature decisions made by the respective parent of the one or more child nodes, and wherein the one or more child nodes may make additional feature decisions that further constrain the space of available feature choices;
wherein downselection in a partially bound feature profile constrains the space of available feature choices by excluding from further consideration some feature decisions;
wherein any direct connected path from a root node in the product family tree to a leaf node in the product family tree is a monotonically decreasing sequence of available feature choices;
wherein a feature decision or downselection at an internal node in the product tree will be propagated by a computer algorithm to the children of the internal node, and wherein a feature decision or downselection at an internal node in the product tree will stop propagating feature decisions from a parent of the internal node to the children of the internal node and will instead propagate the feature decisions of the internal node to the children of the internal node; and
wherein creation and modification of the product family tree computer data structure is performed using at least one processor.

US Pat. No. 10,657,466

BUILDING CUSTOM APPLIANCES IN A CLOUD-BASED NETWORK

Red Hat, Inc., Raleigh, ...

1. A method comprising:receiving a request to build a software appliance, the request comprising a set of software modules from a repository of software modules to be included in the software appliance and an indication of a period of time for utilization of the software appliance;
determining, by a processor, a minimum amount of an operating system necessary to allow the set of software modules to run on one or more sets of virtual machines in a cloud computing environment, wherein the minimum amount of the operating system comprises a subset of a complete operating system, the subset sufficient to support the set of software modules, and wherein the minimum amount of the operating system provides a set of reduced features and components required to provide an application space for the set of software modules;
configuring the software appliance in view of the request, wherein the software appliance comprises the set of software modules and the minimum amount of the operating system, and wherein configuring the software appliance comprises embedding a management identifier into the software appliance, the management identifier to permit tracking of the software appliance;
identifying a set of resource servers hosted in the cloud computing environment that are available during the period of time specified in the request;
creating the one or more sets of virtual machines using the set of resource servers hosted in the cloud computing environment to support the software appliance, the one or more sets of virtual machines comprising a first set of virtual machines running on a first partition of the set of resources servers and a second set of virtual machines running on a second partition of the set of resource servers, wherein the first partition and the second partition are isolated to support a multi-tenant cloud arrangement;
instantiating the software appliance on the one or more sets of virtual machines using the minimum amount of the operating system during the period of time specified in the request; and
tracking a utilization of the software appliance, including a duration for which the software appliance is instantiated, the period of time during which the software appliance is instantiated, and an amount of resources consumed by the software appliance, in order to determine a charge, wherein the charge is determined in view of the duration, the period of time and the amount of resources consumed.

US Pat. No. 10,657,465

DOUBLE-BOOKING PREVENTION

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

1. A method for preventing double booking in response to a repeated hypertext transfer protocol (HTTP) request received from a client, the method comprising:providing a web page to the client, wherein the web page includes a reference to a uniform resource indicator (URI) and a session identifier is embedded in the URI;
after providing the web page to the client, receiving a first hypertext transfer protocol (HTTP) request from the client at a server, wherein the first HTTP request includes the session identifier;
providing, by the server in response to the first HTTP request, mobile program code to the client, wherein the mobile program code causes the client to display booking status information indicative of a processing status of the first booking request and the mobile program code repeatedly updates the displayed booking status based on repeated communication of the processing status from the server to the client;
initiating, by the server, preparation of response data for the client to process the first HTTP request;
creating a response wrapper, by the server, wherein a first response object is assigned to the response wrapper and the first response object represents a first transport-protocol connection established by the client for transmitting the first HTTP request;
assigning, by the server, the prepared response data to the first response object;
storing, by the server, the response data and the response wrapper in a job repository at the server, wherein response data is continuously prepared as a result of the ongoing process initiated by the first HTTP request and incrementally stored in the job repository;
receiving a second hypertext transfer protocol (HTTP) request from the client at the server, wherein the second HTTP request includes the session identifier;
determining the second HTTP request is a repetition of the first HTTP request based on the session identifier;
preventing, by the server, the second HTTP request from being processed;
checking, by the server, whether the response wrapper already exists in the job repository for the received second HTTP request by comparing session identifiers,
updating, by the server in response to existence of the response wrapper in the job repository, the response wrapper with a second response object representing a second transport-protocol connection established by the client for transmitting the second HTTP request;
performing, by the server, response swapping by assigning the response data prepared in response to the first HTTP request from the first response object to the second response object; and
returning, by the server in response to the repeated request, a response to a web browser of the client comprising the response data prepared in response to the first HTTP request.

US Pat. No. 10,657,464

PLANNING SYSTEM FOR AUTONOMOUS OPERATION

TECHNOLOGICAL RESOURCES P...

1. A mine automation system to operate autonomous entities in a mine region, comprising:a memory;
a processing unit comprising one or more processors coupled to the memory;
a mine planning system comprising:
a mine planner module coupled to the one or more processors that is configured to generate, based on at least one model of the mine region, a plan of activities for the mine region, the plan of activities including a first set of jobs to be performed by the autonomous entities; and a location associated with each of the jobs;
a job planner module coupled to the one or more processors that is configured to receive the set of jobs from the mine planner module; and to output a job plan including a set of tasks for a set of the autonomous entities to satisfy each of the jobs, each of the tasks defining the location and one of the autonomous entities to perform the task, wherein the job planner module is created using the mine planner module coupled to the one or more processors; and
a task planner module coupled to the one or more processors that is configured to receive the plurality of tasks from the job planner module and to generate a set of actions for each of the autonomous entities, wherein the task planner module is created using the job planner module coupled to the one or more processors;
a mine control system coupled to the mine planning system, the mine control system comprising:
a plurality of island controllers to control a plurality of zones within the mine region; and
a managing controller to control the plurality of island controllers;
a mine analysis system coupled to the mine planning system, the mine analysis system comprising the at least one model of the mine region, wherein the mine analysis system coupled to the one or more processors is configured to:
receive sensor information indicating at least one change within the plurality of zones within the mine region, the at least one change resulting from implementation of the set of actions for at least one of the autonomous entities; and
update, based on the received sensor information, the at least one model of the mine region;
wherein the mine planning system coupled to the one or more processors is configured to generate, based on the at least one updated model of the mine region, an updated plan of activities for the mine region, the updated plan of activities including a second set of jobs, different from the first set of jobs, to be performed by the autonomous entities to provide a safe operation for the autonomous entities.

US Pat. No. 10,657,463

BOT-BASED DATA COLLECTION FOR DETECTING PHONE SOLICITATIONS

International Business Ma...

1. A method comprising:detecting an unsolicited phone call based on a real-time analysis of a conversation between a caller who initiated the unsolicited phone call and a bot, wherein the bot is configured to select a voice recording impersonating an individual belonging to a particular demographic targeted by the caller, and dynamically converse with the caller utilizing the selected voice recording; and
blocking the unsolicited phone call.

US Pat. No. 10,657,462

METHODS, SYSTEMS AND DEVICES FOR MONITORING AND CONTROLLING MEDIA CONTENT USING MACHINE LEARNING

1. A device, comprising:a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, comprising:
determining, by a machine learning application, that a first media content presented to a target user in a primary window on a display of a target user device does not conform to a group of control rules;
providing a selectable list of distraction media content to the target user device, wherein the selectable list of distraction media content is presented in a distraction window on the display while the first media content is being presented in the primary window; and
providing a selected distraction media content to the target user device in response to receiving a first user-generated input, wherein the first user-generated input comprises a selection of the selected distraction media content, wherein the selectable list of distraction media content comprises the selected distraction media content, wherein the selected distraction media content is presented in the primary window.

US Pat. No. 10,657,461

COMMUNICATION EFFICIENT FEDERATED LEARNING

Google LLC, Mountain Vie...

1. A computer-implemented method for communication efficient machine learning, the method comprising:obtaining, by a client computing device, global values for a set of parameters of a machine-learned model;
training, by the client computing device, the machine-learned model based at least in part on a local dataset to obtain an update matrix that is descriptive of updated values for the set of parameters of the machine-learned model, wherein the update matrix is restricted to be a low-rank matrix, and wherein the local dataset is stored locally by the client computing device; and
communicating, by the client computing device, information descriptive of the update matrix to a server computing device for use by the server computing device in computation of a global update to the machine-learned model, wherein:
training, by the client computing device, the machine-learned model based at least in part on the local dataset to obtain the update matrix comprises:
defining, by the client computing device, the update matrix as a product of a first matrix and a second matrix, wherein the first matrix comprises fixed values and the second matrix comprises optimizable variables, and wherein the fixed values of the first matrix are known to the server computing device; and
training, by the client computing device, machine-learned model based at least in part on the local dataset to obtain the second matrix; and
communicating, by the client computing device, information descriptive of the update matrix to the server computing device comprises communicating, by the client computing device, information descriptive of the second matrix to the server computing device without sending the first matrix from the client computing device to the server computing device.

US Pat. No. 10,657,460

SYSTEMS AND METHODS TO FACILITATE LOCAL SEARCHES VIA LOCATION DISAMBIGUATION

1. A method comprising:generating, by a first system comprising a processor, a location model, wherein generating the location model comprises
filtering a query log to identify first queries associated with locations without location ambiguity,
removing at least one respective component of each of the first queries to generate second queries having location ambiguity,
identifying location candidates for the second queries,
generating a training dataset based on comparing the locations without location ambiguity of the first queries and the location candidates for the second queries, and
applying a machine learning technique to the training dataset to generate the location model;
receiving, at a second system comprising a processor, a search query submitted by a searcher, the search query having location ambiguity;
identifying, by the second system, using the location model, an unambiguous location for the search query to resolve the location ambiguity, wherein parameters for generating the location model used to identify the unambiguous location for the search query comprise a distance between the searcher and the unambiguous location, a search hit value associated with the unambiguous location, and a number of businesses contained within the unambiguous location;
determining, by the second system, a search result corresponding to the unambiguous location identified for the search query; and
providing, by the second system, the search result as a response to the search query having the location ambiguity.

US Pat. No. 10,657,459

COORDINATED VERSION CONTROL SYSTEM, METHOD, AND RECORDING MEDIUM FOR PARAMETER SENSITIVE APPLICATIONS

INTERNATIONAL BUSINESS MA...

1. A coordinated version control system including a parameter server having a plurality of parameter sets and a plurality of learners communicating with the plurality of parameter sets, the system comprising:a leader parameter collecting circuit configured to collect parameter set data for a leader parameter set from the plurality of learners;
a follower parameter collecting circuit configured to collect parameter set data for a follower parameter set from the plurality of learners;
a leader aggregated parameter generating circuit configured to generate a new leader version of a leader aggregated parameter set based on the leader parameter set data;
an event broadcasting circuit configured to generate a broadcast event indicating that the new leader version of the leader aggregated parameter set has been generated;
a broadcast detecting circuit configured to detect the broadcast event;
a checking circuit configured to check if a version of the follower parameter set matches the new leader version of the leader aggregated parameter set based on the broadcast detecting circuit detecting the broadcast event; and
a follower aggregated parameter generating circuit configured to generate a new follower version of a follower aggregated parameter that matches the new leader version of the leader aggregated parameter set.

US Pat. No. 10,657,458

METHOD AND SYSTEM FOR FORECASTING

InMobi PTE LTD., Singapo...

1. A forecasting engine comprising:a processor; and
a memory, coupled to the processor, that includes code stored therein that is executable by the processor to implement:
a. a receiver configured to receive training data samples, wherein each sample consists of a set of input attributes and a target value;
b. a base learner model configured to, in accordance with an error function, generate predicted target values that predict the target value as a function of the input attributes and generates prediction errors representing errors between the predicted target values and the received target values;
c. the error function which generates the prediction errors and emphasizes each prediction error along a pre-configured preferred direction, wherein the direction is chosen in at least one of a positive and a negative direction as a sign between the predicted target value and the target value received with the training data samples and for each training data sample, the error function weights the prediction errors with greater weight for prediction errors in the pre-configured preferred direction;
d. an error determination module configured to apply the error function to determine the prediction error made by the base learner model on an independent test dataset;
e. an error minimization module configured to construct a new model which has a lesser prediction error than the base learner model, wherein:
the prediction error is defined by the error function that emphasizes minimization of the prediction error so that a predicted value is less than a true observed value; and
to construct the new model comprises:
differentiating the prediction error with respect to the base learner model to determine a derivative of the prediction error with respect to the base learner model; and
generating the new model by moving the base learner model in a direction against a direction of the derivative;
f. an iteration module configured to manage multiple iterations of the error determination module and the error minimization module, wherein the iteration module continues to iterate until further iterations of the prediction error of the new model is minimized; and
g. an error convergence module to provide the new model as the base learner model in element b. for construction of another model and provide the new model to a system to process data to generate results that trend to false negative over false positive results in accordance with the pre-configured preferred direction.

US Pat. No. 10,657,457

AUTOMATIC SELECTION OF HIGH QUALITY TRAINING DATA USING AN ADAPTIVE ORACLE-TRAINED LEARNING FRAMEWORK

GROUPON, INC., Chicago, ...

1. A computer-implemented method, comprising:receiving, by a processor, a feature representation of a multi-dimensional data instance having a particular data type and k features, wherein the feature representation includes the k features, each feature of the k features representing a value of a corresponding attribute of the multi-dimensional data instance;
calculating, by a processor and for each feature of the k features, a per operator estimate confidence value to produce a set of k per operator estimate confidence values, each per operator estimate confidence value associated with a unique operator estimate and representing a probability of the feature representation belonging to a specific distribution, each unique operator estimate associated with an operator powered by a statistical model and configured to clean data;
calculating, by a processor, an operator estimation score for the multi-dimensional data instance using the feature representation, the operator estimation score calculated based on the set of k per operator estimate confidence values and calculated using a trained per operator estimator;
calculating, by a processor and for each global data set of a set of n global data sets, a per data set global estimate confidence value to produce a set of n per data set global estimate confidence values, each per data set global estimate confidence value representing a probability of the feature representation belonging to a corresponding global distribution represented by the global data set;
calculating, by a processor, a global estimation score using the feature representation, the global estimation score calculated based on the set of n per data set global estimate confidence values;
updating, by the processor, at least one initial training data set with the multi-dimensional data instance upon determining that the multi-dimensional data instance will be included in the at least one initial training data set based on the operator estimation score and the global estimation score; and
deriving, by the processor, at least one model from the at least one initial training data set.

US Pat. No. 10,657,456

QUANTUM COMPUTING USING CHIRAL QUBITS

BROOKHAVEN SCIENCE ASSOCI...

1. An apparatus for performing quantum computing, the apparatus comprising:a plurality of qubits, each of at least a subset of the plurality of qubits comprising a loop formed of a Dirac or Weyl semimetal and having at least two stable quantum states; and
at least one terahertz cavity coupled with the plurality of qubits, the terahertz cavity being configured to detect the quantum states of the qubits;
wherein each of at least the subset of qubits is configured to receive a circularly polarized radiation source, the radiation source being adapted to excite a chiral current in each of at least the subset of qubits, the quantum states of the plurality of qubits being a function of the chiral current.

US Pat. No. 10,657,455

PROGRAMMABLE UNIVERSAL QUANTUM ANNEALING WITH CO-PLANAR WAVEGUIDE FLUX QUBITS

Google LLC, Mountain Vie...

1. A quantum computing device comprising:a plurality of co-planar waveguide flux qubits, wherein each co-planar waveguide flux qubit of the plurality of co-planar waveguide flux qubits comprises (a) a qubit quantum device and (b) an elongated thin film superconductor waveguide electrically coupled in parallel with the qubit quantum device;
a coupler element arranged such that a first co-planar waveguide flux qubit of the plurality of co-planar waveguide flux qubits is operatively couplable to a second co-planar waveguide flux qubit of the plurality of co-planar waveguide flux qubits,
wherein the coupler element comprises a thin film superconductor spaced apart from a first elongated thin film superconductor waveguide of the first co-planar waveguide flux qubit and spaced apart from a second elongated thin film superconductor waveguide of the second co-planar waveguide flux qubit to allow inductive coupling between the first co-planar waveguide flux qubit and the second co-planar waveguide flux qubit; and
a tuning quantum device comprising at least one Josephson junction, wherein the tuning quantum device is in electrical contact with the first co-planar waveguide flux qubit of the plurality of co-planar waveguide flux qubits and with the second co-planar waveguide flux qubit of the plurality of co-planar waveguide flux qubits, and wherein the tuning quantum device is operable to tune a magnitude of interactions between the first co-planar waveguide flux qubit and the second co-planar waveguide flux qubit.

US Pat. No. 10,657,454

METHODS AND APPARATUS TO PREDICT MACHINE FAILURES

1. An apparatus, comprising:a text miner to text mine first alert data to identify a first machine failure within the first alert data;
a failure alert sequence identifier to identify a first alert sequence associated with the first machine failure;
a conditional probability determiner to determine a conditional probability of the first alert sequence leading to failure based on i) a number of work machines in which the first alert sequence ended in failure and ii) a number of work machines in which the first alert sequence did not end in failure; and
a collator to update a model by correlating the first alert sequence with the first machine failure and first probable parts used to repair the first machine failure.

