US Pat. No. 10,430,849

PROPAGATION OF CUSTOMER PREFERENCES

SQUARE, INC., San Franci...

1. A method comprising:receiving, at a payment service and from a first merchant point of sale (POS) device of a first merchant, a first request to authorize a payment instrument of a user for a cost of a first transaction between the user and the first merchant, the first request indicating at least payment information associated with the payment instrument and order information pertaining to the first transaction, the order information including a first item customization preference of the user customizing an item acquired by the user in the first transaction;
attempting to authorize the payment instrument for the cost of the first transaction;
identifying, using the payment information, a profile of the user at the payment service;
identifying, from the order information, the first item customization preference;
storing the first item customization preference of the user in the profile of the user at the payment service along with at least a second item customization preference of the user;
receiving, from a second merchant POS device of a second merchant and after storing the first item customization preference, a second request to authorize the payment instrument for a cost of a second transaction between the user and the second merchant, the second request indicating at least the payment information and identifying a second item to be acquired by the user in the second transaction;
identifying the profile of the user at the payment service using the payment information in response to receipt of the second request;
ranking a plurality of item customization preferences according to pertinence to the second merchant, wherein the plurality of item customization preferences include the first item customization preference amd the second item customization preference;
identifying one or more most pertinent item preferences of the plurality of item customization preferences based on the ranking of the plurality of item customization preferences according to pertinence to the second merchant, wherein the one or more most pertinent item preferences include the first item customization preference;
sending the one or more most pertinent item preferences to the second merchant POS device of the second merchant in response to identifying the one or more most pertinent item preferences of the plurality of item customization preferences, thereby sending the first item customization preference to the second merchant POS device without sending the second item customization preference to the second merchant POS device; and
attempting to authorize the payment instrument for the cost of the second transaction after sending the one or more most pertinent item preferences to the second merchant POS device, wherein the second transaction includes acquisition by the user of the second item customized according to the first item customization preference.

US Pat. No. 10,430,846

TRANSACTION FACILITATING MARKETPLACE PLATFORM

Panjiva, Inc., New York,...

1. A computer-implemented method for ranking supplier or buyer search results comprising:converting, with a processor, structured data associated with a plurality of suppliers into a unified data format independent of a physical format of delivery and a logical formatting of the structured data;
storing, in a memory device, the structured data in the unified format;
comparing, with a processor, the structured data to search keywords received from a user through a user interface hosted by a server;
generating, with the processor, a candidate search result set of entities based on the comparison, wherein the candidate search result set of entities comprises a filtered number of suppliers from the plurality of suppliers;
weighting a combination of a plurality of entity performance measures for a portion of the entities in the candidate search result set of entities, wherein the plurality of entity performance measures includes at least one measure selected from the list consisting of: number of shipments made by the supplier that matches at least one aspect of a buyer's request, number of similar products the supplier makes that match the buyer's request, export value per category of product exported by the supplier, and number of certifications or clearances that a particular supplier has;
ranking, with the processor, the filtered number of suppliers based on the weighted combination of the plurality of entity performance measures; and
arranging the search results based on the ranking.

US Pat. No. 10,430,845

SYSTEMS AND METHODS FOR AUTOMATED PURCHASE REQUESTS

ADVENTIVE, INC., Rochest...

1. A method for facilitating automated product procurement according to established authorization level data, the method comprising:receiving by a processor of an application provider apparatus a purchase request to purchase at least one product, the purchase request submitted by a specified user within a group of users in a business enterprise and via a shopping cart of a Website, wherein the shopping cart includes transaction detail data comprising the purchase request;
determining and providing by the processor of the application provider apparatus payment option data comprising one or more of a plurality of payment options available for use by the specified user based on an established authority of the specified user;
receiving by the processor of the application provider apparatus a selection of one of the one or more provided payment options from the specified user;
determining by the processor of the application provider apparatus the submitted purchase request does not comply with stipulated approval level data for the specified user based at least in part on at least a portion of the transaction detail data, without user intervention, wherein the stipulated approval level data comprises a level of purchasing authority of the specified user based on designation data for the specified user comprising a designation of the user within the business enterprise, the level of purchasing authority comprising a maximum allowable number of purchase requests for the specified user within a specified time period;
and
denying by the processor of the application provider apparatus the submitted purchase request and transferring the transaction detail data comprising the purchase request from the shopping cart to a computing device associated with another of the group of users having associated authority data indicating an authority to submit the purchase request within the specified time period based on an obtained number of purchase requests previously-submitted by the other of the group of users within the specified time period.

US Pat. No. 10,430,843

METHOD AND SYSTEM FOR PURCHASING NON-FUEL MERCHANDISE

ADDITECH, INC., Sugar La...

1. A system, comprising:a fuel dispenser for dispensing fuel to a vehicle;
a fuel additive system in communication with the fuel dispenser, wherein the fuel additive system comprises:
a computer system; and
a hydraulic controller for dispensing a fuel-additive product to the vehicle; and
a point-of-sale system in communication with the fuel dispenser and the fuel additive system, wherein at least a portion of the point-of-sale system is located inside a retail store, and wherein the computer system of the fuel additive system is for:
monitoring purchase messages between the fuel dispenser and the point-of-sale system for purchase selections made at the fuel dispenser to determine whether purchases at the fuel dispenser include the fuel-additive product;
upon a determination that a first purchase message of the purchase messages between the fuel dispenser and the point-of-sale system does not include the fuel-additive product, subsequently passing the first purchase message to the point-of-sale system; and
upon a determination that the first purchase message includes the fuel-additive product:
creating a new purchase message regarding the fuel-additive product in a format receivable by the point-of-sale system and forwarding the new purchase message to the point-of-sale system; and
upon detecting dispenser fuel pulses from the fuel dispenser indicative of fuel flow, controlling the hydraulic controller to dispense the fuel-additive product for the vehicle; and
wherein the point-of-sale system is for presenting a total amount of the purchase selections at the point-of-sale system.

US Pat. No. 10,430,842

METHOD, SYSTEM AND COMPUTER PROGRAM PRODUCT FOR DYNAMICALLY PRICING PERISHABLE GOODS

ECONOMEMETICS AB, Helsin...

1. A method comprising:performing a pricing process for perishable goods on a programmed data processing apparatus,
wherein the programmed data processing apparatus comprises a memory system for storing program code instructions and data, a processing system configured to execute at least some of the program code instructions and to process the data stored in the memory system, and
wherein the processing system is operatively coupled to a database system,
wherein the database system stores information on a plurality of items of goods, wherein the memory system comprises program code instructions for causing the processing system to carry out the pricing process, wherein the pricing process comprises the following acts for each of a plurality of items of goods:
a) monitoring a time parameter T corresponding to the time period from T0 to Tn when an item of goods is good for sale, and if the time parameter T b) periodically updating a current price Pcurrent for the item of goods at every predetermined time interval to dynamically reflect potential buyers' interests, based on an estimation of how many items of goods should have been sold in order for exactly all of the items of goods to be sold at the highest possible average price before Tn, and a real demand for an ongoing sale situation after commerce starts;
c) producing a virtual marketplace displaying in a general buyer interface information of the item of goods including the periodically updated current price Pcurrent viewable by buyers through buyer terminals connected to the virtual marketplace via a network;
d) setting a maximum number of items Vquote for the buyers indicating a maximum number of items of goods purchasable by each buyer during a freeze time period ?Tfreeze, Vquote being equal to or smaller than a maximum cumulative volume of the perishable goods MAX(CV);
e) receiving an indication of interest to buy at least one item of goods from a particular buyer through one of the buyer terminals interacting with the virtual marketplace;
f) in response to receiving the indication of interest to buy the at least one item of goods, generating a buyer specific buyer interface associated with the time of receiving the indication of interest, displaying in the buyer specific buyer interface a temporarily fixed price Pfreeze equal to current price Pcurrent for the freeze time period ?Tfreeze, viewable through the buyer terminal by said particular buyer that indicated the interest to buy the at least one item of goods;
g) automatically updating the current price Pcurrent in response to offering a temporarily fixed price Pfreeze, taking into consideration the indication of interest, and displaying in the general buyer interface the updated current price Pcurrent viewable by buyers through buyer terminals connected to the virtual marketplace;
h) keeping periodically updating the current price Pcurrent for the item of goods displayed in the general buyer interface while keeping the temporarily fixed price Pfreeze displayed in the buyer specific buyer interface unchanged during the freeze time period ?Tfreeze;
i) accepting a purchase order for the at least one item of goods at the temporarily fixed price Pfreeze if a number of the at least one item of goods of the purchase order is equal to or smaller than the maximum number of items Vquote for the particular buyer and the purchase order is received within the freeze time period ?Tfreeze from the buyer terminal interacting with the displayed item of goods in the virtual marketplace;
j) rejecting the purchase order if the number of the at least one item of goods of the purchase order exceeds the maximum number of items Vquote for the particular buyer;
k) rejecting the purchase order if the purchase order is received after the freeze time period ?Tfreeze;
l) automatically updating the current price Pcurrent of the item of goods in response to receiving an accepted and/or rejected order and displaying in the general buyer interface the updated current price Pcurrent viewable by buyers through buyer terminals connected to the virtual marketplace; and
automatically repeating the acts b) through l) until the time parameter T equals the maximum time Tn.

US Pat. No. 10,430,841

SYSTEMS FOR DETERMINING CUSTOMER INTEREST IN GOODS

Capital One Services, LLC...

1. A system for determining customer interest in goods, comprising:one or more memory devices storing instructions; and
one or more processors configured to execute the instructions to:
receive customer location data from a smart device associated with a customer indicating the customer is within a retail venue of a retailer;
monitor, based on the customer location data, a current location of the customer within the retail venue;
receive goods location data from a plurality of transmitter devices indicating locations of goods for sale within the retail venue;
monitor, based on the goods location data, a current location of the goods within the retail venue;
determine that the customer is interested in a particular good for sale within the retail venue based on one of the current customer location remaining in proximity to the current location of the particular good for a predetermined period of time, or a listing of the particular good within proximity to the customer on a customer account;
store each determination that the customer is interested in the particular good for sale within the retail venue;
generate a profile of shopping behavior of the customer based on the stored interest determinations;
conduct a search of pricing of the particular good at one or more other retailers;
send a price comparison to the customer for the particular good based on results of the price search; and
generate a model of the customer interest in a plurality of goods at the retail venues.

US Pat. No. 10,430,840

SYSTEMS AND METHODS FOR CREATING AN INTERSTITIAL AD EXPERIENCE WITHIN A SCROLLING CONTENT FRAME

GOOGLE LLC, Mountain Vie...

1. A method of controlling the display of content of information resources, comprising:receiving, by one or more servers including one or more processors, a request for an information resource from an application executing on a client device; and
transmitting, by the one or more servers, the information resource to the client device, the information resource including at least a first content portion, a second content portion, and a content display management script, the content display management script including computer-executable instructions, which when executed by a processor of the client device, causes the application of the client device to:
set a scroll range of the information resource to a first range extending from a first location in the information resource to a second location in the information resource to allow scrolling through the first content portion and a content item and to restrict scrolling onto the second content portion;
permit, based on the scroll range set to the first range, display of the first content portion and the content item between the first location and the second location of the information resource, the content item including an actionable item configured to cause the application to set the scroll range of the information resource to a second range extending from the first location to a third location; and
responsive to detecting an interaction on the actionable item of the content item, set the scroll range to the second range extending from the first location to the third location of the information resource to allow scrolling through the first content portion, the content item, and the second content portion while maintaining a current scroll position within the information resource.

US Pat. No. 10,430,839

DISTRIBUTED ADVERTISEMENT INSERTION IN CONTENT-CENTRIC NETWORKS

Cisco Technology, Inc., ...

1. A computer-executable method for facilitating delivery of advertisements over a Content-Centric Network, comprising:receiving, by a computing device implementing an affiliate network node in the Content-Centric Network, a content piece from a content producer, wherein the affiliate network node that receives the content piece is not the same as the content producer from which the content piece originated, and wherein the content piece includes a placeholder name prefix associated with a predetermined advertising slot;
modifying, by the affiliate network node, the content piece by replacing the placeholder name prefix with a name prefix of an advertisement or a name prefix associated with an advertiser;
hosting the modified content piece at the computing device implementing the affiliate network node for distribution to one or more clients;
receiving a request over the Content-Centric Network for the content piece from a client; and
delivering, by the affiliate network node, the modified content piece to the client over the Content-Centric Network.

US Pat. No. 10,430,838

METHODS AND SYSTEMS FOR GENERATION, CURATION, AND PRESENTATION OF MEDIA COLLECTIONS WITH AUTOMATED ADVERTISING

Snap Inc., Santa Monica,...

1. A method for automatic curation and editing of video and image content collections with a curation tool, the method comprising:receiving, at a server computer, a first plurality of content messages from a plurality of content sources, each content message comprising media content, and each content message being associated with a first media collection;
generating, using the curation tool and one or more processors, a presentation order for the first plurality of messages of the first media collection;
generating, by the curation tool and the one or more processors, a first continuous presentation group by associating a first content element from a first content message of the plurality of content messages and a second content element from a second content message of the plurality of content messages to associate the first content element and the second content element as the first continuous presentation group;
automatically determining advertising element placement within the presentation order for the first media collection using the curation tool and the one or more processors; and
automatically adjusting placement of a first advertising element within the presentation order, using the curation tool and the one or more processors, based on the association between the first content element and the second content element as the continuous presentation group to generate an adjusted presentation order.

US Pat. No. 10,430,837

DISPLAY REGION ALLOCATION USING CATEGORY-BASED CONTEXTUAL TECHNIQUES

PAYPAL, INC., San Jose, ...

1. A method, comprising:receiving, at a computer system from a user, a search query entered by the user via an input interface displayed on a user device;
causing allocation, by the computer system in response to the search query, of a first display region of the user device for displaying a combination of variable revenue ads and fixed price ads, the first display region including a first display portion allocated for display of only variable revenue ads and a second display portion allocated for display of only fixed price ads;
in response to a determination that there are not enough fixed price ads in a paid inventory of fixed price ads to fill positions allocated for fixed price ads in the first display region, the computer system moving at least one variable revenue ad into a position in the first display region that would otherwise be occupied by a fixed price ad, wherein the at least one variable revenue ad is selected to occupy the position based at least in part on a number of clicks associated with the at least one variable revenue ad;
causing display, by the computer system, of the first display region on the user device, including the first display portion including only variable revenue ads and the second display portion including only fixed price ads;
receiving a selection of one of the variable revenue ads or one of the fixed price ads; and
causing a view item page to be presented on the user device, the view item page being associated with the selected one of the variable revenue ads or one of the fixed price ads, the view item page being a different page than a first page, the view item page including a link to a merchant website that is associated with the selected one of the variable revenue ads or the one of the fixed price ads.

US Pat. No. 10,430,836

TARGETING AN AGGREGATE GROUP

Google LLC, Mountain Vie...

1. A computer implemented method for providing content comprising:identifying, using a processor, a relevant content item to be provided in a content slot associated with a content site at a first user device;
providing, for presentation with the relevant content item, a first user selectable re-publishing control, wherein selection of the first re-publishing control causes display of one or more second-republishing controls;
receiving first user input indicative of a selection of the first re-publishing control;
displaying, in response to receiving the first user input indicative of the selection of the first re-publishing control, one or more second re-publishing controls, wherein the one or more second re-publishing controls were not displayed prior to selection of the first re-publishing control, and wherein the one or more second re-publishing controls allow a user of content site to enter text to be associated with the relevant content item as a comment;
receiving, via the one or more second re-publishing controls, second user input including text to be associated with the relevant content item as a comment;
receiving third user input selecting a portion of the one or more second re-publishing controls and designating a group of recipients that is designated by the user and does not include the user as recipients of the relevant content item;
responsive to receiving the third user input, associating the text with the relevant content item and re-publishing the relevant content item along with the associated text to the group of recipients;
wherein re-publishing the relevant content item to the group of recipients includes providing to a second user device associated with a recipient from the group of recipients, the relevant content item along with content overlay information, the content overlay information causing the second user device to present a graphical visualization of a content overlay having (1) a third re-publishing control configured to allow the recipient from the group of recipients to re-publish the relevant content item, (2) an information control that, when selected, causes the second user device to retrieve and present additional information associated with the relevant content item, and (3) an indication of a geographic proximity of the user of the first user device to the second user device.

US Pat. No. 10,430,835

METHODS, SYSTEMS, AND MEDIA FOR LANGUAGE IDENTIFICATION OF A MEDIA CONTENT ITEM BASED ON COMMENTS

Google LLC, Mountain Vie...

1. A method for language identification of media content, the method comprising:obtaining a plurality of comments associated with a media content item;
selecting a subset of the plurality of comments based on one or more criteria;
assigning, for each comment in the subset of the plurality of comments, a representation of language probabilities, wherein each component of the representation is assigned a language probability that indicates the likelihood that the comment includes content in a language from a plurality of languages;
combining the representation of language probabilities for each comment in the subset of the plurality of comments to generate a combined language representation;
identifying a language associated with the media content item based on the combined language representation; and
performing an action based on the identified language that includes determining that a second media content item to be presented has a language identifier that is different than the identified language and presenting subtitle information during the presentation of the second media content item, wherein the subtitle information is in the identified language.

US Pat. No. 10,430,834

COMPUTER STORE OF POSTS FOR POSTING TO USER WEBPAGES OF SOCIAL NETWORKING SERVICES FROM A CONTENT PROVIDER FOR EXPANDING COMMERCIAL ADVERTISING AT THE USER WEBPAGES

1. A system, comprising:a content provider serving a first user webpage;
a computer store containing a library of posts, the posts are different from one another, each of the posts is associated with a post select control, and is for being posted to a second user webpage of a social networking service;
the first user webpage displays an external posting link associated with the computer store and the second user webpage;
a computer server at the content provider, the computer server is coupled to the computer store and for each of the posts is programmed to receive from a web browser of a computer user a signal indicating activation of the post select control of a selected one of the posts displayed by the first user webpage, automatically link the selected one of the posts to the external posting link, receive from the web browser of the computer user a signal indicating activation of the external posting link, and automatically issue the selected one of the posts to the second user webpage for posting thereon.

US Pat. No. 10,430,833

SENSOR SURFACE OBJECT DETECTION METHODS AND SYSTEMS

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

1. A method, comprising:receiving, via a processor, output from sensors of a vehicle monitoring an environment around a portion of the vehicle;
determining, via the processor, a first output over time for a first sensor of the sensors of the vehicle;
determining, via the processor, a second output over time for a second sensor of the sensors of the vehicle;
identifying, via the processor and based on sensor information in the first output over time and the second output over time, an obstructed sensor from at least one of the first sensor and the second sensor; and
sending, via the processor, a message including information about the obstructed sensor to one or more devices of the vehicle,
wherein the sensor information in the first output over time includes a time of flight defining a time for a detection signal emitted by the first sensor to be detected by the first sensor,
wherein the first sensor is identified as the obstructed sensor when the time of flight in the first output over time is less than a time of flight minimum threshold, the time of flight minimum threshold being defined as a minimum time of flight for maintaining a desired distance between the first sensor and possible obstructions,
wherein the message instructs a sensor cleaning system of the vehicle to clean the obstructed sensor,
wherein the sensor cleaning system includes:
an actuator attached to the obstructed sensor that moves the obstructed sensor between a first position and a second position;
a support structure around the obstructed sensor and set back from a wall of the vehicle; and
at least one flexible cleaning member that covers the obstructed sensor in the second position and that bends over the support structure at a location between the obstructed sensor and the support structure,
wherein, as the actuator moves the obstructed sensor between the first position and the second position and vice versa, the at least one flexible member cleans the surface of the obstructed sensor.

US Pat. No. 10,430,832

FACILITY MAPPING AND INTERACTIVE TRACKING

1. A city-based facility mapping and visitor tracking system that tracks a location of a city visitor within a city to display a city map and deliver targeted area-specific advertising to the city visitor based on the location of the city visitor, said city-based facility mapping and visitor tracking system comprising:a database management system that stores advertising data associated with a plurality of businesses within the city;
a plurality of areas of the city, wherein each area in the plurality of areas is defined by a perimeter that surrounds the area, wherein each area in the plurality of areas includes a set of businesses that are located within the perimeter that surrounds the area;
a plurality of wireless communication devices, wherein each wireless communication device in the plurality of wireless communication devices is located within a corresponding area of the plurality of areas and provides wireless communication over a wireless communication range of the corresponding area defined by the perimeter that surrounds the corresponding area;
a plurality of portable electronic devices dispensed to a plurality of city visitors to provide city map views of the city and deliver targeted advertising to each city visitor, wherein each city visitor is dispensed a portable electronic device at one of a plurality of portable electronic device dispensers, wherein a particular portable electronic device is configured to connect wirelessly to a particular wireless communication device based on a location of a particular city visitor, wherein the location of the particular city visitor is within the corresponding wireless communication range associated with the particular area, wherein the particular portable electronic device is configured to receive a particular city map view from the particular wireless communication device and to display the particular city map view on a screen of the particular portable electronic device while the particular city visitor is located within the wireless communication range corresponding to the particular area, wherein the particular portable electronic device is configured to update the city map view displayed on the screen in real-time as the location of the particular city visitor changes from the wireless communication range corresponding to the particular area to a different wireless communication range corresponding to a different wireless communication device, wherein targeted advertisements are displayed on the portable electronic device dispensed to each visitor; and
a central server that generates a unique identifier (UID) to associate with identifying information about each city visitor and a unique hardware identifier of each portable electronic device dispensed to each city visitor, wherein the central server is configured to transmit city map views to the portable electronic device based on the location of each city visitor.

US Pat. No. 10,430,831

PRIORITIZING COMPANIES FOR PEOPLE SEARCH

Microsoft Technology Lice...

1. A computer-implemented method comprising:generating a people search results page (PSERP), the PRERP comprising references to one or more member profiles representing respective members in an on-line social network system;
using at least one processor, identifying a company keyword as representing the PSERP, the company keyword associated with a company identification representing a company profile maintained in the on-line social networking system;
determining importance score for the company keyword utilizing data reflecting how frequently people-related search requests include the company keyword and also reflecting a number of member profiles in the on-line social network system that follow the company profile;
generating a priority score for the company keyword, utilizing the importance score; and
generating a web page including a reference to the PSERP based on the priority score for the company keyword.

US Pat. No. 10,430,830

ADVERTISEMENT SELECTION USING UNCERTAIN USER DATA

Samsung Electronics Co., ...

1. A method comprising:identifying, by a processing device, at least one user data including a combination of actual user data and noise data;
wherein identifying the at least one user data includes:
identifying an actual user profile based on the actual user data, the actual user profile including one or more first data fields, each of the one or more first data fields having an actual value assigned thereto indicative of the actual user data;
identifying a fake user profile as the noise data, the fake user profile including one or more second data fields, each of the one or more second data fields having a fake value assigned thereto, the fake value being different than the actual value; and
obtaining the at least one user data by combining the actual user profile and the fake user profile;
transmitting, by the processing device, the identified at least one user data to a remote computing device;
receiving, by the processing device, an advertisement response message from the remote computing device, the advertisement response message including one or more ad content, and one or more conditions, wherein the one or more ad content, and the one or more conditions are identified based on the identified at least one user data including the combination of the actual user data and the noise data by the remote computing device;
in response to identifying that a first condition among the one or more conditions is satisfied based on the actual user data, identifying, by the processing device, a first ad content corresponding to the first condition among the one or more ad content; and
displaying, by the processing device, an advertisement that is based on the first ad content.

US Pat. No. 10,430,829

SYSTEMS AND METHODS FOR GENERATING CURATED AND CUSTOM CONTENT FOR DATA-DRIVEN APPLICATIONS USING CLOSED-LOOP DATA

AMERICAN EXPRESS TRAVEL R...

1. A method comprising:obtaining, by a processor, first user data for a first user including first user transaction data based on records of charge, first user spend frequency, first user historical demographic data, first user historical account information, third party data, social media data, government data, first user feedback data, first user preferences, first user settings, application settings, click stream data, and first user interaction data;
providing, by the processor, real-time updates of at least a portion of the first user data;
determining, by the processor and using first user transaction data, first user interests based on patterns in types of merchant visitation displayed in a first transaction history of the first user data;
creating, by the processor, interest scores for the first user interests;
determining, by the processor, merchant statistics based on percent of different segments of consumers that return to a merchant location, wherein the merchant statistics are used to evaluate lodging, flights, dining and travel products;
profiling, by the processor, spend of different segments of consumers to create spend profiles based on repeat visits by the consumers, international visits by the consumers and duration of visits by the consumers;
providing, by the processor and using a computational framework, data transformations of at least the portion of the first user data, wherein the data transformations include raw data transformations, custom content, first user spend predictions, the interest scores, merchant scores, the merchant statistics and the spend profiles;
generating, by the processor, second user characteristics for a second user based on similarity matrices with the first user by using the first user transaction data and collaborative filtering;
determining, by the processor, that the second user has similar attributes as the first user and based on the similarity matrices;
implementing, by the processor, lookalike modeling and segmentation to provide the second user with the custom content based on similarity with the first user in a similar segment;
creating, by the processor, merchant-to-merchant similarity matrices based on the first user transaction data and using the collaborative filtering;
generating, by the processor, a merchant score based on the merchant-to-merchant similarity matrices, merchant visitations, a repeat customer base in the merchant visitations and spend patterns by different segments of the consumers, the first user data, first user spend patterns, types of merchants visited by the first user, travel preferences, first user interests, the first user spend frequency and the first user historical demographic data;
generating, by the processor and using a computational framework, the first user spend predictions based on the first user transaction data;
generating, by the processor, a first user profile based on the first user data; mapping, by the processor and using the first user spend predictions, the first user profile with merchant profiles to identify relevant merchants for the first user;
receiving, by the processor, a search parameter that identifies a travel preference associated with the first user profile;
retrieving, by the processor, a search result matching the travel preference associated with the first user profile;
sorting, by the processor, the search result to create a sorted search result based on search result characteristics of importance to the first user according to the first user profile; and
providing, by the processor and via a travel application, the sorted search result.

US Pat. No. 10,430,828

METHOD AND SYSTEM FOR AMBIENT MEDIA SELECTION BASED ON TRANSACTION HISTORY AND DEMOGRAPHICS

MASTERCARD INTERNATIONAL ...

1. A method for identifying ambient media selections based on transaction history, comprising:communicating, by a receiving device of a processing server, with a payment network and receiving, from the payment network, transaction data associated with a plurality of payment transactions conducted by a plurality of consumers, wherein the processing server is configured to communicate with the payment network using a specially configured infrastructure associated with the payment network;
storing, in a transaction database of the processing server, a plurality of transaction data entries for the plurality of consumers, wherein each transaction data entry is associated with a respective consumer of the plurality of consumers and includes respective transaction data, received from the payment network, related to a payment transaction including at least a merchant identifier associated with a merchant involved in the related payment transaction, and a primary account number associated with a transaction account, of the respective consumer, used in the related payment transaction;
receiving, by the receiving device of the processing server, an ambient media request, wherein the request originates from a processor of the merchant and includes at least a specific merchant identifier associated with the merchant;
identifying, by a processing device of the processing server, a subset of transaction data entries from the plurality of transaction data entries stored in the transaction database, wherein each transaction data entry in the subset includes a merchant identifier corresponding to the specific merchant identifier;
identifying, by the processing device of the processing server, at least one set of demographic characteristics of a group of consumers associated with the identified subset of transaction data entries based on at least one of the primary account number and the transaction data included in the transaction data entries in the identified subset of transaction data entries;
identifying, by the processing device of the processing server, an ambient media selection corresponding to each identified set of demographic characteristics based on the respective demographic characteristics of the group of consumers; and
transmitting, by a transmitting device of the processing server, to the merchant at least the identified ambient media selection corresponding to each of the at least one set of demographic characteristics of the group of consumers.