US Pat. No. 10,657,453

MALFUNCTION PREDICTION FOR COMPONENTS AND UNITS OF TECHNICAL ENTITIES

CASSANTEC AG, Zurich (CH...

1. Method for predicting a malfunction of a mechanical or electrical component of a unit comprising the steps of:measuring a current value of a parameter of the component;
in an apparatus, determining a conditional probability distribution of the parameter for a future point in time given the current value of the parameter based on the current value of the parameter;
in the apparatus, determining a conditional probability for a malfunction at the future point in time given the current value of the parameter based on the conditional probability distribution of the parameter for the future point in time given the current value of the parameter and on a conditional probability distribution for the malfunction given the parameter,
predicting the malfunction of the component on the basis of the conditional probability for a malfunction at the future point in time given the current value of the parameter, and
determining a probability for a malfunction of a unit comprising the component on the basis of the probability of the malfunction of the component and on the basis of probabilities of malfunction of other components of the unit.

US Pat. No. 10,657,452

DEVICE AND METHOD FOR ESTIMATING TRAVEL SPEED

Toyota Jidosha Kabushiki ...

1. A travel speed estimating device that estimates a travel speed of a mobile body, the travel speed estimating device comprising:a holding unit configured to hold map information, environment information associated with a map in the map information, and travel speed and time period that are associated with roads in the map information;
a subject road specifying unit configured to specify a subject road, which is subject to travel speed estimation, from the roads in the map information;
a dividing unit configured to divide the map in the map information into a plurality of sections;
a speed similarity degree calculating unit configured to calculate a speed similarity degree, which is a similarity degree of the travel speed associated with the subject road and the travel speed associated with each of the plurality of sections;
an environment similarity degree calculating unit configured to calculate an environment similarity degree, which is a similarity degree of the environment information corresponding to one of the plurality of sections including the subject road and the environment information corresponding to each of the plurality of sections;
a total similarity degree calculating unit configured to calculate a total similarity degree for each of the plurality of sections based on the calculated speed similarity degree and the environment similarity degree, wherein the total similarity degree calculating unit calculates the total similarity degree based on the speed similarity degree, the environment similarity degree, a weight coefficient applied to the speed similarity degree, and a weight coefficient applied to the environment similarity degree, and wherein the weight coefficient applied to the speed similarity degree and the weight coefficient applied to the environment similarity degree are based on a degree of importance placed on the travel speed and the environment information; and
an estimating unit configured to estimate the travel speed of the mobile body on the subject road when past accumulation of the travel speed associated with the subject road is insufficient to estimate the travel speed on the subject road, wherein the estimating unit selects a section similar to the section including the subject road from the plurality of sections based on the total similarity degree, and the estimating unit sets the travel speed associated with the selected section as a travel speed of a corresponding time period on the subject road.

US Pat. No. 10,657,451

PATTERN RECOGNITION SYSTEM

Rokio, Inc., Kentfield, ...

1. A pattern recognition system comprising:one or more memories configured to maintain a knowledge element array; and logic configured to:
present a graphical user interface (GUI) in which waveform data are depicted, the waveform data being a digital representation of a waveform;
provide a tool accessible via the GUI by which a user may graphically select portions of the waveform data;
receive input representing use of the tool in the GUI to graphically select a portion of the waveform data having a pattern of interest;
responsive to the input, automatically extract one or more waveform characteristics from the portion of the waveform data;
create a pattern definition based on the one or more waveform characteristics; generate one or more knowledge elements based on the pattern definition for inclusion in the knowledge element array, each knowledge element comprising i) one or more operands collectively defining a data vector representing the pattern of interest and ii) a category identifier;
define a region of search relative to an occurrence in the waveform data of at least one of the waveform characteristics, each occurrence of the region of search representing a data range within the waveform data in which to search for the pattern of interest;
identify a dithered pattern that falls entirely outside the region of search;
generate a dithered knowledge element based on the dithered pattern;
identify an occurrence of the region of search based on a corresponding occurrence of the at least one of the waveform characteristics;
select a portion of the waveform data based on the occurrence of the region of search;
generate input vectors from the portion of the waveform data;
search for the pattern of interest by performing a pattern recognition operation on the input vectors generated from the portion of the waveform data by comparing the input vectors to the one or more knowledge elements of the knowledge element array, and by comparing the input vectors to the dithered knowledge element, wherein one or more portions of the waveform data are excluded from the pattern recognition operation based on the occurrence of the region of search;
identify an occurrence of the pattern of interest based on the pattern recognition operation; and
present a representation of the identified occurrence of the pattern of interest in the GUI.

US Pat. No. 10,657,450

SYSTEMS AND METHODS FOR MACHINE DIAGNOSTICS BASED ON STORED MACHINE DATA AND AVAILABLE MACHINE TELEMATIC DATA

1. A machine diagnostics system used for monitoring and servicing a machine using a machine telematics system, the machine diagnostics system comprising:a communication transceiver configured to receive from the machine telematics system sensor data recorded during routine operation of a first machine of a plurality of monitored machines by sensors equipped on the first machine;
a non-transitory computer-readable memory storing machine information for the plurality of monitored machines and received sensor data from the first machine, the machine information including at least one from a group consisting of hardware configuration information, area of use information, and historical service information for each of the plurality of machines;
an automated planning system server coupled to the non-transitory computer-readable memory and the communication transceiver, the automated planning system server configured to
receive an indication of a service issue for the first machine of the plurality of machines;
automatically analyze the stored sensor data for the first machine,
automatically generate a list of identified conditions for the first machine based at least in part on the analysis of the sensor data for the first machine,
automatically generate an ordered list of diagnostic procedures to be performed during a servicing of the first machine to address the indicated service issue, wherein the ordered list includes a plurality of diagnostic procedures to address the indicated service issue, and wherein the automated planning system server is configured to generate the ordered list of diagnostic procedures by arranging the diagnostic procedures of the plurality of diagnostic procedures in a prioritized order based at least in part on the stored machine information for the first machine and the identified conditions of the first machine,
wherein the automated planning system is further configured to automatically generate a second ordered list of diagnostic procedures to be performed during a separate service call for a second machine of the plurality of machines by arranging the plurality of diagnostic procedures in a different prioritized order based on the stored machine information for the second machine and not based on any measured data received from any machine telematics system for the second machine, wherein the second machine is not equipped with a machine telematics system of the second machine.

US Pat. No. 10,657,449

SYSTEM AND METHOD FOR LOAD DISTRIBUTION IN A NETWORK

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

1. A method of distributing access requests among a plurality of data sources by a computer backend machine of a computer network, the method comprising:providing a target value of a statistical indicator to the computer backend machine, wherein the statistical indicator is indicative of data accesses to a given data source among the plurality of data sources, and wherein at least two data sources among the plurality of data sources have different accuracy levels;
associating to the computer backend machine a decision rule associated with cache updates;
observing a current value of the statistical indicator by an observer of the computer backend machine;
dynamically re-computing the decision rule upon detecting that the observed current value of the statistical indicator differs from the target value of the statistical indicator; and
distributing the access requests among the plurality of data sources with the computer backend machine based on the re-computed decision rule.

US Pat. No. 10,657,448

DEVICES AND METHODS TO NAVIGATE IN AREAS USING A MACHINE LEARNING MODEL

1. A method of planning movement of a person in an area comprising:operating a machine learning system implemented on a first processor with a machine learning model, wherein:
(a) the model has been pre-trained in a first step on a second processor with data concerning at least one of layout of areas of potential movement of persons and methods of movement of persons in areas of potential movement of persons
(b) the model has been transferred to one of the first processor and a third processor subsequent to the first step and prior to entry into the area by the person;
(c) the model has been trained in a second step subsequent to the transfer and subsequent to entry into the area by the person on one of the first processor and the third processor with data gathered subsequent to the entry with a sensor concerning at least one of a location of objects in the area, conditions in the area, and behavior of persons attempting to move in the area;
(d) the first processor has a memory containing a program to use the machine learning model to produce subsequent to the second step a plan to move in the area subsequent to the entry into the area; and
(e) guiding the person using an output device in moving in the area in accordance with the plan.

US Pat. No. 10,657,447

AUTOMATED MODEL BUILDING SEARCH SPACE REDUCTION

SPARKCOGNITION, INC., Au...

1. A method of neural network generation, the method comprising:receiving, by a processor, an input data set, the input data set including a plurality of features;
determining, by the processor, one or more characteristics of the input data set;
based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process, wherein the automated model generation process is configured to generate a plurality of models using a weighted randomization process, wherein the one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features, and wherein adjusting the one or more architectural parameters includes setting a first architectural parameter to a first value, the first architectural parameter associated with a probability that models of a first epoch of the weighted randomization process have a first model type; and
executing, by the processor, the automated model generation process to output a model, the model including data representative of a neural network.

US Pat. No. 10,657,446

SPARSITY ENFORCING NEURAL NETWORK

Mitsubishi Electric Resea...

1. A computer implemented image reconstruction system for reconstructing images from data acquired by at least one sensor that is one of an optical sensor, LIDAR sensor or radar sensor, wherein an input interface receives the data that includes measurements of a scene, comprising:a sparsity enforcing neural network (SENN), includes a first subset of weights indicative of elements of an observation matrix representing physics of a structure of the at least one sensor and a second subset of weights, wherein the SENN is formed by layers of nodes propagating messages through the layers, at least one node of the SENN modifies an incoming message with a non-linear function to produce an outgoing message and propagates the outgoing message to another node of the SENN, such that the non-linear function is a dual-projection function that limits the amplitude of the incoming message if the incoming message exceeds a threshold, wherein the SENN is trained to enforce the sparsity of transform domain coefficients of the reconstructed image, where the transform domain coefficients are duals of the outgoing messages between the nodes of the SENN, such that the transform domain coefficients are determined from second subset of the trained weights D, the outgoing messages g, and the estimate of the reconstructed image z, such that, the determining of the transform domain coefficients are obtained by the mathematical relation D(DTg?z), and wherein the SENN is trained to reconstruct an image of the scene from the measurements of the scene;
a processor in communication with the input interface, to process the measurements with the SENN to reconstruct the image of the scene; and
an output interface in communication with the processor to render the reconstructed image of the scene.

US Pat. No. 10,657,445

SYSTEMS AND METHODS FOR TRAINING AND EXECUTING A NEURAL NETWORK FOR COLLABORATIVE MONITORING OF RESOURCE USAGE

Capital One Services, LLC...

1. A computer system for training and executing a neural network for collaborative monitoring of resource usage metrics, the system comprising:a memory having processor-readable instructions stored therein; and
at least one processor configured to access the memory and execute the processor-readable instructions, which when executed by the processor configures the processor to perform a plurality of functions, including functions for:
receiving or generating a plurality of user data sets, wherein each user data set of the plurality of user data sets comprises a user identification data of a user and a detailed user data of the user;
grouping the plurality of the user data sets into one or more clusters of user data sets based on criteria that is independent of fiscal decision behavior qualities of the user;
grouping each of the one or more clusters into a plurality of subclusters based on criteria associated with fiscal decision behavior qualities of the user;
for each of the plurality of subclusters, training the neural network to associate the subcluster with one or more sequential patterns found within the subcluster, based on the user data sets in the subcluster, to generate a trained neural network;
grouping the plurality of user data sets into a plurality of teams, each team in the plurality of teams including a plurality of teamed user data sets among the plurality of user data sets;
receiving a first series of transactions of a first user, the first user corresponding to a first teamed user data set included in the plurality of teamed user data sets in a first team among the plurality of teams, and the first series of transactions including one or more transactions performed by the first user;
inputting the first series of transactions into the trained neural network;
classifying, using the trained neural network, the first user into a subcluster among the plurality of subclusters, based on the first series of transactions input into the trained neural network, to generate a classified subcluster of the first user;
based on the classified subcluster of the first user, generating a metric associated with the first series of transactions;
generating a recommendation to the first user, the recommendation requesting the first user to enter the metric associated with the first series of transactions for updating one or more team metrics associated with the first team;
updating a team standing associated with the first team based on the metric associated with the first series of transactions; and
transmitting the updated team standing to the plurality of teams upon the first user entering the metric associated with the first series of transactions.

US Pat. No. 10,657,444

DEVICES AND METHODS USING MACHINE LEARNING TO REDUCE RESOURCE USAGE IN SURVEILLANCE

7. A method of making observations comprising:a) making a first observation of an object using a sampling sensor at a coarse level of granularity and a low sampling density chosen to conserve a resource;
b) using a processor with a machine learning program with a machine learning model trained to use the first observation to determine the need to make a second observation at a finer level of granularity and at a higher sampling density than the first observation wherein the second observation requires a greater use of the resource than the first observation, and
c) making an observation of the object using a sampling sensor at the finer level of granularity and at the higher sampling density.

US Pat. No. 10,657,443

DETECTION OF HAZARDOUS LEAKS FROM PIPELINES USING OPTICAL IMAGING AND NEURAL NETWORK

Southwest Research Instit...

1. A method of training a learning machine to detect spills of hydrocarbon liquids from pipelines, comprising:collecting samples of a number of different ground materials;
collecting samples of a number of hydrocarbon materials that are or become liquid when spilled from a pipeline;
for each hydrocarbon material, simulating a spill on each ground material, thereby providing a collection of spill samples;
for each spill sample, performing the following steps: using a thermal camera to capture a thermal image of the spill sample; using a visible wavelength camera to capture a red, blue, green (RGB) image of the spill sample; fusing the thermal image and the RGB image, thereby providing a fused image; inputting the fused image to a neural network, comparing the output of the neural network to at least one hydrocarbon classification represented by the fused image, and adjusting the neural network to provide output data that more closely matches the hydrocarbon identifier.

US Pat. No. 10,657,442

DEEP LEARNING ACCELERATOR ARCHITECTURE WITH CHUNKING GEMM

INTERNATIONAL BUSINESS MA...

1. A method comprising:configuring a compute matrix comprising a set of compute units wherein each compute unit comprises a multiplier and an accumulator, each of the multiplier and the accumulator formed using at least one floating point unit (FPU);
configuring an accumulator array comprising a set of external accumulators;
operating the compute matrix to produce a chunk dot-product using a first chunk of a first input vector and a first chunk of a second input vector;
operating the accumulator array to output a dot-product of the first input vector and the second input vector using the chunk dot-product;
chunking the first input vector into a first set of chunks, each chunk in the first set of chunks including a non-overlapping subset of values from a first set of values in the first input vector, wherein the first set of chunks includes the first chunk of the first input vector; and
chunking the second input vector into a second set of chunks, each chunk in the second set of chunks including a non-overlapping subset of values from a second set of values in the second input vector, wherein the second set of chunks includes the first chunk of the second input vector.

US Pat. No. 10,657,441

MODEL GENERATION FOR REAL-TIME RATE OF PENETRATION PREDICTION

Landmark Graphics Corpora...

1. A method, comprising:receiving raw data sets comprising dynamic data and static data, wherein the dynamic data comprises drilling parameter and operating condition values generated during subterranean drilling operations, wherein the static data is indicative of one or more types of the subterranean drilling operations that generated the dynamic data;
separating the raw data sets into training data sets based, at least in part, on the one or more types of the subterranean drilling operations identified in the static data of the raw data sets;
generating at least one predictive model based, at least in part, on at least one training data set of the training data sets, wherein the at least one predictive model determines a rate of penetration (ROP) for the one or more types to which the at least one training data set corresponds, wherein generating the at least one predictive model comprises for each training data set of the training data sets generating a different context-specific predictive model associated with the static data used to generate the at least one predictive model.

US Pat. No. 10,657,440

OPTICAL SYNAPSE FOR NEUROMORPHIC NETWORKS

INTERNATIONAL BUSINESS MA...

1. A neuromorphic network, comprising:a first node configured to transmit a first optical signal;
a second node configured to transmit a second optical signal;
a waveguide optically connecting the first node to the second node; and
an integrated optical synapse located on the waveguide between the first node and the second node, the optical synapse comprising an optical property that is configured to change a strength of an optical connection between the first node and the second node based on a correlation between the first optical signal and the second optical signal; and
a first detector configured to receive a portion of the first optical signal and a second detector configured to receive a portion of the second optical signal, wherein the first detector and the second detector are configured to transmit signals to the optical synapse such that the optical property of the optical synapse changes based on the signals from the first detector and the second detector,
wherein based on a determination that the correlation is strong, the strength of the optical connection between the first node and the second node is increased and based on a determination that the correlation is weak, the strength of the optical connection between the first node and the second node is decreased.

US Pat. No. 10,657,439

PROCESSING METHOD AND DEVICE, OPERATION METHOD AND DEVICE

SHANGHAI CAMBRICON INFORM...