US Pat. No. 10,430,827

MAINTAINING INFORMATION DESCRIBING A GROUP OF ONLINE SYSTEM USERS SPECIFIED BY A THIRD-PARTY SYSTEM

Facebook, Inc., Menlo Pa...

1. A method comprising:maintaining, at an online system, a plurality of target groups of users of the online system, each target group being defined by user characteristics satisfying one or more targeting criteria for the target group, each target group including a plurality of users of the online system;
periodically determining a group score for each target group that corresponds to a value of the online system maintaining the target group, the group score for each target group being determined by:
identifying each of the plurality of users of the online system included in the target group;
identifying, from information maintained by the online system for each user of the plurality of users included in the target group, one or more targeting criteria used by the online system to select content for each user included in the target group;
determining a user score for each of a plurality of the users included in the target group, the user score being determined as a function of a number of the plurality of target groups maintained by the online system in which the user is already included based on the user characteristics for the user satisfying one or more of the targeting criteria for the number of the plurality of target groups, the user score for a user providing a measure of value in having the user be included in the target group based on targeting criteria associated with the user, the user score being inversely related to the number of the plurality of target groups in which the user is included;
aggregating the determined user scores for each of the plurality of the users included in the target group to determine the group score;
responsive to the group score for the target group being greater than at least a threshold value, continue storing, by the online system, the information describing the target group in the memory of the online system; and
responsive to the group score for the target group being less than the threshold value, removing the information describing the target group from the memory of the online system.

US Pat. No. 10,430,826

CONVERSION TIMING PREDICTION FOR NETWORKED ADVERTISING

Quantcast, San Francisco...

1. A computer-implemented method comprising:receiving, from a data repository, histories of a plurality of converted entities, each history comprising records of events associated with a respective converted entity;
calculating a respective conversion timespan for each converted entity, the respective conversion timespan comprising a time difference between an entry event of the respective converted entity and a conversion event of the respective converted entity;
fitting a conversion timing model to a distribution of the calculated conversion timespans, wherein the conversion timing model is configured to predict, from an elapsed time since an entry event of an entity, a likelihood of conversion for the entity;
receiving, from a real time bidding exchange, notification of an opportunity to bid on an advertising exposure associated with a candidate entity;
responsive to receiving notification of the opportunity to bid, predicting a likelihood of conversion for the candidate entity by applying the conversion timing model to an elapsed time since an entry event of the candidate entity;
and
preparing a response to the notification, the response comprising a bid price determined from the predicted likelihood of conversion for the candidate entity.

US Pat. No. 10,430,825

RECOMMENDING ADVERTISEMENTS USING RANKING FUNCTIONS

Adobe Inc., San Jose, CA...

1. In a digital medium environment to recommend one of a plurality of digital content items for a user in order to increase a likelihood of user interaction with the recommended digital content item, a method implemented by at least one computing device comprising:obtaining user data, by the at least one computing device, that provides a user context vector of the user responsive to navigation by a user device of the user to a web page;
for each of the plurality of digital content items, generating, by the at least one computing device, a score using a respective ranking function for a respective digital content item that computes a dot product of the user context vector and ranking weight vectors of the respective digital content item of the plurality of digital content items, the ranking weight vectors for each respective ranking function learned by a training module that obtains training data describing previous positive user interactions and negative user interactions with the plurality of digital content items and learns the ranking weight vectors by controlling scores of the positive user interactions to be higher than the negative user interactions by optimizing an area under the curve ranking loss (AUCL) function for each respective ranking function;
generating, by the at least one computing device, normalized scores by shifting the generated scores for the digital content items using a threshold score;
generating a ranked list of the digital content items by sorting the digital content items in descending order based on the normalized scores of the digital content items;
selecting, by the at least one computing device, a digital content item from the ranked list of the digital content items that is associated with a highest normalized score;
communicating, over a network, the selected digital content item with the highest normalized score to the user device of the user for display within the web page;
receiving user feedback indicating whether the user interacted with the selected digital content item; and
updating the ranking weight vectors associated with the selected digital content item based on the user feedback.

US Pat. No. 10,430,823

SYSTEMS AND METHODS TO OPTIMIZE MEDIA PRESENTATIONS USING A CAMERA

Visa International Servic...

1. A computer-implemented method, comprising:storing, by a data warehouse, transaction data;
receiving, by a communication portal, first images of customers from at least one first digital camera;
identifying, by a computing apparatus, a characteristic of a plurality of customers based on the first images of the customers;
receiving, by the communication portal, from at least one second digital camera, second images of customers, including a first customer using a first computing device, who make payment transactions, the at least one second digital camera attached to a transaction terminal;
identifying, by the computing apparatus, a subset of customers from the plurality of customers who make payment transactions and who have the identified characteristic, the identifying comprising correlating the first images and the second images to identify the subset of customers based on facial recognition, wherein customers who do not make a payment transaction within a predetermined period of time are excluded from the subset of customers;
generating, by the computing apparatus, an aggregated spending profile for the subset of customers based on transactions of the subset of customers, the generating based on the transaction data stored in the data warehouse;
modifying, by a media controller, content for sending to a point of interaction as controlled by the aggregated spending profile of the subset of customers;
sending, by the communication portal, the modified content to the point of interaction to cause display of the modified content;
generating, by the media controller, an electronic file;
transmitting, by the communication portal, a communication to the first computing device of the first customer, the communication to cause display of the electronic file in a user interface of the first computing device; and
receiving an authorization request from a first transaction terminal of the at least one transaction terminal for a transaction made by the first computing device using the electronic file.

US Pat. No. 10,430,822

ADVERTISING AND CUSTOMER LOYALTY SYSTEM

1. An advertising and customer loyalty method operable to facilitate an enhanced relationship between businesses and customers comprising the steps of:providing a server, wherein the server includes the necessary electronics to receive, store, transmit and manipulate data, wherein the server is operably coupled to the Internet;
providing a website, wherein the website is operated on said server, said website providing a user interface to install a software application of the advertising and customer loyalty system;
registering a plurality of businesses, said plurality of businesses having a physical location, wherein during registration of the plurality of businesses a business profile is created and stored in a database operably coupled with said server;
registering a plurality of customers, wherein during registration of the plurality of customers a customer profile for each customer is created and stored in said database, said customer profile containing informational and demographic data about each customer;
installing the software application, wherein the at least one customer installs the software application on a portable computing device;
creating a reward campaign, wherein one of the plurality of businesses creates a reward campaign wherein a business will exchange a reward for a customer that has accumulated a quantity of points;
proceeding to one of the plurality of businesses, wherein one of the plurality of customers traverses to said physical location of the one of the plurality of businesses;
taking a photograph, said photograph being taken by the portable computing device, said photograph having a subject matter relevant to the business where the photograph was taken;
incorporating an image, wherein the software application incorporates an image into the photograph;
moving the image, wherein the software application facilitates the ability to move the image on the photograph so as to place in a desired position;
saving the photograph, wherein the photograph is saved to said database on said server, said photograph being saved with the image being a part thereof;
posting said photograph, said photograph being posted to at least one social media platform utilizing the portable computing device;
earning a point, wherein the customer taking the photograph and posting to at least one social media platform earns a point for posting said photograph to a social media platform; and
visiting the business at least one additional time, taking a second photograph, wherein said second photograph is taken with the portable computing device and wherein the second photograph includes subject matter relevant to the business;
posting the second photograph, wherein the second photograph is posted to a social media platform;
earning a second point, said customer earning a second point for posting the second photograph to the social media platform;
earning a reward, said reward being earned by the customer for posting the photograph and the second photograph to the social media platform; and
redeeming points, said customer redeeming points earned for a reward at a business with a reward campaign.

US Pat. No. 10,430,821

PREPAID REWARDS CREDITED TO A TRANSACTION ACCOUNT

AMERICAN EXPRESS TRAVEL R...

1. A method, comprising:receiving, by a computer based system, a prepaid transaction account identifier that corresponds to a prepaid transaction account,
wherein the prepaid transaction account identifier does not particularly identify a user of the prepaid transaction account;
linking, by the computer based system and in response to the receiving, the prepaid transaction account with a rewards program based on the prepaid transaction account identifier,
wherein the rewards program includes a rewards program identifier, and
wherein the rewards program is linked to a social networking channel profile for a social networking channel;
receiving, by the computer based system and from a merchant system, an authorization request for a transaction including transaction information, wherein the transaction was initiated with the prepaid transaction account;
determining, by the computer based system and in response to the receiving the authorization request from the merchant system and prior to approving the authorization request, an offer from a plurality of offers based on the authorization request associated with the prepaid transaction account, wherein the offer applies to the transaction initiated with the prepaid transaction account;
transmitting, by the computer based system and through the social networking channel, a notice of a reward credit amount associated with the offer;
approving, by the computer based system, the authorization request for the transaction based on the transaction information received from the merchant; and
crediting, by the computer based system, the reward credit amount to the transaction account in response to the authorizing the transaction initiated by the prepaid transaction account.

US Pat. No. 10,430,820

ENHANCING REVENUE BY DRIVING CREDIT ACCOUNT PURCHASES THROUGH A SINGLE NATIVE MOBILE APPLICATION

Comenity LLC, Columbus, ...

1. A computer-implemented method for enhancing revenue by driving credit account purchases through a single native mobile application, said computer-implemented method comprising:browsing, on a mobile device, retail items via said single native mobile application executing on the mobile device, wherein said browsing is not required to be web-based browsing, and wherein said single native mobile application is provided by a party;
determining, at a point of sale (POS), a multi-tender payment for said retail items, said multi-tender payment comprising two or more distinct payment types,
a first of said distinct payment types comprising a cash payment with reference to a mobile marketing loyalty reward program, and
a second of said distinct payment types comprising an amount to be paid via credit;
presenting, via a display on the mobile device, an additional mobile marketing loyalty reward earning opportunity for a user of said mobile device by said single native mobile application,
said additional mobile marketing loyalty reward earning opportunity providing an additional amount of mobile marketing loyalty rewards for said mobile marketing loyalty reward program that can be obtained by said user when a credit account issued by the party is used to make at least part of the multi-tender payment; and
providing said additional amount of mobile marketing loyalty rewards for said mobile marketing loyalty reward program to said user after said retail items are purchased by said user, said additional amount of mobile marketing loyalty rewards based on the amount of the multi-tender payment actually made with the credit account issued by the party.

US Pat. No. 10,430,819

SYSTEMS AND METHODS FOR CONNECTING MERCHANT LOYALTY PROGRAMS WITH PAYMENT CARDS

Mastercard International ...

1. A computer-based method for providing a loyalty identifier to a merchant using a payment network, said method implemented using a loyalty program (LP) computing device in communication with a memory and a payment network server of the payment network, said method comprising:storing, in the memory, a link to a plurality of consumer profiles, each of the consumer profiles associated with a corresponding cardholder of a plurality of cardholders and including a biometric reference data associated with the corresponding cardholder;
storing, in the memory, a plurality of loyalty programs each associated with a corresponding merchant identifier of a plurality of merchant identifiers;
receiving, by the LP computing device from a client device, a registration request for a first cardholder of the plurality of cardholders, the registration request including a selection of a first of the plurality of loyalty programs and a loyalty identifier associated with the first cardholder and the first loyalty program;
storing, by the LP computing device, a second link between the loyalty identifier, the first loyalty program, and the corresponding consumer profile within the memory, wherein the first loyalty program includes a discount amount;
receiving, by the LP computing device from the payment network server, a first authorization request message for a payment transaction initiated by the first cardholder using a payment card at an originating merchant, the first authorization request message including a biometric scan data obtained from the first cardholder during the payment transaction, a first payment amount, and a first merchant identifier of the plurality of merchant identifiers, the first merchant identifier corresponding to the originating merchant;
retrieving, by the LP computing device, the first merchant identifier and the biometric scan data from the first authorization request message;
in response to retrieving, automatically querying, by the LP computing device, the memory to identify at least one of the plurality of loyalty programs associated with the first merchant identifier, wherein the at least one loyalty program includes the first loyalty program;
querying, by the LP computing device, the memory to identify one of the plurality of consumer profiles having the biometric reference data matching the biometric scan data;
querying, by the LP computing device, the identified consumer profile to determine the loyalty identifier associated with the first loyalty program;
determining, by the LP computing device, the discount amount associated with the first loyalty program for the payment transaction;
calculating, by the LP computing device, a second payment amount based on the first payment amount and the discount amount;
transmitting, by the LP computing device, the second payment amount and the loyalty identifier to the payment network server;
generating, by the LP computing device, a second authorization request message from the first authorization request message by replacing the first payment amount with the second payment amount;
transmitting, by the payment network server, the second authorization request message to an issuer processor computer device;
receiving, by the payment network server from the issuer processor computer device, in response to the second authorization request message being approved by the issuer processor computer device, an authorization response message;
formatting, by the payment network server, the loyalty identifier to enable inclusion of the loyalty identifier in the authorization response message; and
transmitting, by the payment network server, the authorization response message to the originating merchant including the formatted loyalty identifier.

US Pat. No. 10,430,818

SYSTEMS AND METHODS FOR VISUAL REPRESENTATION OF OFFERS

VISA INTERNATIONAL SERVIC...

1. A method comprising:monitoring for an event to trigger a targeted offer, wherein the event is based on a transaction;
generating the offer based on the transaction, the offer targeted to a consumer associated with a portable consumer device, wherein the offer is generated using payment data generated in response to transactions conducted by the consumer with a plurality of different merchants, and wherein the portable consumer device comprises a physically separate and secure data space configured to store operating parameters;
determining a geographic location for redeeming the offer;
generating a notification message about the offer, the notification message including the offer and the geographic location for redeeming the offer that is generated based on the transaction; and
sending the notification message to a notification device operated by the consumer,
wherein a graphical depiction of the offer is displayed on a map on the notification device based on the notification message.

US Pat. No. 10,430,817

PARTIALITY VECTOR REFINEMENT SYSTEMS AND METHODS THROUGH SAMPLE PROBING

Walmart Apollo, LLC, Ben...

1. A retail shopping customer partiality vectorization refinement system, comprising:a memory having stored therein:
a customer database storing at least a different set of multiple customer partiality vectors for each of multiple different customers wherein each of the customer partiality vectors has at least one of a magnitude and an angle that corresponds to a magnitude for the person associated with that partiality; and
a product database storing at least a different set of multiple product vectorized characterizations for each of multiple different products, wherein each of the vectorized characterizations indicates a measure regarding an extent to which a corresponding one of the products accords with a corresponding one of the multiple customer partiality vectors; and
a vectorized refinement control circuit operably coupled with the customer database and the product database, wherein the refinement control circuit:
identifies, for a first customer of the multiple customers, a multi-dimensional partiality vector target area defined within a multi-dimensional representative volume defined by a limited range of partiality magnitudes and limited range of representative partiality directions for a first customer partiality vector, wherein the partiality vector target area represents a multi-dimensional representation of an area in which an unknown actual magnitude and direction for the first customer partiality vector are predicted to lie;
selects a first product from the multiple different products having at least a first product vectorized characterization that is within a threshold alignment with the partiality vector target area, and causes the first product to be presented to the first customer;
receives, following the first product being presented to the first customer, feedback associated with the first customer and corresponding to the first product; and
adjusts the partiality vector target area based on the feedback;
wherein the customer database comprises a distributed database maintained across at least multiple different customer computing devices, and the refinement control circuit receives processing of at least the distributed database from a plurality of customer computing device control circuits located in the multiple different customer computing devices that are geographically distributed over a geographic area.

US Pat. No. 10,430,816

STRATEGY FOR COLLECTION FLOW AND SEEDING ACROSS COHORTS

Microsoft Technology Lice...

1. A computerized method comprising:identifying a cohort to target, the cohort including a plurality of members of a social networking service having member profiles that all share at least one attribute value;
identifying, from the plurality of members of the cohort, a plurality of eligible members, the eligible members being members eligible to receive an invitation to submit confidential data;
identifying a minimum number of eligible members needed to provide relevant statistical insights from confidential data submitted by eligible members of the cohort;
based on an assumed response rate for eligible members of the cohort, a total number of eligible members in the cohort, and the minimum number of eligible members needed to provide relevant statistical insights, determining that an estimated amount of responses to invitations to submit confidential data to eligible members of the cohort is less than the minimum number of eligible members needed to provide relevant statistical insights, the assumed response rate estimated based on past history of response rates to similar invitations to cohorts similar to the cohort;
in response to the determination, altering the cohort to include eligible members from at least one other cohort;
based on an assumed response rate for eligible members of the altered cohort, a total number of eligible members in the altered cohort, and the minimum number of eligible members needed to provide relevant statistical insights, determining that an estimated amount of responses to invitations to submit confidential data to eligible members of the cohort meets or exceeds the minimum number of eligible members needed to provide relevant statistical insights;
sending invitations to submit confidential data to eligible members in the altered cohort;
receiving confidential data from one or more of the eligible members in the altered cohort;
organizing received confidential data into slices organized by cohort;
anonymizing the confidential data in each slice;
encrypting the anonymized confidential data in each slice;
storing the encrypted anonymized confidential data on an external data source;
performing statistical analysis of confidential data in a slice corresponding to the cohort by accessing the encrypted anonymized confidential data on the external data source; and
providing results of the statistical analysis to eligible members of the cohort who have submitted confidential data.

US Pat. No. 10,430,815

SYSTEM AND METHOD FOR OPTIMIZING THE USE OF MOBILE DEVICES TO COMPLETE ONLINE SURVEYS

Lucid Holdings, LLC, New...

1. A method in a survey platform for routing a respondent using a mobile device among a plurality of online surveys hosted on the survey platform, the method comprising the steps of:receiving, over a communication network from a respondent's mobile device, a request to access a listing of available online surveys;
collecting the respondent's mobile device information;
accessing a survey repository database to compile the listing of available online surveys;
calculating a mobile conversion rate for each of the available online surveys, wherein the mobile conversion rate is a total number of completions by respondents for the available online survey using mobile devices divided by a total number of entries by respondents into the available online survey using mobile devices;
calculating a conversion rate for each of the available online surveys, wherein the conversion rate is a total number of completions by respondents for the available online survey using all devices divided by a total number of entries by respondents into the available online survey using all devices;
calculating a mobile conversion delta for each of the available online surveys, wherein the mobile conversion delta is the difference between the mobile conversion rate for the available online survey and the conversion rate for the available online survey;
for each of the available online surveys, comparing the mobile conversion delta to a mobile conversion delta threshold and the mobile conversion rate to a mobile conversion rate threshold;
creating a listing of qualified surveys by removing, from the listing of available online surveys, any survey where the mobile conversion delta is higher than the mobile conversion delta threshold and the mobile conversion rate is lower than the mobile conversion rate threshold; and
providing a connection, to the mobile device, for a first online survey selected from the listing of qualified surveys.

US Pat. No. 10,430,814

SYSTEM, METHOD AND COMPUTER PROGRAM FOR IMPROVED FORECASTING RESIDUAL VALUES OF A DURABLE GOOD OVER TIME

ALG, Inc., Santa Monica,...

1. A method, comprising:collecting used market data, non-industry-specific data, and industry-specific data from disparate data sources into a database, the collecting performed simultaneously, continuously, or periodically by a system communicatively connected to the disparate data sources over a network, the system having a processor and a non-transitory computer-readable medium;
transforming, by the system, all or part of the used market data, the non-industry-specific data, and the industry-specific data into data representations internal to the system;
determining, by the system using the used market data, a baseline value for an item of interest with a base configuration in an industry at an initial time point, the determining comprising taking an average of historical market values from the used market data;
determining, by the system at the initial time point, a reference period at which the baseline value for the item of interest is adjusted;
determining, by the system, a number of forecasts desired between the initial time point and the reference period;
determining, by the system, a locality adjustment to the item of interest at a forecast time, the locality adjustment representing a ratio of an average cost of items in the industry in a locality at the forecast time over a local cost of items in the industry across all localities at the forecast time;
determining, by the system, a locality-adjusted value of the item of interest as modified at the forecast time;
constructing, by the system, competitive sets of similar items, substitute items, or a combination thereof in the industry to which the item of interest belongs;
determining, by the system, to which one and only one of the competitive sets the item of interest belongs;
determining, by the system using the non-industry-specific data, a macroeconomic factor by taking a set of macroeconomic variables over a plurality of industries, the set of macroeconomic variables representing macroeconomic features;
determining, by the system using the industry-specific data, a microeconomic factor by taking a linear combination of observed or forecasted values of microeconomic variables specific to the industry to which the item of interest belongs;
generating, by the system at the forecast time, a residual value for the item of interest, the generating utilizing the baseline value for the item of interest at the initial time point determined by the system using the used market data, the macroeconomic factor determined by the system using the non-industry-specific data, and the microeconomic factor determined by the system using the industry-specific data;
storing the residual value for the item of interest in a data storage device; and
providing the residual value forecast for the item of interest for presentation on a client device over the network.

US Pat. No. 10,430,813

PREDICTION MARKET SYSTEM AND METHODS

CONSENSUS POINT, INC., N...

1. A prediction market system comprising:a computer system comprising a server computer and at least one database in communication over a network, wherein the at least one database is in communication over the network with at least one remote computing device, the server computer running a software providing:
an automated market maker;
a liquidity management system (LMS) with administrative controls for the automated market maker; and
an investment transaction graphical user interface (GUI) that allows selection of an amount of points or an amount of money for buying, selling, or short-selling a stock,
wherein the investment transaction GUI permits automated management of the LMS;
wherein the automated market maker creates liquidity in the system by providing ongoing buy, sell, and short-sell orders that are spaced in a price ladder;
wherein the automated market maker automatically calculates and displays in the investment transaction GUI the amount of the stock a user is to receive or sell in a prediction market; and
wherein the administrative controls include sensitivity, quantity, fulcrum and window, and wherein the administrative controls adjust a liquidity value.

US Pat. No. 10,430,812

RETAIL SALES FORECAST SYSTEM WITH PROMOTIONAL CROSS-ITEM EFFECTS PREDICTION

ORACLE INTERNATIONAL CORP...

1. A non-transitory computer-readable medium having instructions stored thereon that, when executed by a processor, cause the processor to predict promotional cross item (PCI) effects for retail items for a store, the predicting comprising:receiving historical sales data for the store;
storing the historical sales data in a panel data format that comprises multi-dimensional data;
aggregating the stored sales data as a first level of aggregation, wherein the first level of aggregation is aggregated to the store, a product and a time period;
aggregating the first level of aggregation aggregated data as a second level of aggregation, wherein the second level of aggregation is based on a promotional cross effect attribute (PCEA) and is aggregated to the store, the time period and a PCEA level;
deriving PCI effect predictor variables from the second level of aggregation;
for each PCEA within a retail item family, forming a regression model, wherein each PCEA comprises a retail item attribute; and
generating estimated model parameters for one or more PCI effects for each PCEA from the regression models;
wherein the PCI effect predictor variables comprise a sales shock variable that comprises a multiplier if sales are greater than a baseline.

US Pat. No. 10,430,811

TRANSACTION-SPECIFIC CUSTOMER SURVEY SYSTEM

AFTERWORDS, INC., Tampa,...

1. A system for implementing transaction-specific surveys comprising:(a) a point-of-sale interface used in conducting a commercial transaction between a consumer and a vendor, the point-of-sale interface being configured to record transaction data relating to the commercial transaction wherein the transaction data comprises at least one purchase detail identifier and a survey token;
(b) a survey server computing device configured to receive and store the transaction data generated by the point-of-sale interface, wherein:
(i) the survey server computing device comprises (A) a vendor database storing a plurality of purchase detail identifiers, and (B) a campaign data structure having survey question data and a configurable Condition that is satisfied by the detection of a given purchase detail identifier; and wherein
(ii) the survey server computing device is configured to perform the operations comprising (A) receiving a survey token, (B) retrieving the transaction data having the stored survey token corresponding to the received survey token, (C) determining whether the transaction data includes the given purchase detail identifier such that the configurable Condition is satisfied, and if the configurable Condition is satisfied, generating a Survey Question using the given survey question data and the purchase detail identifier, and (D) generating a Survey Module comprising software code for displaying the at least one Survey Question;
(c) a vendor survey interface configured to perform the operations comprising: (i) transmitting the survey token to the survey server computing device; (ii) receiving from the survey server computing device the Survey Module; (iii) generating a graphical user interface on a display screen; (iv) running the Survey Module to display the at least one Survey Question as an integrated component within the graphical user interface; (v) generating a Respondent Header based on user-generated inputs in response to the at least one Survey Question; and (vi) transmitting the Respondent Header to the survey server computing device.

US Pat. No. 10,430,810

SYSTEMS AND METHODS FOR ASSESSING THE MARKETABILITY OF A PRODUCT

Health Care Direct, Inc.,...

1. A system for assessing the marketability of a product comprising:at least one data gathering system for sensing subject product data and subject benchmark data, at least a portion of the at least one data gathering system equipped to a subject;
a computing device having a processing unit for receiving the subject product data and the subject benchmark data from said at least one data gathering system, the processing unit operatively coupled to a non-transitory computer readable medium, comprising instructions stored thereon, which, when executed by the processing unit, perform the steps of:
presenting a product stimulus and at least one benchmark stimulus to the at least one subject;
recording the subject product data and the subject benchmark data;
manipulating the subject product data to create a single subject product data point representing a first location of the product stimulus on a 3D mood map;
manipulating the subject benchmark data to create at least one subject benchmark data point, each of the at least one subject benchmark data point associated with one of the at least one benchmark stimulus, the at least one single subject benchmark data point representing a second location of a respective one of the at least one benchmark stimulus on the 3D mood map;
calculating at least one emotional term value based upon said single subject product data point and the at least one subject benchmark data point; and
assigning an emotional term to the product based upon the at least one emotional term value.

US Pat. No. 10,430,809

INFORMATION PROCESSING APPARATUS AND INFORMATION PROCESSING METHOD FOR MODIFYING A LIST ASSOCIATED WITH A USER

Rakuten, Inc., Setagaya-...

1. An information processing apparatus comprising:at least one memory configured to store computer program code;
at least one processor configured to access said memory and operate as instructed by said computer program code, said computer program code including:
identification information obtaining code configured to cause at least one of said at least one processor to based on receiving a plurality of add-to-list requests, obtain object identification information identifying a plurality of objects associated with the add-to-list requests, which are objects object to be added to a list associated with user identification information identifying a user who transmitted the add-to-list requests;
storage control code configured to cause at least one of said at least one processor to store, in the at least one memory, the obtained object identification information as items added to the list associated with the user identification information;
information retrieval code configured to cause at least one of said at least one processor to retrieve specific information indicating a plurality of common attributes or common attribute ranges that are common to at least two of the plurality of objects stored in the memory in the list associated with the obtained user identification information; and
modification control code configured to cause at least one of said at least one processor to (i) determine whether the plurality of common attributes or common attribute ranges include common attributes or common attribute ranges that are on different levels of a multi-level hierarchy, and (ii) based on determining that the common attributes or common attribute ranges include common attributes or common attribute ranges that are on different levels of the multi-level hierarchy, determine, as a convergence attribute or a convergence attribute range, an attribute or attribute range that is at a lower level of the multi-level hierarchy from among the different levels that the common attributes or common range of attributes are on, and control modification of the list based on the convergence attribute or convergence attribute range, the modification including at least one of: (i) newly-adding an object, which is not already included in the list and that has the convergence attribute or convergence attribute range, to the list, or (ii) deleting one of the objects from the list that has at least one of the common attributes or common attribute ranges that are on different levels, but does not have the convergence attribute or convergence attribute range, wherein
the convergence attribute or the convergence attribute range is an attribute or an attribute range that one or more objects among the plurality objects have,
the one or more objects were added to the list at a relatively later time among a plurality of times at which the respective plurality of objects were added to the list,
the object that is to be newly-added to the list has already been accessed or viewed by the user, and
the modification includes both of newly-adding and deleting.