1. An operation device, comprising:an instruction control unit configured to decode a received instruction and generate lookup control information; and
a lookup table unit configured to identify output neurons in an operation codebook according to the lookup control information and a received weight dictionary, a neuron dictionary, an operation codebook, weights, and input neurons, wherein the instruction is a neural network-dedicated instruction, and the neural network-dedicated instruction includes:
a control instruction configured to control a neural network execution process;
a data transfer instruction configured to complete data transfer between different storage media, a data format including a matrix, a vector, and a scalar;
an computation instruction configured to complete arithmetic operation of a neural network and including a matrix computation instruction, a vector computation instruction, a scalar computation instruction, a convolutional neural network computation instruction, a fully connected neural network computation instruction, a pooling neural network computation instruction, a Restricted Boltzmann Machine (RBM) neural network computation instruction, a Local Response Normalization (LRN) neural network computation instruction, a Local Response Normalization (LRN) neural network computation instruction, a Long Short-Term Memory (LSTM) neural network computation instruction, a Recurrent Neural Networks (RNN) computation instruction, a rectified linear unit (ReLU) neural network computation instruction, a parametric rectified linear unit (PReLU) neural network computation instruction, a sigmoid neural network computation instruction, a tan h neural network computation instruction, and a maxout neural network computation instruction; and
a logical instruction configured to complete logical operation of the neural network and including a vector logical computation instruction and a scalar logical computation instruction.

US Pat. No. 10,657,438

BACKPRESSURE FOR ACCELERATED DEEP LEARNING

Cerebras Systems Inc., L...

1. A method comprising:managing a plurality of virtual input queues of a first processing element having a first coupling to a fabric, each virtual input queue enabled to store a respective number of fabric packets received via the fabric, the first coupling associated with a plurality of fabric virtual channels each associated with one of the virtual input queues;
managing a plurality of backpressure indicators, each backpressure indicator associated with a respective one of the fabric virtual channels and enabled to selectively indicate one of a stall state and a ready state, each respective backpressure indicator set to the ready state when the virtual input queue associated with the fabric virtual channel associated with the respective backpressure indicator holds less than a respective threshold number of fabric packets and otherwise set to the stall state;
transmitting the backpressure indicators via the first coupling to the fabric and through routing paths enabled by the fabric and determinable at least in part by referencing information identified by fabric virtual channel identifiers respectively associated with each of the fabric virtual channels and wherein each of the fabric packets comprises a respective instance of one of the fabric virtual channel identifiers;
receiving the backpressure indicators via the fabric at a second processing element, the second processing element comprising a second coupling to the fabric, the second coupling associated with the fabric virtual channels; and
in the second processing element and responsive to ones of the received backpressure indicators in the stall state, stalling transmission associated with the fabric virtual channels associated with the ones of the received backpressure indicators in the stall state, the stalling transmission being with respect to fabric packets from the second processing element destined for the first processing element.

US Pat. No. 10,657,437

TRAINING OF FRONT-END AND BACK-END NEURAL NETWORKS

International Business Ma...

1. A computer-implemented method for training a front-end neural network and a back-end neural network, the method comprising:combining the back-end neural network with the front-end neural network so that an output layer of the front-end neural network is also an input layer of the back-end neural network to form a joint layer to thereby generate a combined neural network; and
training the combined neural network for a speech recognition with a set of utterances as training data, wherein the joint layer comprises a plurality of frames and each frame comprises a plurality of bins, and wherein one or more specific units in each frame are dropped during the training, each of the specific units being selected randomly or based on a bin number to which the respective unit is set within its frame, the plurality of the specific units corresponding to one or more common frequency bands.

US Pat. No. 10,657,436

GENERATIVE NEURAL NETWORKS

DeepMind Technologies Lim...

1. A neural network system implemented by one or more computers, the neural network system comprising:a recurrent neural network that is configured to, for each time step of a predetermined number of time steps, receive a set of latent variables for the time step and process the set of latent variables to update a hidden state of the recurrent neural network; and
a generative subsystem that is configured to:
receive one or more context images;
for each time step of the predetermined number of time steps:
generate the set of latent variables for the time step from the one more context images and provide the set of latent variables as input to the recurrent neural network;
update a hidden canvas using the updated hidden state of the recurrent neural network; and
for a last time step of the predetermined number of time steps:
generate an output image using the updated hidden canvas for the last time step.

US Pat. No. 10,657,435

PROCESSING INPUTS USING RECURRENT NEURAL NETWORKS

Google LLC, Mountain Vie...

1. A method for processing an input sequence using a recurrent neural network to generate an output for the input sequence, the method comprising:receiving the input sequence;
generating a doubled sequence comprising a first instance of the input sequence followed by a second instance of the input sequence, wherein generating the doubled sequence comprises concatenating the first instance of the input sequence and the second instance of the input sequence; and
processing the doubled sequence using the recurrent neural network to generate the output for the input sequence.

US Pat. No. 10,657,434

ANOMALY SCORE ADJUSTMENT ACROSS ANOMALY GENERATORS

Intellective Ai, Inc., D...

1. A computer-implemented method for anomaly detection, the method comprising:executing a neuro-linguistic model to generate a raw unusualness score based on input data obtained from at least one of a video data source, a supervisory control and data acquisition (SCADA) system, or a data network security system, the raw unusualness score indicating how often a characteristic is observed in the input data;
comparing the raw unusualness score with an unusualness score model to generate an unusualness score, the unusualness score model produced from historical raw unusualness scores;
comparing the unusualness score with an anomaly score model to generate an anomaly score that represents, as a percentile, an unusualness of the input data, the anomaly score model produced from historical unusualness scores; and
sending alert data based on the anomaly score.

US Pat. No. 10,657,433

BALE IDENTIFICATION ASSEMBLY FOR BINDING AN IDENTIFICATION TAG TO A BALE OF AGRICULTURAL CROP MATERIAL

AGCO Corporation, Duluth...

1. A bale identification assembly for use with an agricultural baler used to take loose crop material from the ground into bales and compress a formed bale in a baling chamber with a reciprocating plunger, the baler having at least one crop sensor and/or bale sensor configured to sense a parameter of the crop material or formed bale, and a discharge chute at the rear end of the bale-forming chamber through which a completed bale is discharged, the bale identification assembly comprising:a knotter system that guides binding material around a formed bale and ties a knot in the binding material to bind the formed bale, the knotter system comprising at least one supply roll used to provide binding material used to bind the formed bale wherein the binding material on the one supply roll has identification tags at spaced intervals, wherein the binding material on the first at least one supply roll comprises at least one strand of a non-identifying filament and one strand of an identifying filament incorporating the identification tags, wherein the non-identifying filament and the identifying filament are wound together before the binding material is incorporated onto the first at least one supply roll;
a read module with an antenna configured to transmit interrogator signals and also receive authentication replies from identification tags;
a bale drop sensor comprising a bale activation device, wherein as a completed bale passes through the discharge chute, the completed bale interacts with the bale activation device causing the antenna to activate for a specified active cycle, and wherein during its active cycle, the read module assigns any identification tag that is sensed by the read module to the completed bale that is leaving the discharge chute; and
a controller configured to receive information from the at least one crop sensor and/or bale sensor and associate the information about the completed bale with the identification tag on the completed bale that is leaving the discharge chute.

US Pat. No. 10,657,432

SYSTEM AND METHOD FOR MODIFYING RFID TAGS

KONICA MINOLTA LABORATORY...

1. A method for modifying at least one RFID tag comprising a chip on a first side of a substrate and an antenna configured to transmit data from the chip, the RFID tag having an initial transmission range, the method comprising:modifying the RFID tag to have a modified transmission range, the modifying performed by printing a modification element over the antenna of the RFID tag, the modified transmission range being greater than or less than the initial transmission range.

US Pat. No. 10,657,431

ENERGY HARVESTING RFID CIRCUIT, ENERGY HARVESTING RFID TAG, AND ASSOCIATED METHODS

LENLOCK HOLDINGS, LLC, W...

1. An energy harvesting circuit, comprising:a radio-frequency identification (RFID) transponder chip configured to:
receive an interrogation request signal, and
produce an activation signal,
at least one capacitor configured to store and output a harvested voltage from a harvested energy;
a boost converter configured to boost the harvested voltage to a boosted voltage; and
a switch configured to receive the activation signal produced by the RFID transponder chip and to activate the boost converter when the activation signal is received by the switch and the harvested voltage is equal to or greater than a first threshold.

US Pat. No. 10,657,430

ONION LAYER ENCRYPTION SCHEME FOR SECURE MULTI-ACCESS WITH SINGLE CARD

Carrier Corporation, Pal...

1. A magnetic strip card of less than several hundred bits, comprising:a card payload with a code key of an access control encrypted with a short key to generate a partial encrypted card payload, the partial encrypted card payload encrypted with a long shared key to provide a final encrypted payload.

US Pat. No. 10,657,429

IMAGE FORMING APPARATUS AND CONTROL METHOD

KABUSHIKI KAISHA TOSHIBA,...

1. A data read/write apparatus for a wireless tag, comprising:a sheet conveyer configured to convey a sheet;
a tag reader/writer configured to read tag information stored in a wireless tag on the sheet and to write tag information to the wireless tag;
a read/write controller configured to control the tag reader/writer to read tag information stored in the wireless tag and to write tag information to the wireless tag; and
a sheet conveyance controller configured to control a conveyance speed of the sheet according to a total number of wireless tags on the sheet.

US Pat. No. 10,657,428

IMAGE PROCESSING UNIT, IMAGE FORMING APPARATUS, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM

SHARP KABUSHIKI KAISHA, ...

1. An image processing unit comprising:an image processor that functions as:
a line width determination device that detects line widths of a manuscript image in which the line widths are different between a vertical line and a horizontal line and determines which of the vertical line and the horizontal line is thinner; and
an emphasizing processor that executes an emphasizing process to make a first widening ratio of a thinner line of the vertical line and the horizontal line higher than a second widening ratio of the other line; wherein
the first widening ratio is a ratio by which the line width of the thinner line of the vertical line and the horizontal line is thickened; and
the second widening ratio is a ratio by which the line width of the other line is thickened.

US Pat. No. 10,657,427

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD AND STORAGE MEDIUM

Canon Kabushiki Kaisha, ...

1. An information processing apparatus comprising:a memory that stores a program; and
a processor that executes the program to perform generating PDL data by:
calculating, in a case where a drawing-target object within XPS format drawing data is a text-attribute character object that is drawn by using a font, a first character advance width from font data installed in the information processing apparatus; and
performing rendering for the XPS format drawing data by using the calculated first character advance width instead of a second character advance width described in the XPS format drawing data.

US Pat. No. 10,657,426

ACCELERATING LONG SHORT-TERM MEMORY NETWORKS VIA SELECTIVE PRUNING

Samsung Electronics Co., ...

1. A method for performing machine learning in a first neural network comprising one or more long short-term memory cells, a first long short-term memory cell of the one or more long short-term memory cells comprising:an input having a first weight matrix Wc;
an input gate having a first weight matrix Wi;
a forget gate having a first weight matrix Wf; and
an output gate having a first weight matrix Wo,
the method comprising:
maintaining the first weight matrix Wc unchanged; and
pruning the first weight matrix Wf, the pruning of the first weight matrix Wf comprising:
calculating a standard deviation over a subset of elements of the first weight matrix Wf;
determining that a first element, at a first position in the first weight matrix Wf, fails to meet a first threshold, the first threshold being based on a second threshold and the standard deviation;
setting to zero the first element, at the first position in the first weight matrix Wf, based on determining that the first element, at the first position in the first weight matrix Wf, fails to meet the first threshold;
determining that a second element, at a second position in the first weight matrix Wf, meets the first threshold; and
maintaining the second element unchanged, based on determining that the second element, at the second position in the first weight matrix Wf, meets the first threshold.

US Pat. No. 10,657,425

DEEP LEARNING ARCHITECTURES FOR THE CLASSIFICATION OF OBJECTS CAPTURED WITH A LIGHT-FIELD CAMERA

Ricoh Company, Ltd., Tok...

1. A method implemented on a computer system comprising a processor, the processor executing instructions to effect a method for classifying an object, the method comprising:receiving a light-field image of the object, the light-field image comprising a plurality of views of the object taken simultaneously from different viewpoints;
pre-processing the light-field image to produce derivative image data, the pre-processing comprising:
determining masking to select regions of interest within the light-field image, and
applying the masking; and
applying the derivative image data as input to a deep learning model, the deep learning model producing a decision classifying the object, wherein producing the decision classifying the object comprises:
the deep learning model producing a plurality of intermediate decisions classifying the object; and
applying a voting schema to the intermediate decisions to produce the decision classifying the object.

US Pat. No. 10,657,424

TARGET DETECTION METHOD AND APPARATUS

Samsung Electronics Co., ...

1. A method of detecting a target, the method comprising:generating an image pyramid based on an image on which a detection is to be performed;
classifying a plurality of candidate areas in the image pyramid using a cascade neural network; and
determining a target area corresponding to a target included in the image based on the plurality of candidate areas,
wherein the cascade neural network comprises a plurality of neural networks, and at least one neural network among the plurality of neural networks comprises a plurality of parallel sub-neural networks.

US Pat. No. 10,657,423

METHODS FOR USING FEATURE VECTORS AND MACHINE LEARNING ALGORITHMS TO DETERMINE DISCRIMINANT FUNCTIONS OF MINIMUM RISK LINEAR CLASSIFICATION SYSTEMS

1. A computer-implemented method of using feature vectors and machine learning algorithms to determine a discriminant function of a minimum risk linear classification system that classifies said feature vectors into two classes and using said discriminant function of said minimum risk linear classification system to classify unknown feature vectors related to said feature vectors, said method comprising:receiving an N×d data set of feature vectors within a computer system, wherein N is a number of feature vectors, d is a number of vector components in each feature vector, and each one of said N feature vectors is labeled with information that identifies which of two classes each one of said N feature vectors belongs to, and wherein each said feature vector is defined by a d-dimensional vector of numerical features, wherein said numerical features are extracted from digital signals;
receiving within said computer system unknown feature vectors related to said data set;
determining a Gram matrix using said data set, said determination of said Gram matrix being performed by using processors of said computer system to calculate a matrix of all possible inner products of signed said N feature vectors, wherein each one of said N feature vectors has a sign of +1 or ?1 that identifies which of said two classes each one of said N feature vectors belongs to, and using said processors of said computer system to calculate a regularized Gram matrix from said Gram matrix;
determining scale factors of a geometric locus of signed and scaled extreme points using said regularized Gram matrix, wherein said extreme points are located within overlapping regions or near tail regions of distributions of said N feature vectors, said determination of said scale factors being performed by using said processors of said computer system to determine a solution of a dual optimization problem, wherein said scale factors and said geometric locus satisfy a system of fundamental locus equations of binary classification, subject to geometric and statistical conditions for a minimum risk linear classification system in statistical equilibrium, and wherein said scale factors determine conditional densities for said extreme points and also determine critical minimum eigenenergies exhibited by scaled extreme vectors on said geometric locus, wherein said critical minimum eigenenergies determine conditional probabilities of said extreme points and also determine corresponding counter risks and risks of a minimum risk linear classification system, wherein said counter risks are associated with right decisions and said risks are associated with wrong decisions of said minimum risk linear classification system, and wherein said geometric locus determines the principal eigenaxis of the decision boundary of said minimum risk linear classification system, wherein said principal eigenaxis exhibits symmetrical dimensions and density, wherein said conditional probabilities and said critical minimum eigenenergies exhibited by said minimum risk linear classification system are symmetrically concentrated within said principal eigenaxis, and wherein counteracting and opposing components of said critical minimum eigenenergies exhibited by said scaled extreme vectors on said geometric locus together with said corresponding counter risks and risks exhibited by said minimum risk linear classification system are symmetrically balanced with each other about the geometric center of said principal eigenaxis, wherein the center of total allowed eigenenergy and minimum expected risk of said minimum risk linear classification system is located at the geometric center of said geometric locus, and wherein said geometric locus determines a primal representation of a dual locus of likelihood components and principal eigenaxis components, wherein said likelihood components and said principal eigenaxis components are symmetrically distributed over either side of the axis of said dual locus, wherein a statistical fulcrum is placed directly under the center of said dual locus, and wherein said likelihood components of said dual locus determine conditional likelihoods for said extreme points, and wherein said principal eigenaxis components of said dual locus determine an intrinsic coordinate system of geometric loci of a linear decision boundary and corresponding decision borders that jointly partition the decision space of said minimum risk linear classification system into symmetrical decision regions;
determining said extreme vectors on said geometric locus using the vector of said scale factors, said determination of said extreme vectors being performed by using said processors of said computer system to identify said scale factors that exceed zero by a small threshold, and using said processors of said computer system to determine a sign vector of signs associated with said extreme vectors using said data set, and compute the average sign using said sign vector;
determining a locus of average risk for said minimum risk linear classification system using said extreme vectors, said determination of said locus of average risk being performed by using said processors of said computer system to calculate the average vector of said extreme vectors;
determining said geometric locus, said determination of said geometric locus being performed by using said processors of said computer system to calculate a matrix of inner products between said signed said N feature vectors and said unknown feature vectors, and multiply said matrix by said vector of scale factors;
determining the discriminant function of said minimum risk linear classification system, using said locus of aggregate risk and said average sign and said geometric locus, said determination of said discriminant function of said minimum risk linear classification system being performed by using said processors of said computer system to subtract said locus of aggregate risk from sum of said geometric locus and said average sign, wherein said discriminant function of said minimum risk linear classification system satisfies said system of fundamental locus equations of binary classification, and wherein said discriminant function of said minimum risk linear classification system determines likely locations of said N feature vectors and also determines said geometric loci of said linear decision boundary and said corresponding decision borders that jointly partition said extreme points into said symmetrical decision regions, wherein said symmetrical decision regions span said overlapping regions or said tail regions of said distributions of said N feature vectors, and wherein said discriminant function of said minimum risk linear classification system satisfies said linear decision boundary in terms of a critical minimum eigenenergy and said minimum expected risk, wherein said counteracting and opposing components of said critical minimum eigenenergies exhibited by said scaled extreme vectors on said geometric locus associated with said corresponding counter risks and risks exhibited by said minimum risk linear classification system are symmetrically distributed over said axis of said dual locus, on equal sides of said statistical fulcrum located at said geometric center of said dual locus, wherein said counteracting and opposing components of said critical minimum eigenenergies together with said corresponding counter risks and risks exhibited by said minimum risk linear system are symmetrically balanced with each other about said geometric center of said dual locus, and wherein said statistical fulcrum is located at said center of said total allowed eigenenergy and said minimum expected risk of said minimum risk linear classification system, wherein said minimum risk linear classification system satisfies a state of statistical equilibrium, wherein said total allowed eigenenergy and said expected risk of said minimum risk linear classification system are minimized, and wherein said minimum risk linear classification system exhibits the minimum probability of error for classifying said N feature vectors that belong to said two classes and said unknown feature vectors related to said data set, wherein said distributions of said feature vectors have similar covariance matrices;
determining which of said two classes said unknown feature vectors belong to using said discriminant function of said minimum risk linear classification system, said determination of said classes of said unknown feature vectors being performed by using said processors of said computer system to apply said discriminant function of said minimum risk linear classification system to said unknown feature vectors, wherein said discriminant function determines likely locations of said unknown feature vectors and identifies said decision regions related to said two classes that said unknown feature vectors are located within, wherein said discriminant function recognizes said classes of said unknown feature vectors, and wherein said minimum risk linear classification system decides which of said two classes said unknown feature belong to and thereby classifies said unknown feature vectors.