US Pat. No. 10,430,807

AUTOMATIC CREATION AND REFINING OF LEAD SCORING RULES

Adobe Inc., San Jose, CA...

1. A method for customizing electronic content delivery to target devices with machine learning algorithms that adaptively update scoring rules for content recipients, the method comprising:receiving, by a lead scoring server, activity participation data indicating participation in an activity by prior leads that resulted in conversions or rejections;
correlating, with a machine learning algorithm executed by the lead scoring server, the activity with conversion events or rejection events;
creating, by the lead scoring server and using the machine learning algorithm, a scoring rule for the activity that assigns a score to the activity based on the activity participation data and a measure of correlation computed with the machine learning algorithm, wherein creating the scoring rule comprises:
identifying (i) a percentage ‘C’ of users among converted leads who participated in the activity and (ii) a percentage ‘R’ of users among rejected leads who participated in the activity,
computing a difference ‘D’ between ‘C’ and ‘R’ as the measure of correlation between the activity and conversion or rejection, and
modifying the score based on a comparison of the difference ‘D’ with a threshold;
scoring, by the lead scoring server and using the machine learning algorithm, a new lead using the scoring rule, wherein the new lead is assigned the score based on participation by the new lead in the activity;
transmitting, by the lead scoring server, the score to a marketer computing system and thereby causing the marketer computing system to transmit an electronic communication to a user device of the new lead; and
periodically, by the lead scoring server and using the machine learning algorithm, updating the scoring rule based on subsequent activity participation data indicating participation in the activity that resulted in the conversions or the rejections, wherein periodically updating the scoring rule includes updating score data transmitted to the marketer computing system.

US Pat. No. 10,430,806

INPUT/OUTPUT INTERFACE FOR CONTEXTUAL ANALYSIS ENGINE

Adobe Inc., San Jose, CA...

1. A method of analyzing digital content to generate contextual analysis data based on the digital content, the method comprising:receiving a request to analyze the digital content;
invoking a text extraction service configured to extract a corpus of plain text from the digital content;
receiving, from a first text analytics service, a plurality of topics extracted from a topic ontology, each of the topics having associated therewith a relevancy score, wherein at least one of the topics is not included in the corpus of plain text;
receiving, from a second text analytics service, tag data derived from the corpus of plain text, the tag data including a listing of n-grams extracted from the corpus of plain text and n-gram frequency data; and
generating a hierarchical output schema that includes a schema resource node at an upper hierarchical level, the schema resource node including, at a lower hierarchical level within the schema resource node,
a first sub-node that identifies the first text analytics service and a corresponding first graph index parameter,
a second sub-node that identifies the second text analytics service and a corresponding second graph index parameter, and
a third sub-node that identifies the text extraction service and a corresponding third graph index parameter;
wherein the hierarchical output schema further includes an analyzer/-enhancer node at the upper hierarchical level, the analyzer/enhancer node including, at a lower hierarchical level within the analyzer/enhancer node,
a first sub-node that is identified by the first graph index parameter and that includes the plurality of topics and the corresponding relevancy scores,
a second sub-node that is identified by the second graph index parameter and that includes the tag data, and
a third sub-node that is identified by the third graph index parameter and that includes the corpus of plain text.

US Pat. No. 10,430,805

SEMANTIC ENRICHMENT OF TRAJECTORY DATA

SAMSUNG ELECTRONICS CO., ...

1. A method, comprising:in response to receiving user generated data including a plurality of visual assets and corresponding trajectory data from a first user device, determining, using a processor, enrichment data items related to a plurality of points of presence within the trajectory data, wherein the points of presence specify time and location data for the first user device;
determining, using the processor, ranking metrics for the enrichment data items;
ranking, using the processor, the enrichment data items according to the ranking metrics;
in response to determining a difference between properties of a first point of presence of the plurality of points of presence corresponding to a first visual asset of the plurality of visual assets and a second point of presence of the plurality of points of presence corresponding to a second visual asset of the plurality of visual assets, generating, using the processor, a connective message, wherein the connective message is synthetic text dialog describing the difference and generated using a finite state machine configured to prevent repetitiveness of connective messages and generate dialog linked to previous messages displayed in scenes of a multimedia composition;
generating, using the processor, a manifest specifying directives for generating the multimedia composition including the first visual asset linked to the second visual asset by the connective message and at least one ranked enrichment data item in association with the related plurality of points of presence; and
providing the manifest to a second user device, wherein the second user device implements the directives to generate the multimedia composition.

US Pat. No. 10,430,804

SYSTEM AND METHOD FOR ACCESSING A HUB

1. A computer implemented method for user specific management of search results accessed from a storage hub, the method comprising the steps of:sending of a search query, by a user, from a user device to a web search engine operated by at least one server device;
receiving, at the user device, a web page comprising an authentication element and the search results based on the search query as individual embedded objects defined as individually selectable items within the web page by a script embedded into the web page as a self-contained block by said at least one server device of the search engine provider;
determining, using the authentication element, whether the user device has a cookie stored locally on the user device, wherein the web page identifies and verifies the user based on the cookie;
displaying on a display of the user device, upon verification of the user, the web page of search results using a web browser executed by the user device and enabling the user to input a first type of selection of one of the search results, a second type of selection of one of the search results or a selection of an element displayed within the webpage other than one of the search results;
determining if the user input the first type of selection of one of the search results, the second type of selection of one of the search results, or the selection of an element displayed within the webpage other than one of the search results;
causing, upon determining that the user input the first type of selection of one of the search results, the web browser to follow a link to an online resource associated with the selected one of the search results, wherein the first type of selection comprises one of: a left-click of a mouse, a touch gesture equivalent of a left-click of a mouse on a touch screen or a voice command equivalent of a left click of a mouse,
causing, upon determining that the user input the second type of selection of one of the search results, wherein the second type of selection comprises one of: a right-click of a mouse, a touch gesture equivalent of a right-click of a mouse on a touch screen or a voice command equivalent of a right click of a mouse:
accessing user specific information from the storage hub based on the cookie;
execution of script, embedded within the web page of the search results, by the web browser defining the selected search result as a selectable item to display a user interface unique to the web pages of search results; and
display of the unique user interface, based on the user specific information, within the web page of the search results on the user device overlaying the previously displayed search results, wherein the unique user interface comprises a menu displaying selectable control options associated exclusively with the search engine provider for user specific management of the selectable search results displayed in the web page, the control options comprising at least:
at least one function standard to the web browser;
a save search result control function, selection of which causes saving, by the at least one server device, of details of the search result selected by the user together with the cookie to the storage hub remote from the user device and provided by the search engine provider,
an email function that enables a user to open an email interface and enter an email address or find an email be selecting a contacts button;
an invite function that displays a contact list associated with the user and enables the user to select and invite at least one contact from the contact list to access the web page, wherein the at least one contact selected from the contact list is able to accept, decline or ignore the invite;
a recommend function that displays the details of the search result on the user's social network page;
a post function that enables the user to enter a comment to be posted on their social network page;
a comment function that displays a comments interface that shows comments from other users related to the content of the search result;
a chat function that enables the user to select contacts to communicate with;
a reminder function that enables the user to set a reminder associated with a search result saved by the user;
a wallet function that displays the user's account balance;
a buy now function that enables a user to go to a checkout page of an advertisement associated with the search result;
a saved advertisements function that displays at least one advertisement saved by the user; and
a saved search result access function, selection of which causes:
accessing, by the at least one server device in bidirectional communication with the storage hub provided by the search engine provider, user specific information including the cookie;
accessing, by the at least one server device, of details of at least one search result previously saved by the user to the storage hub with the cookie, and
transmitting the details of the at least one previously saved search result to the user device for display to the user within a secondary interface overlaying the previously displayed search results within the web page of search results on the user device; and
causing, upon determining that the user input the selection of an element displayed within the webpage other than of one of the search results, the display of a context menu standard to the web browser.

US Pat. No. 10,430,803

METHODS AND SYSTEMS FOR PREDICTING CONSUMER BEHAVIOR FROM TRANSACTION CARD PURCHASES

MASTERCARD INTERNATIONAL ...

1. A computer-based method for predicting consumer behavior within a predetermined time period, said method performed using a payment processor computer device coupled to a database, said method comprising:recording, by the payment processor computer device, electronic consumer data in the database for each consumer of a global population of consumers including historical purchases made by each consumer, including at least one electronic transaction initiated by a consumer using a transaction card at a point-of-sale (POS) device;
defining, by the payment processor computer device, a life event by assigning spending variables to the life event, wherein a spending variable represents a quantity of consumer spending associated with one or more of (i) a particular merchant and (ii) a particular type of good or service;
generating an anticipated spend for each spending variable assigned to the life event by extrapolating a historical actual spend based on the historical purchases, wherein the anticipated spend represents anticipated spending in each spending variable assigned to the life event;
calculating a residual value of a determined variance between the anticipated spend and an actual spend for each consumer by calculating a quotient of (i) the difference between the anticipated spend and the actual spend and (ii) the anticipated spend;
determining that a residual value of a determined variance between the anticipated spend and the actual spend for each consumer exceeds a predefined threshold;
assigning, by the payment processor computer device, the consumer to a sample group, wherein the sample group represents consumers that are experiencing the life event;
generating, by the payment processor computer device, a predictive model based on historical purchases made by consumers within the sample group;
applying, by the payment processor computer device, the predictive model to predict each consumer within the global population and outside of the sample group that will experience the life event; and
outputting, by the payment processor computer device, a list of consumers outside of the sample group that are predicted to experience the life event within the predetermined time period.

US Pat. No. 10,430,802

SCREEN-IMAGE BASED CLASSIFICATION

ENTIT SOFTWARE LLC, Sunn...

1. A method for screen-image based record classification, comprising:acquiring a screen-image from a user device, the screen-image of a graphical user interface associated with an information technology (IT) service;
analyzing, by a processor, the acquired screen-image to recognize unstructured data within the screen-image;
processing, by the processor, the unstructured data recognized from the screen-image against a database of historical data to discern a plurality of different field values; and
automatically maintaining, by the processor, an electronic record associated with the IT service based on the discerned plurality of different field values, wherein the electronic record is a ticket of an IT management system.

US Pat. No. 10,430,801

GENERATING AND PROVIDING A SELF-SERVICE DEMONSTRATION TO FACILITATE PERFORMANCE OF A SELF-SERVICE TASK

Accenture Global Services...

1. A device, comprising:one or more memories; and
one or more processors, communicatively coupled to the one or more memories, to:
provide a user interface to a user device,
the user interface being provided by executing an application;
obtain a user identifier associated with a user of the user device,
the user identifier being obtained via the user interface;
provide, via the user interface, a list of self-service tasks that the user may perform via a web self-service;
identify a self-service task from the list of the self-service tasks to be performed by the user using the user device,
the self-service task being a task that does not require the user to interact with another person,
the self-service task being identified by the user selecting the self-service task via the user interface,
the self-service task to be performed via an input mechanism,
information identifying the self-service tasks being stored in a data structure of the device,
the data structure of the device associating the self-service tasks with one or more types of account information;
obtain account information, specific to the user, based on the user identifier and the self-service task;
identify a code template based on the self-service task;
generate code for a self-service demonstration using the code template that includes:
first code for instructions for performing the self-service task,
second code for media content for communicating the instructions,
the media content including at least one of:
 video content,
 audio content,
 textual content, or
 graphical content, and
third code for providing the account information specific to the user,
the media content being based on the account information specific to the user;
execute the code for the self-service demonstration for presentation to the user via the user interface,
the self-service demonstration and the self-service task being provided via a single user interface without leaving a flow of the instructions provided in the self-service demonstration,
the single user interface including at least one of audio or visual content provided via the self-service demonstration to guide the user through the self-service task,
 the at least one of the audio or visual content being provided via the self-service demonstration upon execution of the code, and
the self-service demonstration including a plurality of stages,
each stage of the plurality of stages requiring user input prior to moving to a next stage;
receive an indication of an interaction, by the user, with the self-service demonstration,
the interaction with the self-service demonstration including the user input to perform the self-service task via the input mechanism; and
modify the account information based on the user input.

US Pat. No. 10,430,800

FASTER PRODUCT IMPROVEMENT

1. A method for monitoring a vehicle, the method comprises:measuring multiple vehicle operating parameters using a vehicle monitor; wherein the vehicle monitor is mechanically coupled to the vehicle or installed in the vehicle;
searching, by the vehicle monitor, for one or more out-of-range vehicle operating parameters; wherein an out-of-range vehicle operating parameter is a vehicle operating parameter that is outside an allowable range of the vehicle operating parameter; and
responding to the one or more out-of-range vehicle operating parameters by the vehicle monitor;
wherein the one or more out-of-range vehicle operating parameters are indicative of at least one vehicle failure that is impending;
wherein the responding precedes an occurrence of the at least one vehicle failure that is impending; and
wherein the responding comprises requesting to receive a vehicle monitor software update for managing the one or more out-of-range vehicle operating parameters; receiving, by the vehicle monitor, the software update; updating, by the vehicle monitor, the vehicle monitor software with the software update; and managing, by the vehicle monitor, the one or more out-of-range vehicle operating parameters.

US Pat. No. 10,430,799

SYSTEM AND METHOD FOR DETERMINING A TIME THRESHOLD GUARANTEE OF A TASK FOR UPDATING IN A PENALTY CLAUSE OF A SERVICE LEVEL AGREEMENT

Numerify, Inc., San Jose...

1. One or more non-transitory computer readable storage mediums storing one or more sequences of instructions for automatically determining a time threshold guarantee of a task using a time threshold determination system and updating said time threshold guarantee in a penalty clause of a Service Level Agreement (SLA) of a service provider tool, which when executed by one or more processors, performs the steps of:automatically determining, by a tasks determination module, a total number of tasks by analyzing a table that comprises historical data for each of a plurality of customers, wherein said historical data comprises a plurality of tasks and a completion time associated with each of said plurality of tasks for said plurality of customers, wherein said table is sorted in ascending order of said completion times upon retrieval by a table obtaining module;
automatically determining, by a graphical representation generation module, a granularity for plotting percentage completion in a graphical representation between said completion time and a percentage of tasks completed by analyzing data distribution of said table, wherein said analyzing of the data distribution of said table comprises:
determining a number of said plurality of tasks for which said completion time is available;
determining a percentage completion granularity (G) by ensuring that there are at least 100/G tasks for which the completion time data is available; and
overriding if required by the plurality of customers (i) said percentage completion granularity, (ii) a default minimum percentage of completion threshold to achieve, and (iii) a maximum completion time threshold that should not be exceeded by said plurality of tasks, wherein said maximum completion time threshold is initially set to the maximum completion time obtained from said table;
automatically computing, by said graphical representation generation module, points to plot said graphical representation between said completion time and a percentage of tasks completed for said percentage completion granularity by (a) calculating said percentage of completion granularity of said total number of tasks and (b) computing an average completion time for each successive percentage of completion granularity of said plurality of tasks;
automatically determining, by a slope determination module, a slope for each consecutive set of points of said graphical representation;
automatically determining, by said slope determination module, a slope difference for each set of consecutive slopes;
automatically determining, by a time threshold guarantees determination module, for each of said plurality of customers, a time threshold guarantee below said maximum completion time threshold, and above said minimum percentage of completion by identifying one of (a) a point where said slope difference is highest and higher than at other points in concave up portions of said graphical representation, and (b) a point furthest to right of said minimum percentage of completion threshold and below said maximum completion time threshold in concave down portions of said graphical representation, and transforming the historical data, for each of the plurality of customers, into the time threshold guarantee;
automatically identifying, by a peer customers identification module, a plurality of peer customers similar to each of said plurality of customers for whom said time threshold guarantee is being determined and historical warehouse data is not available;
retrieving, by a peer customers retrieval module, time threshold guarantees of said plurality of peer customers, wherein said time threshold guarantee of said plurality of peer customers are obtained from a plurality of peer customer specific stores through a network; and
determining, by said peer customers retrieval module, said time threshold guarantee for each of said plurality of customers for whom historical warehouse data is not available as the average of said time threshold guarantees of said plurality of peer customers obtained from said plurality of peer customers specific stores;
wherein said time threshold determination system updates said time threshold guarantee in a penalty clause of a Service Level Agreement (SLA) of a service provider tool, for each of said plurality of customers, for the practical application of imposing a penalty on the service provider when said time threshold is exceeded, wherein said time threshold guarantee is determined for a plurality of metrics associated with said plurality of customers.

US Pat. No. 10,430,798

SYSTEM AND METHOD OF A MEDIA DELIVERY SERVICES PLATFORM FOR TARGETING CONSUMERS IN REAL TIME

19. A method for targeting a consumer for delivery of media across a plurality of promotion channels utilized for advertisement and promotion of products, the method being implemented on a computer having one or more processors programmed with computer program instructions that, when executed, cause the computer to perform the method, the method comprising:obtaining, by the computer, a first promotion targeted for a consumer;
receiving, by the computer, signal strength data of a device associated with the consumer while the consumer is within a store;
processing, by the computer, the signal strength data into identifications of zone locations of the store;
providing, by the computer, in response to a determination, based on processing the signal strength data into identifications, that the first promotion is associated with one of the identifications of the zone locations, the first promotion to the consumer via a first promotion channel;
obtaining, by the computer, a second promotion targeted for the consumer and an indication that the second promotion is to be delivered to the consumer via a second promotion channel different from the first promotion channel;
determining, by the computer and after providing the first promotion to the consumer via a first promotion channel, a conflict between the second promotion to be delivered via the second promotion channel and the first promotion that was delivered via the first promotional channel, wherein the conflict comprises showing to the consumer across the first promotion channel and the second promotion channel multiple instances of a particular offer, multiple offers for a particular product, offers from competing brands, multiple offers for products from a particular category, or offers from a retailer if the same product is being promoted through channels controlled by a vendor; and
preventing, by the computer, delivery of the second promotion, via the second promotion channel, to the consumer based on the conflict.

US Pat. No. 10,430,797

PROXY CARD PAYMENT WITH DIGITAL RECEIPT DELIVERY

Square, Inc., San Franci...

1. A method comprising:receiving, at a computer system and from a point-of-sale (POS) system associated with a payee, an indication of a financial transaction between a payer and the payee, the financial transaction involving use of a payment object associated with the payer to pay for products or services provided by the payee in the financial transaction;
receiving, by the computer system, a notification of payment authorization of a particular payment account associated with the payment object for charging a payment associated with the financial transaction; and
in response to the payment authorization of the particular payment account, automatically transmitting, by the computer system over a network to a computing device associated with the payer, a digital receipt indicative of the financial transaction,
the digital receipt including a time-based interactive feedback component that enables the payer to input feedback to the time-based interactive feedback component, the feedback associated with the products or services relating to the financial transaction.

US Pat. No. 10,430,796

AUTOMATIC DETECTION OF MOBILE PAYMENT APPLICATIONS

PAYPAL, INC., San Jose, ...

1. A system, comprising:a device screen associated with a mobile device;
a non-transitory memory storing instructions; and
one or more hardware processors coupled to the non-transitory memory and configured to read the instructions to cause the system to perform operations comprising:
determining a selection of a user interface element of a first web page displayed on the device screen, the device screen further displaying one or more items requested by a user, wherein the user interface element, when selected, is configured to cause the device screen to display a second web page when a custom Uniform Resource Locator (URL) is not registered with the mobile device;
based on the selection of the user interface element, determining that the custom URL is registered with the mobile device by executing the custom URL;
initiating, based on the determining that the custom URL is registered with the mobile device, an app-based checkout process for the one or more items by executing the custom URL registered with the mobile device instead of displaying the second web page;
based on the initiating the app-based checkout process, causing the device screen to further display information associated with an account of the user;
receiving a user identifier from the device screen that displays the information associated with the account of the user;
authenticating the account of the user based at least on the user identifier received; and
based on the authenticating the account, completing the app-based checkout process for the one or more items.

US Pat. No. 10,430,795

RULES ENGINE FOR APPLYING RULES FROM A REVIEWING NETWORK TO SIGNALS FROM AN ORIGINATING NETWORK

MASTERCARD INTERNATIONAL ...

1. A rules engine for applying rules for a reviewing network to data signals from an originating network, the data signals associated with a transaction, said rules engine comprises a processor communicatively coupled to a memory device, said rules engine is communicatively coupled to the reviewing network, said rules engine is configured to:store the rules within said memory device, wherein the rules are provided on behalf of an issuer bank that issued a payment card to a cardholder that is used to initiate the transaction, the issuer bank being associated with an issuer computer system, the issuer computer system in communication with the originating network;
receive an authorization data signal from the originating network when the issuer computer system fails to respond to the authorization data signal transmitted by the originating network and the issuer computer system is determined to be unavailable to authorize the transaction, the authorization data signal including authorization data for the transaction processed by the originating network and a stand-in authorization request message including a flag requesting that the reviewing network perform stand-in authorization for the transaction on behalf of the unavailable issuer computer system associated with the originating network, wherein the originating network and the reviewing network are separate payment networks;
identify the unavailable issuer bank based on a transaction identifier and retrieve the rules associated with the unavailable issuer bank from said memory device after receiving the authorization data signal;
detect an account identifier associated with the transaction in the authorization data signal;
retrieve historical transaction data associated with the detected account identifier from said memory device;
generate, by said rules engine, an authorization response data signal including authorization response data by comparing the authorization data to the rules associated with the unavailable issuer bank stored in said memory device and applying the rules to the retrieved historical transaction data, wherein the authorization response data indicates whether the reviewing network authorizes or declines the transaction included in the authorization data on behalf of the issuer bank; and
transmit the authorization response data signal to the originating network.

US Pat. No. 10,430,794

SYSTEM AND METHOD INCLUDING CUSTOMIZED LINKAGE RULES IN PAYMENT TRANSACTIONS

Visa International Servic...

1. A system comprising:a computer readable storage medium; and
a processor coupled to the computer readable storage medium, wherein the processor is configured to execute program code stored on the computer readable storage medium to implement a method comprising:
linking, using a linkage rule, (1) a verification token device, (2) a user communication device, and (3) a payment account of a portable consumer device;
receiving an authentication request message for a payment transaction on the payment account, the authentication request message received from the user communication device, the authentication request message comprising (1) a verification token identifier that identifies the verification token device used to conduct a payment transaction, (2) a user communication device identifier that identifies the user communication device used to conduct the payment transaction, and (3) an account identifier that identifies the payment account for conducting the payment transaction, wherein the verification token device receives the account identifier from the portable consumer device;
identifying the linkage rule based on the account identifier included in the authentication request message;
authenticating the payment transaction using the identified linkage rule by verifying that the verification token identifier that identifies the verification token device used to conduct the payment transaction and the user communication device identifier that identifies the user communication device used to conduct the payment transaction included in the authentication request message respectively identify the verification token device and the user communication device specified in the linkage rule;
in response to the authenticating of the payment transaction using the identified linkage rule, generating a dynamic verification value based at least in part on the account identifier;
providing the dynamic verification value to either (1) the verification token device used to conduct the payment transaction or (2) the user communication device used to conduct the payment transaction, wherein either the verification token device or the user communication device provides the dynamic verification value to a merchant server to conduct the payment transaction on the payment account; and
receiving an authorization request message from the merchant server, the authorization request message comprising the dynamic verification value; and
sending an authorization response message indicating whether the payment transaction is approved or declined based on verification of the dynamic verification value.

US Pat. No. 10,430,793

FRAUD MANAGEMENT SYSTEM AND METHOD

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

8. A fraud management method comprising:receiving, at a server of a fraud management system, a plurality of transaction requests;
sorting, by the server, the transaction requests into a plurality of groups;
selecting, by the server, a number of the transaction requests from each group to define a sample of the group that contains less than all the transaction requests in the group;
for each transaction request in each sample;
determining, by the server, which rules of a plurality of rules are satisfied by the transaction request,
selecting, by the server, an acceptance flow from a plurality of acceptance flows based on the rules satisfied by the transaction request,
calculating, by the server, a total cost of fraud for the transaction request by applying the selected acceptance flow to the transaction request, and
storing, by the server, the total cost of fraud in a total cost of fraud database;
determining, by the server, a total cost of fraud for each group based on the total costs of fraud calculated for the transaction requests in the sample of the group and stored in the total cost of fraud database; and
monitoring, by the server, an efficiency of the fraud management system by computing a key performance indicator for each rule based on the total costs of fraud stored in the total cost of fraud database and the value of the transactions associated with the transaction requests to which the rule applied.

US Pat. No. 10,430,792

TRANSACTION DEVICE

1. A method by which a transaction system stores a biometric identification parameter used by the transaction system to perform transactions, the method comprising:receiving, from a user, the biometric identification parameter;
storing the biometric identification parameter in a primary biometric identification parameter data file;
assigning to the user a user identification number;
creating a plurality of pieces of the primary biometric identification parameter data file, each piece from the plurality of pieces being assigned a data sequence number different from data sequence numbers assigned to all other pieces in the plurality of pieces;
assigning to each piece of the plurality of pieces, a mathematical operation encryption number from a plurality of mathematical operation encryption numbers, wherein each mathematical operation encryption number represents a mathematical encryption operation that is different from mathematical encryption operations represented by all other mathematical operation encryption numbers from the plurality of mathematical operation encryption numbers;
encrypting each piece of the plurality of pieces using a mathematical encryption operation represented by the mathematical operation encryption number assigned to the piece in order to produce a plurality of transformed data pieces;
assigning each transformed data piece in the plurality of transformed data pieces a transformed data identification number, the transformed data piece identification number including:
a type identifier that indicates a type of biometric identification stored,
the user identification number,
the data sequence number for the piece, and
the mathematical operation encryption number for the piece;
storing the plurality of transformed data pieces in a primary biometric identification parameter database;
storing the primary biometric identification parameter database on a plurality of servers so that the transformed data pieces in the plurality of transformed data pieces are distributed among the plurality of servers.

US Pat. No. 10,430,791

BIOMETRIC SECURE SALES AND PAYMENT TERMINAL USING FACE RECOGNITION AND FINGER PRINT DEFINITION METHODS

MT BILGI TEKNOLOJILERI VE...

1. A biometric secure sales and payment terminal using face recognition and fingerprint recognition, comprising: an electronic TFT screen which displays transactions carried out by a user,a customer screen where a customer can see information about expenses and costs,
a paper roll on which a payment information of the customer is printed,
a motherboard which arranges a system algorithm, stores the program as digital and analogue data, and compares a fingerprint and/or a face recognition data by communicating with a bank,
a battery which enables the transactions to be carried out by providing power to the terminal when there is no mains electricity,
a thermal printer which prints the information slips about sales, payment, report receipts on a paper roll,
a speaker which enables the customer and the user to hear the transactions carried out,
a card reader where a card contact is physically carried out and the card is magnetically read,
a GSM antenna which carries out data flow with a base station, and enables the communication of the terminal with the necessary posts,
a keyboard which enables the transactions to be carried out on the terminal by the user,
a top cover which protects the terminal from impact that may be received from the top,
a financial stamp screw which shows that access into the secure sales and payment terminal is performed by leaving a mark in the case that the secure sales and payment terminal is tampered,
a financial stamp screw slot which enables the attachment of the financial stamp screw,
a program which manages the communication between all the analogue and digital parts found inside the terminal and which is uploaded into a memory within the motherboard,
an internal EKU which is an electronic record unit where all the copies of all transactions carried out on the secure sales and payment terminal are recorded therein,
a chip card reader which is located on the secure sales and payment terminal and which can read the information of the customer loaded inside a chip found on the bank card,
a GPS antenna which communicates with a satellite, and aids in determining the position of the secure sales and payment terminal,
a camera located on the terminal, which captures a face image of the customer and submits face information to the motherboard so that the face information can be compared with the face data of the bank,
a fingerprint reader, located on the terminal, which takes the fingerprint of the customer and submits fingerprint information to the motherboard so that the fingerprint is matched with the fingerprint information of the bank,
a micro processor secure financial memory module which erases daily total sales and total VAT amount inside the secure sales and payment terminal and stores the daily total sales and the total VAT amount in a secure state which cannot be changed and which is in compliance with a financial cash register technical specification.

US Pat. No. 10,430,790

REAL-TIME PROCESSING OF REQUESTS RELATED TO FACILITATING USE OF AN ACCOUNT

Capital One Services, LLC...

1. A system, comprising:one or more memories; and
one or more processors, communicatively coupled to the one or more memories, configured to:
receive, from a plurality of user devices, information related to a first plurality of individuals and a second individual,
each of the first plurality of individuals being associated with a respective one or more accounts,
a first user device, of the plurality of user devices, being associated with a first individual, of the first plurality of individuals, to facilitate use, by a second user device, of the plurality of user devices, associated with the second individual, of the respective one or more accounts associated with the first individual in association with completing a transaction,
the information being received from a web interface or an application operating on the plurality of the user devices, and
the plurality of user devices being registered for a matching service via the web interface or the application;
receive a request to match the second individual and one or more individuals of the first plurality of individuals,
the request being received from the second user device, of the plurality of user devices, associated with the second individual;
determine a match of the second individual and the one or more individuals of the first plurality of individuals after receiving the request to match the second individual and the one or more individuals of the first plurality of individuals,
the one or more individuals of the first plurality of individuals including the first individual;
determine to optimize an objective associated with the transaction,
the objective including at least one of:
an amount of cash back received in association with the transaction,
an amount of rewards points received in association with the transaction, or
an amount of a discount applied to the transaction; and
the objective being optimized based upon the information related to the first plurality of individuals and the second individual,
where the one or more processors, when determining the match, are to:
determine the match based on the objective to be optimized;
receive, from the second user device, a selection of an account, of the respective one or more accounts, associated with the first individual by the second individual;
provide, for display to the first individual, a notification that the second individual and the first individual have been matched and that the second individual selected the account associated with the first individual,
the notification being provided to the first user device, of the plurality of user devices, associated with the first individual;
determine a first set of instructions to reconfigure a transaction card associated with the second individual to use account information associated with the account, of the respective one or more accounts, associated with the first individual, based on receiving an amount of money from another account associated with the second individual,
the account information being associated with a secure token;
transmit, to the transaction card associated with the second individual, the first set of instructions to reconfigure the transaction card to use the account information associated with the account, of the respective one or more accounts, associated with the first individual, based on determining the first set of instructions;
transmit, to a transaction backend device, a second set of instructions to process the transaction,
the second set of instructions to configure the transaction backend device to process the secure token; and
complete the transaction after receiving the amount of money from the other account associated with the second individual based on processing the secure token.

US Pat. No. 10,430,789

SYSTEM, METHOD AND COMPUTER PROGRAM PRODUCT FOR SECURE RETAIL TRANSACTIONS (SRT)

LOCKHEED MARTIN CORPORATI...

1. A systematic system comprising:a. a point of sale seller device to interact with a buyer device and communicate with a seller's financial institution system, the seller device further generates seller information including a financial transaction invoice with a unique, one-time-only transaction identification and seller's financial institution data associated with the seller's financial institution system including financial routing number, wherein the seller information is generated based on a purchase being initiated with a buyer device in which buyer's financial data from the buyer device is never provided by the buyer device to the seller device;
b. the buyer device including a controller, the buyer device receives a transaction invoice having transaction invoice information data and generate encrypted buyer data that includes buyer identification information and buyer's financial data based on the purchase;
c. a transaction manager generates a single transaction and time limited data packet comprised of the encrypted buyer data associated with the buyer device during the purchase and the seller information transmitted from the seller device to the buyer device and, for the buyer device, establish a communication session to transmit the encrypted transaction data packet directly to a buyer's financial institution system associated with the buyer's financial data;
d. the buyer's financial institution system sends transaction packet information to the seller's financial institution system for pairing with a unique, one-time-only seller encrypted transaction invoice within an allotted time window of a payment session established by the seller as directed by the transaction manager and provides transaction confirmation to the buyer device; and
e. the seller's financial institution system determines that the unique, one-time-only transaction pairing is valid, and in response to the valid determination completes the transaction with transaction notification back to the buyer's financial institution system and to the seller device wherein the seller device further comprises a network interface, the network interface receives a confirmation of said payment from the seller's financial institution system and the transaction invoice generated by the seller device includes data associated with the time allotted window established by the seller for establishing the time allotted window for the payment session.

US Pat. No. 10,430,788

SYSTEMS AND METHODS FOR FUND TRANSFERS

Green Dot Corporation, P...

1. A method for conducting peer-to-peer transfers, comprising:obtaining a cash-out request data using a fund transfer server system,
wherein the fund transfer server system comprises a processor and a memory coupled to the processor;
generating a cash-out code based on the cash-out request data using the fund transfer server system,
wherein the cash-out request data comprises fund data and target account data,
wherein the fund data comprises identification data associated with the cash-out request data and metadata describing funds to be provided in response to redeeming a cash-out request, and
wherein the target account data comprises metadata identifying a consumer account and specifies an account to which funds will be provided;
providing the cash-out code to a client device associated with the target account data using the fund transfer server system;
obtaining cash-out code redemption data from the client device associated with the target account data using the fund transfer server system, wherein the cash-out code redemption data identifies the provided cash-out code;
verifying the cash-out request data using the fund transfer server system, wherein the verification is based on the cash-out code identified by the cash-out request data, wherein the cash-out code includes the fund data and target account data; and
transmitting a request to provide the funds described by the fund data using the fund transfer server system.

US Pat. No. 10,430,787

DIGITAL WALLET BROADCASTING

PAYPAL, INC., San Jose, ...

1. A system, comprising:a memory configured to store a merchant key; and
one or more processors coupled to the memory and configured to cause the system to:
capture a wireless signal unique to a customer key broadcasted from a customer device;
access the merchant key in the memory;
determine the customer key provides a unique customer key/merchant key pair with the merchant key based on the wireless signal;
send a notification of the unique customer key/merchant key pair through a network; and
in response, receive customer information of a customer associated with the customer key through the network.

US Pat. No. 10,430,786

ENHANCED CERTIFICATE AUTHORITY

1. A computerized system for managing digital certificates, said computerized system comprising:one or more communicatively coupled computer processors, said one or more computer processors forming a certificate authority computer system (CACS) configured to perform the steps of:
receiving, at said computer system, a request for an online or offline authorization (OOA) request, said OOA request containing one or more OOA request data elements, said OOA request data elements comprising the data for each user related data field and/or a pointer to the location of said data, said user data information being required by the computer system to accomplish (directly or via third parties having proper compliance requirements) the one or more registration validation actions necessary to establish the bona fides of said user in real time and to perform said user registration within the system;
providing, upon said bona fides satisfaction, said user with said OOA request, requested ancillary data element and one or more OOA requested data elements associated with said one or more OOA request data elements;
receiving, by said Certificate Authority computer system (CACS), a request for a Transactional Digital Certificate (TCERT) from a user, said request containing the desired one or more TCERT user data elements and establishing the existence of a valid OOA data request, performing data validation of one or more of said TCERT request data elements, and/or said OOA data elements, and upon acceptance generating said TCERT digital certificate and TCERT ancillary data for said user;
transmitting, by said Certificate Authority computer system, said TCERT digital certificate and any appropriate TCERT ancillary data to said user.

US Pat. No. 10,430,785

PREPAID CHIP CARD EXCEPTION PROCESSING

VISA INTERNATIONAL SERVIC...

1. A method for processing a transaction with a transaction card, the transaction having a value, the method comprising:retrieving, using a processor from a memory of the transaction card, a value of an accumulator record stored in the memory of the transaction card;
wherein retrieving the value of the accumulator record automatically increments the accumulator record by the value of the transaction upon initiation of the transaction;
sending, by the processor to an issuer associated with the transaction card, an authorization request message requesting authorization for the transaction;
receiving, by the processor from the issuer, an authorization response message indicating whether the transaction is authorized or declined;
retrieving, using the processor from the memory of the transaction card, a value of an exception record stored in the memory of the transaction card when the authorization response message indicates that the transaction is authorized;
wherein the exception record is incremented by the value of the transaction only upon successful completion of the transaction, the exception record stored in the memory of the transaction card is not incremented when the transaction fails, the accumulator record and the exception record illustrate a record of past transactions associated with the transaction card; and
transmitting, using the processor, the accumulator record and the exception record to the issuer for determining that the past transactions include an exception if there is a difference between the accumulator record and the exception record stored in the memory of the transaction card.

US Pat. No. 10,430,784

MULTI-LAYER ANTENNA

Square, Inc., San Franci...

1. A transaction processing device for engaging in near-field communications (NFC) with a wireless transaction device, comprising:a processing unit configured to output a NFC source signal at two NFC source signal outputs of the processing unit;
NFC transmit circuitry coupled to the processing unit to receive the NFC source signal, wherein the NFC transmit circuitry comprises matching circuitry and filtering circuitry, and wherein the NFC transmit circuitry outputs a transmit signal from two NFC transmit terminals based on the NFC source signal, the matching circuitry, and the filtering circuitry;
a flexible circuit board having a top surface and a bottom surface, wherein the top surface and the bottom surface are opposite each other and parallel to each other;
an antenna coupled to the two NFC transmit terminals to transmit the transmit signal, comprising:
a first antenna terminal coupled to a first NFC transmit terminal of the two NFC transmit terminals;
a second antenna terminal coupled to a second NFC transmit terminal of the two NFC transmit terminals;
a top antenna portion located on the top surface of the flexible circuit board, wherein the top antenna portion has a first top end that is coupled to the first antenna terminal and a second top end, wherein the top antenna portion comprises a first circuit path between the first top end and the second top end, the first circuit path having a single loop and a substantially rectangular shape;
a through connection coupled to second top end of the top antenna portion, and wherein the through connection provides a series connection from the second top end to the bottom surface; and
a bottom antenna portion located on the bottom surface of the flexible circuit board, wherein the bottom antenna portion has a first bottom end that is coupled to the through connection and a second bottom end coupled to the second antenna terminal, wherein the bottom antenna portion comprises a second circuit path between the first bottom end and the second bottom end, wherein the shape of the second circuit path is substantially identical to the shape of the first circuit path, and wherein the second circuit path is substantially aligned with the first circuit path.

US Pat. No. 10,430,783

TRANSMIT PHASE DETECTION CIRCUIT

Square, Inc., San Franci...

1. A system for measuring a phase difference of a near field communication (NFC) transmission circuit, comprising:a processing unit to provide a transmission source signal having a source signal phase;
a tuning circuit coupled to the processing unit to provide a tuned transmission signal from the transmission source signal;
an antenna coupled to the tuning circuit to transmit the tuned transmission signal;
a sense circuit coupled to the antenna to measure the transmitted signal, wherein the transmitted signal has a transmitted signal phase;
a phase detection circuit, comprising:
a measured signal input coupled to receive a first signal representative of the measured transmitted signal;
a source signal input coupled to receive a second signal representative of the transmission source signal; and
a phase detection output to output a phase difference signal based on a comparison of the first signal and the second signal, wherein a duty cycle of the phase difference signal changes based on whether the first signal and the second signal are associated with different logical values, and wherein the duty cycle of the phase difference signal is proportional to a phase difference between the source signal phase and the transmitted signal phase; and
an analog filtering circuit coupled to the phase detection circuit to generate an analog phase signal based on the duty cycle of the phase difference signal, wherein an amplitude of the analog phase signal is proportional to the phase difference between the source signal phase and the transmitted signal phase.

US Pat. No. 10,430,782

MERCHANT-SPECIFIC FUNCTIONALITY SERVICES

GOOGLE LLC, Mountain Vie...

1. A computer-implemented method to facilitate payments with merchant-specific financial accounts during proximity payment transactions, comprising by a user computing device:detecting a radio frequency field generated by a merchant computing device add-on component, a user operating the user computing device desiring to complete a payment transaction with a merchant operating the merchant computing device;
during creation of a communication channel, receiving, from the merchant computing device add-on component, a list of communication protocols comprising a modified handshake communication protocol enabling devices to transmit payment and additional information in a bi-direction communication via a secure bi-directional proximity communication channel;
establishing the secure bi-directional proximity communication channel between the merchant computing device add-on component and the user computing device using the modified handshake communication protocol, the confirmation of capability causing transmission of a merchant identifier from the merchant computing device add-on component via the established secure bi-directional proximity communication channel;
receiving the merchant identifier from the merchant computing device add-on component via the secure bi-directional proximity communication channel using the modified handshake communication protocol;
determining that a merchant-specific private label financial account is available for use during the payment transaction based on the received merchant identifier, the merchant-specific account limited to use only during payment transactions with the merchant associated with the received merchant identifier and differing from open loop financial account that can be used at unlimited locations;
enabling the merchant-specific account for use during the payment transaction;
receiving a payment request via the secure bi-directional proximity communication channel from the merchant computing device add-on component for the payment transaction, the add-on component receiving the payment request from a merchant computing device payment component;
preparing a response comprising the enabled merchant-specific account information; and
transmitting the response to the add-on component via the secure bi-directional proximity communication channel, the merchant computing device add-on component communicating the response to the payment component for payment processing.

US Pat. No. 10,430,781

USING A MOBILE DEVICE IN A COMMERCIAL TRANSACTION

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

US Pat. No. 10,430,780

SYSTEM AND METHOD FOR PAYING A MERCHANT BY A REGISTERED USER USING A CELLULAR TELEPHONE ACCOUNT

Payfone, Inc., New York,...

1. A method of issuing a virtual credit or debit card for a mobile subscriber comprising: performing the following operations using one or more computing systems:receiving a request to issue a virtual credit or debit card for a mobile subscriber and a current mobile telephone number for the mobile subscriber;
querying a mobile service provider and/or a clearinghouse for mobile services for a current mobile subscriber identifier associated with the mobile telephone number; and
comparing at least the current mobile subscriber identifier and a mobile subscriber identifier associated with the mobile telephone number to authenticate the mobile subscriber before issuing the virtual credit or debit card.

US Pat. No. 10,430,779

SYSTEMS AND METHODS FOR TRANSACTING AT AN ATM USING A MOBILE DEVICE

Capital One Services LLC,...

1. A system for transacting at an automated teller machine (ATM), comprising:one or more memory devices storing instructions; and
one or more processors configured to execute the instructions to:
receive transaction data associated with a transaction request received from a mobile device associated with a customer, wherein the transaction data includes a customer identifier,
identify a customer account based on the customer identifier;
determine that the mobile device is physically located within a predetermined distance from the ATM, by detecting an identification signal transmitted from the mobile device to the ATM via a local network;
responsive to the detected identification signal, transmit a signal to the mobile device indicating that the mobile device is within the predetermined distance from the ATM, for displaying a notification and prompt on the mobile device;
wherein a financial service provider system associated with the ATM detects capabilities associated with the mobile device;
prompt, via the signal, the mobile device based on the detected capabilities associated with the mobile device to provide authentication data associated with the customer;
receive, from the mobile device and in response to the displayed prompt, the authentication data associated with the customer, the authentication data being provided by the customer operating the mobile device and without requiring the customer to directly input data at the ATM and wherein a transaction amount above a predefined threshold requires receipt of a more secure type of authentication data or greater amount of authentication data;
determine, based on the transaction amount, whether the received authentication data authenticates the transaction;
based on the determination, iteratively prompt the mobile device to enter additional authentication data;
wherein a number of iterations depends on the customer account and the transaction amount;
authorize the transaction when the authentication data authenticates the transaction by comparing the received authentication data with stored customer data corresponding to the customer; and
based on the determination, provide an indication to the ATM to perform the transaction.

US Pat. No. 10,430,778

USING AUGMENTED REALITY FOR SECURE TRANSACTIONS

PAYPAL, INC., San Jose, ...

1. A method for accessing transactions via augmented reality devices, the method comprising:acquiring, via an augmented reality (AR) device, an image of a display of a user device;
determining, based on image analysis of the image, that the user device displays an interactive transaction element for a transaction between the user device and a server;
communicating with a server to move functionality of the interactive transaction element from the user device to the AR device;
generating a new interactive transaction element providing access to the transaction at the server;
visually projecting the new interactive transaction element using the AR device; and
providing access to the new interactive transaction element that is visually projected via the AR device.

US Pat. No. 10,430,777

BILL PAYMENT SYSTEM AND METHOD

GELLINER LIMITED, Dougla...

1. A method performed by a mobile wireless communication device, the method comprising:scanning, via a scanner of the mobile wireless communication device, a non-textual image that encodes a merchant identification code corresponding to (i) a merchant and (ii) a merchant template;
decoding the non-textual image to recover the merchant identification code;
sending, to an application server, a request for a template corresponding to the merchant, wherein the request includes the merchant identification code recovered from decoding the non-textual image;
capturing an image of text of a bill from the merchant;
receiving, from the application server, the merchant template, wherein the merchant template associates (i) a bill identification code data field with a first location within the image of text and (ii) an amount due data field with a second location within the image of text;
performing optical character recognition to identify the text of the bill;
using the merchant template to determine (i) that a first portion of the text that appears at the first location is a bill identification code and (ii) that a second portion of the text that appears at the second location is an amount due; and
sending, to the application server, the bill identification code, the amount due, and information identifying a payment instrument, thereby initiating payment of the amount due by the payment instrument.

US Pat. No. 10,430,769

SYSTEM FOR ATYPICAL THIRD PARTY CHANNEL UTILIZATION FOR RESOURCE DISTRIBUTION COMPLETION

BANK OF AMERICA CORPORATI...

1. A system for atypical third party channel utilization for resource distribution, the system comprising:a memory device with non-transitory computer-readable program code stored thereon;
a communication device;
a processing device operatively coupled to the memory device and the communication device within a distributive network for authorization and instant integration approval for a digital resource distribution, wherein the processing device is configured to execute the computer-readable program code to:
identify a user requesting the digital resource distribution to a merchant, wherein identifying the request comprises integrating within a user device associated with the digital resource distribution request and wherein the digital resource distribution further comprises a digital wallet, wherein a digital resource distribution token includes a virtual credit card token that is stored in a user device memory for digital resource distribution to the merchant;
determine software and hardware incapability within merchant system to complete the digital resource distribution, wherein the merchant system is a POS device and the merchant system does not have NFC or digital wallet transaction software and hardware;
identify, in response to determining software and hardware incapability, merchant wireless channel and link communicably to the wireless channel; wherein the merchant wireless channel further comprises a wireless network associated with a merchant place of business;
request and receive resource distribution information from the user device, wherein the resource distribution information includes a digital resource distribution token required for the digital resource distribution to the merchant;
translate the digital resource distribution token into a physical resource distribution account number;
distribute the translated digital resource distribution token to a resource distribution network system for processing and authorization;
match, within the resource distribution network, the distributed translated digital resource distribution token with resource distribution processing transmitted from the merchant system to the resource distribution network; and
transmit resource distribution network resource distribution approval to user device.

US Pat. No. 10,430,761

SYSTEMS AND METHODS FOR A GRAPHICAL INTERFACE INCLUDING A GRAPHICAL REPRESENTATION OF MEDICAL DATA

ICU Medical, Inc., San C...

14. A method comprising:receiving data associated with operation of medical devices and location of the medical devices within an environment, wherein the location of the medical devices corresponds to a physical clinical care area in the environment;
providing, by a computing device, on a display, a graphical representation of operations of the medical devices organized based on the location of the medical devices within the environment, wherein the graphical representation includes a number and a status of IV bags associated with the medical devices; and
providing, by the computing device, in the graphical representation, a graphical depiction that multiple IV bags have been ordered for a patient for the medical devices to graphically illustrate IV bags in waiting for the patient for the medical devices.

US Pat. No. 10,430,759

SYSTEMS AND METHODS FOR DISCOVERING A PERFORMANCE ARTIST

Viacom International Inc....

1. A method, comprising:receiving a user request for primary content of a primary artist from a user media device, the primary content being characterized with a primary content theme;
identifying a social connection between the primary artist and a secondary artist a social network;
identifying secondary content of the secondary artist, the secondary content being characterized with a secondary content theme; and
providing to the user media device a user recommendation for the secondary content of the secondary artist based on the identified social connection between the primary and secondary artists and the identified primary and secondary content themes; and
displaying a video feed for the content of the secondary artist via a graphical user interface of the user media device; and
displaying social media overlay including the social connection via the graphical user interface of the user media device.

US Pat. No. 10,430,748

UTILIZING SOCIAL PERFORMANCE PATTERNS TO MANAGE AND EVALUATE PERFORMANCE OF USER

International Business Ma...

1. A method for improving management and performance of an employee, the method comprising:receiving, by a social performance evaluator, an indication of a goal sponsored by an owner, wherein said goal is a desired result that a person, a group or an organization desires to achieve, wherein said owner is a user of a first client device connected to said social performance evaluator via a network;
receiving, by said social performance evaluator, an indication of a first user of a second client device connected to said network subscribing to said goal sponsored by said owner;
monitoring, by said social performance evaluator, communications on a social network involving said first user subscribed to said goal that includes a tag designating said goal;
detecting, by said social performance evaluator, a completion of said goal based on said monitored communications using natural language processing;
determining, by said social performance evaluator, a pattern of steps in accomplishing said goal by using natural language processing on said monitored communications involving said first user subscribed to said goal;
evaluating, by said social performance evaluator, an effectiveness of said pattern to accomplish said goal by other subscribed users, wherein said effectiveness of said pattern is based on a success or a failure in achieving said goal using said pattern, a length of time in achieving said goal, social media comments pertaining to said pattern, and a profit or revenue generated from achieving said goal, wherein said social performance evaluator utilizes a timer to determine said length of time in achieving said goal from a time said goal was sponsored by said owner to a time said goal was achieved by a subscribed user; and
recommending, by said social performance evaluator, actions to a second user of a third client device connected to said network concerning accomplishing said goal based on said pattern of steps, wherein said second user subscribed to said goal sponsored by said owner.

US Pat. No. 10,430,742

SYSTEM AND METHOD FOR MODULAR CUSTOMIZATION OF INTERMEDIATE BUSINESS DOCUMENTATION GENERATION

JABIL INC., St. Petersbu...

1. A system capable of providing customized subset business processes accessible from within a standard business process flow system, comprising:a process interface for continuous receiving of the standard business process flow;
a computing memory comprising non-transient computing code which, when executed by at least one computing processor communicatively associated with the computing memory, provides at least:
a developmental graphical user interface capable of developing a plurality of object-oriented custom modules of the subset processes indicative of a plurality of custom business steps within the standard business process flow;
a plurality of data libraries, wherein at least one of the plurality of data libraries is at least semi-private and at least one is semi-public, capable of storing at least configurations and rules applicable to the plurality of object-oriented custom modules;
a run time graphical user interface capable of receiving a selecting, via a drag and drop interface, of multiple ones of the plurality of object-oriented custom modules for inclusion in a custom process stack;
a selectable trigger sensor capable of receiving a trigger indicated by one of the configurations at the process interface, and capable of diverting the standard business process flow to process the custom process stack related to the trigger according to the configurations and rules upon receipt of the trigger;
a return interface that returns an output of the custom process stack to the standard business process flow; and
a runtime graphical user interface capable of illustrating at least the trigger and the diversion.

US Pat. No. 10,430,726

MACHINE LEARNING DEVICE THAT LEARNS SHOCKS TO TEACHING DEVICE, SHOCK PREVENTION SYSTEM OF TEACHING DEVICE, AND MACHINE LEARNING METHOD

FANUC CORPORATION, Yaman...

1. A machine learning device, which learns shocks to a teaching device, comprising:a state observation unit which observes data based on an inclination of the teaching device or a present position of the teaching device;
a label obtaining unit which obtains a label based on a shock received by the teaching device; and
a learning unit which generates a learning model based on an output of the state observation unit and an output of the label obtaining unit.

US Pat. No. 10,430,725

PETROLEUM ANALYTICS LEARNING MACHINE SYSTEM WITH MACHINE LEARNING ANALYTICS APPLICATIONS FOR UPSTREAM AND MIDSTREAM OIL AND GAS INDUSTRY

AKW ANALYTICS INC., New ...

1. A method for optimizing exploration, production and gathering from at least one well of oil and natural gas fields using a petroleum analytics learning machine system to maximize production while minimizing costs, comprising the steps of:collecting structured digital data and unstructured textual data from geological, geophysical, reservoir modeling, drilling, completion and production of crude oil, natural gas, ethane, butane, propane and condensate;
receiving an incoming data over a communications network and storing the incoming data into a system integration database by a processor based server or cloud based distribution of servers to provide collected data, the incoming data comprises digital exogenous data, real-time and historical endogenous data, historical data from surrounding production wells, hydraulic fracture completion data, and progress, status and maintenance data from new vertical and horizontal wells, including kickoffs, sidetracks, step-outs, pipeline gathering systems, compressor stations, and oil and gas sensor data including from public and private data sources;
recording a time and depth for each data point of the collected data;
cleaning the collected data to eliminate extraneous and noisy data;
normalizing and storing the clean collected data;
processing the normalized data to determine clusters of correlation in multi-dimensional space to identify a machine learned ranking of importance weights for each attribute;
ranking said importance weights, and identifying patterns to enhance production of said at least one well of oil and natural gas fields;
performing predictive and prescriptive optimization on the normalized data utilizing unique combinations of machine learning and statistical algorithm ensembles, including at least two of the following: linear and non-linear support vector machines and regressions, decision trees, hidden Markov models, random forests, neural networks, deep learning networks, bagging, boosting, feature selection, clustering, approximate and dynamic programming;
classifying unstructured textual data to correlate with optimal production by utilizing progressive clustering with learned seeds, information extraction and retrieval, image recognition, textual mining, keyword and key phrase extraction, semantic and sentiment analysis, entity and pattern recognition and knowledge discovery processing to capture the dynamics of said at least one or more wells of oil and natural gas fields and provide categorization results from labeled data sets to identify patterns;
displaying data and analyses, transmitting recommendations, and receiving actual field actions and reactions on a graphical user interface on a network-enabled processing device over the communications network, the recommendations being based on the collected data of one or more wells, or one or more predicted conditions, communications with the one or more of the field systems is autonomous and personalized to steer disparate data simultaneously to operators working on vertical and horizontal wells, hydraulic fractures, or other field operations that are needed to improve future production from of a well in response to one or more trends, said one or more predicted conditions, or recommendations displayed on the graphical user interface connected to the petroleum analytics learning machine system; and
wherein the petroleum analytics learning machine system utilizes:
an exploration and production synthesizer of available data from wells in an area or play, in order to score and rank the combined importance weights of attributes to predict maximum production at minimum costs when convolved with specific attributes of each well;
a real-time synthesizer to optimize drilling to match a designed pathway of a drilled well including hitting one or more target landing zones, while minimizing sinuosity and missed targeting of horizontal, diagonal and vertical components of the drilled wells;
a real-time processor to:
convolve importance weight values of attributes received by the petroleum analytics learning machine system from historical data and attribute data from each new well as it progresses in real time to predict future production of said each new well before oil and gas are delivered to the surface; and
to utilize time-series attributes during each hydraulic fracturing stage to automatically classify production effectiveness of said each hydraulic fracturing stage and provide recommendations to maximize future production of said each new well; and
wherein the recommendations are directed autonomously to optimize the production of oil, natural gas, and natural gas liquids while minimizing water production over time.