US Pat. No. 10,657,422

METHODS AND SYSTEMS FOR HYPER-SPECTRAL SYSTEMS

THE BOEING COMPANY, Chic...

9. A method, said method implemented using a hyperspectral analysis computer device, said hyperspectral analysis computer device comprising a processor in communication with a memory, said method comprising:storing, in the memory, a plurality of spectral analysis data;
receiving first input data indicative of at least one background item and at least one item to be detected;
generating, by the processor, one or more spectral bands for analysis based on the at least one background item, the at least one item to be detected, and the stored plurality of spectral analysis data;
receiving second input data indicative of one or more mission parameters;
comparing, by the processor, the one or more mission parameters to the generated one or more spectral bands to determine whether the at least one item will be detected; and
generating, by the processor, a plurality of images based on a distribution of simulated individual pixel measurements associated with the one or more mission parameters, wherein the plurality of images comprise a plurality of random pixel mixtures associated with the at least one background item to train a program to recognize the at least one item to detect.

US Pat. No. 10,657,421

SHAPE DETECTION

Morpho Trust USA, LLC, B...

1. A computer-implemented method comprising:receiving, by a computing device, an image;
generating, by the computing device, a shape of an object to detect in the image;
identifying, by the computing device and in the image, edges that are parallel to a side of the shape and that are within a threshold distance of the side of the shape;
determining, by the computing device, a contrast of each edge;
based on the contrast of each edge, selecting, by the computing device and from among the edges, a plurality of edges;
determining, by the computing device, a plurality of candidate objects that are defined by the plurality of edges;
comparing, by the computing device, each candidate object of the plurality of objects to the shape of the object to detect in the image; and
based on comparing each candidate object of the plurality of objects to the shape of the object to detect in the image, selecting, by the computing device, a candidate object as the object to detect in the image.

US Pat. No. 10,657,420

MODELING POST-LITHOGRAPHY STOCHASTIC CRITICAL DIMENSION VARIATION WITH MULTI-TASK NEURAL NETWORKS

International Business Ma...

1. A method of modeling distributions of post-lithography critical dimensions, comprising:generating a plurality of aerial images of respective portions of a physical design layout of a semiconductor wafer;
employing the plurality of aerial images as training data;
generating a first portion of a neural network architecture, wherein the first portion comprises a neural network which is shared by a plurality of output channels;
generating a second portion of the neural network architecture, wherein the second portion comprises a plurality of neural networks, each of the plurality of neural networks respectively corresponding to one of the plurality of output channels;
training the first and second portions of the neural network architecture with the training data; and
outputting the distributions of the post-lithography critical dimensions based on the plurality of output channels;
wherein the method is performed by at least one computer system comprising at least one memory and at least one processor coupled to the memory.

US Pat. No. 10,657,419

MACHINE VISION AND ROBOTIC INSTALLATION SYSTEMS AND METHODS

The Boeing Company, Chic...

1. A robotic installation method, comprising:performing an automated machine vision method for determining if an object within a work field has one or more predetermined features, the automated machine vision method comprising:
capturing image data of the work field from a camera system, wherein the camera system is mounted to, mounted with, or mounted as an end effector of a robotic arm;
following the capturing the image data, binary thresholding the image data based on a presumed feature of the one or more predetermined features, wherein the presumed feature comprises a thread pitch;
responsive to the binary thresholding, identifying one or more groups of pixels as candidates for the thread pitch;
following the identifying, applying a filter to the identified one or more groups of pixels to create filtered data, wherein the filter comprises an aspect corresponding to the thread pitch; and
based at least in part on the applying, determining if the object has the thread pitch;
based on the determining, instructing the robotic arm to install a component in a predetermined configuration relative to the object; and
installing, using the robotic arm, the component in the predetermined configuration relative to the object.

US Pat. No. 10,657,418

OBJECT DETECTION ON LOCAL DEVICES USING REMOTELY GENERATED MACHINE LEARNING MODELS

International Business Ma...

1. A computer-implemented method for configuring devices comprising:monitoring an area with a device comprising a camera and a computing device;
capturing data at the device, wherein the captured data includes at least one image or video captured by the camera;
transmitting the captured data to a remote system;
receiving configuration data at the device, wherein the configuration data has been generated by processing the captured data at the remote system using a plurality of different machine learning techniques and generating the configuration data based on at least one of the plurality of different machine learning techniques, wherein the configuration data includes a machine learning model for detecting at least one object in the image or video; and
configuring the device using the received configuration data; and
detecting, at the device, at least one object using the machine learning model during monitoring of the area.

US Pat. No. 10,657,417

PERSON INFORMATION DISPLAY APPARATUS, A PERSON INFORMATION DISPLAY METHOD, AND A PERSON INFORMATION DISPLAY PROGRAM

AMBASS INC., Tokyo (JP)

1. A person information display apparatus for displaying information of a person in order to create cast information serving as information regarding a person displayed in moving image data, comprising:a characteristic extraction unit for extracting facial characteristics of persons from the moving image data;
a correspondence information extraction unit for extracting characteristic information corresponding to the facial characteristics extracted by the characteristic extraction unit from pre-stored characteristic information on faces of multiple persons;
an exclusion candidate setting unit for setting, to an exclusion candidate serving as a candidate of a person excluded from the cast information, the characteristic information selected in accordance with an input of a user or a predetermined criterion among mutually analogous characteristic information if there is the mutually analogous characteristic information among the multiple characteristic information extracted by the correspondence information extraction unit; and
a person information output unit for displaying, on a display unit, information indicating a person corresponding to the characteristic information extracted by the correspondence information extraction unit and set to the exclusion candidate by the exclusion candidate setting unit, as well as information indicating a person corresponding to the characteristic information extracted by the correspondence information extraction unit and not set to the exclusion candidate, wherein
the person information output unit differentiates a display mode of information indicating a person corresponding to the characteristic information extracted by the correspondence information extraction unit and set to the exclusion candidate by the exclusion candidate setting unit, from a display mode of information indicating a person corresponding to the characteristic information extracted by the correspondence information extraction unit and not set to the exclusion candidate, and displays it on the display unit.

US Pat. No. 10,657,416

METHOD AND SYSTEM FOR DETECTING DRIFT IN IMAGE STREAMS

Capital One Services, LLC...

1. A computer-implemented method comprising:receiving, by a first device, a first image stream, wherein the first image stream comprises training data;
determining, by the first device, a first numeric representation of a first image in the first image stream, wherein the first numeric representation quantifies visual content of the first image;
determining, by the first device, a second numeric representation of a second image in the first image stream, wherein the second numeric representation quantifies visual content of the second image;
determining, by the first device, a first plurality of features that appear in both the first numeric representation and the second numeric representation;
building, by the first device, a first model using the plurality of features that appear in both the first numeric representation and the second numeric representation;
receiving, by the first device, a second image stream, wherein the second image stream includes at least a third image and a fourth image;
determining, by the first device, a third numeric representation of the third image, wherein the third numeric representation quantifies visual content of the third image;
determining, by the first device, a fourth numeric representation of the fourth image, wherein the fourth numeric representation quantifies visual content of the fourth image;
determining, by the first device, a second plurality of features that appear in both the third numeric representation and the fourth numeric representation;
building, by the first device, a second model using the second plurality of features that appear in both the third numeric representation and the fourth numeric representation;
comparing, by the first device, the second model to the first model to determine a difference between the second image stream and the first image stream; and
indicating, by the first device, that the second image stream is significantly different from the first image stream when the difference is greater than or equal to a threshold, wherein significantly different indicates that the second image stream is outside a permitted variability from the first image stream.

US Pat. No. 10,657,415

IMAGE CORRESPONDENCE DETERMINING METHOD AND APPARATUS

HTC Corporation, Taoyuan...

1. An image correspondence determining method for performing image correspondence determining through a neural network system implemented by an image correspondence determining apparatus, the image correspondence determining method comprising:concatenating a first image and a second image by a first concatenating unit of the neural network system to generate a concatenated image having global information;
extracting a plurality of features from the concatenated image by a convolutional neural network unit of the neural network system to generate a plurality of feature maps and dividing the feature maps into a plurality of first feature maps and a plurality of second feature maps;
extracting a plurality of first image patches from the first feature maps corresponding to a first region of the first image and extracting a plurality of second image patches from the second feature maps corresponding to a second region of the second image by an image patch extracting unit of the neural network system;
concatenating the first image patches and the second image patches by a second concatenating unit of the neural network system to generate a plurality of concatenated image patches; and
calculating a similarity metric according to the concatenated image patches by a metric learning network unit of the neural network system to determine a similarity between the first region and the second region.

US Pat. No. 10,657,414

OBJECT RECOGNITION STATE INDICATORS

Google LLC, Mountain Vie...

1. A computer-implemented method, comprising:providing an image for display in an application environment of an application executing on a user device;
performing object recognition on the image by use of an object recognition model that has a plurality of object recognition states, where at least one object recognition state is an identification state that is achieved when a candidate object detected in the image is positively identified by the model as an object in the image, and at least one or more states are precursor states to the identification state, and each of the identification state and the one or more precursor states are indicated by a respective identification state indicator and respective precursor state indicators;
providing, to the application executing on the user device, data that causes each of the precursor state indicators to be displayed within the image in the application environment to visually emphasize the candidate object and to indicate the respective precursor state of the object recognition model and the identification state indicator to be displayed within the image to visually emphasize the candidate object as being positively identified and to indicate the identification state of the object recognition model;
in response to the candidate object being positively identified and indicated by a display of the identification state indictor over the candidate object, enabling selection of the identification state indicator by the user to trigger further search actions.

US Pat. No. 10,657,413

RESTORATION OF DEFACED MARKINGS USING LOCK-IN INFRARED THERMOGRAPHY

Idaho State University, ...

1. A computer-implemented non-destructive method for identifying a defaced mark in a metal surface comprising:obtaining a plurality of infrared thermal images of a defaced area on a metal surface according to a lock-in thermal imaging technique;
developing, by a computing system comprising one or more computing devices, a plurality of input images from the plurality of infrared thermal images, the input images comprising phase images, amplitude images or a combination thereof;
developing, by the computing system, a plurality of score images from the plurality of input images, each score image being a reconstruction into an image of a single principal component;
applying, by the computing system, a plurality of similarity measures to one or more of the plurality of score images and to each of a plurality of reference images to obtain a plurality of similarity values for each of a plurality of possible identities of the defaced mark; and
assigning, by the computing system, an identity to the defaced mark based upon the similarity values.

US Pat. No. 10,657,412

CALCULATION OF DEGREE OF SIMILARITY BETWEEN TWO IMAGES

Synaptics Japan GK, Toky...

1. A method comprising:for each pixel of a first image and of a second image, applying a convex function to grayscale values for elementary colors of the pixel, wherein the convex function is monotonically non-decreasing in a domain defined between an allowed minimum value and an allowed maximum value of the grayscale values; and
calculating a degree of similarity between the first image and the second image after application of the convex function, wherein the degree of similarity is based on absolute differences between corresponding pixels of the first image and of the second image for each of the elementary colors.

US Pat. No. 10,657,411

ITEM IDENTIFICATION

Amazon Technologies, Inc....

1. An item identification system, comprising:determining an item pick of a first item from an inventory location;
receiving an image that includes a representation of the first item;
determining a plurality of candidate items, each of the plurality of candidate items having corresponding candidate item information;
determining that a plurality of processing techniques are to be performed to identify the first item represented in the received image;
initiating each of the plurality of processing techniques, wherein each of the plurality of processing techniques determine a similarity score between first item image information that is representative of the image and at least one of the plurality of candidate item information;
determining a first similarity score using a first processing technique of the plurality of processing techniques, wherein the first similarity score is representative of a similarity between the first item image information and a first candidate item information of the plurality of candidate items;
receiving a second similarity score from the first processing technique of the plurality of processing techniques, wherein the second similarity score is representative of a second similarity between the first item image information and a second candidate item information of the plurality of candidate items;
determining that a ratio between the first similarity score and the second similarity score does not exceed a defined amount;
receiving a third similarity score from a second processing technique of the plurality of processing techniques, wherein the third similarity score is representative of a third similarity between the first item image information and the first candidate item information;
receiving a fourth similarity score from the second processing technique of the plurality of processing techniques, wherein the fourth similarity score is representative of a fourth similarity between the first item image information and the second candidate item information;
determining that a second ratio between the third similarity score and the second similarity score exceeds a second defined amount;
identifying, based at least in part on determining that the second ratio exceeds the second defined amount, the first item as the candidate item associated with the first candidate item information; and
in response to identifying the first item as the candidate item, updating an item identifier list associated with a user that picked the first item from the inventory location to include an item identifier representative of the first item.

US Pat. No. 10,657,410

METHOD AND SYSTEM FOR ABNORMAL TISSUE DETECTION USING Z-SCORES IN A JOINT HISTOGRAM

Siemens Healthcare GmbH, ...

1. A method for automatically comparing organ tissue properties of a patient with corresponding organ tissue properties of a group of healthy subjects, the method comprising the following steps:determining a population norm for the organ tissue properties by:
a) selecting at least two different tissue properties of the organ to be investigated;
b) determining for each tissue property previously selected and for each subject of said group a quantitative tissue property map;
c) for each subject of the group, calculating a joint histogram from all the quantitative tissue property maps obtained for said subject;
d) normalizing each previously calculated joint histogram;
e) determining an averaged joint histogram by averaging the normalized joint histograms across all subjects of the healthy group, wherein said averaged joint histogram defines said population norm;
automatically performing a comparison of the averaged joint histogram with a patient joint histogram obtained for the organ tissue properties of the patient, wherein the patient joint histogram is obtained through the following steps:
b1) determining for each tissue property selected in step a) a quantitative tissue property map for the patient organ; and
c1) calculating a joint histogram from all the quantitative tissue property maps obtained for the organ of said patient;
d1) normalizing the previously calculated joint histogram; and
wherein the comparison is obtained by calculating a statistical deviation of values of the patient joint histogram with respect to values of the averaged joint histogram and mapping the statistical deviation to the patient organ.

US Pat. No. 10,657,409

METHODS AND APPARATUS FOR TRACKING OBJECTS USING SALIENCY

Brain Corporation, San D...

1. A system for tracking an object in a visual field, comprising:a memory including computer readable instructions stored thereon; and
at least one processor configured to execute the computer readable instructions to,
generate a first image corresponding to a saliency image, the saliency image being based on a back projection image, the back projection image being the same size as an input image,
generate a heat map based on a distance function of the back projection image and the input image,
determine a mask corresponding to a region of the visual field based on a peak in the heat map, the heat map representing likelihood of presence of the object in the visual field based on a confidence value of the heat map, and
combine the saliency image and the mask in order to track the object in the visual field.