US Pat. No. 10,430,724

ECONOMIC OPTIMIZATION FOR PRODUCT SEARCH RELEVANCY

PAYPAL, INC., San Jose, ...

1. A method comprising:tracking, by a computer system comprising one or more computer processors, traffic exchange between users and a web site and capturing exchange data, the exchange data comprising at least data related to content requests from the users;
accessing, by the computer system, an artificial intelligence (AI) library that includes one or more AI algorithms;
creating, by the computer system, via one or more of the AI algorithms in the AI library and based on the captured exchange data and a measure of success derived therefrom, decisional logic for selecting a set of traffic optimizer modules for optimizing a web page generated in response to each of the content requests, the selected set of traffic optimizer modules comprising one or more traffic optimizer modules from a plurality of traffic optimizer modules associated with a plurality of respective aspects of the web page; and
processing, by the computer system, the content requests by creating optimized web pages responsive to the content requests, wherein the processing, by the computer system, of a content request comprises:
retrieving content responsive to the content request from a content database,
selecting, via execution of the decisional logic, the set of traffic optimizer modules, wherein selecting, via execution of the decisional logic, the set of traffic optimizer modules comprises:
generating a page optimization instruction set; and
optimizing, via execution of the selected set of traffic optimizer modules, presentation of the retrieved content, wherein optimizing, via execution of the selected set of traffic optimizer modules comprises assembling, via execution of the page optimization instruction set, the optimized retrieved content; and
presenting the optimized retrieved content in the form of an optimized web page.

US Pat. No. 10,430,723

STORAGE SYSTEM WITH MACHINE LEARNING BASED SKEW PREDICTION

EMC IP Holding Company LL...

1. An apparatus comprising:a plurality of storage tiers each comprising a plurality of storage drives;
at least one data mover module coupled to the storage tiers and configured to control transfer of data between the storage tiers; and
a skew predictor configured in accordance with a predictive model to convert skew measurements obtained for a given period of time less than a desired time granularity to corresponding skew measurements in the desired time granularity;
wherein one or more of the converted skew measurements are utilized by the at least one data mover module in controlling transfer of data between the storage tiers; and
wherein the at least one data mover module and the machine learning system are implemented using at least one processing device comprising a processor coupled to a memory.

US Pat. No. 10,430,722

LEARNING PARAMETERS IN A FEED FORWARD PROBABILISTIC GRAPHICAL MODEL

INTERNATIONAL BUSINESS MA...

1. A method comprising:creating an inference model via a computer processor, the creating comprising:
receiving a training set that includes multiple scenarios, each scenario comprising one or more natural language statements, and each scenario corresponding to a plurality of candidate answers;
constructing evidence graphs for each of the multiple scenarios based on the training set, wherein constructing the evidence graphs comprises for each scenario:
extracting factors from the scenario; and
generating intermediate nodes based on the extracted factors,
wherein the factors are root nodes in the evidence graphs and the candidate answers are terminal nodes in the evidence graphs; and
calculating weights for common features across the evidence graphs that will maximize a probability of the inference model locating correct answers from corresponding candidate answers across all of the multiple scenarios, wherein calculating the weights comprises assigning a highest weight to a factor having a largest number of unique terms relative to a selected domain; and
in response to an inquiry from a user via the computer processor, the inquiry comprising a scenario, constructing, using the inference model, an evidence graph and recursively constructing formulas to express a confidence of each node in the evidence graph in terms of corresponding parents in the evidence graph.

US Pat. No. 10,430,721

CLASSIFYING USER BEHAVIOR AS ANOMALOUS

Pivotal Software, Inc., ...

1. A computer-implemented method comprising:obtaining user behavior data representing behavior of a user in a subject system, wherein the user behavior data indicates one or more resources accessed by the user in the subject system and, for each resource accessed by the user, when the resource was accessed;
generating test data from the user behavior data, the test data comprising a first representation of resources accessed by the user during a test time period;
generating training data from the user behavior data, the training data comprising respective second representations of resources accessed by the user in each of multiple time periods prior to the test time period;
generating an initial path graph from the training data, wherein the initial path graph comprises nodes that represent resources accessed by the user in the subject system during one or more time periods represented by the training data, and links between one or more pairs of nodes, wherein each link between each pair of nodes represents that the user accessed a first resource represented by a first node of the pair and then navigated to a second resource represented by a second node of the pair;
generating a test path graph from the test data representing how the user navigated to a plurality of resources, wherein the test path graph comprises nodes that represent resources accessed by the user in the subject system during the test time period, and links between one or more pairs of nodes, wherein each link between each pair of nodes represents that the user accessed a first resource represented by a first node of the pair and then navigated to a second resource represented by a second node of the pair;
computing a difference between the initial path graph and the test path graph; and
classifying the user behavior by the user in the test time period as anomalous based on the difference between the initial path graph and the test path graph.

US Pat. No. 10,430,720

MOVEABLE STORAGE

Comcast Cable Communicati...

1. An apparatus comprising:one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the apparatus to:
determine an anticipated location change of a user from a first geographical location to a second geographical location; and
after determining the anticipated location change, based on an indication that the user will access data associated with the user during the anticipated location change, and before the user changes location from the first geographical location to the second geographical location, move the data associated with the user from a storage device associated with the first geographical location to a mobile device associated with the user.

US Pat. No. 10,430,719

PROCESS CONTROL TECHNIQUES FOR SEMICONDUCTOR MANUFACTURING PROCESSES

STREAM MOSAIC, INC., San...

13. A method useful in a multi-step semiconductor process, comprising:receiving sensor data from a plurality of pieces of production equipment during prior production runs of the semiconductor process;
receiving metrology measurements from a plurality of sampled wafers of the prior production runs;
determining a multi-variate relationship between the sensor data, the metrology measurements, and a targeted process parameter for one step of the multi-step semiconductor process; and
predicting metrology measurements for subsequent production runs based on the multi-variate relationship.

US Pat. No. 10,430,718

AUTOMATIC SOCIAL MEDIA CONTENT TIMELINE SUMMARIZATION METHOD AND APPARATUS

OATH INC., New York, NY ...

1. A method comprising:receiving, at a computing device, a request from a social media service user for information about an entity;
identifying, via the computing device, a plurality of social media content items, the social media content item identification comprising searching a number of social media content item data stores for the plurality of social media content items containing information about the entity;
determining, via the computing device and using each social media content item of the plurality, a timeline of episodes, the determined timeline of episodes comprising a number of episodes, the determination of the timeline of episodes comprising using a combined modeling, determined using statistical machine modeling, of content of the plurality of social media content items in combination with temporal information of the plurality of social media content items, the determination of the timeline of episodes further comprising using the combined modeling in assigning a number of social media content items of the plurality of social media content items to each episode of the number of episodes in the timeline of episodes;
determining, via the computing device and for an episode in the timeline of episodes, a ranking of the number of social media content items assigned to the episode, the rank determination comprising determining a set of features for each social media content item of the number of social media content items and using statistical machine modeling to rank the social media content items of the number of social media content items assigned to the episode in the timeline of episodes;
automatically selecting, via the computing device and for the episode, a predetermined number of top-ranked social media content items from the number of social media content items assigned to the episode; and
automatically creating, via the computing device, a summarization of the timeline of episodes, the summarization of the timeline of episodes comprising a number of entries corresponding to the number of episodes in the timeline of episodes, an entry corresponding to an episode of the number of episodes comprising the content of the predetermined number of top-ranked social media content items automatically selected from the number of social media content items assigned to the episode of the number of episodes.

US Pat. No. 10,430,717

COMPLEX PREDICATE TEMPLATE COLLECTING APPARATUS AND COMPUTER PROGRAM THEREFOR

National Institute of Inf...

1. A complex predicate template collecting apparatus, comprising:simple predicate template storage comprising a non-transitory computer readable medium for storing simple predicate templates, wherein:
each simple predicate template does not include a noun and does include:
a combination of a particle and a predicate; and
a positive or a negative polarity;
a word dictionary storing information for specifying a word;
a processor configured to:
extract a complex predicate template candidate from a first corpus including a plurality of natural language sentences, wherein:
the complex predicate template candidate is formed of a combination of a noun specified by said word dictionary and a simple predicate template stored by said simple predicate template storage;
determine, for each extracted complex predicate template candidate, a polarity of its noun; and
calculate, for each of said complex predicate template candidates, a polarity of the complex predicate template as a whole from a combination of:
the determined polarity of the noun included in the complex predicate template candidate, and
the polarity of the simple predicate template included in the complex predicate template candidate,
adding the calculated polarity to the complex predicate template candidate; and
outputting the complex predicate template candidate as a complex predicate template.

US Pat. No. 10,430,716

DATA DRIVEN FEATURIZATION AND MODELING

GROUND ROUNDS, INC., San...

1. An electronic device for producing predictive models comprising:a data storage configured to store one or more data sets associated with a target event, wherein the target event is associated with a healthcare condition;
a data input engine configured to obtain the one or more data sets associated with the target event from one or more data sources, wherein at least one of the one or more data sources is associated with healthcare information;
a featurization engine comprising:
an annotator configured to annotate the one or more data sets, wherein the annotations include an identification of the target event, an identification of records of the one or more data sets that are associated with the target event, and an establishment of one or more limits on the one or more data sets based on established criteria;
a data censor configured to censor the one or more data sets based on the annotations, wherein censoring the data includes filtering from the one or more data sets records that do not meet the established criteria; and
a summarizer configured to determine one or more features of the censored data, wherein the one or more features are representative of data in the one or more data sets and wherein at least one of the one or more features is based on a domain of the target event;
an analysis engine configured to:
analyze the one or more features, wherein the analysis identifies a subset of the one or more features that are indicative of the target event; and
produce a predictive model based on the analysis, wherein the predictive model provides an indication of a future occurrence of the target event based on data associated with a person.

US Pat. No. 10,430,715

PREDICTIVE MODELING SYSTEM FOR A MULTI-USER CAX ENVIRONMENT

United Technologies Corpo...

1. A system for facilitating multi-user computer aided design comprising:a plurality of locally stored multi-user design (CAx) environments; and
a hardware server including a server side CAx environment, wherein the hardware server is communicatively coupled to each of said locally stored CAx environments, the server side CAx environment including a plurality of model editing commands, and further including a predictive modeling module operable to receive an incomplete model editing command from a first user, and predict a complete model editing command including one or more predicted omitted parameters based on the incomplete model editing command, wherein the incomplete model editing command is within the plurality of model editing commands;
wherein said server side CAx environment includes a set of default parameters corresponding to each possible model editing command; and
altering a collaborative part file in the server side CAx environment according to a predicted resultant action based on the predicted complete model editing command;
modifying the predicted omitted parameters in response to a received actual parameter thereby determining a new predicted resultant action and altering the collaborative part file in the server side Cax environment according to the new predicted resultant action;
reiterating the step of modifying the predicted omitted parameters in response to a received actual parameter thereby determining a new predicted resultant action and altering the collaborative part file in the server side CAx environment according, to the new predicted resultant action until all omitted parameters have been replaced with actual parameters; and
propagating a visual representation of the resultant collaborative file to each of a plurality of locally stored user Cax environments.

US Pat. No. 10,430,714

AUTOMATIC SUGGESTION OF EXPERTS FOR ELECTRONIC DISCUSSIONS

International Business Ma...

1. A computer-implemented method, comprising:analyzing a text portion of a discussion thread generated during an electronic discussion in a social software system between a first participant and a second participant;
extracting a topic from the text portion;
determining, for the topic, a set of experts associated with the social software system, the set of experts having a level of expertise in the topic;
generating a list of experts from the set of experts, each expert on the list of experts being socially connected via the social software system with at least one of the first participant and the second participant;
determining a set of social closeness scores of each expert in the list of experts with respect to the first participant and with respect to the second participant;
arranging the list of experts as a ranked list by ranking the experts according to a summarized score that combines the set of social closeness scores with a degree of experience of each corresponding expert of the list of experts;
presenting the ranked list to the first and second participants during the electronic discussion, the experts on the ranked list being selectable by the first and second participants and
responsive to selection of an expert from the ranked list, sending an invitation to the expert inviting the expert to join the electronic discussion.

US Pat. No. 10,430,713

PREDICTING AND ENHANCING DOCUMENT INGESTION TIME

International Business Ma...

1. A method, in a data processing system, for predicting and enhancing ingestion time for a set of input documents, the method comprising:receiving a set of documents to be added to a corpus of documents;
recording document characteristics of each document within the set of documents using a characteristic recording annotator executing within the data processing system;
predicting an ingestion time for each document within the set of documents based on the document characteristics and a machine learning model, wherein the ingestion time is a predicted time to ingest each given document by a plurality of annotators executing within the computing device;
determining, for a given document, a document characteristic, wherein the document characteristic corresponds to a corresponding annotator used to process the document characteristic during ingestion; and
assigning the set of documents to question answering system resources to be processed based on the predicted ingestion time for each document, wherein assigning the set of documents to the question answering system resources comprises disabling or delaying execution of the corresponding annotator during ingestion of the given document.

US Pat. No. 10,430,712

COGNITIVE PLATFORM FOR USING KNOWLEDGE TO CREATE INFORMATION FROM DATA

1. A method comprising:retrieving, by at least one processor in a distributed parallel processing environment, source data from a datastore;
converting, by the at least one processor, the source data into raw Resource Description Framework (RDF) triples by applying RDF triple mapping language;
converting, by the at least one processor, the raw RDF triples into knowledge model RDF triples by applying semantic transform rules provided by a knowledge model, wherein the knowledge model RDF triples provide normalized and semantically consistent representations of the source data;
writing, by the at least one processor, the knowledge model RDF triples to a high throughput file system;
obtaining, by the at least one processor, a forward inference rule, including a pattern of knowledge concepts and relationships, from the knowledge model;
searching, by the at least one processor, the knowledge model RDF triples based on the pattern of knowledge concepts and relationships; and
inferring, by the at least one processor, a new knowledge model RDF triple based on identification of the pattern,
wherein converting the raw RDF triples into the knowledge model RDF triples includes generating specified RDF output classes.

US Pat. No. 10,430,711

METHOD AND SYSTEM FOR FUNC-BASED EXPERIENCE FRAMEWORK WITH CROSS-USER INTELLIGENCE

TCL RESEARCH AMERICA INC....

1. A method for providing desired application usage experience to a user on a user device, comprising:automatically converting a plurality of App pages into FUNC descriptors to be stored, wherein each FUNC descriptor includes at least non-functional properties of a FUNC, capability of the FUNC, and an interface of the FUNC to invoke the FUNC;
obtaining at least one user intention inputted by the user;
determining at least one FUNC descriptor from the FUNC descriptors for fulfilling the user intention;
recommending to the user with at least one FUNC corresponding to the at least one FUNC descriptor by rendering the at least one FUNC descriptor on the user device;
invoking the at least one FUNC directly from the user device without going through a launching page of an App page providing the at least one FUNC;
repurposing the at least one FUNC descriptor based on preference of the user and characteristics of the user device; and
rendering the at least one FUNC descriptor on the user device based on the repurposing of the at least one FUNC descriptor, comprising:
using an estimation (EST) of effort that the user makes to use the at least one FUNC to establish an underlying mechanism for the repurposing, wherein:

wherein M is a match cost that measures how appropriate each widget is for consuming an information of a FUNC element, N is a navigational cost that estimates an extra user effort required to manipulate the widget, F is the FUNC element, R is a rendering of the FUNC element (F) and is a trader off of two factors, M and N of using the rendering, giving a device (D) and a user (U).

US Pat. No. 10,430,710

CONNECTED HOTELS GUEST EXPERIENCE

Accenture Global Services...

1. A computer-implemented method comprising:receiving, by one or more property management servers of a connected hotel system that includes (i) beacons that are each associated with different locations on a hotel premises, (ii) a guest mobile device, (iii) the property management servers, (iv) an external temperature sensor that is configured to output data indicative of a current external temperature value, and (v) in-room thermostats that are each associated with different hotel rooms on the hotel premises, data from the guest mobile device indicating a sequence of the beacons that have been detected by the guest mobile device;
classifying, by the property management servers and using the data indicating the sequence of beacons that have been detected by the guest mobile device, the sequence of beacons as indicative of the user of the guest mobile device likely being in one of two, defined states, including (a) an on-property, non-returning state in which the user is indicated as on-property, moving, and likely remaining on the hotel premises away from their hotel room and not going directly to their hotel room, and (b) an on-property, returning state in which the user is indicated as on-property, moving, and likely going directly to their hotel room; and
based on classifying the sequence of beacons as indicative of the user of the guest mobile device likely being in the one of two, defined states, including (a) the on-property, non-returning state in which the user is indicated as on-property, moving, and likely remaining on the hotel premises away from their hotel room and not going directly to their hotel room, and (b) the on-property, returning state in which the user is indicated as on-property, moving, and likely going directly to their hotel room, setting, by the in-room thermostat that is associated with the hotel room of the user, a temperature setting value for the hotel room to the guest preferred temperature if the user is indicated as likely being in the on-property, returning state, or, if the user is indicated as likely being in the on-property, non-returning state, to a value that (i) is different than the guest preferred temperature value, (ii) is based on the guest preferred temperature value, the current external temperature value, and an empirically derived factor that reflects energy efficiency characteristics of the hotel room of the user, and (iii) is chosen to allow a temperature of the hotel room of the user to reach the guest preferred temperature value when the user later returns to the hotel room.

US Pat. No. 10,430,709

DATA MINING TECHNIQUE WITH DISTRIBUTED NOVELTY SEARCH

Cognizant Technology Solu...

1. An arrangement of processing units, for use with a data mining training database containing training data, comprising:a first processing unit having a first processor and a first memory, the first memory storing a first local pool of candidate individuals, each of the candidate individuals in the first local pool identifying at least one classification rule and further identifying a respective fitness estimate centric to the first processing unit; and
a second processing unit disposed down-chain of the first processing unit, the second processing unit having a second processor and a second memory, the second memory storing a second local pool of candidate individuals, each of the candidate individuals in the second local pool identifying at least one classification rule and further identifying a respective fitness estimate centric to the second processing unit,
wherein the first processor is configured to:
store in the first memory individuals for evaluation against portions of the training data,
delegate, to the second processing unit, evaluation of individuals from the first local pool of candidate individuals,
update the fitness estimates, centric to the first processing unit, for selected ones of individuals received back from the second processing unit after testing, in dependence upon results of such testing, and
select individuals for discarding from the first local pool, in dependence upon their fitness estimates relative to the fitness estimates of the other individuals within the first local pool,
and wherein the second processor is configured to:
store in the second local pool of candidate individuals, individuals received by the second processing unit from the first processing unit for evaluation,
test individuals from the second local pool of candidate individuals against a portion of the training data, wherein testing individuals from the second local pool of candidate individuals against a portion of the training data, includes recording, for each individual tested, an identification of the behavior of the individual when tested against the portion of the training data,
and wherein selecting individuals for discarding from the second local pool in dependence upon their novelty relative to other individuals in the second local pool comprises iteratively:
identifying, among the individuals in at least a non-null subset of the individuals in the second local pool, the pair whose recorded behavior is most similar; and
selecting one individual of the identified pair for discarding,
update the fitness estimates, centric to the second processing unit, for selected ones of individuals tested, in dependence upon the results of such testing,
select individuals for discarding from the second local pool, in dependence upon their novelty relative to other individuals in the second local pool, and
report to the first processing unit, individuals from the second local pool and not selected for discarding, in conjunction with the individuals' fitness estimates, centric to the second processing unit.

US Pat. No. 10,430,708

SYSTEM AND METHOD FOR NOISE-BASED TRAINING OF A PREDICTION MODEL

AIVITAE LLC, Redwood Cit...

1. A method for training a neural network, the method being implemented by one or more processors configured to execute one or more computer program instructions, the method comprising:obtaining randomly generated noise data,
obtaining common noise data;
generating a first noise image based on the randomly generated noise data and the common noise data by incorporating the common noise data as a foreground object at a first location over the randomly generated noise data;
generating a second noise image based on the randomly generated noise data and the common noise data by incorporating the common noise data as a foreground object at a second location over the randomly generated noise data, wherein the second location is a random location in the second noise image and different from the first location;
providing the first noise image and the second noise image to a neural network to obtain information indicating predicted locations of the common noise data in each of the first noise image and the second noise image; and
providing one or more target output indications to the neural network as reference feedback to update one or more configurations of the neural network, the one or more configurations being updated based on the information indicating the predicted locations and the one or more target output indications, and the one or more target output indications comprising information indicating locations of the common noise data in each of the first noise image and the second noise image.

US Pat. No. 10,430,707

INFORMATION PROCESSING DEVICE

SONY CORPORATION, Tokyo ...

1. An information processing device comprising:a control unit configured to control display related to a setting of a parameter related to physical simulation; and
a communication unit configured to transmit image information associated with the parameter obtained in the physical simulation to a machine learning unit and receive a determination result based on the image information from the machine learning unit,
wherein the setting of the parameter includes a parameter range indicating a range of a numerical value of the parameter, the range having an upper bound and a lower bound, and
wherein the control unit causes a display unit to display the determination result and the parameter range, including the upper bound and the lower bound, in visual association with each other.

US Pat. No. 10,430,706

PROCESSOR WITH MEMORY ARRAY OPERABLE AS EITHER LAST LEVEL CACHE SLICE OR NEURAL NETWORK UNIT MEMORY

VIA ALLIANCE SEMICONDUCTO...

1. A processor, comprising:a plurality of processing cores;
a last level cache memory (LLC) shared by the plurality of processing cores, the LLC comprising a plurality of slices; and
a neural network unit (NNU), comprising:
an array of neural processing units (NPU); and
a memory array;
wherein to transition from a first mode in which the memory array operates to store neural network weights read by the plurality of NPUs to a second mode in which the memory array operates as a slice of the LLC in addition to the plurality of slices, the processor:
write-back-invalidates the LLC; and
updates a hashing algorithm into a hashing-include algorithm to include the memory array as a slice of the LLC in addition to the plurality of slices; and
wherein to transition from the second mode to the first mode, the processor:
write-back-invalidates the LLC; and
updates the hashing algorithm into a hashing-exclude algorithm to exclude the memory array from the LLC;
wherein to write-back-invalidate the LLC to transition from the first mode to the second mode, the processor only write-back-invalidates cache lines of the plurality of slices whose addresses are hashed by the hashing-exclude algorithm; and
wherein to writeback-invalidate the LLC to transition from the second mode to the first mode, the processor only write-back-invalidates cache lines of the plurality of slices and the memory array whose addresses are hashed by the hashing-exclude algorithm.

US Pat. No. 10,430,705

SECURE TRAILER CONNECTION SYSTEM

ROBERT BOSCH GMBH, Stutt...

1. A system for detecting if a hitch connecting a trailer and a vehicle is not secure, the system comprising;a video camera;
an output device; and
an electronic control unit configured to,
receive from the video camera, video of the hitch connecting the trailer and the vehicle;
using the video of the hitch, detect if the hitch connecting the trailer and the vehicle is not secure when a trailer coupler is not in a latched position or a trailer chains are not crossed and connected to the trailer and the vehicle;
generate a driver notification; and
control a motion of the vehicle upon detecting the hitch connecting the trailer and the vehicle is not secure.

US Pat. No. 10,430,704

PAYMENT CARDS AND DEVICES WITH DISPLAYS, CHIPS, RFIDS, MAGNETIC EMULATORS, MAGNETIC ENCODERS, AND OTHER COMPONENTS

DYNAMICS INC., Pittsburg...

1. A payment card comprising:a first button;
a light source;
a magnetic emulator operable to communicate data in serial;
an RFID;
an IC chip; and
a processor operable to control said magnetic emulator, said RFID, said IC chip, and said light source.

US Pat. No. 10,430,703

RFID TAGS IN WEARABLES

Motorola Mobility LLC, C...

1. An article of manufacture comprising:a wearable, stretchable article comprising stretchable material, said wearable, stretchable article selected from a group comprising: clothing, a hat, a headband, a wristband, socks, footwear, handwear, shorts, or an undergarment;
at least one RFID tag mounted on the wearable, stretchable article; and
a stretch-activated switch on the at least one RFID tag, the stretch-activated switch having a first mode and a second mode, the first mode being associated with a first RFID tag state and the second mode being associated with a second RFID tag state, wherein the stretch-activated switch comprises a ground contact, an RFID enable contact and a contact to slidably engage the ground contact and the RFID enable contact to transition between the first RFID tag state and the second RFID tag state.

US Pat. No. 10,430,702

RF TAG NETWORK CONNECTIVITY THROUGH GATEWAY FACILITY

TEGO, INC., Waltham, MA ...

1. A system, comprising:a radio frequency (RF) tag configured to communicate data stored in a memory of the RF tag to a networked computing device through a wired connection or to an RF interrogator device through a wireless connection, the RF tag comprising (i) an RF and analog block for receiving an RF signal from and transmitting an RF signal to the RF interrogator device, (ii) a data processing and controller block for digital information processing, (iii) a memory store, and (iv) a communication facility, wherein the RF tag is at least in part powered by an external RF signal received by the RF and analog block; and
a sensor communicatively coupled to the communication facility,
wherein the RF tag is adapted to enable the networked computing device to access the memory store through a communication bus connected between the communication facility and the networked computing device when the external RF signal provides power to the RF tag, wherein the network computing device is communicatively connected to a network,
wherein the communication facility transfers data collected from the sensor by the RF tag to the networked computing device.

US Pat. No. 10,430,701

MAGNETIC SECURE TRANSMISSION DEVICE, ELECTRONIC DEVICE AND MOBILE SYSTEM INCLUDING THE SAME

Samsung Electronics Co., ...

1. A magnetic secure transmission (MST) system, comprising:an inductor;
a switching circuit connected to the inductor; and
a control circuit,
the control circuit being configured to control the switching circuit to adjust a level of a current in the inductor by a first amount over a data transmission period, such that the inductor emits a magnetic pulse including a first magnitude during the data transmission period,
the control circuit being configured to control the switching circuit to adjust the level of the current in the inductor such that the level of the current in the inductor is maintained at a first constant level during a first sub-period of a data non-transmission period, the level of the current in the inductor changes a second amount at a constant slope during a second sub-period of the data non-transmission period, the level of the current in the inductor is maintained at a second constant level during a third sub-period of the data non-transmission period, and the inductor emits a magnetic pulse including a second magnitude during the second sub-period of the data non-transmission period,
the second sub-period of the data non-transmission period being after the first sub-period of the data non-transmission period and before the third sub-period of the data non-transmission period in a same one of the data non-transmission period,
the second amount being less than the first amount,
the second constant level being greater than or less than the first constant level,
the first magnitude being greater than a threshold value corresponding to a noise level, and
the second magnitude being less than the threshold value.