US Pat. No. 10,657,408

SPEAKER SPIDER MEASUREMENT TECHNIQUE

Sonos, Inc., Santa Barba...

1. A system comprisinga processor;
a non-transitory computer-readable medium; and
program instructions stored on the non-transitory computer-readable medium that, when executed by the processor, cause the system to perform functions comprising:
receiving a digital image of a fabricated speaker spider;
detecting voids in the digital image of the fabricated speaker spider corresponding to one or more pixels of the digital image, wherein detecting the voids is based on a comparison of a first color value of each of the one or more pixels of the digital image to a predetermined threshold color value;
filtering the digital image to fill in the voids in the digital image, wherein the voids in the digital image are indicative of holes in the fabricated speaker spider;
determining a feature of the fabricated speaker spider based on the filtered digital image;
comparing the feature to corresponding design criteria associated with the fabricated speaker spider; and
outputting an indication of whether the fabricated speaker spider meets the design criteria.

US Pat. No. 10,657,406

OPTICAL CHARACTER RECOGNITION TEXT EXPORT FROM VIDEO PROGRAM

The DIRECTV Group, Inc., ...

1. A device, comprising:a processor; and
a computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
presenting a video program via a display screen of a user;
receiving, from a control device associated with the display screen, a request to capture text from the video program;
identifying text from a frame of the video program via optical character recognition;
presenting, via the display screen, the text from the frame in a selectable format, when the text from the frame is identified via the optical character recognition;
receiving, from the control device, a selection of at least a portion of the text that is presented in the selectable format;
presenting, via the display screen, a plurality of alternate destinations that are available to which to send the at least the portion of the text;
receiving, from the control device, a selection of an alternate destination from among the plurality of alternate destinations, wherein the alternate destination is identified by a first telephone number; and
sending the at least the portion of the text in a textual format to the alternate destination via the first telephone number in accordance with the selection of the at least the portion of the text and the selection of the alternate destination, wherein the alternate destination comprises a computing device of the user, wherein the computing device and the display screen are different devices.

US Pat. No. 10,657,405

VIDEO PROCESSING USING TOPOLOGICAL MAP

LIFESIZE, INC., Austin, ...

7. A videoconferencing system, comprising:a sensor configured to capture sequential frames of video image data during a videoconference; and
a processing subsystem configured to:
designate at least one group of pixels within a given frame of the sequential frames of video image data as an active area of interest, based on filtering individual pixels of the given frame to identify pixels of interest and applying a multidimensional filter to the pixels of interest to identify the at least one group of pixels;
based upon one or more inclusion criteria, include the active area of interest within a stack, wherein the stack occupies a primary frame within a two-dimensional video space;
update a topological map of the two-dimensional video space dependent upon the stack;
identify a framing region within the topological map; and
adjust framing of a primary imaging camera based on the framing region.

US Pat. No. 10,657,404

CHARACTER RECOGNITION DEVICE, CHARACTER RECOGNITION METHOD, AND CHARACTER RECOGNITION PROGRAM

Rakuten, Inc., Setagaya-...

1. A character recognition device comprising:at least one memory operable to store computer program code;
at least one processor operable to read said program code and operate according to said program code, said program code including:
acquisition code configured to cause at least one of said at least one processor to acquire an image;
first recognition code configured to cause at least one of said at least one processor to identify a plurality of character regions in the image and recognize a character from each of the plurality of character regions of the image by a first recognition method;
setting code configured to cause at least one of said at least one processor to set, for at least some of a plurality of characters recognized by the first recognition code, at least one reference line along an alignment direction of the plurality of characters and passing through a specified position in each character;
second recognition code configured to cause at least one of said at least one processor to recognize a character by a second recognition method, the second recognition method being a method that recognizes a character from an image within a recognition window by scanning in a recognition target region in an image while changing a size of the recognition window, and configured to set a position or a height in a vertical direction of the recognition window based on at least one reference line out of the reference lines set by the setting code; and
output code configured to cause at least one of said at least one processor to output, as a recognition result, a word composed of characters recognized by the second recognition code, wherein
the setting code is further configured to cause at least one of said at least one processor to set at least two reference lines, and
the second recognition code is further configured to cause at least one of said at least one processor to set the position and the height in the vertical direction of the recognition window to a position and a height of a scanning region specified by predetermined two reference lines out of the at least one reference line set by the setting code.

US Pat. No. 10,657,403

MEDICAMENT DOSAGE DETERMINATION

Sanofi-Aventis Deutschlan...

1. A method of recording a medicament dose using a data collection device, the method comprising:capturing, by a camera of the data collection device, at least two images of a medicament dose indicator of a medicament delivery device;
determining a current medicament dosage amount displayed by the medicament dose indicator in the at least two images using a first character identification technique, the first character identification technique comprising a first algorithm;
displaying a current dosage amount based on a result of said first character identification technique;
determining whether the current medicament dosage amounts in the at least two images are different; and
in response to a determination that the current displayed dosage amounts are not different, identifying at least one character in one of the at least two images using a second character identification technique, the second character identification technique comprising a second algorithm that is different than the first algorithm, and determining the medicament dosage amount indicated by the medicament dose indicator based on a result of the second character identification technique, wherein the first character identification technique is less computationally intensive than the second character identification technique.

US Pat. No. 10,657,402

ELECTRONIC DEVICE AND METHOD FOR IDENTIFYING SENSOR POSITION BY USING PIXELS OF DISPLAY

Samsung Electronics Co., ...

1. An electronic device comprising:a display;
a biometric sensor disposed in the display; and
a processor operatively coupled to the display and the biometric sensor,
wherein the processor is configured to:
activate at least one pixel included in the display,
acquire position information corresponding to the at least one pixel through the biometric sensor, and
identify a position of the biometric sensor disposed in the display based on the position information.

US Pat. No. 10,657,401

BIOMETRIC OBJECT SPOOF DETECTION BASED ON IMAGE INTENSITY VARIATIONS

Microsoft Technology Lice...

1. A method of biometric object spoof detection, comprising:receiving a first image, including an eye, captured at a first time in response to a first incident light emitted from a light source at a wavelength with a first set of illumination characteristics;
receiving a second image, including the eye, captured at a second time in response to a second incident light emitted from the light source at the wavelength with a second set of illumination characteristics;
determining a first set of one or more corneal glints in the first image;
determining a second set of one or more corneal glints in the second image, wherein each of the second set of one or more corneal glints corresponds to one of the first set of one or more corneal glints;
determining a glint intensity difference feature between corresponding corneal glints in the first image and the second image; and
classifying the eye as being a fake eye or a real eye based on the glint intensity difference feature.

US Pat. No. 10,657,400

METHOD AND APPARATUS WITH VEIN PATTERN AUTHENTICATION

Samsung Electronics Co., ...

1. A terminal authentication method, the method comprising:projecting a near infrared (NIR) ray using a light emitting diode (LED) of a terminal;
receiving a light reflected by a vein of a user using an image sensor of the terminal;
verifying whether an image generated using the received light exhibits a vein pattern;
in response to the image generated using the received light being verified as exhibiting the vein pattern, generating a vein pattern of the vein based on an image generated using the received light; and
in response to the generated vein pattern being determined to match a pre-stored vein pattern, authenticating the user as a registered user corresponding to the pre-stored vein pattern.

US Pat. No. 10,657,399

BIOMETRIC IMAGING DEVICE, BIOMETRIC IMAGING METHOD AND PROGRAM

NEC CORPORATION, Tokyo (...

1. A biometric imaging device comprising:a memory storing a program including instructions;
a placement stand including a transparent plate onto which a biological object is placed;
a camera being positioned to take images of said biological object; and
a processor configured to execute the program to perform the instructions including;
controlling the camera to take images of said biological object; and
determining whether or not said biological object is placed on said placement stand based on a feature of said biological object at a place where said placement stand and said biological object are in contact and a feature of said biological object at a place where said placement stand and said biological object are not in contact, in said images;
wherein the transparent plate is configured to support at least a part of the biological object so that said camera takes the images including a part of said biological object that is in contact to the transparent plate and a part which is consecutive to the part of said biological object that is not in contact to the transparent plate.

US Pat. No. 10,657,398

SLEEPY DRIVER ALERT SYSTEM AND METHOD

1. A sleepy driver alert method, comprising:providing a vehicle with a cold air system;
providing a platform accessible from a computing device, the platform being configured to communicate with one or more sensors of the vehicle;
monitoring driver posture via a first sensor in communication with the platform;
monitoring the vehicle swaying via a second sensor in communication with the platform;
determining if a driver posture is within a pre-determined normal range;
determining if the vehicle swaying is within a pre-determined normal range;
providing an alert via a list of alerts to increase awareness of the driver when the driver posture or the vehicle swaying is not within the predetermined normal ranges;
activating the cold air system to blow cold air on the driver if the detection of the driver posture and the detection of the vehicle swaying is outside the predetermined normal ranges;
autonomously communicating between the vehicle and a second vehicle of the driver awareness solely if the driver posture is sensed outside the pre-determined normal range and if the vehicle swaying is sensed outside the pre-determined normal range.

US Pat. No. 10,657,397

APPARATUS FOR DETERMINING CONCENTRATION OF DRIVER, SYSTEM HAVING THE SAME, AND METHOD THEREOF

HYUNDAI MOTOR COMPANY, S...

1. An apparatus for determining a concentration of a driver, the apparatus comprising:a region-of-interest definition processor configured to define a region-of-interest based on traffic-related information on front image information of a vehicle running;
a driver eye-gaze detection processor configured to detect a plurality of eye-gaze points from driver image information of a driver in accordance with an eye-gaze movement of the driver;
a driver concentration information calculation processor configured to calculate concentration information of each of the plurality of eye-gaze points;
an image coordinate system processor configured to convert the region-of-interest to an image coordinate system and convert positions of the plurality of eye-gaze points to the image coordinate system; and
a concentration determination processor configured to:
determine the concentration of the driver on the image coordinate system based on the concentration information,
calculate at least one or more of an average value of an eye-gaze movement speed, a dispersion value of the positions of the plurality of eye-gaze points, or an area value of the plurality of eye-gaze points from the concentration information of each of the plurality of eye-gaze points, and
decide a line connected between a first eye-gaze point and a last eye-gaze point in a monitoring unit pattern among the plurality of eye-gaze points as a reference line and calculate the dispersion value of the positions of the plurality of eye-gaze points using distances between the reference line and the plurality of eye-gaze points.

US Pat. No. 10,657,396

METHOD AND DEVICE FOR ESTIMATING PASSENGER STATUSES IN 2 DIMENSION IMAGE SHOT BY USING 2 DIMENSION CAMERA WITH FISHEYE LENS

STRADVISION, INC., Pohan...

1. A method for detecting one or more passenger statuses by analyzing an interior image of a vehicle, comprising steps of:(a) if at least one 2D interior image of an interior of the vehicle taken by at least one camera with a fisheye lens is acquired, a passenger status-detecting device performing a process of inputting the 2D interior image into a pose estimation network, to thereby allow the pose estimation network to acquire one or more pose points corresponding to each of one or more passengers from the 2D interior image; and
(b) the passenger status-detecting device performing (i) a process of calculating location information on the pose points corresponding to each of the passengers relative to a preset reference point of the vehicle by referring to a predetermined pixel-angle table, wherein, on condition that a grid board of grid cells has been placed in the interior of the vehicle, the pixel-angle table has been created such that each of vertical angles and each of horizontal angles, formed by a first line and each of second lines, correspond to each of pixels of each of corners of the grid cells, in which the first line connects the camera and a top center of the grid board on a grid image taken by the camera, and each of the second lines connects each of the corners and the camera and (ii) a process of detecting each of the passenger statuses by referring to the location information on the pose points corresponding to each of the passengers.

US Pat. No. 10,657,395

REAL TIME TRAFFIC SIGN RECOGNITION

TEXAS INSTRUMENTS INCORPO...

1. An apparatus comprising:an input to receive data corresponding to an image of a captured scene;
a processor; and
a memory to store instructions that, when executed by the processor, cause the processor to:
identify one or more approximate locations of interest in the image based on extracting color information from the image, wherein extracting the color information includes:
extracting, from the image, an initial binary mask for a respective color of a plurality of colors; and
applying to each of the initial binary masks, a morphological opening operation to produce a respective final binary mask for each of the initial binary masks;
process each of the one or more approximate locations of interest in the image to identify one or more localized windows in the image in which a traffic sign is present;
for each of the one or more localized windows, determine classification information of the respective traffic sign present in the localized window; and
output information that identifies, for each traffic sign present in the captured scene, a traffic sign type based on the classification information.

US Pat. No. 10,657,394

METHOD AND SYSTEM FOR HANDLING MISCLASSIFICATION OF SPEED SIGNS

HERE Global B.V., Eindho...

1. A method for providing a speed limit related recommendation to a user of a vehicle, the method comprising:receiving an image data representing a posted sign, in a vicinity of the vehicle, the image data being detected by one or more image capturing devices;
processing the image data received to determine an observed numerical value;
calculating, by a processor, a sign reliability factor based on a function of at least the observed numerical value, a historic mean of one or more vehicle speeds at the time of sign observation and a standard deviation of the one or more vehicle speeds at the time of sign observation; and
providing data for an indication of a speed limit to be followed by the vehicle, on a user interface, based on the sign reliability factor of the observed numerical value being above or below a pre-defined threshold.

US Pat. No. 10,657,393

DEVICE AND A METHOD FOR DISTINGUISHING BETWEEN TRAVERSABLE AND NONTRAVERSABLE OBJECTS

Aptiv Technologies Limite...

1. A device (1) for distinguishing between traversable and non-traversable objects, said device (1) comprising:an object-detection sensor unit (2) configured to monitor a space around the object-detection sensor unit (2) and to generate data about the space,
a map generation unit (3) configured to use the data generated by the object-detection sensor unit (2) in order to generate an occupancy grid map and a free space grid map for the space around the object-detection sensor unit (2), wherein each of the occupancy grid map and the free space grid map comprises an array of cells, each cell of the occupancy grid map contains an occupied space probability value representing the probability for the respective cell being occupied and each cell of the free grid map contains a free space probability value representing the probability for the respective cell being free, and
a classifier unit (4) configured to classify at least one of the cells as containing a traversable or non-traversable object by calculating a difference of two free space probability values derived from the free space probability values of at least two of the cells adjacent to the at least one cell and by using the difference as well as the occupied space probability value of the at least one cell to classify the at least one cell.

US Pat. No. 10,657,392

OBJECT DETECTION DEVICE, OBJECT DETECTION METHOD, AND PROGRAM

OMRON Corporation, Kyoto...

1. An object detection device comprising:an output unit that outputs a first signal to an object;
a plurality of detection units that are respectively arranged at predetermined positions on a detection surface and detect a second signal that occurs due to the first signal being reflected by the object;
a first data generation unit that generates first data that is a group of a plurality of first position information items, in each of which coordinate value and signal detection information are associated, wherein the coordinate values represent the arrangement positions of the plurality of detection units with first coordinates set on the detection surface, and the signal detection information are information calculated on the basis of the second signal detected by the detection units and include at least distance information between the detection surface and the object;
a second data generation unit that generates second data that includes a plurality of second position information items by extracting the plurality of second position information items that are the first position information corresponding to representative points that represent a presence range of the object from the first data; and
an information processing unit that executes information processing related to presence of the object by using the second data,
wherein the second data generation unit performs, on at least one direction, processing of extracting two first position information items that are located at extreme ends in a predetermined direction on the first coordinates from the first data and extracts the first position information extracted by the processing as the second position information.

US Pat. No. 10,657,391

SYSTEMS AND METHODS FOR IMAGE-BASED FREE SPACE DETECTION

UATC, LLC, San Francisco...

1. A computer-implemented method of detecting free space in a surrounding environment of an autonomous vehicle, the method comprising:obtaining, by a computing system comprising one or more computing devices, image data from one or more cameras affixed to the autonomous vehicle, the image data comprising a representation of the surrounding environment from a perspective associated with each of the one or more cameras affixed to the autonomous vehicle;
generating, by the computing system, a cylindrical image depicting an approximately 360-degree perspective of the surrounding environment based, at least in part, on the image data from the one or more cameras;
generating, by the computing system, a reprojected image depicting a top-down perspective of the approximately 360-degree perspective of the surrounding environment based, at least in part, on the cylindrical image;
inputting, by the computing system, the reprojected image to a machine-learned detector model to obtain, as an output of the machine-learned detector model, object data characterizing one or more objects in the surrounding environment;
determining, by the computing system, a free space in the surrounding environment of the autonomous vehicle based at least in part on the object data.

US Pat. No. 10,657,390

SYSTEM AND METHOD FOR LARGE-SCALE LANE MARKING DETECTION USING MULTIMODAL SENSOR DATA

TUSIMPLE, INC., San Dieg...