US Pat. No. 10,430,700

GRAPHENE-BASED MICRO-SCALE IDENTIFICATION SYSTEM

INTERNATIONAL BUSINESS MA...

1. An object label comprising:a plurality of individual layers of a material that is transparent in a visible light domain and absorbs incident energy outside the visible light domain at a ratio proportional to a thickness of the material; and
a pattern comprising variations in the thickness of the material along at least one of two orthogonal directions across the label, the pattern readable by variations in an amount of energy outside the visible light domain reflected through the object label.

US Pat. No. 10,430,699

IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND COMPUTER-READABLE RECORDING MEDIUM

Ricoh Company, Ltd., Tok...

1. An image processing apparatus, comprising:a memory to store a dither table in which a plurality of dither patterns are recorded, each of the dither patterns being formed with a halftone dot screen in which an output area ratio that is a proportion of void halftone dots per unit area corresponds to any one of gradation values of image data; and
processing circuitry configured to
read a gradation value for each region in image data input for each toner color,
decide a dither pattern to be applied to the read gradation value, wherein the dither pattern is the halftone dot screen formed such that formation of a void halftone dot shape is finished at an output area ratio of 40% or less, and the dither pattern is formed by performing dot growth such that a first number of screen lines, defined as a number of halftone dots per inch, within a range of an output area ratio of 18% to 34% is greater than a second number of screen lines outside the range,
read out the decided dither pattern from the dither table, and
perform dither processing of applying the read dither pattern to the region in the image data.

US Pat. No. 10,430,698

IMAGE PROCESSING SYSTEM, METHOD OF CONTROLLING IMAGE PROCESSING SYSTEM, AND STORAGE MEDIUM

RICOH COMPANY, LTD., Tok...

1. An image processing system, comprising:an offset printer;
a digital printer; and
a server that is communicable with the offset printer and the digital printer, the server including processing circuitry configured to:
perform a first image processing to generate first raster data based on print target data, the first raster data to be used for generating a plate that is used by the offset printer; and
perform a second image processing to generate second raster data based on the print target data, the second raster data used by the digital printer, wherein
a first image formed by the offset printer and a second image formed by the digital printer are substantially the same,
the offset printer uses the plate to form the first image on a recording medium,
the digital printer uses the second raster data to form the second image on the recording medium,
the digital printer includes second processing circuity, and
the processing circuitry performs a part of the second image processing and the second processing circuitry performs another part of the second image processing.

US Pat. No. 10,430,697

PRINTER AND METHOD FOR PROCESSING STRING INFORMATION

SEIKO EPSON CORPORATION, ...

16. A control method of a printer having a receive buffer configured to receive string information indicating a string including substrings segmenting the string, wherein the string is segmented into the substrings by at least one delimiter, and at least some characters in the string are character codes that relate to font information, and storage configured to store style information indicating one or more styles defined by one or more specific rules, and to store the font information related to the character codes, comprising:generating, for one or more of the substrings in the string information received by the receive buffer, a command string including a command and the one or more of the substrings based on the style information stored in the storage indicating a style of the one or more of the substrings;
executing the one or more commands included in the generated command string, and generating image data by referencing the font information in the storage; and
printing based on the image data,
wherein the command string is generated according to the style information, which is applied according to an order of the one or more of the substrings.

US Pat. No. 10,430,696

COMPUTATIONALLY-EFFICIENT HUMAN-IDENTIFYING SMART ASSISTANT COMPUTER

MICROSOFT TECHNOLOGY LICE...

1. A method for a smart assistant computer to track a human, the method comprising:receiving data from one or more sensors configured to monitor a physical environment;
computer-analyzing the data to recognize presence of a human in the physical environment and to determine the human to be one of the following: a previously identified human, an unidentified human in the presence of a known user, and an unidentified human not in the presence of a known user;
based at least on determining the human to be a previously identified human, dedicating a first level of computational resources of the smart assistant computer to track the human;
based at least on determining the human to be an unidentified human in the presence of a known user, dedicating a second level of computational resources of the smart assistant computer, greater than the first level of computational resources, to determine an identity of the human; and
based at least on determining the human to be an unidentified human not in the presence of a known user, dedicating a third level of computational resources of the smart assistant computer, greater than the second level of computational resources, to determine the identity of the human.

US Pat. No. 10,430,695

SYSTEM AND METHOD FOR CONTEXTUALIZED VEHICLE OPERATION DETERMINATION

Nauto, Inc., Palo Alto, ...

1. A method for determining event data comprising:sampling a first image stream within a first time window at an interior-facing camera of an onboard vehicle system, wherein the onboard vehicle system is integrated into a mountable unit coupled to a vehicle at a single interior location;
extracting interior activity data, comprising a driver gaze direction, from the first image stream;
sampling a second image stream within a second time window at an exterior-facing camera of the onboard vehicle system, wherein the first and second time window are coextensive;
extracting exterior activity data from the second image stream;
determining an interior event based on the interior activity data, comprising mapping the driver gaze direction relative to a first region of the second image stream based on a relative orientation between the interior-facing camera and the exterior-facing camera of the onboard vehicle system;
determining an exterior event based on the exterior activity data, comprising determining that a distance between the vehicle and an object depicted in the first region of the second image stream has fallen below a threshold distance;
correlating the interior event with the exterior event to generate combined event data, comprising determining that the driver gaze direction overlaps with the first region of the second image stream at a time point within the first time window;
automatically classifying the combined event data to generate an event label; and
automatically labeling the first image stream within the first time window and the second image stream within the second time window with the event label to generate labeled training data;
transmitting the labeled training data to a remote computing system; and
aggregating the labeled training data at the remote computing system with a corpus of labeled training data, wherein the corpus of labeled training data is received from a plurality of onboard vehicle systems operating in a plurality of vehicles.

US Pat. No. 10,430,694

FAST AND ACCURATE SKIN DETECTION USING ONLINE DISCRIMINATIVE MODELING

Intel Corporation, Santa...

1. A computer-implemented method for performing skin detection comprising:applying face detection to received image data representative of an image to detect a first skin dominant region corresponding to a first face in the image and a second skin dominant region corresponding to a second face in the image;
combining the first and second skin dominant regions to generate a combined skin dominant region of the received image data;
randomly selecting a background region of the received image data outside of the first and second skin dominant regions;
generating a skin model based on the combined skin dominant region of the image data and a non-skin model based on the randomly selected background region of the image data;
determining a discriminative skin likelihood function based on the skin model and the non-skin model; and
classifying individual pixels of the image data as skin pixels or non-skin pixels based on the discriminative skin likelihood function to generate skin label data associated with the image data; and
outputting the skin label data, wherein the skin label data comprises one of a binary value of skin or non-skin for each of the individual pixels or a confidence value of skin pixel classification for each of the individual pixels.

US Pat. No. 10,430,693

PIPING AND INSTRUMENTATION PLANNING AND MAINTENANCE SYSTEM

Accenture Global Solution...

1. A piping and instrumentation planning and maintenance system comprising:an input/output (I/O) interface for receiving a target piping and instrumentation diagram (PID) from a document source system;
a processor in communication with the I/O interface; and
non-transitory computer readable media in communication with the processor that stores instruction code, which when executed by the processor, causes the processor to:
select, based on a type of the target PID, a process pipeline of a plurality of process pipelines for processing PIDs;
classify, using the selected process pipeline, entities and properties thereof within the target PID, wherein the entities include one or more assets and interconnections therebetween specified in the PID;
compare the classified entities to a knowledge base that represents relationships between a plurality of assets and interconnections between the plurality of assets;
determine, based on the comparison, whether the one or more assets in the target PID are interconnected correctly; and
when the one or more assets are not interconnected correctly, generate a report to identify the one or more assets that are not interconnected correctly.

US Pat. No. 10,430,692

GENERATING SYNTHETIC MODELS OR VIRTUAL OBJECTS FOR TRAINING A DEEP LEARNING NETWORK

Capital One Services, LLC...

1. A method, comprising:receiving, by a training platform, data for generating synthetic models of a body part,
the body part including a hand, and
the data including information relating to a plurality of potential poses of the hand;
generating, by the training platform, a set of synthetic models of the hand based on the information,
a synthetic model, in the set of synthetic models, representing a pose of the plurality of potential poses,
wherein generating the set of synthetic models includes:
generating the synthetic model such that no portions of two of a first component of the synthetic model, a second component of the synthetic model, a third component of the synthetic model, a fourth component of the synthetic model, or a fifth component of the synthetic model occupy a common voxel,
wherein the first component corresponds to a first finger of the hand,
wherein the second component corresponds to a second finger of the hand,
wherein the third component, corresponding to a third finger of the hand,
wherein the fourth component, corresponding to a fourth finger of the hand, and
wherein the fifth component, corresponding to a fifth finger of the hand;
deriving, by the training platform and after generating the set of synthetic models, an additional set of synthetic models based on the set of synthetic models,
the deriving including:
performing one or more processing operations with respect to at least one synthetic model in the set of synthetic models; and
causing, by the training platform, the set of synthetic models and the additional set of synthetic models to be provided to a deep learning network to train the deep learning network to perform image segmentation, object recognition, or motion recognition.

US Pat. No. 10,430,691

LEARNING METHOD AND LEARNING DEVICE FOR OBJECT DETECTOR BASED ON CNN, ADAPTABLE TO CUSTOMERS' REQUIREMENTS SUCH AS KEY PERFORMANCE INDEX, USING TARGET OBJECT MERGING NETWORK AND TARGET REGION ESTIMATING NETWORK, AND TESTING METHOD AND TESTING DEVICE USING

StradVision, Inc., Gyeon...

1. A method for learning parameters of an object detector based on a CNN by using a target object merging network and a target region estimating network, comprising steps of:(a) a learning device, if at least one training video is acquired, (i) instructing an image-manipulating network to generate a (1_1)-st manipulated image to a (1_n)-th manipulated image corresponding to first estimated target regions, where each of at least one target objects is estimated as located, on each of a (1_1)-st image to a (1_n)-th image included in a first image pyramid corresponding to a first frame which is a current frame of the training video, and generate a first integrated training image by concatenating the (1_1)-st manipulated image to the (1_n)-th manipulated image, (ii) instructing one or more convolutional layers to apply one or more convolution operations to the first integrated training image, to thereby generate a first feature map, instructing an RPN to generate (1_1)-st object proposals to (1_n)-th object proposals, corresponding to the target object located on each of the (1_1)-st manipulated image to the (1_n)-th manipulated image in the first integrated training image by using the first feature map, instructing a pooling layer to generate a first pooled feature map by applying one or more pooling operations to one or more regions, corresponding to the (1_1)-st object proposals to the (1_n)-th object proposals, on the first feature map, and instructing an FC layer to apply at least one fully connected operation to the first pooled feature map, to thereby generate (1_1)-st object detection information to (1_n)-th object detection information, corresponding to the target object, and (iii) instructing the target object merging network to generate first merged object proposals by merging the (1_1)-st object proposals to the (1_n)-th object proposals, and generate first merged object detection information by merging the (1_1)-st object detection information to the (1_n)-th object detection information, and instructing an FC loss layer to calculate one or more first FC losses by referring to the first merged object detection information and its corresponding GT, to thereby learn at least part of parameters of the FC layer and the convolutional layers by backpropagating the first FC losses; and
(b) the learning device (i) instructing the target object estimating network to search for (k?1)-th target regions, where the target object is estimated as located, on the (k?1)-th frame by referring to {(k?1)_1}-st object proposals to {(k?1)_n}-th object proposals on a (k?1)-th integrated training image, and instructing the target region estimating network to search for k-th estimated target regions, corresponding to one or more regions, where the (k?1)-th target regions are estimated as located, on a k-th frame, (ii) instructing the image-manipulating network to generate a (k_1)-st manipulated image to a (k_n)-th manipulated image corresponding to the k-th estimated target regions, on each of a (k_1)-st image to a (k_n)-th image included in a k-th image pyramid corresponding to the k-th frame, and generate a k-th integrated training image by concatenating the (k_1)-st manipulated image to the (k_n)-th manipulated image, (iii) instructing the convolutional layers to apply the convolution operations to the k-th integrated training image, to thereby generate a k-th feature map, instructing the RPN to generate (k_1)-st object proposals to (k_n)-th object proposals, corresponding to the target object located on each of the (k_1)-st manipulated image to the (k_n)-th manipulated image in the k-th integrated training image by using the k-th feature map, instructing the pooling layer to generate a k-th pooled feature map by applying the pooling operations to one or more regions, corresponding to the (k_1)-st object proposals to the (k_n)-th object proposals, on the k-th feature map, and instructing the FC layer to apply the fully connected operation to the k-th pooled feature map, to thereby generate (k_1)-st object detection information to (k_n)-th object detection information, corresponding to the target object, and (iv) instructing the target object merging network to generate k-th merged object proposals by merging the (k_1)-st object proposals to the (k_n)-th object proposals, and generate k-th merged object detection information by merging the (k_1)-st object detection information to the (k_n)-th object detection information, and instructing the FC loss layer to calculate one or more k-th FC losses by referring to the k-th merged object detection information and its corresponding GT, to thereby learn at least part of parameters of the FC layer and the convolutional layers by backpropagating the k-th FC losses, by increasing k from 2 to n.

US Pat. No. 10,430,690

MACHINE LEARNING PREDICTIVE LABELING SYSTEM

SAS INSTITUTE INC., Cary...

1. A non-transitory computer-readable medium having stored thereon computer-readable instructions that when executed by a computing device cause the computing device to:read a plurality of labeled observation vectors from a dataset;
read a plurality of unlabeled observation vectors from the dataset;
(A) train a labeling model using the read plurality of labeled observation vectors;
(B) execute the trained labeling model with each observation vector of the plurality of unlabeled observation vectors to define a label distribution probability matrix, wherein the label distribution probability matrix defines a label probability for each label of a label set for each observation vector of the plurality of unlabeled observation vectors;
(C) select a label for each observation vector of the plurality of unlabeled observation vectors as the label associated with a maximum label probability value in the label distribution probability matrix for a respective observation vector of the plurality of unlabeled observation vectors;
(D) for each label of the label set, compute a mean observation vector from the observation vectors of the plurality of unlabeled observation vectors selected to have each respective label;
(E) for each label of the label set, compute a covariance matrix from the observation vectors of the plurality of unlabeled observation vectors selected to have each respective label;
(F) for each label of the label set, select a number of eigenvalues from the covariance matrix computed for each respective label, wherein the selected eigenvalues have a smallest value of the eigenvalues for each respective label;
(G) for each label of the label set, define a null space using the selected eigenvalues for each respective label;
(H) for each observation vector of the plurality of unlabeled observation vectors, compute a distance vector from each respective observation vector to the computed mean observation vector associated with the label selected for each respective observation vector;
(I) for each observation vector of the plurality of unlabeled observation vectors, compute a distance value from each respective computed distance vector projected into the defined null space associated with the label selected for each respective observation vector;
(J) for each observation vector of the plurality of unlabeled observation vectors, determine a diversity rank based on a minimum computed distance value for the computed distance value for each respective observation vector;
(K) select a predefined number of observation vectors from the plurality of unlabeled observation vectors, wherein the predefined number of observation vectors have the predefined number of observation vectors number of highest values for the diversity rank;
(L) update the plurality of labeled observation vectors to include the selected observation vectors with the label selected for each respective observation vector;
(M) remove the selected observation vectors from the plurality of unlabeled observation vectors;
(N) repeat operations (A) to (M) a predefined number of times; and
after the predefined number of times, output the label selected for each observation vector of the plurality of unlabeled observation vectors to a second dataset.

US Pat. No. 10,430,688

KNOWLEDGE-BASED ULTRASOUND IMAGE ENHANCEMENT

Siemens Medical Solutions...

11. A system for image enhancement in medical diagnostic ultrasound, the system comprising:a receive beamformer configured to acquire ultrasound data representing a region of a patient;
a B-mode detector configured to output detected data from the ultrasound data;
a processor configured to extract input features from the detected data, identify an artifact as a grating lobe, shadow, or blood from the detected data as a function of a knowledge base, and image process the detected data as a function of the artifact, the image process including filtering locations of the artifact differently than other locations; and
a display configured to display an image of the region based on the image processed detected data, the image being a B-mode image with the artifact reduced.

US Pat. No. 10,430,687

TRADEMARK GRAPH ELEMENT IDENTIFICATION METHOD, APPARATUS AND SYSTEM, AND COMPUTER STORAGE MEDIUM

1. A method for automatically dividing trademark figurative element codes, comprising:S101, establishing a sample trademark library and establishing a corresponding relationship between sample trademarks and division data for figurative element codes of known filed/registered figurative trademarks;
S102, extracting and processing image feature information of the sample trademarks, and establishing a corresponding relationship between the sample trademarks and the extracted image feature information, specifically including extracting coordinate values (xn, yn), relative coordinate values (xn?, yn?) and rounded relative coordinate values (xn?, yn?) of pixels in a contour feature line of a sample trademark image to obtain the image feature information of the sample trademark, wherein xn represents a coordinate value of an nth pinxel on an x axis in a coordinate system, yn represents a coordinate value of the nth pixel on a y axis in the coordinate system;
S103, extracting and processing image feature information of a trademark to be identified, specifically including extracting coordinate values (xn, yn), relative coordinate values (xn?, yn?) and rounded relative coordinate values (xn?, yn?) of pixels in a contour feature line of a trademark image to be identified to obtain the image feature information of the trademark to be identified;
S104, performing a matching retrieval by taking the image feature information of the trademark to be identified as a retrieval condition, and finding out a sample trademark with a highest similarity degree to the image feature information of the trademark to be identified, and a corresponding trademark figurative element code, specifically including performing the matching retrieval in the sample trademark library by taking the image feature information of the rounded relative coordinate values (xn?, yn?) of the pixels in the contour feature line of the trademark image to be identified as a retrieval keyword, and for each sample trademark respectively finding out a number of pixels matched with the rounded relative coordinate values (xn?, yn?) of the pixels in the contour feature line of the trademark image to be identified and a number of pixels mismatched with the rounded relative coordinate values (xn?, yn?) of the pixels in the contour feature line of the trademark image to be identified, to find out the sample trademark with a highest similarity degree to the image feature information of the trademark to be identified, and the corresponding trademark figurative element code;
S105, outputting the trademark figurative element code corresponding to the sample trademark with a highest similarity degree to the image feature information of the trademark to be identified as a figurative element code of the trademark to be identified,
wherein a similarity degree between two trademark images is obtained using the following formula:
Similarity degree between two trademark images=Similarity rate of subfigure segments or arrays of continuous pixels of the two trademark images*weight of the subfigure segments of the two trademark images+Overlapping rate of the rounded relative coordinate values of the pixels*weight of overlapped rounded relative coordinate values+Non-overlapping rate of the rounded relative coordinate values of the pixels*weight of non-overlapped rounded relative coordinate values.

US Pat. No. 10,430,686

SYSTEMS AND METHODS FOR ENHANCING IMAGE RECOGNITION TECHNIQUES USING PRIMARY AND SECONDARY FOCI

Verizon Patent and Licens...

1. A device, comprising:a non-transitory computer-readable medium storing a set of processor-executable instructions; and
one or more processors configured to execute the set of processor-executable instructions, wherein executing the set of processor-executable instructions causes the one or more processors to:
use one or more image recognition techniques to automatically identify, in a reference image, a primary focus of the reference image, the primary focus being a first feature of the reference image;
use the one or more image recognition techniques to automatically identify, in the reference image, one or more secondary foci of the reference image, the secondary foci including at least a second feature of the reference image;
use the one or more image recognition techniques to automatically identify at least one of:
characteristics of at least one of the one or more secondary foci of the reference image, or
a positional relationship of the at least one of the one or more secondary foci to the primary focus;
score a set of candidate images based on the identified primary focus and the one or more secondary foci, the scoring for a particular candidate image, in the set of candidate images, being based on at least one of the following factors:
whether the particular candidate image includes the primary focus,
whether the particular candidate image includes the one or more secondary foci,
whether characteristics, of a particular secondary focus included in the candidate image, match characteristics of a corresponding secondary focus included in the reference image, or
whether a positional relationship, of the particular secondary focus included in the candidate image, matches a positional relationship of the corresponding secondary focus included in the reference image; and
rank the set of candidate images based on the scoring.

US Pat. No. 10,430,685

DEEP MULTI-SCALE VIDEO PREDICTION

Facebook, Inc., Menlo Pa...

1. A method comprising:by a computing device, receiving a plurality of input frames of a video sequence associated with a time t;
by the computing device, training a convolutional network to predict one or more future frames of the video sequence from the plurality of input frames based on a generative model,
wherein the training comprises using an adversarial model and an image gradient difference loss model, and
wherein the training comprises randomly selecting temporal sequences of a n×m grid of pixels from the plurality of input frames exhibiting a threshold of optical flow; and
by the computing device, outputting a first future frame of the video sequence associated with a time t+1 as predicted by the generative model.

US Pat. No. 10,430,684

SIGNAL PROCESSOR AND SIGNAL PROCESSING METHOD

CANON KABUSHIKI KAISHA, ...

1. A signal processor comprising:an acquisition unit configured to acquire input pixel signals I(x) corresponding to two-dimensionally arranged pixels (x), respectively; and
a processing unit configured to apply a predetermined stochastic resonance process to each of the input pixel signals I(x) acquired by the acquisition unit,
wherein the predetermined stochastic resonance process includes addition of noise obtained by multiplying generated random number by K to the input pixel signal I(x), a binarization process of comparing the result of the addition of the noise to the input pixel signal I(x) with a threshold T2 and a threshold T1 (where T2>T1), and a process of calculating a probability related to the result of the binarization process,
the binarization process includes:
a first nonlinear process of outputting “0” in a case where the input pixel signal I(x) after the addition of the noise is less than the threshold T1, “1” in a case where the input pixel signal I(x) after the addition of the noise is greater than the threshold T2, and “P” in a case where the input pixel signal I(x) after the addition of the noise is greater than or equal to the threshold T1 and less than or equal to the second threshold T2; and
a second nonlinear process of determining whether to output “1” or “0” for a processing target pixel, in which the result of the first nonlinear process is “P,” based on input pixel signals of pixels around the processing target pixel, the second nonlinear process being subsequent to the first nonlinear process, and
the process of calculating a probability is a process of calculating a probability J(x) that the result of the first nonlinear process is “1,” or the result of the first nonlinear process is “P” and the result of the second nonlinear process is “1” in the binarization process.

US Pat. No. 10,430,683

IMAGE PROCESSING METHOD AND PROCESSING DEVICE

BOE TECHNOLOGY GROUP CO.,...

1. An image processing method, comprising:acquiring an input image;
acquiring a first noise image and a second noise image;
executing image conversion processing on the input image with the first noise image using a generative neural network, to output the input image converted as a first output image; and
executing high resolution conversion processing on the first output image with the second noise image using a super-resolution neural network, to output the first output image converted as a second output image,
wherein the first noise image is different from the second noise image.

US Pat. No. 10,430,682

SYSTEMS AND METHODS FOR DECODING IMAGE FILES CONTAINING DEPTH MAPS STORED AS METADATA

FotoNation Limited, Galw...

1. A system for rendering an image using an image container file, the system comprising:a processor; and
memory containing a rendering application and an image container file, wherein the image container file comprises:
an encoded image synthesized from a plurality of images captured by a plurality of heterogeneous cameras, wherein each camera of the plurality of heterogeneous cameras captures the scene from a different viewpoint;
a depth map that specifies depths from a reference viewpoint for pixels in the encoded image based on disparity between pixels of the plurality of images;
an auxiliary map that provides information corresponding to pixel locations within a synthesized image; and
metadata describing the image container file, wherein the metadata comprises offset information to locate the encoded image, the depth map, and the auxiliary map;
wherein the rendering application configures the processor to:
locate the encoded image within the image container file;
decode the encoded image;
locate the depth map and the auxiliary map within the image container file; and
post process the decoded image to apply a depth based effect to the pixels of the decoded image based on the depth map, the auxiliary map, and the metadata to create a rendered image.

US Pat. No. 10,430,681

CHARACTER SEGMENTATION AND RECOGNITION METHOD

GRG Banking Equipment Co....

1. A character segmentation and recognition method, comprising:collecting image data to obtain a to-be-recognized image;
positioning a character line candidate region on the to-be-recognized image, wherein the character line candidate region comprises a plurality of characters which do not overlap with each other;
obtaining pre-set character line prior information, wherein the character line prior information comprises a quantity of the plurality of characters, a spacing among the plurality of characters, and a size of the plurality of characters;
obtaining a segmentation point template based on the character line prior information, wherein the segmentation point template comprises boundary frames of each of the plurality of characters;
traversing the segmentation point template within the character line candidate region, to obtain credible degrees of different positions in the character line candidate region;
determining an optimal segmentation position from the different positions, wherein the credible degree of the optimal segmentation position is largest among the credible degrees of the different positions;
segmenting the character line candidate region based on the segmentation point template and the optimal segmentation position to obtain a plurality of single-character regions which do not overlap with each other, wherein each of the plurality of single-character regions comprises one of the plurality of characters; and
performing character recognition on each of the plurality of single-character regions to obtain a corresponding recognition result;
wherein traversing the segmentation point template within the character line candidate region, to obtain credible degrees of different positions in the character line candidate region comprises:
recording position information of the segmentation point template, in response to the segmentation point being traversed to each of the different positions; and
obtaining the credible degrees corresponding to the position information; and
wherein the obtaining the credible degrees corresponding to the position information comprises:
obtaining the first number of first effective pixel points of the character line candidate region on a left boundary of a character segmentation point, wherein the segmentation point template comprises a plurality of character segmentation points, each of the character segmentation points corresponds to one character on a character line, each of the character segmentation points comprises the left boundary and a right boundary, and the first effective pixel points are pixel points with gray values in a pre-set first threshold range;
obtaining a first evaluation value based on the first number and a pre-set first weight;
obtaining the second number of second effective pixel points of the character line candidate region on the right boundary of the character segmentation point, wherein the second effective pixel points are pixel points with gray values in a pre-set second threshold range;
obtaining a second evaluation value based on the second number and a pre-set second weight;
obtaining the third number of third effective pixel points of the character line candidate region within the segmentation point template, wherein the third effective pixel points are pixel points with gray values in a pre-set third threshold range;
obtaining a third evaluation value based on the third number and a pre-set third weight; and
obtaining the credible degrees corresponding to the position information based on the first evaluation value, the second evaluation value and the third evaluation value.

US Pat. No. 10,430,680

IMAGE PROCESSING ALGORITHM

Robert Bosch GmbH, Stutt...

1. A method for allocating processor/computing times of a processor or of a computing unit for a driver assistance system of a vehicle, comprising:allocating processor/computing times to at least two functions of the driver assistance system as a function of a signal representing a state of the vehicle, wherein each function has assigned to it a control loop such that prior to the functions being executed each of the respective control loops requests a processor/computing time for the associated function.

US Pat. No. 10,430,679

METHODS AND SYSTEMS FOR DETECTING HEAD MOTION DURING AN AUTHENTICATION TRANSACTION

DAON HOLDINGS LIMITED, G...

1. A method for detecting user head motion comprising:generating, by a computing device, a motion type feature vector and a user head motion type prediction based on data generated for a sequence of frames, the frames include an image of a biometric modality of a user;
generating a liveness rating feature vector based on the data generated for the sequence of frames;
merging the motion type and liveness rating vectors;
generating a spoof prediction from the merged vector;
changing the user head motion type prediction to no motion when the generated spoof prediction indicates the image in the frames was spoofed;
storing the user head motion type prediction in a buffer; and
determining a final user head motion type detected for the frames.

US Pat. No. 10,430,678

BIOMETRIC INFORMATION PROCESSING DEVICE, BIOMETRIC INFORMATION PROCESSING METHOD AND NON-TRANSITORY COMPUTER-READABLE RECORDING MEDIUM

FUJITSU LIMITED, Kawasak...

1. A biometric information processing device comprising:a memory;
a processor coupled to the memory and the processor configured to:
extract a surface pattern and a blood vessel pattern of a living body from a biometric image;
extract a feature point of the surface pattern;
set a region that contains the feature point, where the region being smaller than the biometric image; and
extract a feature of the blood vessel pattern in the region,
wherein pixels representing the blood vessel pattern exist in the region with a ratio that is equal to or more than a threshold value.

US Pat. No. 10,430,677

METHOD FOR CLASSIFYING DRIVER MOVEMENTS

Robert Bosch GmbH, Stutt...

1. A method for classifying driver movements for ascertaining a degree of driver attentiveness during driving of a motor vehicle, using an interior compartment camera, the method comprising:recording at least a part of the driver;
based on the recording, evaluating a movement quantity representing a head movement of the driver; and
classifying the head movement of the driver as a safety view if the movement quantity corresponds to a defined condition;
wherein the head movement of the driver is classified as the safety view if a lateral head movement is recognized as the movement quantity;
wherein the lateral head movement is recognized if, starting from a first head orientation, a beginning of a head rotation in a first direction is ascertained, a beginning of a head rotation in the first direction being ascertained if a speed of the head rotation in the first direction corresponds to a defined first speed threshold value or exceeds a defined first speed threshold value.

US Pat. No. 10,430,676

APPARATUS DETECTING DRIVING INCAPABILITY STATE OF DRIVER

DENSO CORPORATION, Kariy...

1. An apparatus detecting driving incapability state of a driver, the apparatus comprising:an imaging device that is mounted on a vehicle and is configured to capture a driver's seat;
a memory storing a head detection portion and a shake detection portion; and
a processor executing the head detection portion and the shake detection portion stored in the memory, wherein
the head detection portion detects a head of the driver based on an image of the driver's seat captured by the imaging device, and
the shake detection portion detects the driver is incapable of driving when an amplitude of a shake of the head detected by the head detection portion is smaller than a first amplitude or larger than a second amplitude, which is larger than the first amplitude, before a shake determination time elapses after external force has been applied to the vehicle during travel of the vehicle, causing the vehicle to be safely stopped in a case where it is determined that the driver is incapable of driving.

US Pat. No. 10,430,675

METHOD AND DEVICE FOR PROVIDING A PIECE OF OCCUPANT INFORMATION FOR A SAFETY UNIT FOR A VEHICLE

Robert Bosch GmbH, Stutt...

1. A method for providing a piece of occupant information for a safety unit of a vehicle, the method comprising:obtaining, by a processor and via an interface to an image recording unit of the vehicle, image data representing an occupant of the vehicle;
obtaining, by the processor and via an interface to a mobile device or a data memory, plausibility check data representing a person;
determining, by the processor and based on the obtained image data and plausibility check data, occupant data characterizing the occupant; and
at least one of (a) providing, by the processor, the determined occupant data to an interface to the safety unit for the vehicle and (b) adapting, by the processor, the safety unit based on the determined occupant data;
responsive to initially being unable to determine the occupant data based on the obtained image data and plausibility check data, requesting further plausibility check data representing a further person, wherein the determination of the occupant data is additionally based on the further plausibility check data.

US Pat. No. 10,430,674

VEHICLE VISION SYSTEM USING REFLECTIVE VEHICLE TAGS

MAGNA ELECTRONICS INC., ...

1. A vision system for a vehicle, said vision system comprising:a camera configured to be disposed at a vehicle equipped with said vision system so as to have a field of view forward of the equipped vehicle;
an image processor operable to process image data captured by said camera when said camera is disposed at the equipped vehicle;
a tag element disposed at another vehicle, said tag element having a pattern thereat;
wherein, with said camera disposed at the equipped vehicle and when the tag element is present in the field of view of said camera, said image processor is operable to process image data by said camera to determine the pattern of the tag element present in the field of view of said camera;
wherein said image processor compares the determined pattern of the tag element to a database of patterns and classifies the tag element at least in part responsive to determination that the determined pattern of the tag element generally matches a pattern of the database;
wherein the pattern of the tag element disposed at the other vehicle includes information at least pertaining to a type of the other vehicle; and
wherein, responsive to determination that the determined pattern of the tag element generally matches a pattern of the database, headlamps of the equipped vehicle are adjusted.

US Pat. No. 10,430,673

SYSTEMS AND METHODS FOR OBJECT CLASSIFICATION IN AUTONOMOUS VEHICLES

GM GLOBAL TECHNOLOGY OPER...

1. An object classification method comprising:receiving lidar point cloud data associated with an object observed by a sensor system of an autonomous vehicle;
determining, with a processor, a bounding curve as an outline of the object in the lidar point cloud data and having a plurality of curve segments;
determining, with the processor, a feature vector for each of the plurality of curve segments based on convexities and concavities associated with the bounding curve; and
classifying, with the processor, the object by applying the feature vectors to a machine learning model and receiving a classification output that classifies the object for assisting in control of the autonomous vehicle.

US Pat. No. 10,430,672

HITCH ASSIST SYSTEM WITH TRAILER HEIGHT ESTIMATION AND HITCH COUPLER IDENTIFICATION

Ford Global Technologies,...

1. A hitch assist system comprising:an imager for capturing rear-vehicle images; and
a processor configured to:
extract trailer and ground features from the captured images;
compute vehicle motion displacement based on optical flow of the ground features;
estimate a height of each trailer feature based on vehicle motion displacement and optical flow of the trailer features; and
determine a trailer height based on the estimated heights of at least a portion of the trailer features.

US Pat. No. 10,430,671

SYSTEM AND METHOD FOR REMAPPING SURFACE AREAS OF A VEHICLE ENVIRONMENT

Honda Motor Co., Ltd., T...

1. A computer-implemented method for remapping surface areas of a vehicle environment, comprising:receiving a plurality of images of the surface areas of the vehicle environment from a computing device, wherein the surface areas of the vehicle environment includes an internal environment of a vehicle and an external environment surrounding the vehicle;
evaluating the plurality of images to determine an optical flow value associated with at least one pixel of at least two images of the plurality of images;
determining at least one surface area that includes the external environment of the vehicle; and
remapping the surface areas by filtering the at least one surface area from which the external environment is captured, wherein filtering the at least one surface area includes prohibiting rendering of at least one graphic through at least one window of the vehicle.

US Pat. No. 10,430,669

METHODS, SERVERS AND SYSTEMS FOR OPERATING ON SECURITY INSPECTION DATA

Nuctech Company Limited, ...

1. A method performed by a server for operating on security inspection image data, comprising:receiving an operation request for target security inspection image data from a client through a network;
loading the target security inspection image data from a storage server based on the operation request;
performing, by an image processing module, image processing on the loaded target security inspection image data;
encoding the processed target security inspection image data or a graphic interface including the processed target security inspection image data; and
transmitting the encoded target security inspection image data or graphic interface to the client through the network in a video stream,
wherein the server selects one of a plurality of data loading applications according to parameter information of the target security inspection image data to load the target security inspection image data from the storage server, and
wherein the server performs image processing on the loaded target security inspection image data using an image processing module corresponding to the selected data loading application.

US Pat. No. 10,430,668

SITUATION ASCERTAINMENT SYSTEM USING CAMERA PICTURE DATA, CONTROL DEVICE, AND SITUATION ASCERTAINMENT METHOD USING CAMERA PICTURE DATA

HITACHI SYSTEMS, LTD., T...

1. A situation confirmation system for using camera image data that enables an image data from a camera to be applied for a purpose of use in addition to preventing crime or monitoring safety, the situation confirmation system comprisinga central processing unit receive image data from a camera via a network
set header information to a header of the image data;
analyze the image data to identify objects and movement;
receive respective information entered from another system excluding the camera and/or an information processing device via the network;
automatically create, in response to the analyzing of the image data, auxiliary information that includes a number of objects and a direction of movement based on the created auxiliary information and the respective information,
create and add to the image data additional information according to a purpose of use of the image data by correlating the image data with a portion of additional information according to the purpose of use of the image data; wherein:
the additional information includes:
information of an installation location of the camera entered from the information processing device;
a vicinity event and disaster information entered from the information processing device; and
the auxiliary information; and the vicinity event and disaster information includes a set of weighting ranks; the purpose of use of the image data comprises marketing, traffic, amusement, sightseeing, festival, event, medical service and care giving;
store the image data including the additional information; and
the purpose of use of the image data of the camera in addition to crime prevention or safety monitoring, and stored in an image recording device;
search image data and display the same on a display
receiving a search condition;
searching the image data correlated with the portion of the additional information;
extract a search result based on the search condition; and
based on the search result, set a weighting rank according to the vicinity event and disaster information, the weighting rank indicating a level of influence
wherein the image data is correlated with the portion of the additional information of the other system and/or the information processing device according to the purpose of use of the image data of the camera in addition to crime prevention or safety monitoring and stored in an image recording device.

US Pat. No. 10,430,667

METHOD, DEVICE, AND COMPUTER PROGRAM FOR RE-IDENTIFICATION OF OBJECTS IN IMAGES OBTAINED FROM A PLURALITY OF CAMERAS

Canon Kabushiki Kaisha, ...

1. A method for re-identification by a computing device of at least one target object in images obtained from at least two image sources, each of the image sources obtaining images representing an area associated with the corresponding image source, the method comprising:identifying, by the computer device, at least one target object in images obtained from one of a pair of image sources;
estimating, by the computer device, a relative velocity of the at least one target object in comparison with at least another object previously identified in images obtained from the one of the pair of image sources, wherein the previously identified another object is a moving object; and
establishing, by the computer device, based on the estimated relative velocity of the at least one target object, a correspondence between the at least one target object identified in images obtained from the one of the pair of image sources and a plurality of candidate objects represented in images obtained from an other image source of the pair of image sources, thereby determining which among the plurality of candidate objects is the at least one target object; and
wherein the method further comprises, by the computer device, a step of extracting, for the at least one target object and each of the plurality of candidate objects, respective image-based features, and a step of selecting at least one candidate object of the plurality of candidate objects based on the extracted image-based features and the relative velocity of each of the plurality of candidate objects, and on the extracted image-based features and the relative velocity of the at least one target object.

US Pat. No. 10,430,666

TARGET OBJECT IDENTIFYING DEVICE, TARGET OBJECT IDENTIFYING METHOD AND TARGET OBJECT IDENTIFYING PROGRAM

NEC CORPORATION, Tokyo (...

1. A target object identifying device comprising:a processor;
a non-transitory computer-readable data storage medium storing computer-executable code that the processor executes to:
match monitoring targets shown in video captured by one or more imaging devices, identify monitoring targets estimated to be the same monitoring target, as an identified monitoring target, and identify other monitoring targets estimated to be different monitoring targets and responsively add the other monitoring targets within a first storage device upon which basis further matching of additional monitoring targets is performed;
identify a desired target object from one or more identified monitoring targets, using imaging times of each of the one or more identified monitoring targets, the desired target being a suspicious person or object; and
store the identified desired target object within a second storage device, wherein the desired target object is identified as the identified monitoring target whose frequency of monitoring target imaging information with an imaging time in a predetermined period is greater than or equal to a predetermined threshold,
wherein the desired target object is identified as the identified monitoring target whose time width between an earliest imaging time and a latest imaging time, among time widths between imaging times in a predetermined period, is greater than or equal to a predetermined threshold specified by a determination condition,
wherein the processor executes the computer-executable code to further generate the determination condition for specifying a condition of the time width between the earliest imaging time and the latest imaging time, based on imaging times of monitoring targets not identified as the desired target object.

US Pat. No. 10,430,665

VIDEO COMMUNICATIONS METHODS USING NETWORK PACKET SEGMENTATION AND UNEQUAL PROTECTION PROTOCOLS, AND WIRELESS DEVICES AND VEHICLES THAT UTILIZE SUCH METHODS

GM GLOBAL TECHNOLOGY OPER...

1. A video communications method comprising:segmenting an image frame or an image frame portion into a first source network packet block and a second source network packet block, wherein the first source network packet block comprises a first number of source network packets and the second network packet block comprises a second number of source network packets;
encoding the first source network packet block to produce a first encoded network packet block and encoding the second source network packet block to produce a second encoded network packet block, wherein the first encoded network packet block comprises a first number of encoded network packets and the second encoded network packet block comprises a second number of encoded network packets, and wherein the first number of encoded network packets is greater than or equal to the first number of source network packets and the second number of encoded network packets is greater than or equal to the second number of source network packets; and
transmitting the first encoded network packet block and the second encoded network packet block over a wireless network.

US Pat. No. 10,430,664

SYSTEM FOR AUTOMATICALLY EDITING VIDEO

1. A method comprising:receiving, by a computer system, an input media file;
decomposing, by the computer system, the input media file into a sequence frames;
identifying, by the computer system, for each frame subsequent to a first frame of the sequence of frames, motion values of pixels of the each frame relative to a preceding frame of the plurality of frames;
generating, by the computer system, a sequence of filtered motion values by smoothing the motion values of the sequence of frames;
identifying, by the computer system, one or more hotspots in the media file from the sequence of filtered motion values, each hotspot of the one or more hotspots including a video segment of the media file; and
generating an output including the one or more hotspots and excluding portions of the input media file not identified as hotspots.

US Pat. No. 10,430,663

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

INSTITUTE FOR INFORMATION...

1. An image annotation method implemented by an electronic device including a processor, comprising:acquiring a sequence of image frames comprising a plurality of image frames from video data by the processor;
performing an object detecting and tracking procedure on the sequence of image frames by the processor, so as to identify and track one or more target objects from the image frames;
selecting a plurality of candidate key image frames from the image frames according to a first selection condition by the processor, wherein the first selection condition comprises when a target object in the one or more target objects starts to appear or disappears in an image frame of the image frames, selecting the image frame as one of the candidate key image frames;
determining a plurality of first similarity indexes of the candidate key image frames by the processor, wherein each of the first similarity indexes is determined by the processor through a similarity calculation according to a first covariance value of a corresponding one of the candidate key image frames and a plurality of first variation values statistically calculated in different directions of the corresponding candidate key image frame;
determining a plurality of second similarity indexes of a plurality of adjacent image frames by the processor, wherein each of the adjacent image frames is adjacent to at least one of the candidate key image frames, and each of the second similarity indexes is determined by the processor through the similarity calculation according to a second covariance value of a corresponding one of the adjacent image frames and a plurality of second variation values statistically calculated in different directions of the corresponding adjacent image frame;
selecting the candidate key image frames as well as the adjacent image frames that meet a second selection condition as a plurality of key image frames, wherein the second selection condition comprises when a difference between a corresponding second similarity index of an adjacent image frame of the adjacent image frames and a corresponding first similarity index of a candidate key image frame adjacent to the adjacent image frame exceeds a similarity threshold, selecting the adjacent image frame as one of the key image frames; and
presenting the key image frames on a graphical user interface and displaying annotation information for the one or more target objects through the graphical user interface by the processor.

US Pat. No. 10,430,662

TRAINING MACHINE LEARNING MODELS TO DETECT OBJECTS IN VIDEO DATA

GumGum, Inc., Santa Moni...

11. A computer-implemented method comprising:as implemented by one or more computing devices configured with specific executable instructions,
receiving one or more video files as potential training data for one of more machine learning models;
selecting a first sample set of frames from the one or more video files;
receiving indication that (a) a first portion of a first sample frame includes the object of interest and (b) a second portion of a second sample frame includes the object of interest, wherein an intermediary plurality of frames appear in the one or more video files between the first sample frame and the second sample frame;
determining an in-frame location of the object of interest in at least a subset of the intermediary plurality of frames using a tracker;
storing frame annotation data for the one or more video files, wherein the frame annotation data includes an in-frame location of the object of interest in each of the first sample frame, the second sample frame, and the at least a subset of the intermediary plurality of frames;
training the one or more machine learning models to identify the object of interest, wherein the frame annotation data is used as training data in training the at least one machine learning model;
determining that performance of the one or more machine learning models when trained using the frame annotation data is below a performance threshold, wherein the performance threshold relates to at least one of accuracy or speed;
selecting a second sample set of frames from the one or more video files, wherein the first sample set of frames is different than the second sample set of frames;
receiving indications of portions of the second sample set of frames that include the object of interest; and
retraining the one or more machine learning models based at least in part on the portions of the second sample set of frames that include the object of interest.

US Pat. No. 10,430,661

GENERATING A COMPACT VIDEO FEATURE REPRESENTATION IN A DIGITAL MEDIUM ENVIRONMENT

Adobe Inc., San Jose, CA...

1. In a digital medium environment to learn a compact feature representation of video, a method implemented by at least one computing device, the method comprising:determining, by the at least one computing device, temporal order dynamics exhibited by a plurality of frames of the video through machine learning, the temporal order dynamics describing changes to the plurality of frames, one to another, over time;
generating, by the at least one computing device, a video feature representation from the temporal order dynamics, the generating based on:
a value of each feature of a plurality of features that has been reached for the plurality of frames in the video from the machine learning; and
a timestamp indicating when the value is reached for each feature of the plurality of features; and
outputting, by the at least one computing device, the video feature representation as a basis to determine similarity of the video with at least one other video.

US Pat. No. 10,430,660

IMAGE PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND STORAGE MEDIUM

Canon Kabushiki Kaisha, ...

1. An image processing apparatus comprising:a motion vector detection unit configured to perform motion vector detection by using an image signal output from an image sensor;
a generation unit configured to generate information regarding a result of the motion vector detection as metadata;
a recording unit configured to record each frame image of moving image output from the image sensor in a recording medium in association with the metadata; and
a control unit configured to cause, during an image capturing operation, the motion vector detection unit to perform motion vector detection by using an image signal output from the image sensor on which first reduction processing to reduce a number of pixels of the frame image was performed, and cause, during a playback operation of playing back the recorded age instructed by a user, the motion vector detection unit to narrow an image area in the each frame image in which motion vector detection is to be performed based on the metadata and to perform motion vector detection by using an image signal output from the recording medium on which second reduction processing to reduce a number of pixels of the frame image was not performed or on which the second reduction processing was performed such that a number of pixels of the frame image which has undergone the second reduction processing is larger than number of pixels of the frame image which has undergone the first reduction processing.

US Pat. No. 10,430,659

METHOD AND APPARATUS FOR URBAN ROAD RECOGNITION BASED ON LASER POINT CLOUD, STORAGE MEDIUM, AND DEVICE

Baidu Online Network Tech...

1. A method for urban road recognition based on a laser point cloud, comprising:constructing a corresponding road edge model according to the laser point cloud acquired by a laser sensor;
determining a height of a mobile carrier provided with the laser sensor and constructing a corresponding road surface model based on the height and the laser point cloud;
eliminating a road surface point cloud and a road edge point cloud in the laser point cloud according to the road edge model and the road surface model, segmenting a remaining laser point cloud using a point cloud segmentation algorithm, and recognizing an object corresponding to a segmenting result,
wherein the method is performed by one or more processors.

US Pat. No. 10,430,658

AUGMENTED REALITY SYSTEM AND KIT

1. A method of participating in an augmented reality experience, the method comprising the steps of:(a) obtaining a kit that includes a printed media member and at least a first instrument, wherein the kit has a theme, wherein the first instrument is associated with the theme, and wherein the printed media member includes at least a first image target that includes first linked augmented reality content,
(b) obtaining a mobile device that includes software running thereon that is in communication with a target database, wherein the first linked augmented reality content is associated with the software, wherein the first linked augmented reality content includes audio instructions that instruct the user how to utilize the first instrument, and wherein the first linked augmented reality content includes video instructions that instruct the user how to utilize the first instrument, wherein the mobile device includes a camera that has a camera lens,
(c) orienting the mobile device such that the camera lens is directed toward the printed media member, wherein the first image target is recognized by the software and the first linked augmented reality content is displayed on the mobile device, and
(d) viewing the first linked augmented reality content on a screen of the mobile device, such that the video instructions instruct the user how to utilize the first instrument and the audio instructions instruct the user how to utilize the first instrument.

US Pat. No. 10,430,657

OBJECT RECOGNITION TOOL

X Development LLC, Mount...

1. A method performed by a data processing apparatus of a robot:navigating a robot through an area to identify objects located in the area, the robot detecting presence of the objects in the area using one or more sensors;
attempting to determine an identity of a particular object detected in the area using an image processing technique and one or more images of the particular object captured by a camera of the robot;
determining that the robot cannot determine the identity of the particular object using the image processing technique;
in response to determining that the robot cannot determine the identity of the particular object using the image processing technique, providing data that causes a user device to present a user interface that includes data describing the particular object, the data describing the particular object including the one or more images of the particular object captured by the camera of the robot, the user interface being configured to present multiple categories of objects and to receive user input that identifies a category for the particular object;
receiving, in response to interaction with the user interface, data identifying the category for the particular object; and
in response to receiving the data identifying the category for the particular object:
updating a database for the robot with the data identifying the category for the particular object; and
enabling the robot to perform one or more actions with respect to objects of the identified category that the robot was previously unable to perform before receiving the data identifying the category for the particular object.

US Pat. No. 10,430,656

ANALOG UTILITY METER READING

UTILITY METER READER, LLC...

1. A method of reading a utility meter with a mobile device having a camera, a processor, and wireless communication transceiver associated therewith, the utility meter having a plurality of scrolling dials, the plurality of scrolling dials each having a scrolling dial indicator, the method comprising:taking a digital image of the plurality of scrolling dials of the utility meter with the camera of the mobile device;
analyzing the digital image to identify the dial indicators in the digital image;
analyzing the identified dial indicators to determine a value of the dials with the processor of the mobile device; wherein analyzing the digital image to identify the dial indicators in the digital image includes converting the digital image to a gray-scale image, inverting the gray-scale image to produce a high contrast image, applying a morphological filter to the high contrast image to produce a smoothed image, applying a top-hat transform to the smoothed image to produce a transformed image, eroding boundaries of regions in the transformed image to produce an eroded image, applying a threshold filter to the eroded image to produce a bi-level image, and analyzing the bi-level image to identify the dial indicators in the digital image with the processor of the mobile device; and
transmitting the determined value with the wireless communication transceiver of the mobile device, whereby the utility meter is read with the mobile device.

US Pat. No. 10,430,655

AUGMENTED REALITY INFORMATION PROCESSING SYSTEM AND AUGMENTED REALITY DISPLAY CONTROL METHOD WITH SPACE INFORMATION CONVERSION AND DISPLAY CONTROL FEATURES

FUJITSU LIMITED, Kawasak...

1. A system, comprising:circuitry configured to:
obtain an image;
detect a first actual object in the image;
obtain, from storage, space information indicating a first space in a three-dimensional coordinate system whose criterion is based on the first actual object;
convert, in accordance with a first shape of the first actual object in the image, the space information into first area information corresponding to an arrangement enable area in which the first space is projected onto the image;
obtain, from the storage, other space information indicating a second space in the three-dimensional coordinate system whose criterion is based on the first actual object, the second space being different from the first space;
convert, in accordance with the first shape of the first actual object, the other space information into second area information corresponding to an arrangement disable area in which the second space is projected onto the image; and
control, based on the first area information and the second area information when at least a part of the arrangement enable area is included in the arrangement disable area, a display to display a content in a third area within the arrangement enable area in the image, the third area not being included in the arrangement disable area, the content being associated with the actual object.

US Pat. No. 10,430,654

AUTOMATED DETECTION OF ENVIRONMENTAL MEASURES WITHIN AN OCEAN ENVIRONMENT USING IMAGE DATA

1. A method comprising using at least one hardware processor to:in a machine-learning phase during a first time period,
receive first image data of an ocean environment,
receive ocean sensor data that represent one or more environmental measurements of the ocean environment collected by at least one ocean sensor contemporaneously with a time at which the first image data of the ocean environment was captured, and
correlate the first image data with the ocean sensor data to train a predictive model to emulate an output of the at least one ocean sensor based on the first image data; and,
in an operational phase during a second time period that is subsequent to the first time period,
for each of one or more ocean-facing cameras that are positioned to capture second image data of the ocean environment,
receive the captured second image data via at least one network, and
use the predictive model to
identify one or more features within the captured second image data, and
estimate the one or more environmental measures of the ocean environment based on the identified one or more features within the captured second image data, and,
for each of one or more user systems,
receive a request for data from the user system via the at least one network,
generate the requested data based on the estimated one or more environmental measures, and
send the requested data to the user system via the at least one network.

US Pat. No. 10,430,653

SYSTEM AND METHOD FOR AUTONOMOUS VEHICLE CONTROL

Landing Technologies, Inc...

1. A system for localizing an autonomous vehicle to a target landing area, comprising:an unmanned aerial vehicle with a plurality of directional control components, the unmanned aerial vehicle including a control system for controlling the directional control components, and having three separated light emitting diodes providing a position indicator;
a camera proximate the target landing area, the camera for detecting the three LEDs on the unmanned aerial vehicle;
a computation device proximate or in association with the camera and the target landing area, the computation device in communication with the camera and configured to compute a position of the vehicle based on the detected three LEDs and the relationship of the three LEDs to the vehicle orientation and to provide a path to the target landing area;
a transmitter proximate the computation device in communication with the computation device and configured to receive information from the computation device and produce a signal carrying the information;
a receiver on the vehicle and configured to receive the signal from the transmitter, the control system in communication with the receiver, the control system configured to control the plurality of directional control components of the vehicle based on the information received from the receiver to localize the unmanned aerial vehicle to the target area.

US Pat. No. 10,430,652

PROCESS AND SYSTEM FOR VIDEO SPOOF DETECTION BASED ON LIVENESS EVALUATION

1. A process for determining a video of a biometric characteristic as being a spoof or a genuine recording of a live biometric characteristic, wherein the video comprises a temporal sequence of frames (j), the process being implemented in a system comprising a processing unit,characterized in that it comprises the steps of:
preprocessing the video, said preprocessing comprising aligning the biometric characteristic on each frame of the video,
determining a liveness score of the video, said determination comprising, for each frame of a plurality of frames:
computing a difference between a motion intensity of a current frame and a motion intensity of each frame of a set of preceding frames,
inferring, from said differences, a differential motion intensity of the current frame,
inferring from the differential motion intensities of the plurality of frames a motion intensity of the video,
comparing said motion intensity to a predetermined threshold, and assigning a liveness score to the video, depending on a comparison of the motion intensity of the video with the threshold, and
according to the liveness scores of the video, determining whether the video is a genuine recording of a biometric characteristic or a spoof.

US Pat. No. 10,430,651

ELECTRONIC DEVICE INCLUDING IRIS CAMERA

SAMSUNG ELECTRONICS CO., ...