1. A system comprising:a data processor; and
a multimodal lane detection module, executable by the data processor, the multimodal lane detection module being configured to perform a multimodal lane detection operation configured to:
receive image data from an image generating device mounted on a vehicle, the received image data corresponding to a particular location;
receive point cloud data from a distance and intensity measuring device mounted on the vehicle;
fuse the image data and the point cloud data to produce a set of lane marking points in three-dimensional (3D) space that correlate to the image data and the point cloud data, the fusion including aligning and orienting the image data with a terrain map corresponding to the particular location and using terrain map elevation data to transform the image data to the 3D space; and
generate a lane marking map from the set of lane marking points.

US Pat. No. 10,657,389

STATIONARY-VEHICLE STRUCTURE FROM MOTION

TEXAS INSTRUMENTS INCORPO...

1. An automotive system comprising:a processor; and
a non-transitory computer readable storage medium storing instructions that, when executed by the processor, cause the processor to:
receive a sequence of image frames from a camera;
determine whether a vehicle associated with the sequence of image frames is stationary;
in response to determining that the vehicle is stationary, change an order for storing the sequence of image frames in a frame stack from a first technique to a second technique that is different from the first technique; and
store a first image frame of the sequence of image frames in the frame stack according to the second technique.

US Pat. No. 10,657,388

ROBUST SIMULTANEOUS LOCALIZATION AND MAPPING VIA REMOVAL OF DYNAMIC TRAFFIC PARTICIPANTS

HONDA MOTOR CO., LTD., T...

1. A method for localization and mapping for an autonomous vehicle, comprising:obtaining, via a camera, an image acquired at a first location;
assigning labels to one or more objects of the image;
obtaining, via a light detector, a point cloud acquired at a second location, which is within a threshold distance of the first location;
determining one or more object clusters of the point cloud;
associating the labels assigned to the one or more objects of the image with points of the object clusters of the point cloud; and
identifying three-dimensional (3D) objects of the point cloud based on the labels associated with the points of the object clusters.

US Pat. No. 10,657,387

METHOD AND APPARATUS FOR CONTROLLING VISION SENSOR FOR AUTONOMOUS VEHICLE

SAMSUNG ELECTRONICS CO., ...

1. A method of controlling a vision sensor of a host vehicle, the method comprising:capturing an image of a traveling path of the host vehicle while the host vehicle travels on the traveling path using the vision sensor;
predicting based on analyzing shapes of objects within the image an expected point, on the traveling path of the host vehicle, at which an illumination variation of an external environment on the traveling path of the host vehicle greater than or equal to a threshold is expected to occur;
determining that the host vehicle is located within a threshold distance from the expected point; and
controlling the vision sensor in the host vehicle to adjust an image capture parameter of the vision sensor based on the expected illumination variation in response to determining that the host vehicle is located within the threshold distance from the expected point,
wherein the determining that the host vehicle is located within the threshold distance from the expected point comprises:
identifying an object associated with the expected point among the objects within the image;
obtaining global positioning system (GPS) coordinates of the object using GPS coordinates of a current location of the host vehicle and map data of the traveling path;
determining a distance between the GPS coordinates of the object and the GPS coordinates of the current location of the host vehicle; and
determining that the host vehicle is located within the threshold distance from the expected point based on the distance between the GPS coordinates of the object and the GPS coordinates of the current location of the host vehicle being less than the threshold distance.

US Pat. No. 10,657,386

MOVEMENT STATE ESTIMATION DEVICE, MOVEMENT STATE ESTIMATION METHOD AND PROGRAM RECORDING MEDIUM

NEC CORPORATION, Minato-...

1. A movement state estimation device comprising:at least one memory storing instructions; and
at least one processor executing the instructions to perform:
estimating a quantity of monitoring targets in each local region of a plurality of time-series images, a state of each of the monitoring targets expressed using a plurality of particles; and
estimating the state of each of the monitoring targets on the basis of a change with time in a sum of weight values of the plurality of particles, wherein
the weight values depend on a detection probability of at least one of the monitoring targets from the plurality of time-series images, the detection probability depending on a location of the at least one of the monitoring targets in the plurality of time-series images.

US Pat. No. 10,657,385

SYSTEM AND METHOD FOR ADAPTIVE, RAPIDLY DEPLOYABLE, HUMAN-INTELLIGENT SENSOR FEEDS

CARNEGIE MELLON UNIVERSIT...

1. An adaptive sensor system comprising:a sensor, wherein the sensor provides a sensor feed of an environment;
a user interface,
wherein a user can enter a question to be answered by the sensor system using the user interface,
wherein the question relates to a condition of the environment;
a dispatcher, wherein the dispatcher directs the sensor feed and question to at least one of a crowd module and a machine learning module,
wherein at least one of the crowd module and the machine learning module generates a labeled sensor feed derived from the sensor feed,
wherein the labeled sensor feed comprises an answer to the question; and
a periodic comparator that evaluates a relative accuracy of the labeled sensor feed generated by the machine learning module as compared to the labeled sensor feed generated by the crowd module.

US Pat. No. 10,657,384

METHOD AND SYSTEM FOR DETERMINING COMPLEX SITUATION ACCORDING TO TIME FLOW OF EVENTS OCCURRING IN EACH DEVICE

SK HOLDINGS CO., LTD., S...

1. A method for determining a complex situation, the method comprising the steps of:obtaining, by an apparatus, events occurring in a set of devices among a plurality of devices connected to the apparatus via a network, wherein the events occur at time intervals and are detected by the set of devices, the apparatus includes a database in which complex situation analytic rules are established, the complex situation analytic rules map a plurality of situations onto a plurality of conditions, and each of the plurality of conditions is defined by events occurring in devices of the plurality of devices and time intervals of the events occurring in the devices; and
determining, by the apparatus, a current situation by referring to a result of obtaining the events occurring in the set of devices in the step of obtaining and a complex situation analytic rule of the complex situation analytic rules,
wherein the complex situation analytic rule is a rule which maps the current situation onto a condition included in the plurality of conditions and defined by the events occurring in the set of devices and the time intervals between the events occurring in the set of devices,
wherein the plurality of conditions comprise a first detection condition defined by events occurring in a first device, a second device and a third device among the set of devices and time intervals among the events occurring in the first device, the second device and the third device, and each of events of the second device and the third device occurs after an event of the first device occurs,
wherein the current situation is determined based on the rule mapping the current situation onto the first detection condition,
wherein the first device, the second device and the third device are separate devices, and each of the first device, the second device and third device is connected to the apparatus via the network, and
wherein the method further comprises:
determining, by the apparatus, whether a determination withdrawal condition for withdrawing the determined current situation is satisfied based on an event occurring in the third device and obtained by the apparatus from the third device via the network and one of a time interval between the event occurring in the first device and obtained by the apparatus from the first device via the network and the event occurring in the third device and obtained by the apparatus from the third device via the network and a time interval between an event occurring in the second device and obtained by the apparatus from the second device via the network and the event occurring in the third device and obtained by the apparatus from the third device via the network, and
withdrawing, by the apparatus, the determined current situation according to a result of the determination that the determination withdrawal condition is satisfied.

US Pat. No. 10,657,383

COMPUTER VISION TO ENABLE SERVICES

Amazon Technologies, Inc....

1. A system comprising:one or more processors; and
one or more computer-readable media storing computer-instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
storing first data associated with a scheduled delivery of a physical package, the first data indicating a delivery time and a delivery location;
storing second data designating an area within an environment in which an animal is able to access a delivery zone for the physical package, the animal is non-human;
determining that a current time is within a threshold period of time from the delivery time;
sending, to a camera apparatus, a first message requesting image data captured by the camera apparatus;
receiving the image data from the camera apparatus, the image data representing at least a portion of the area of the environment;
analyzing the image data with respect to a computer vision classifier trained to detect the presence of the animal;
determining that the animal is within the area of the environment;
determining, using the second data, that the animal is able to access the delivery zone for the physical package;
based at least in part on determining that the animal is able to access the delivery zone for the physical package, determining how to proceed with delivering of the physical package;
sending a second message to a first electronic device associated with a first user profile, the second message including a first indication that the animal is within the environment and information specifying how to proceed with the delivering of the physical package; and
sending a third message to a second electronic device associated with a second user profile, the third message including a second indication that the animal is within the environment.

US Pat. No. 10,657,382

METHODS AND SYSTEMS FOR PERSON DETECTION IN A VIDEO FEED

GOOGLE LLC, Mountain Vie...

1. A method, comprising:at a computing system having one or more processors and memory:
obtaining a video feed; and
for a frame of the video feed, analyzing the frame at a first resolution to determine whether the frame includes a potential instance of a person;
in accordance with a determination that the frame includes the potential instance, denoting a region around the potential instance;
analyzing the region at a second resolution, greater than the first resolution; and
in accordance with a determination that the region includes the instance of the person:
determining that the frame includes the person; and
storing an indication of the determination for use in subsequent alert notification processing.

US Pat. No. 10,657,381

SYSTEMS AND METHODS FOR SHARING CONTENT

Facebook, Inc., Menlo Pa...

1. A computer-implemented method comprising:determining, by a computing system, a video being posted through a social networking system;
determining, by the computing system, one or more portions of the video to be compressed; and
compressing, by the computing system, the one or more portions of the video, wherein, upon being compressed, a playback speed corresponding to at least one of the portions is increased by some rate.

US Pat. No. 10,657,380

ADDRESSABLE IMAGE OBJECT

1. A method, comprising:analyzing, by a processing system comprising a processor, closed captioning provided with media content, the media content being provided as a video stream displayed to a user of a media device, the media content comprising a plurality of digital frames transported to the media device over a private network;
recognizing, by the processing system, product information, the recognizing being based on the analyzing of the closed captioning;
determining, by the processing system, product website information for providers of goods or services associated with the product information, the providers of the goods or services being selected during the determining based on a proximity to the user of the media device;
receiving, by the processing system from the media device, a user input selecting a product associated with the product information, the selecting resulting in a selected product; and
providing, by the processing system, a connection to a website associated with the selected product to the media device through the private network, the product website information comprising a uniform resource locator to the website, and the website enabling the user to securely procure the selected product by having the selected product being paid for without providing payment information by the user to the providers of the goods or services.

US Pat. No. 10,657,379

METHOD AND SYSTEM FOR USING SEMANTIC-SEGMENTATION FOR AUTOMATICALLY GENERATING EFFECTS AND TRANSITIONS IN VIDEO PRODUCTIONS

Vimeo, Inc., New York, N...

1. A method of automatic video production comprising:obtaining a set of media entities comprising pixels, wherein at least one of the media entities comprises a background and at least one foreground object;
automatically analyzing the media entities using visual analysis;
automatically selecting at least two visual portions, based on said visual analysis;
computing, for at least one of said visual portions, semantic segmentation indicative of a support of the at least one foreground object, based on said visual analysis, wherein said computing assigns said pixels with respective pixel values based on the sematic segmentation;
generating at least one masking transition being temporally ordered between at least a first and a second visual portions, wherein, in said masking transition, either the foreground object of the first visual portion appears over the second visual portion, or the foreground object of the second visual portion appears over the first visual portion wherein in a time prior to the transition, only said first visual portion is visible and wherein in a time post to said transition only said second visual portion is visible, wherein the masking transition is generated based on said respective pixel values; and
generating a video production by combining a plurality of the visual portions into one video production, while including the at least one masking transition in the video production in said temporal order.

US Pat. No. 10,657,378

CLASSIFYING IMAGES AND VIDEOS

Board of Regents, The Uni...

1. A method for classifying an image or video, the method comprising:receiving an image or video to be classified;
capturing scene statistics in said image or video;
creating a model of said image or video using said captured scene statistics;
comparing, by a processor, said model of said image or video with a model of visible light images or videos and with a model of infrared images or videos; and
classifying, by said processor, said image or video as a visible light or video or an infrared light or video based on said comparison.

US Pat. No. 10,657,377

MODEL-DRIVEN LEARNING FOR VIDEO ANALYTICS

1. A method comprising:receiving, by a processing system having a processor, a plurality of media items, wherein each of the plurality of media items includes an object having a plurality of variables;
performing an adaptive analysis, by the processing system, of the plurality of media items by comparing a first one of the plurality of media items and a second one of the plurality of media items, wherein only one of the variables is different between the first one of the plurality of media items and the second one of the plurality of media items;
performing a transfer analysis, by the processing system, of the plurality of media items by comparing a third one of the plurality of media items and a fourth one of the plurality of media items, wherein more than one of the variables is different between the third one of the plurality of media items and the fourth one of the plurality of media items;
generating, by the processing system, a model based on both the adaptive analysis and the transfer analysis, wherein the adaptive analysis and the transfer analysis are performed iteratively and simultaneously; and
recognizing, using the model, the object in media content, wherein the model is configured to provide a description of at least one of the plurality of variables of the object in the media content.

US Pat. No. 10,657,376

ROOM LAYOUT ESTIMATION METHODS AND TECHNIQUES

Magic Leap, Inc., Planta...

1. A system comprising:non-transitory memory configured to store:
a room image for room layout estimation; and
a neural network for estimating a layout of a room, the neural network comprising:
an encoder-decoder sub-network configured to receive the digital room image as an input, wherein the encoder-decoder sub-network comprises an encoder and a decoder; and
a classifier sub-network in communication with the encoder-decoder sub-network configured to classify a room type associated with the room image;
a hardware processor in communication with the non-transitory memory, the hardware processor programmed to:
access the room image;
determine, using the encoder, decoder, and the room image, a plurality of predicted two-dimensional (2D) keypoint maps corresponding to a plurality of room types;
determine, using the encoder, the classifier sub-network and the room image, a predicted room type from the plurality of room types;
determine, using the plurality of predicted 2D keypoint maps and the predicted room type, a plurality of ordered keypoints associated with the predicted room type; and
determine, using the plurality of ordered keypoints, a predicted layout of the room in the room image.

US Pat. No. 10,657,375

AUGMENTED REALITY SYSTEM FOR FACILITATING CURRENCY CONVERSION

Capital One Services, LLC...

1. An augmented reality system for facilitating currency conversion, comprising:one or more processors programmed with instructions that, when executed, cause the augmented reality system to:
obtain, via a wearable device, a live video stream of an environment at which the wearable device is located, the live video stream comprising an image portion and an audio portion that are representative of the environment;
perform image recognition on the image portion of the live video stream to extract an image-derived indicator in real time from the image portion of the live video stream, wherein the image-derived indicator represents a quantity of units of a local currency that correspond to a feature in the image portion of the live video stream;
continuously track the corresponding feature in the live video stream;
perform natural language processing on the audio portion of the live video stream to extract the audio-derived indicator in real time from the audio portion of the live video stream, wherein the audio-derived indicator represents the local currency;
generate, via a neural network, a predicted equivalent price in a user-selected currency based on (i) the image-derived indicator from the live video stream and (ii) the audio-derived indicator from the live video stream, the predicted equivalent price corresponding to the quantity of the units of the local currency; and
cause, based on the continuous tracking of the corresponding feature, augmentation of the corresponding feature with the predicted equivalent price in the live video stream such that the predicted equivalent price of the user-selected currency is displayed proximate the corresponding feature in the live video stream.

US Pat. No. 10,657,374

SYSTEMS, METHODS, AND APPARATUS FOR PROVIDING IMAGE SHORTCUTS FOR AN ASSISTANT APPLICATION

GOOGLE LLC, Mountain Vie...

1. A computing device, comprising:a camera;
a microphone;
a display device;
a speaker;
one or more processors in communication with the camera, the microphone, the display device, and the speaker; and
memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform certain operations that include:
generating an object identifier based on an image provided by the camera,
wherein the image characterizes an object that corresponds to the object identifier, and
wherein generating the object identifier includes processing the image via the one or more processors using one or more image processing techniques;
determining, using the object identifier that is generated based on the image, that the object identifier corresponds to an image shortcut setting,
wherein the image shortcut setting causes an automated assistant application of the computing device to render certain data in response to the object appearing in one or more images provided by the camera, and
wherein the image shortcut setting is generated in response to one or more previous inputs from a user to the automated assistant application; and
causing, based on the object identifier corresponding to the image shortcut setting, the automated assistant application to render the certain data via the display device and/or the speaker.

US Pat. No. 10,657,373

SYSTEMS AND METHODS FOR AUTOMATICALLY VARYING PRIVACY SETTINGS OF WEARABLE CAMERA SYSTEMS

OrCam Technologies Ltd., ...

1. A wearable imaging apparatus having variable privacy settings, the wearable apparatus comprising:a wearable image sensor configured to capture a plurality of images from an environment of a wearer of the wearable imaging apparatus;
a memory for storing privacy mode triggers and associated privacy mode settings;
at least one processing device programmed to:
analyze the plurality of images and recognize within one or more of the plurality of images a presence of at least one of the privacy mode triggers;
based on the presence of at least one of the privacy mode triggers, identify multiple portions of image data associated with the recognized privacy mode trigger;
blur, based on the identification, a first portion of the image data associated with the recognized privacy mode trigger, wherein the first portion includes a representation of at least one recognized individual;
prohibit transmission, based on the identification, of a second portion of the image data associated with the recognized privacy mode trigger, wherein the second portion includes information indicative of the identity of the individual; and
transmit the first portion including the blurred image data to an external device that is paired with the wearable imaging apparatus to enable the external device to execute a function relating to the individual.