1. An electronic device comprising:a light source module comprising a light source and associated circuitry;
an iris camera configured to capture an image of an iris using infrared rays radiated from the light source module; and
a processor electrically connected with the light source module and the iris camera and configured to generate an image regarding the iris, and
wherein, the light source module and the iris camera are arranged such that a distance between the light source module and the iris camera is between a first threshold distance and a second threshold distance, the first threshold distance being for generating a retina reflection region having a specified size in the image of the iris obtained by detecting, by the iris camera, the infrared rays reflected from the retina, the second threshold distance being for generating a darkest portion to be displayed in an iris region in the image of the iris having a specified luminance.

US Pat. No. 10,430,650

IMAGE PROCESSING SYSTEM

FANUC CORPORATION, Yaman...

1. An image processing system that detects an image of a target in input shape information based on a model pattern representing the feature of the image of the target, comprising:a model pattern acquisition unit that acquires the model pattern generated from the input shape information;
a model pattern correction unit used for correcting the model pattern acquired by the model pattern acquisition unit; and
a machine learning unit that generates generation information for generating the model pattern from the input shape information by performing supervised learning using a set of learning data pieces each including correction information about the model pattern corrected by using the model pattern correction unit and the input shape information associated with each other, wherein
the image processing system is capable of generating a model pattern in which a result of the learning is reflected using the input shape information input to the image processing system and the generation information.

US Pat. No. 10,430,649

TEXT REGION DETECTION IN DIGITAL IMAGES USING IMAGE TAG FILTERING

Adobe Inc., San Jose, CA...

1. An automated text region detection method implemented by at least one computing device, the method comprising:locating, by the at least one computing device, a text region candidate in a digital image;
generating, by the at least one computing device, a plurality of image tags for the text region candidate using a plurality of classifiers trained as part of machine learning, the plurality of classifiers including:
a classifier having a model configured to generate an image tag indicative of text; and
a classifier having a model configured to generate an image tag not indicative of text;
determining, by the at least one computing device, whether the text region candidate includes text based on inclusion of the image tag indicative of text and the image tag not indicative of text in the plurality of image tags generated for the text region candidate; and
outputting, by the at least one computing device, an indication of a text region corresponding to the text region candidate in the digital image responsive to the determining the text region candidate includes text.

US Pat. No. 10,430,648

METHOD OF PROCESSING CONTENT AND ELECTRONIC DEVICE USING THE SAME

Samsung Electronics Co., ...

1. A method of processing content in an electronic device, the method comprising:acquiring, by a controller in the electronic device, content including a plurality of characters;
generating, by the controller, a plurality of editable images using the acquired content;
grouping the plurality of editable images into a plurality of blocks, based on sizes of the plurality of editable images, intervals between the plurality of editable images, and shapes of the plurality of editable images, wherein each of the plurality of blocks includes a plurality of characters;
editing, by the controller, the plurality of editable images based on the grouped plurality of editable images; and
displaying, by the controller, the edited plurality of editable images,
wherein the editing of the plurality of editable images comprises:
identifying an interval between at least two adjacent blocks among the plurality of blocks; and
adjusting the interval between the at least two adjacent blocks based on the identified interval of the at least two adjacent blocks.

US Pat. No. 10,430,647

TAILORED ILLUMINATION PROFILE FOR ARTICULATED HAND TRACKING

Microsoft Licensing Techn...

1. A near-eye display device comprising:an illumination module that, when in operation, provides illumination having an illumination profile that matches a predicted interaction volume within which a user of the near-eye display device is expected to place a body part of the user to interact with a user interface of the near-eye display device, wherein the illumination profile includes an upper portion and a lower portion, the upper portion corresponding to a first part of the predicted interaction volume from a shoulder height of the user and above, the lower portion corresponding to a second part of the predicted interaction volume from the shoulder height of the user and below, and wherein the upper portion of the illumination profile has an average illumination power that is lower than an average illumination power of the lower portion of the illumination profile;
an imaging sensor that, when in operation, receives light reflected by an environment of the near-eye display device and the body part of the user and generates depth values corresponding to depths of the environment and the body part relative to the near-eye display device; and
a processor that, when in operation, tracks a location of the body part of the user based on the depth values.

US Pat. No. 10,430,646

SYSTEMS AND METHODS FOR OPERATING A VIRTUAL REALITY ENVIRONMENT USING COLORED MARKER LIGHTS ATTACHED TO GAME OBJECTS

ZERO LATENCY PTY LTD, No...

1. A system for operating a virtual reality environment including at least one space, the system comprising:at least one color camera configured to view the at least one space;
at least one object, wherein the at least one object comprises at least one of a player, a controller and a device related to the virtual reality;
at least one colored light attached to each of the at least one object configured to be used as a tracking marker;
at least one server configured to track movements of the at least one object during the virtual reality;
a memory containing machine readable medium comprising machine executable code having stored thereon instructions for tracking the movements of the at least one object; and
a control system comprising a processor or processors coupled to the memory, the control system configured to execute the machine executable code to cause the control system to:
assign a color choice to each of the at least one colored light, wherein the assignment of the first color to the first colored light from among the at least one colored light is based on a spatial proximity of the first colored light to other colored lights in the at least one space.

US Pat. No. 10,430,645

FACIAL RECOGNITION OPERATIONS BASED ON POSE

Apple Inc., Cupertino, C...

1. A device, comprising:a camera;
at least one illuminator providing illumination;
circuitry coupled to the camera and the illuminator, wherein the circuitry is programmed to:
obtain at least one image of a face of a user using the camera while the face of the user is illuminated with the illumination;
encode the at least one image to generate at least one feature vector, wherein the at least one feature vector represents one or more facial features of the user in the at least one image;
determine a pose of the user in the at least one image;
in response to the pose of the user being determined to be a first pose:
compare the at least one feature vector to a first set of dynamic reference templates and a set of static reference templates to obtain a first matching score; and
authorize the user to perform at least one operation on the device that requires authentication in response to the first matching score being above a first unlock threshold of the device;
in response to the pose of the user being determined to be a second pose:
compare the at least one feature vector to a second set of dynamic reference templates and the set of static reference templates to obtain a second matching score; and
authorize the user to perform at least one operation on the device that requires authentication in response to the second matching score being above a second unlock threshold of the device.

US Pat. No. 10,430,644

BLENDED IRIS AND FACIAL BIOMETRIC SYSTEM

Global Bionic Optics Ltd....

1. A method for identifying a candidate, comprising:capturing, by an optical system, a raw image of the candidate;
identifying, by the optical system, iris features and facial features within the raw image;
quantifying, by the optical system, each of the iris features;
quantifying, by the optical system, each of the facial features;
determining, by the optical system, a first weight associated with the iris features;
determining, by the optical system, a second weight associated with the facial features, wherein the first weight and second weight are based on a distance of the candidate from the optical system;
comparing, by the optical system, the quantified iris features with iris enrollment data to determine an iris match probability;
comparing, by the optical system, the quantified facial features with facial enrollment data to determine a facial match probability;
modifying, by the optical system, the iris match probability based on the first weight;
modifying, by the optical system, the facial match probability based on the second weight;
calculating, by the optical system, a combined probability based on the modified iris match probability and the modified facial match probability; and
confirming, by the optical system, an identity of the candidate based on the combined probability.

US Pat. No. 10,430,643

FACIAL RECOGNITION PET IDENTIFYING SYSTEM

Finding Rover, Inc., Bre...

1. A user interface device, comprising:a processor;
a display;
a memory configured to store a first image, wherein a first animal appears in the image; and
a network interface device configured to:
transmit the first image;
transmit a first geographical location indicator, wherein the first geographical location indicator is generated in response to a user input;
receive a second image, wherein the first animal appears in the second image; and
receive a contact information associated with the second image, wherein the second image is received in response to a networked device determining that the first animal appears in the second image, and wherein the determining that the first animal appears in the second image is only performed by the networked device when the first geographical location indicator indicates a first location that is within a distance from a second location that is indicated by a second geographical location indicator associated with the second image.

US Pat. No. 10,430,642

GENERATING ANIMATED THREE-DIMENSIONAL MODELS FROM CAPTURED IMAGES

Apple Inc., Cupertino, C...

1. A method, comprising:obtaining at least one image of a face of a user using a camera located on a device, the device comprising a computer processor, a memory, and a display;
encoding, using the computer processor, the at least one image to generate one or more first feature vectors, wherein the first feature vectors represent one or more facial features of the user in the at least one image;
determining, using the computer processor, a pose of the face of the user and one or more muscle activations of the face of the user in the at least one image from the first feature vectors;
generating, using the computer processor, a three-dimensional model of the user's face based on the determined pose and muscle activations for the user's face;
projecting, using the computer processor, the three-dimensional model onto the at least one image;
defining, using the computer processor, one or more selected locations on the three-dimensional model;
using the three-dimensional model projected onto the at least one image, encoding, at least once, using the computer processor, the at least one image at the selected locations to generate one or more second feature vectors for the at least one image, wherein the second feature vectors represent one or more facial features of the user at the selected locations in the at least one image;
refining, at least once, using the computer processor, the determination of the pose of the face of the user and the one or more muscle activations of the face of the user in the at least one image using the second feature vectors; and
refining, at least once, using the computer processor, the three-dimensional model of the user's face generated from the at least one image based on the refined pose and muscle activations for the user's face.

US Pat. No. 10,430,640

SYSTEM AND METHOD FOR CLASSIFICATION OF PARTICLES IN A FLUID SAMPLE

KONINKLIJKE PHILIPS N.V.,...

1. A system for classifying particles in a water sample, system comprising:an optical detection assembly comprising at least one image acquisition device and corresponding lens with an optical axis, the image acquisition device is configured to acquire images of an image acquisition area perpendicular to the optical axis;
a sample device comprising at least one sample container suitable for holding a water sample in liquid form comprising particles;
a translating arrangement configured to translate said image acquisition area through at least a part of said sample container with a step length between each acquired image;
a controller configured to control said optical detection assembly and said translating arrangement to acquire images of a plurality of image acquisition areas;
an image processor programmed to analyze said acquired images and to determine a set of features for an individual particle captured by said acquired images by creating objects of the individual particle and assigning each of the objects to a corresponding stack of objects comprising different images of the individual particle; and
an artificial intelligent processor programmed to associate said set of features for said individual particle to a particle classification of particles,
wherein said step length between each acquired image is used to determine a distance between the objects in the stacks of objects.

US Pat. No. 10,430,639

USER AUTHENTICATION DEVICE, INPUT SENSING MODULE FOR THE SAME, AND METHOD OF AUTHENTICATING USER

Samsung Display Co., Ltd....

1. An input sensing module comprising:a flexible base member comprising a three-dimensional base surface; and
a plurality of sensing electrodes disposed on the flexible base member;
wherein:
the flexible base member comprises a first base portion having a first non-flat average curvature and a second base portion having a second non-flat average curvature smaller than the first average curvature;
the plurality of sensing electrodes comprise first sensing electrodes disposed on the first base portion and second sensing electrodes disposed on the second base portion, the first sensing electrodes having a first pitch, and the second sensing electrodes having a second pitch greater than the first pitch;
the first pitch is defined by a sum of a first width of an electrode of the first sensing electrodes and a first distance between the first sensing electrodes adjacent to each other; and
the second pitch is defined by a sum of a second width of an electrode of the second sensing electrodes and a second distance between the second sensing electrodes adjacent to each other.

US Pat. No. 10,430,638

SYSTEMS AND METHODS FOR SPOOF DETECTION RELATIVE TO A TEMPLATE INSTEAD OF ON AN ABSOLUTE SCALE

Synaptics Incorporated, ...

9. A method for performing spoof detection, comprising:receiving, by a processor from a sensor, an input image of a biometric;
extracting, by the processor, one or more anti-spoof metrics from the input image;
receiving, by the processor, an anti-spoof template corresponding to a biometric of a first user;
for a first anti-spoof metric, computing, by the processor, a first amount of a difference between a value of the first anti-spoof metric extracted from the input image and a value of the first anti-spoof metric in the anti-spoof template that corresponds to the biometric of the first user;
for a second anti-spoof metric extracted from the input image, computing, by the processor, a second amount of a difference between a value of the second anti-spoof metric extracted from the input image and a value of the second anti-spoof metric in the anti-spoof template that corresponds to the biometric of the first user;
determining, by the processor, whether the input image is a replica of the biometric of the first user based on the first amount of the difference between the value of the first anti-spoof metric extracted from the input image and the value of the first anti-spoof metric in the anti-spoof template that corresponds to the biometric of the first user and the second amount of the difference between the value of the second anti-spoof metric extracted from the input image and the value of the second anti-spoof metric in the anti-spoof template that corresponds to the biometric of the first user; and
preventing, by the processor, successful authentication on the device in response to determining that the input image is a replica of the biometric of the first user.

US Pat. No. 10,430,637

FINGERPRINT IDENTIFICATION UNIT

Keycore Technology Corp.,...

1. A fingerprint identification unit formed on a base, having a top and a bottom side, comprising:a first coating layer disposed either on the top side or on the bottom side of the base and being a film layer, not a silicon substrate, the first coating layer being a base layer for the fingerprint identification unit;
a first fingerprint identification electrode layer disposed on one side of the first coating layer opposite to the base and having a plurality of first fingerprint identification electrodes;
a second coating layer covering the first fingerprint identification electrode layer;
a second fingerprint identification electrode layer disposed on one side of the second coating layer opposite to the first fingerprint identification electrode layer and having a plurality of second fingerprint identification electrodes;
a conductor layer having a plurality of metal conductors, which are selectively electrically connected to the first and the second fingerprint identification electrode layer; and
a third coating layer covering the second fingerprint identification electrode layer and part of the conductor layer;
wherein the base is selected from a group consisting of a touch panel, a Color Filter (CF), a Thin-Film Transistor (TFT), and a Liquid Crystal Module (LCM); and
wherein the first, the second, and the third coating layer being a silica film.

US Pat. No. 10,430,636

DISPLAY PANEL AND DISPLAY DEVICE

Shanghai Tianma Micro-Ele...

1. A display panel, comprising:an array substrate including a plurality of organic light-emitting structures;
at least one fingerprint identification unit configured to identity a fingerprint based on light reflected by a touch object to the at least one fingerprint identification unit, wherein an organic light-emitting structure has a first side facing the array substrate and an opposing second side, and the at least one fingerprint identification unit is disposed in a display region on the first side of the organic light-emitting structure;
a plurality of spacers, wherein an orthogonal projection of a spacer onto the array substrate is disposed between orthogonal projections of adjacent organic light-emitting structures onto the array substrate; and
a plurality of anti-crosstalk pads, wherein an anti-crosstalk pad is disposed between the spacer and the at least one fingerprint identification unit, an orthogonal projection of the anti-crosstalk pad onto the array substrate includes a first region, the first region overlaps with the orthogonal projection of the spacer onto the array substrate, and the anti-crosstalk pad blocks light scattered by the spacer from entering the at least one fingerprint identification unit.

US Pat. No. 10,430,635

FINGERPRINT IDENTIFICATION SENSOR, FINGERPRINT IDENTIFICATION METHOD AND ELECTRONIC DEVICE

BOE TECHNOLOGY GROUP CO.,...

1. A fingerprint identification sensor, comprising:a substrate;
a fingerprint sensing element disposed on the substrate and including a thin film transistor, an off-state leakage current of the thin film transistor at an off-state voltage applied to a gate of the thin film transistor varying with the intensity of light irradiating onto an active area thereof, the fingerprint sensing element being configured to generate a sensing signal based on the off-state leakage current; and
a fingerprint identification light source arranged to emit light that irradiates onto a finger and is reflected thereby, the reflected light irradiating onto the active area of the thin film transistor.

US Pat. No. 10,430,634

BIOMETRIC SENSING DEVICE AND DISPLAY DEVICE

InnoLux Corporation, Mia...

1. A biometric sensing device, comprising:a first electricity storage component;
a first sensing component coupled with the first electricity storage component, wherein when the first sensing component is turned on, a charging path is formed between the first sensing component and the first electricity storage component, and the first sensing component makes the first electricity storage component be charged according to a sensed biometric;
a first driving component coupled with the first electricity storage component and the first sensing component, wherein when the first driving component is turned on, the first electricity storage component discharges; and
a control unit coupled with at least one of the first sensing component and the first driving component for turning on the first sensing component and the first driving component.

US Pat. No. 10,430,633

PIXEL ARCHITECTURE AND DRIVING SCHEME FOR BIOMETRIC SENSING

SYNAPTICS INCORPORATED, ...

1. A processing system for a fingerprint sensor, the processing system comprising:a controller circuit configured to:
charge a first sensor electrode of a plurality of sensor electrodes to a first voltage, wherein the plurality of sensor electrodes are disposed in an array;
charge a second sensor electrode to a second voltage different from the first voltage, wherein the first and second voltages are assigned to the first and second sensor electrodes according to a code, and wherein the first sensor electrode and the second sensor electrode are disposed in a same column in the array;
after charging the first and second sensor electrodes, couple the first and second sensor electrodes simultaneously to a same analog front end (AFE) to sense a combined charge on the first and second sensor electrodes; and
determine a fingerprint based at least in part on the sensed combined charge on the first and second sensor electrodes.

US Pat. No. 10,430,632

DISPLAY DEVICE AND DRIVING METHOD THEREOF

Samsung Display Co., Ltd....

1. A display device comprising:a display including a plurality of pixels disposed on a display area;
a display controller including a timing controller and configured to control the display;
a sensor including a plurality of first sensing electrodes and a plurality of second sensing electrodes disposed in the display area; and
a sensor controller including a touch detector configured to recognize a touch of a user inputted into the sensor in a touch sensing mode and a fingerprint authorizer configured to recognize a fingerprint of the user inputted into the sensor in a fingerprint sensing mode,
wherein the sensor controller changes a mode to the fingerprint sensing mode when no touch is inputted for a predetermined time period in the touch sensing mode and changes the mode to the touch sensing mode when authorization on a fingerprint inputted into the sensor is succeeded in the fingerprint sensing mode, and
wherein the sensor controller sequentially drives all the first sensing electrodes in the fingerprint sensing mode and the sensor controller drives all the second sensing electrodes in the fingerprint sensing mode.

US Pat. No. 10,430,631

MUT FINGERPRINT ID SYSTEM

THE REGENTS OF THE UNIVER...

1. A MEMS ultrasound fingerprint ID system configured to detect both epidermis and dermis fingerprint patterns in three dimensions, the system comprising:a) a micromachined ultrasonic transducer (MUT) transmitter-receiver array comprising MUTs that apply an acoustic signal to a finger;
b) a coupling material disposed on the MUT transmitter-receiver array;
c) a voltage driver that applies a voltage to the array;
d) circuitry connected to the array; and
e) a data processor that receives and processes a signal from the array to produce an image of a fingerprint,
wherein the system is configured to drive MUTs in the MUT transmitter-receiver array in groups and scan the acoustic signal by switching excitation of the MUTs from group to group in sequence, and
wherein a focus diameter of the acoustic signal is determined by a pitch between the MUTs in the group and a frequency of the MUTs in the group.

US Pat. No. 10,430,630

ELECTRONIC DEVICE

GUANGDONG OPPO MOBILE TEL...

1. An electronic device, comprising a flexible display screen, a fingerprint identification module and a housing, the housing having a top face and a side face connected with each other, the side face defining a mounting groove, the fingerprint identification module being accommodated in the mounting groove, the flexible display screen comprising a fixed portion and a movable portion connected with each other, the fixed portion being fitted to the top face, and the movable portion extending beyond the top face,wherein when the movable portion is bent relative to the fixed portion, the movable portion covers the side face and the fingerprint identification module performs fingerprint identification through the flexible display screen; when the movable portion is spread out relative to the fixed portion, the fingerprint identification module is exposed out of the flexible display screen, such that a finger is fitted to the side face to perform the fingerprint identification.

US Pat. No. 10,430,629

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

KABUSHIKI KAISHA DDS, Na...

1. A non-transitory computer-readable medium storing computer-readable instructions that are executed by a processor provided in an information processing device comprising a storage portion, the computer-readable instructions, when executed, instructing the processor to perform processes comprising:an image acquisition step of acquiring an image;
a base point determination step of determining a base point from the image acquired by the image acquisition step;
a sample information acquisition step of acquiring sample information that is information indicating a change in color information of a surrounding area of the base point determined by the base point determination step, the sample information acquisition step including
acquiring a sample for each of a plurality of second reference points whose positions are different from each other, the sample being information that associates color information corresponding to the second reference points, which are points on a circumference of a circle whose center is a first reference point and whose radius is a second predetermined value, with position information that is information corresponding to the positions on the image of the second reference points, the first reference point being a point in the image whose distance from the base point is a first predetermined value, and
acquiring, as the sample information, information that associates the acquired plurality of samples with center information that is information corresponding to a position on the image of the first reference point;
a frequency information acquisition step of acquiring frequency information that is generated on the basis of the sample information for each of a plurality of the first reference points acquired by the sample information acquisition step, the frequency information acquisition step including
calculating a frequency component of a change in the color information with respect to the position information, for each of the plurality of first reference points, and
acquiring the frequency information that is information that associates the calculated frequency component with the center information; and
a storage control step of causing the storage portion to store the frequency information acquired by the frequency information acquisition step, as collation information used for collation of biometric information.

US Pat. No. 10,430,628

SLIP PROCESSING DEVICE, SLIP PROCESSING METHOD, AND RECORDING MEDIUM

CASIO COMPUTER CO., LTD.,...

1. A handheld device for slip processing, comprising:an imaging unit that images an object;
a barcode scanner that reads a one-dimensional barcode;
a storage unit; and
a processor configured to perform the following:
causing the barcode scanner to scan a one-dimensional barcode on a slip to obtain identification information on the slip;
determining whether the obtaining of the identification information has succeeded;
when the obtaining of the identification information has succeeded, causing the imaging unit to image the slip to obtain a slip image;
determining whether the one-dimensional barcode is present within the slip image that has been obtained, and, when it is determined that the one-dimensional barcode is present, detecting an inclination of the one-dimensional barcode and then causing a horizontal correction process to be applied to the slip image in accordance with the inclination that has been detected; and
causing the identification information that has been obtained and the slip image that has been corrected by said horizontal correction process to be stored in association with each other in the storage unit.

US Pat. No. 10,430,627

LABEL CREATING DEVICE, SYSTEM, AND LABEL

SEIKO EPSON CORPORATION, ...

1. A system configured to verify an identity of an article, the system comprising:a label creating device configured to create a label associated with the article; and
an information device configured to acquire information used for verifying the identity of the article from a content of the label, wherein
the label creating device includes:
an imaging unit configured to image a first subject including the article, and to acquire first image data of the first subject;
a first analyzer configured to analyze a characteristic of the article in the first subject by using the first image data, and to generate first characteristic information;
a first identification information acquiring unit configured to acquire first identification information associated with the article and used for identifying the article;
a generator configured to generate code information including at least the first characteristic information and the first identification information; and
a printing unit configured to print the code information on a label medium, and to output the label, and
the information device includes:
a device imaging unit configured to image a second subject including the article and the code information, and to output second image data;
an extracting unit configured to extract the first characteristic information and the first identification information from the image data of the code information of the second subject included in the second image data;
a second analyzer configured to analyze a characteristic of the article of the second subject by using the second image data, and to generate the second characteristic information;
a second identification information acquiring unit configured to acquire second identification information to be checked with the first identification information extracted by the extracting unit;
a characteristic information determining unit configured to determine whether the first characteristic information and the second characteristic information match each other;
an identification information determining unit configured to determine whether the first identification information extracted by the extracting unit and the second identification information acquired by the second identification information acquiring unit match each other; and
a display controller configured to control a display to display a determination result determined by the characteristic information determining unit and the identification information determining unit.

US Pat. No. 10,430,626

CARRIER FOR THE EXAMINATION OF WORKPIECES BY COMPUTED TOMOGRAPHY

CARL ZEISS 3D AUTOMATION ...

1. An examination method comprising:scanning, by a computed tomography scanner, a workpiece carrier and a workpiece arranged on the workpiece carrier together by computed tomography (CT) to produce a CT scan, wherein the workpiece is assigned an identification code and the workpiece carrier is coded, by a pattern made from a plurality of separate regions of different densities, with at least one character of the identification code;
identifying in the CT scan, by an evaluation unit, the regions or a part of the regions;
identifying, by the evaluation unit, the respective densities of the identified regions or part of the regions based on the CT scan;
orienting, by the evaluation unit, the scan based on a location of a straight line through two of the identified regions;
determining, by the evaluation unit and based on a pattern of the identified densities, the at least one character; and
processing, by the evaluation unit, the oriented scan based on the determined at least one character.

US Pat. No. 10,430,625

BARCODE READING ACCESSORY FOR A MOBILE DEVICE HAVING A ONE-WAY MIRROR

THE CODE CORPORATION, Dr...

1. A barcode reading enhancement system for a mobile device, the mobile device comprising a processor, a display screen, a camera comprising a camera lens, and memory, the barcode reading enhancement system comprising:an accessory securable to the mobile device, the accessory comprising:
an optic module within a camera field of view of the camera, wherein the optic module folds the camera field of view toward a direction extending away from a top end of the mobile device to create a system field of view; and
a target-generating structure configured to project a targeting pattern through the optic module into a center of the system field of view; and
a mobile barcode reading application comprising executable code stored in the memory that, when executed by the processor, causes the camera to capture an image of a barcode within the system field of view.

US Pat. No. 10,430,624

WIRELESS SENSOR READER ASSEMBLY

ENDOTRONIX, INC., Lisle,...

1. A system for wirelessly sensing a parameter from a remote location, comprising:a handheld reader device configured to communicate with a wireless sensor;
wherein said handheld reader device includes a plurality of modes to establish communication with said wireless sensor, said modes comprising:
a docked mode wherein said handheld reader device is not in use;
a search mode wherein said handheld reader device attempts to establish the proper distance acceptable for taking readings from the wireless sensor, wherein when said handheld reader device is in said search mode, said handheld reader device is configured to receive at least one response signal from said wireless sensor and compare a characteristic of said at least one response signal to a predetermined threshold value, wherein said comparison of said characteristic of the at least one response signal to said predetermined threshold value is used to determine to provide a feedback to a user of said handheld reader device; and
a read mode wherein said handheld reader device reads and samples response signals from the wireless sensor.

US Pat. No. 10,430,623

RFID TAG TRACKING USING TAG POPULATION MANAGEMENT

Impinj, Inc., Seattle, W...

1. A method for a Radio Frequency Identification (RFID) reader system to track the movement of an RFID integrated circuit (IC) of interest coupled to an antenna, the method comprising:receiving an IC response in an inventory round;
determining that the IC response is from the RFID IC of interest;
in response to determining that the IC response is from the RFID IC of interest, preventing the RFID IC of interest from entering a quiet state;
determining, based on at least the IC response, a trajectory of the RFID IC;
generating a plurality of beams along the trajectory;
cooperatively powering the RFID IC using the plurality of beams; and
receiving a subsequent response from the RFID IC in the inventory round.

US Pat. No. 10,430,622

RFID TAG WITH RECONFIGURABLE PROPERTIES AND/OR RECONFIGURING CAPABILITY

INTERMEC, INC., Lynnwood...

1. A radio frequency identification (RFID) tag comprising:an antenna configured to receive a wireless signal from an RFID reader;
an RFID circuit comprising a controller configured to process the wireless signal received from the antenna; and
a first sensor or switch that is connected to the RFID circuit and that outputs a first signal to the RFID circuit when the first sensor or switch is engaged or activated but outputs a second signal when the first sensor or switch is not engaged or activated, wherein the controller is configured to change at least one protocol of the RFID tag when the RFID circuit receives the first signal and when the RFID circuit receives the second signal.