US Pat. No. 10,657,372

SYSTEMS AND METHODS FOR IDENTIFYING AND DISPLAYING OPTIMAL LOCATIONS FOR A GARDEN

Walmart Apollo, LLC, Ben...

1. A system for identifying and displaying one or more optimal locations within a lot for a garden, the system comprising:at least one robotic device positioned and configured to scan a lot and to generate at least one lot parameter;
at least one soil sensor positionable in soil in the lot and configured to generate at least one soil parameter;
a storage device storing predefined criteria for associating plant varieties, lot parameters, and soil parameters with optimal lot locations; and
a computing system communicatively coupled to the at least one soil sensor, the at least one robotic device, the storage device, and a user computing device, the computing system configured to execute a location optimization module that when executed:
receives the at least one lot parameter from the at least one robotic device;
receives the at least one soil parameter from the at least one soil sensor;
determines one or more varieties of suggested plants based on the at least one soil parameter and the at least one lot parameter;
transmits an identification of the one or more varieties of suggested plants to the user computing device, wherein the user computing device displays the identification of the one or more varieties of suggested plants;
receives, from the user computing device, a selection of one or more plants of the one or more varieties of suggested plants;
identifies one or more optimal locations for a garden within the lot for the selected one or more plants based on the at least one lot parameter, the at least one soil parameter and the predefined criteria, the one or more optimal locations representing a portion of the lot that is less than the entire lot; and
transmits the one or more optimal locations for the garden to the user computing device, wherein the user computing device displays the one or more optimal locations for the garden within the lot.

US Pat. No. 10,657,371

MINIATURIZED ASTROMETRIC ALIGNMENT SENSOR FOR DISTRIBUTED AND NON-DISTRIBUTED GUIDANCE, NAVIGATION, AND CONTROL SYSTEMS

United States of America ...

1. A computer-implemented method, comprising:searching, by a computing system, for one or more bright objects in an image captured by a space vehicle onboard camera;
determining, by the computing system, if the one or more bright objects is a genuine star or a secondary element;
cataloging, by the computing system, identified stars after three or more bright objects are determined to be genuine stars;
reporting and displaying, by the computing system, the cataloged entries of the identified stars, wherein the cataloged entries comprises the position and velocity of the space vehicle in relation to the identified stars, and a sensor body reference frame; and
selecting one or more stars in the captured image, wherein the selecting of the one or more stars comprises:
performing a stellar search for stars in the captured image;
computing centroids for the one or more stars;
performing stellar tracking for the one or more stars;
initiating N tracking windows for the one or more stars; and
selecting one or more top N candidates to identify one or more stars:
wherein N is an integer number and TOP N is an integer number less than N.

US Pat. No. 10,657,370

DETERMINING IMAGES HAVING UNIDENTIFIABLE LICENSE PLATES

International Business Ma...

1. A method of processing an image, the method comprising the steps of:a computer determining a category specifying characteristics of a shape of a license plate of a vehicle;
based on the category specifying the characteristics of the shape of the license plate, the computer determining characteristics of objects in the image match the characteristics of the shape of the license plate;
the computer determining the image includes the license plate and an identifier included in the license plate;
the computer determining a category specifying characteristics of an order of alphanumeric characters in the identifier, the order required to be a characteristic of identifiable license plates;
based on the category specifying the characteristics of the order of the alphanumeric characters in the identifier, the computer determining characteristics of the objects in the image do not match the characteristics of the order of the alphanumeric characters in the identifier;
based on the characteristics of the objects in the image not matching the characteristics of the order of the alphanumeric characters in the identifier, the computer determining the image does not include an identifiable license plate; and
in response to the step of determining the image does not include the identifiable license plate, the computer determining the image is invalid and bypassing a manual character recognition process for determining identifiers on license plates.

US Pat. No. 10,657,369

UNSUPERVISED REMOVAL OF TEXT FROM IMAGES USING LINEAR PROGRAMMING FOR OPTIMAL FILTER DESIGN

INTUIT, INC., Mountain V...

1. A method for removing text from an image of a form comprising:generating a matrix representing pixels of the image, wherein the image depicts at least a portion of the form, and wherein the form includes layout elements and content elements;
applying a matrix flattening operation to the matrix;
generating a frequency domain representation of the image by applying a frequency domain transformation to the flattened matrix;
generating a filter to apply to the frequency domain representation;
applying the filter to the frequency domain representation to remove a portion of the frequency domain representation of the image;
generating a reconstructed matrix from the filtered frequency domain representation, wherein a format of the reconstructed matrix is a format of the matrix representing pixels of the image;
generating a reconstructed image of at least the portion of the form by applying an inverse frequency domain transformation to the reconstructed matrix filtered frequency domain representation, wherein the reconstructed image depicts only a portion of the content elements;
matching the reconstructed image to a form template;
generating respective text from the content elements of the image; and
mapping portions of the respective text to a corresponding field of the form template based on a position of the content element in the image.

US Pat. No. 10,657,368

AUTOMATIC HUMAN-EMULATIVE DOCUMENT ANALYSIS

AON RISK SERVICES, INC. O...

1. A computer-implemented method of generating a user interface showing results of human-emulative document analysis, the method comprising:receiving documents containing text, individual ones of the documents associated with a generated document identification number;
pre-processing the documents to generate one or more processed document portions from the individual ones of the documents, individual ones of the processed document portions associated with one of the generated document identification numbers and comprising text parsed into separate words with stop words, duplicate words, and punctuation removed;
detecting anomalies based on anomalous words and normative words in the processed document portions;
generating a word count for the individual ones of the processed document portions by counting the number of separate words in the individual ones of the processed document portions;
identifying a referential word count;
calculating a word count ratio for the individual ones of the processed document portions by dividing the referential word count by the word count for the individual ones of the processed document portions;
determining a word frequency for individual words included in the document portions, the word frequency being a number of instances that a word is found in the document portions prior to removal of duplicate words;
generating a commonness score for the individual ones of the processed document portions by taking the square root of the sum of the squares of the inverse of the word frequency for the individual ones of the separate words in the individual ones of the processed document portions;
identifying a highest commonness score of the processed document portions;
calculating a commonness score ratio for the individual ones of the processed document portions by dividing the highest commonness score by the commonness score for the individual ones of the processed document portions;
calculating an overall score for individual ones of the processed document portions based on a normalization of the square root of the sum of the square of the word count ratio and the square of the commonness score ratio for the individual ones of the processed document portions; and
generating the user interface including at least one overall score for one of the processed document portions in proximity to the generated document identification number associated with the one of the processed document portions and an indicia indicating a result from the detecting anomalies for the one of the processed document portions.

US Pat. No. 10,657,367

METHODS AND SYSTEMS FOR HAND TRACKING

USens, Inc., San Jose, C...

1. A system for hand tracking, comprising:a head mounted display wearable by a user; and
a hand tracking camera module attached to the head mounted display and comprising at least one of a pair of stereo cameras or a depth camera, wherein:
the hand tracking camera module is configured to capture images of at least one physical hand of the user;
the head mounted display is configured to render a virtual hand resembling the physical hand in a virtual environment for viewing by the user based at least on the images; and
a processor and a non-transitory computer-readable storage medium storing instructions that, when executed by the processor, cause the processor to:
(a) obtain an image in a current frame and at least one of determined skeleton joints or a determined 3D object pose in a previous frame as inputs to execute a Hand and Object Detection algorithm to determine if the physical hand holds an object in the current frame;
(b) in response to determining that the physical hand holds no object:
execute a 3D Hand Skeleton Joints Recognition algorithm to determine 3D skeleton joints of the physical hand in 26 degrees-of-freedom in the current frame,
render the virtual hand based at least on the determined 3D skeleton joints, and
feedback the determined 3D skeleton joints to the Hand And Object Detection algorithm for determining if the physical hand holds any object in a next frame;
(c) in response to determining that the physical hand holds an object:
execute a 3D Hand Skeleton Joints And Robust Object Pose Recognition algorithm to determine 3D skeleton joints of the physical hand in 26 degrees-of-freedom and a 3D object pose of the object in the current frame,
render the virtual hand based at least on the determined 3D skeleton joints, and
feedback the determined 3D skeleton joints and the determined 3D object pose to the Hand And Object Detection algorithm for determining if the physical hand holds any object in a next frame; and
(d) recursively perform (a)-(c) for the next frame.

US Pat. No. 10,657,366

INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND STORAGE MEDIUM

Canon Kabushiki Kaisha, ...

1. An image processing apparatus comprising:one or more processors; and
one or more memories having instructions stored thereon which, when executed by the one or more processors, cause the apparatus to:
recognize, based on a first image of a real space captured from a first viewpoint, a posture of a real object in the first image of the real space;
set a second viewpoint which is different from the first viewpoint;
generate a second image of a virtual object corresponding to the real object, in the recognized posture viewed from the set second viewpoint; and
display the generated second image of the virtual object corresponding to the real object, in the recognized posture viewed from the set second viewpoint on a display.

US Pat. No. 10,657,365

SPECIFIC PERSON DETECTION SYSTEM AND SPECIFIC PERSON DETECTION METHOD

HITACHI KOKUSAI ELECTRIC ...

1. A specific person detection system comprising:a detection device including a specific person recording unit that holds a specific person,
an image pickup device, and
a terminal device,
wherein the detection device:
obtains a person most similar to a feature value extracted from image data obtained by the image pickup device from the specific person recording unit, calculates similarity between a feature value extracted from other image data and the person, and outputs a person having angle information most similar to the person, from persons having high similarity, as a collation result to the terminal device,
stores a person's image pickup angle of the person in a list of specific persons,
detects an arbitrary person with his/her image pickup angle, from an image obtained with the image pickup device,
obtains coincidence from feature all collation between the list of specific persons and the detected person, and performs specific person primary detection,
wherein the specific person detection system further comprises a recording device recording other image data,
wherein the detection device;
obtains another image other than the primary-detected image from the recording device,
detects a person the same as a primary-detected person with his/her image pickup angle, from the obtained another image, and performs collation, and
performs specific person comprehensive determination using the coincidence by a series of collation including the primary-detected result and the image pickup angle.

US Pat. No. 10,657,363

METHOD AND DEVICES FOR AUTHENTICATING A USER BY IMAGE, DEPTH, AND THERMAL DETECTION

Motorola Mobility LLC, C...

1. A method in an electronic device, the method comprising:capturing, with an imager, at least one image of an object;
scanning, with a depth imager, at least one depth scan of the object;
detecting, with a thermal sensor, an amount of thermal energy received from the object;
comparing, with one or more processors:
the at least one image with one or more predefined reference images; and
the at least one depth scan with one or more predefined facial maps;
determining, with the one or more processors, whether the amount of thermal energy received from the object is within a predefined temperature range; and
where:
the at least one image sufficiently corresponds to at least one of the one or more predefined images;
the at least one depth scan corresponds to at least one of the one or more predefined facial maps; and
the amount of thermal energy received from the object is within the predefined temperature range;
authenticating the object as a user authorized to use the electronic device.

US Pat. No. 10,657,362

FACIAL RECOGNITION SYSTEM

NEC Corporation of Americ...

1. A facial recognition system, comprising:a camera;
a processor configured to:
receive image data from the camera, the image data including a first image of a face of an individual;
determine a first value for a lighting parameter associated with the first image;
determine whether a collection of previously obtained images of the face of the individual in a biometric database includes a second image having a second value for the lighting parameter that meets a first predetermined condition relative to the first value for the lighting parameter; and,
store the first image in the biometric database along with the first value for the lighting parameter when the collection of previously obtained images does not include a second image having a second value for the lighting parameter that meets the first predetermined condition relative to the first value for the lighting parameter.

US Pat. No. 10,657,361

SYSTEM TO ENFORCE PRIVACY IN IMAGES ON AN AD-HOC BASIS

International Business Ma...

1. A method for selectively modifying digital images, the method comprising:receiving, from a first computing device in broadcast range of a second computing device, a first image-hash, wherein the first image-hash includes data characterizing a face of a first individual;
determining a first location of the second computing device;
registering the first image-hash as active in an image hash list, along with the first location;
capturing, using the second computing device, a first digital image;
identifying a first plurality of faces depicted in the first digital image;
upon determining, based on the first image-hash, that a first face of the first plurality of faces matches the face of the first individual:
altering the first digital image to obscure the face of the first individual depicted in the first digital image;
upon determining, based on the image hash list, that a second face of the first plurality of faces does not match any image-hash in the image hash list:
refraining from altering the second face in the first digital image, such that the second face is not obscured in the first digital image;
capturing, using the second computing device, a second digital image;
determining a updated location of the second computing device; and
upon determining that a distance between the updated location and the first location exceeds a predefined threshold:
registering the first image-hash as disabled in the image hash list, such that the face of the first individual will not be obscured in the second digital image.

US Pat. No. 10,657,360

APPARATUS, SYSTEMS AND METHODS FOR IMPROVED FACIAL DETECTION AND RECOGNITION IN VEHICLE INSPECTION SECURITY SYSTEMS

Gatekeeper Inc., Sterlin...

1. A method for identifying a vehicle occupant, comprising:providing a camera comprising a camera lens having a field of view directed towards an oncoming vehicle;
detecting via a sensor, the presence of the oncoming vehicle, wherein the vehicle includes at least one vehicle window separating a vehicle interior enclosure from an external environment, wherein the at least one vehicle window has a frame surrounding the at least one vehicle window;
upon detecting the presence of the oncoming vehicle, triggering the automatic capture, by the camera, of a plurality of current facial images of at least one vehicle occupant present within the vehicle interior enclosure when the at least one vehicle window frame is determined, via image analysis, to be maximized in the field of view, wherein each of the plurality of current facial images is captured through the camera lens from a different distance to the oncoming vehicle;
processing the captured plurality of current facial images to remove at least one non-face object;
obtaining, by a processing unit, at least one archived image of at least one individual;
comparing, by the processing unit, at least one of the plurality of processed current facial images with the at least one archived image; and
determining whether the vehicle occupant in the at least one of the plurality of current facial images is the same individual as the at least one individual from the at least one archived image.

US Pat. No. 10,657,359

GENERATING OBJECT EMBEDDINGS FROM IMAGES

Google LLC, Mountain Vie...

15. A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations for end-to-end training of an object embedding system, the operations comprising:iteratively training the object embedding system on a plurality of images, each of the images depicting an object of a particular type, each iteration of the training comprising:
providing selected images as input to the object embedding system and generating corresponding embeddings, wherein the object embedding system comprises a thumbnailing neural network and an embedding neural network, wherein each neural network comprises a plurality of consecutive layers that are exclusive of each other, and wherein generating an embedding for an object depicted in an image using the object embedding system comprises:
generating a thumbnail representation of the object depicted in the image as output of the thumbnailing neural network, wherein the thumbnailing neural network processes an input in accordance with values of a set of thumbnailing neural network parameters to:
determine values of parameters of a spatial transformation that defines a correspondence between pixels of the thumbnail representation and pixels of the image; and
generate as output the thumbnail representation using the spatial transformation and the image;
generating an embedding by providing the thumbnail representation as input to the embedding neural network that is configured to process the thumbnail representation in accordance with values of a set of embedding neural network parameters to generate an embedding as output;
determining gradients based on a loss function to reduce a distance between embeddings for same instances of objects, and to increase the distance between embeddings for different instances of objects; and
adjusting the values of the set of thumbnailing neural network parameters and the values of the set of embedding neural network parameters using the gradients.

US Pat. No. 10,657,358

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

FUJITSU LIMITED, Kawasak...

1. An information processing apparatus comprising:a memory configured to store first information of a first fingerprint image; and
a processor coupled to the memory and configured to:
obtain second information of a second fingerprint image;
generate third information of a third fingerprint image by enlarging or reducing the second fingerprint image;
specify an enlargement rate or a reduction rate based on a first similarity between the second information and the first information and a second similarity between the third information and the first information; and
execute a first matching process of the first information and fourth information of a fourth fingerprint image, the fourth fingerprint image being generated by enlarging or reducing the first fingerprint image by the specified enlargement rate or the reduction rate.

US Pat. No. 10,657,357

FINGERPRINT IDENTIFICATION PANEL AND A METHOD FOR DRIVING THE SAME, AND DISPLAY APPARATUS

BOE TECHNOLOGY GROUP CO.,...

1. A fingerprint identification panel, comprising a plurality of first electrode strips, a plurality of second electrode strips, a scanning device, a sensing signal providing device and an identification device, whereinthe plurality of first electrode strips and the plurality of second electrode strips are insulated from and intersected with each other;
the scanning device is configured to provide driving signals to the plurality of first electrode strips in turn, and the sensing signal providing device is configured to provide sensing signals to the plurality of second electrode strips, and a capacitor is formed between each of the plurality of first electrode strips and one second electrode strip adjacent to the first electrode strip;
the plurality of second electrode strips are connected with the identification device, and are configured to transmit signals that reflect electricity quantities of the capacitors to the identification device;
the identification device is configured to determine a morphology of a fingerprint based on the signals received from the second electrode strips, and
the fingerprint identification panel further comprises a counter, a driving signal received by one first electrode strip is a clock signal, coordinates of a touch point are composed of a row number of the one first electrode strip receiving the driving signal and a column number of one second electrode strip at which the signal changed, a count value obtained by the counter is the number of the clock signal plus 1, and a row number of the one first electrode strip corresponding to the touch point is determined based on the counter value of the counter.

US Pat. No. 10,657,356

ELECTRONIC APPARATUS AND FINGERPRINT MODULE THEREOF

GUANGDONG OPPO MOBILE TEL...

1. A fingerprint module, comprising:a fingerprint identifying assembly;
a decoration component, a front side of the decoration component defining an embedded groove, wherein the fingerprint identifying assembly is embedded in the embedded groove;
a circuit board assembly, an end of the circuit board assembly extending into the embedded groove and being attached to a rear end surface of the fingerprint identifying assembly, wherein a ground terminal is disposed on the circuit board assembly; and
a conductive component, sandwiched between the end of the circuit board assembly and a bottom wall in the embedded groove of the decoration component to electrically connect the decoration component to the ground terminal through the circuit board assembly;
wherein the bottom wall defines a through hole, and the circuit board assembly comprises:
a flexible circuit board, an end of the flexible circuit board extends into the embedded groove through the through hole, and is attached to the rear end surface of the fingerprint identifying assembly, and the other end of the flexible circuit is outside the decoration component, the ground terminal is disposed on the other end of the flexible circuit board.

US Pat. No. 10,657,355

ELECTRONIC APPARATUS AND FINGERPRINT MODULE THEREOF

GUANGDONG OPPO MOBILE TEL...

1. A fingerprint module, comprising:an encapsulation layer, configured to encapsulate a fingerprint identifying assembly; wherein the encapsulation layer comprises a plate-shaped portion having a rear wall, and a protruding portion located at the center of the rear wall, and an edge region of the rear wall is recessed relative to the protruding portion, such that a thickness of the protruding portion is larger than a thickness of the edge region; and
a decoration component, defining an embedded groove and a recess portion in the embedded groove;
wherein the fingerprint identifying assembly is embedded in the embedded groove; the plate-shaped portion covers the embedded groove, and the protruding portion is embedded in the embedded groove and attached to one side of the fingerprint identifying assembly, and the protruding portion is embedded to the recess portion.

US Pat. No. 10,657,354

COMPACT SYSTEM FOR REGISTERING PAPILLARY RIDGE PATTERNS

ABILMA LLC, Moscow (RU)

1. A system for recording a ridge pattern comprising:a light source, an element which defines a position of a reading surface of the ridge pattern, an optical system, and a multi-element image receiver, wherein,
the light source and the reading surface are optically linked to the multi-element image receiver by rays emitted from the light source in the direction of the reading surface being reflected from the reading surface and passing through a guiding optical element,
the guiding optical element is made in a form of a prism and comprises an input refractive surface for refraction and reflection of a luminous flux which is a carrier of an image of the ridge pattern and a reflective surface and a surface for output of the luminous flux, and
the guiding optical element is located in a device such that the rays, being a carrier of the ridge pattern and coming out of the element, are first refracted on the input refractive surface, then are reflected from the reflective surface and fall again on the input refractive surface at an angle of full internal reflection, and after having been reflected from the input refractive surface go out through the surface for outputting of the luminous flux towards the multi-element image receiver.

US Pat. No. 10,657,353

PHOTOELECTRIC SENSOR, ARRAY SUBSTRATE, DISPLAY PANEL AND DISPLAY DEVICE

BOE TECHNOLOGY GROUP CO.,...

1. A photoelectric sensor for fingerprint recognition, comprising:a first transparent electrode layer, configured to receive incident light;
a first electrode layer, being lighttight and disposed opposite to the first transparent electrode layer; and
a light sensing layer, located between the first electrode layer and the first transparent electrode layer, wherein the light sensing layer comprises a plurality of nanocrystalline silicon particles with different particle sizes,
wherein the light sensing layer comprises:
a plurality of nanocrystalline silicon layers, each comprising nanocrystalline silicon panicles with a same particle size,
wherein the nanocrystalline silicon particles comprised in one of the plurality of nanocrystalline silicon layers have a particle size different from that of the nanocrystalline silicon particles comprised in another of the plurality of nanocrystalline silicon layers.

US Pat. No. 10,657,352

FLAT PANEL DISPLAY EMBEDDING OPTICAL IMAGING SENSOR

LG Display Co., Ltd., Se...

1. A directional optical unit of a display panel with an embedded image sensor, the display panel having a display area and a non-display area, comprising:a first cover plate and a second cover plate facing each other;
a first low refractive layer disposed between the first and second cover plates;
a light radiating film disposed under the second cover plate and having a length corresponding to the display area;
a light incident film disposed under the second cover plate and outside the display area at one lateral side of the light radiating film;
a second low refractive layer disposed under the light radiating film and the light incident film and attached on the display panel;
a light source disposed at the lateral side of the display panel and facing the light incident film; and
a light blocking layer blocking 0th diffraction light, disposed under the first cover plate and on at least one side of the non-display area.

US Pat. No. 10,657,351

IMAGE PROCESSING APPARATUS

FotoNation Limited, Galw...

1. An image processing apparatus comprising:an image capture sensor;
a plurality of infra-red (IR) sources; and
a processor operatively coupled to the plurality of IR sources and the image capture sensor and configured to:
acquire multiple images from the sensor, each image illuminated with one or more of the IR sources such that each image is captured with illumination from a different direction;
combine component images corresponding to the multiple images into a final combined image by:
determining a median value for corresponding pixel locations of subsets of the component images;
setting the determined median value as a pixel value for a respective intermediate combined image; and
combining the intermediate combined images into the final combined image by selecting a median value for corresponding pixel locations of the intermediate combined images as a pixel value for corresponding pixel locations of the final combined image.

US Pat. No. 10,657,350

FINGER DETECTION WITH AUTO-BASELINE TRACKING

Synaptics Incorporated, ...

1. A processing system for automatically tracking a baseline input into a biometric sensor, the processing system comprising:an amplifier having at least one input terminal and an output terminal for producing an output signal based on at least one input signal received by the at least one input terminal of the amplifier;
at least one signal conditioning element coupled to the at least one input terminal of the amplifier and configured to condition at least one compensation signal;
a control circuit providing a feedback signal to the at least one signal conditioning element that adjusts one or more signal conditioning parameters of the at least one signal conditioning element based on the output signal of the amplifier; and
a comparator configured to compare the output signal of the amplifier to a single baseline threshold,
wherein the control circuit receives an output of the comparator,
wherein the at least one input signal received by the at least one input terminal of the amplifier includes a combination of the at least one compensation signal and a signal from a first set of one or more receiver electrodes of the biometric sensor, and
wherein the feedback signal is derived from the output of the comparator.

US Pat. No. 10,657,349

ULTRASONIC MODULE AND METHOD FOR MANUFACTURING THE SAME

J-METRICS TECHNOLOGY CO.,...

1. An ultrasonic module comprising:a substrate having an upper surface and a lower surface opposite to the upper surface;
a composite layer having a top surface, a bottom surface, and a recessed surface recessed toward the bottom surface, wherein the bottom surface is on the upper surface of the substrate, at least one space is formed between the recessed surface and the upper surface, the composite layer has at least one first groove, the at least one first groove is extending from the top surface toward the recessed surface, and the at least one first groove separates the composite layer into a circuit structure and an ultrasonic structure connected to the circuit structure, the ultrasonic structure corresponds to the recessed surface; and
a covering layer assembled on the top surface of the composite layer.

US Pat. No. 10,657,348

FINGERPRINT SENSOR AND MANUFACTURING METHOD THEREOF

Samsung Display Co., Ltd....

1. A fingerprint sensor comprising:a sensor substrate;
a plurality of sensor pixels configured to sense a capacitance change corresponding to a touch of a user, wherein each of the sensor pixels includes a sensor electrode;
an adhesive member on the sensor substrate and the plurality of sensor pixels; and
a sensor protection layer disposed on the adhesive member,
wherein the sensor protection layer includes a first region having a first permittivity and a second region having a second permittivity less than the first permittivity.

US Pat. No. 10,657,347

METHOD FOR CAPTURING FINGERPRINT AND ASSOCIATED PRODUCTS

GUANGDONG OPPO MOBILE TEL...

1. A terminal device comprising an application processor, an optical fingerprint sensor and a touch screen, the touch screen comprising a first area, and the optical fingerprint sensor being arranged under the first area, whereinthe application processor is configured to detect a fingerprint capturing instruction sent by a currently running application being one of a plurality of applications, to determine a first luminance based on the currently running application when the fingerprint capturing instruction sent by the currently running application is detected, to control light-emitting units for the first area to emit light with the first luminance, and to control the first area to display a prompting message of inputting the fingerprint; and
the optical fingerprint sensor is configured to capture the fingerprint when the light with the first luminance illuminates the first area,
each application of the plurality of applications is assigned to one security level, and each security level is assigned to one specific luminance; when the security level of an application i is greater than the security level of an application j, the first luminance corresponding to the application i is greater than the first luminance corresponding to the application j,
the higher the luminance, the higher the sharpness of a fingerprint captured by the optical fingerprint sensor.

US Pat. No. 10,657,346

3-D LOCALIZATION AND IMAGING OF DENSE ARRAYS OF PARTICLES

The Regents of The Univer...

1. A super-resolution imaging method of at least one object, the method comprising:irradiating at least one object;
capturing a series of sub-images of the at least one object from light collected from the at least one object responsive to the irradiating;
specifying a plurality of point-spread-function dictionary coefficients for each sub-image in the series of sub-images, each of the plurality of point-spread-function dictionary coefficients corresponding with a different point spread function element from a point-spread-function dictionary such that for each sub-image in the series of sub-images, a best representation comprising a superposition of point spread function elements, each multiplied by a corresponding one of the plurality of point-spread-function dictionary coefficients, best represents the data of the sub-image; and
generating a reconstruction of at least one sub-image of the series of sub-images from the corresponding best representation found.

US Pat. No. 10,657,345

MEDIA DESTRUCTION VERIFICATION APPARATUS

Phiston Technologies, Inc...

1. A verification apparatus securable to a media disk destruction device, said verification apparatus comprising:a housing constructed and arranged for securement to an upper surface of said media disk destruction device, said housing having an inlet for receipt of a solid state drive (SSD) disk to be processed, an outlet aligned with an opening to said media destruction device for receipt of an SSD disk that meets predetermined parameters, and a SSD disk ejection outlet for return of an SSD disk that fails to meet said predetermined parameters;
a display screen having an operator interface secured to said housing, said display screen electrically coupled to a microprocessor based controller containing said predetermined parameters;
a scanner camera mounted inside said housing and coupled to said controller, said scanner recording SSD disk label data placed through said housing and displayed on said screen, said controller analyzing if a recorded SSD disk label data is in accordance with said predetermined parameters;
a carrier drum having a receptacle for holding a SSD disk, said carrier drum rotatable to a first position for receipt of the SSD disk, a second position for positioning the SSD disk in front of said scanner camera, a third position for aligning said receptacle to said media destruction device opening, and a fourth position for aligning said SSD disk to said ejection outlet; and
a motor coupled to said carrier drum and said controller;
wherein successful scanning of said SSD disk label data allows said carrier drum to rotate to said third position for directing the SSD disk into said media destruction device opening for sanitization, or alternatively rotating said carrier drum to said fourth position for ejecting the SSD disk due to a scanner fault.

US Pat. No. 10,657,344

TRANSACTION OPTIMIZATION THROUGH SCANNED DATA

United Services Automobil...

1. A computing system comprising:at least one processor; and
memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, instruct the at least one processor to perform operations comprising:
receiving vehicle data associated with a vehicle, wherein the vehicle data is retrieved through a scan, by at least one scanning component, of a vehicle tag that includes the vehicle data;
transmitting, over at least one network, the vehicle data to at least one transaction service executing on at least one remote server computing device;
receiving transaction data that is generated by the at least one transaction service based at least partly on the vehicle data, wherein the transaction data represents a transaction associated with the vehicle; and
presenting the transaction data in a user interface (UI).

US Pat. No. 10,657,343

LOCATION-BASED EMBEDDED PATTERNS FOR VEHICLE DETECTION AND DATA PROCESSING

PAYPAL, INC., San Jose, ...

1. A device comprising:an image capture component;
a non-transitory memory storing instructions; and
one or more hardware processors coupled to the non-transitory memory and configured to read the instructions from the non-transitory memory to cause the device to perform operations comprising:
capturing, using the image capture component, a first image at a first scene during an operation of a vehicle, the first image comprising a first embedded pattern within a first physical object at the first scene;
determining first data from the first embedded pattern;
accessing a pattern database and determining that the first embedded pattern corresponds to first data; and
in response to determining the first embedded pattern corresponds to the first data, launching an application process and performing a transaction utilizing the first data.

US Pat. No. 10,657,342

PORTABLE WIRELESS COMMUNICATION TERMINAL INSTALLED ON A SHOPPING CART

TOSHIBA TEC KABUSHIKI KAI...

1. A portable wireless communication terminal installed on a shopping cart, comprising:a reader;
a first wireless communication interface;
a second wireless communication interface;
a display; and
a processor configured to:
control the reader to read a commodity code that identifies a commodity to be purchased by a customer in a store;
wirelessly retrieve through the first wireless communication interface, information for promotion relating to the commodity; and
upon receipt of the information for promotion, control the display to display a screen indicating the received information;
upon receipt of an input for checkout via the screen, determine whether the communication terminal can communicate with a Point of Sales (POS) terminal through the second wireless communication interface; and
upon determining that the communication terminal can communicate with the POS terminal, control the second wireless communication interface to transmit the commodity code to the POS terminal for checkout.

US Pat. No. 10,657,341

SYSTEM, APPARATUS AND METHOD FOR SEQUENCING OBJECTS HAVING RFID TAGS ON A MOVING CONVEYOR

Walmart Apollo, LLC, Ben...

14. A method of tracking objects using radio frequency identification (RFID) communications, the method comprising:transporting a plurality of objects along a conveyance path of a conveyor system, wherein each of the plurality of objects includes a near field only RFID tag associated therewith and identifying the object;
sending, by a first RFID tag reader positioned relative to a first portion of the conveyor system, read signals to attempt to read the near field only RFID tag of each of the plurality of objects;
receiving, by the first RFID reader, responses from the near field only RFID tag of each of the plurality of objects when the near field only RFID tag is within the near field of RFID communications of the first RFID reader; and
processing, by a control circuit, the responses from the plurality of near field only RFID tags to determine an order of the plurality of objects being conveyed.

US Pat. No. 10,657,340

SYSTEMS AND METHODS FOR IMPROVED TAG POSITION TRACKING

SENSORMATIC ELECTRONICS, ...

1. A method for determining a tag's position in a given area, comprising:performing, by a tag reader, a standard inventory process to obtain a unique identification code for a first tag in a randomly selected timeslot;
assigning, by the tag reader, a local short address to the first tag that is shorter than the unique identification code;
wirelessly communicating the local short address from the tag reader to the first tag;
performing, by the tag reader, an enhanced inventory process to receive a ping command response signal including the local short address from the first tag in an assigned timeslot; and
determining a first position of the first tag in the given area based on the phase of the ping command response signal.

US Pat. No. 10,657,339

AGRICULTURE EXCHANGE

AGEX, INC., Austin, TX (...

1. A system comprising:one or more animal tags, each animal tag having an animal identification data and configured to be affixed to a live animal;
a searchable database containing a product data card for each animal tag, a seller data, a buyer data, and a vendor data, wherein the product data card associates the animal identification data of the animal tag to the live animal and includes an animal data for the live animal;
a server communicably coupled to the searchable database, the server comprising a server memory and a server processor, wherein the server processor stores and maintains each product data card, seller data, buyer data and vendor data in the searchable database;
one or more remote devices communicably coupled to the server, each remote device comprising a remote device memory and a remote device processor, wherein the remote device processor performs one or more functions comprising acquiring the animal data, transmitting the animal data to the server, and monitoring a performance of the live animal; and
the server receives: (1) a seller information from one of the remote devices, and stores, indexes and updates the seller data using the seller information, (2) a buyer information from one of the remote devices, and stores, indexes and updates the buyer data using the buyer information, and (3) a vendor information from one of the remote devices, and stores, indexes and updates the vendor data using the vendor information.

US Pat. No. 10,657,338

MICROWAVE ANTENNA ARRAY AND TESTBED FOR OSTEOPOROSIS DETECTION

1. A microwave sensing device comprising:at least one 2×1 transmitting antenna array assembly comprising:
at least a first and second antenna, wherein each antenna further comprises:
a radiator element, and
a ground element, and
a 180° power splitter, wherein the radiator of the first antenna and the radiator of the second antenna are driven out of phase by the 180° power splitter.