The disclosure relates to a system for detecting fraud behaviour in card payments, the system comprises a merchant wireless device and a processing circuitry configured to obtain unique identifiers of surrounding wireless devices based on received radio signals at the merchant wireless device, and configured to determine a surrounding wireless device delta data by comparing unique identifiers of the surrounding wireless devices obtained at the first point in time with unique identifiers of the surrounding wireless devices obtained at the second point in time and determine a fraud behaviour likelihood value.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G06Q 20/34 - Payment architectures, schemes or protocols characterised by the use of specific devices using cards, e.g. integrated circuit [IC] cards or magnetic cards
A method includes generating a request for a session key from a service. The request is generated based on a first device identifier and an input from a first user, the first user is associated with a first account identifier, and the first account identifier is associated with the service. The method also includes generating a message to a second user device. The message includes the first account identifier, the input, a second account identifier, and a signature generated based on the session key and verifiable by the service with the session key. The method also includes transmitting the message to the second user device while the first user device is within a threshold distance from the second user device and causing the service to modify an account associated with the first account identifier based on the message, in response to transmitting the message to the second user device.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
A method includes generating a request for a session key from a service. The request is generated based on a first device identifier and an input from a first user, the first user is associated with a first account identifier, and the first account identifier is associated with the service. The method also includes generating a message to a second user device. The message includes the first account identifier, the input, a second account identifier, and a signature generated based on the session key and verifiable by the service with the session key. The method also includes transmitting the message to the second user device while the first user device is within a threshold distance from the second user device and causing the service to modify an account associated with the first account identifier based on the message, in response to transmitting the message to the second user device.
H04L 9/32 - Arrangements for secret or secure communicationsNetwork security protocols including means for verifying the identity or authority of a user of the system
H04W 4/80 - Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
G06Q 20/10 - Payment architectures specially adapted for electronic funds transfer [EFT] systemsPayment architectures specially adapted for home banking systems
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
Computer and data processing improvements relating to artificial intelligence (AI) for near real-time (NRT) recommendation are disclosed. A service provider may utilize an AI system including different machine learning (ML) models and a privacy management platform that may manage user consents for profile or other user information usage for NRT recommendations. The AI system may interact with merchant platforms to monitor session data for sessions between computing devices of the user and the merchant platforms. The AI system may detect data from shopping experiences and/or behaviors to generate feature data for ML features of the ML models. The AI system may utilize the data with profile data, when authorized based on the user consents, to generate the NRT recommendations. Further, the AI system may store the data for use by an offline system to train and/or retrain ML models for more accurate decision-making.
Computer and data processing improvements relating to artificial intelligence (AI) for near real-time (NRT) recommendation are disclosed. A service provider may utilize an AI system including different machine learning (ML) models and a privacy management platform that may manage user consents for profile or other user information usage for NRT recommendations. The AI system may interact with merchant platforms to monitor session data for sessions between computing devices of the user and the merchant platforms. The AI system may detect data from shopping experiences and/or behaviors to generate feature data for ML features of the ML models. The AI system may utilize the data with profile data, when authorized based on the user consents, to generate the NRT recommendations. Further, the AI system may store the data for use by an offline system to train and/or retrain ML models for more accurate decision-making.
A plurality of summaries is generated by a summary generator module. A plurality of negative samples is generated by a disruptor module. Each of the plurality of negative samples is tailored to one or more specified criteria. The plurality of summaries and the plurality of negative samples are combined into a dataset. The dataset is evaluated via a summary evaluator module. Based on the evaluating, a plurality of scores is calculated for the plurality of summaries and the plurality of negative samples. Via a recursive auto prompt tuning module, at least one of the summary generator module or the summary evaluator is tuned. The tuning is automatically performed based on the calculated scores. At least the evaluating, the calculating, and the tuning are performed for one or more cycles.
Methods and systems are presented for providing a graph query framework for querying graphs according to different graph schemas. Multiple graphs that are associated with different graph schemas are stored and maintained. When a query for graph data from a merged graph associated with a merged graph schema is received from a computer system, the merged graph is generated by merging two or more of the graphs. The merged graph schema is different from the graph schemas of the stored graphs, and is generated based on combining elements from two or more of the graph schemas. The query is then executed against the merged graph to obtain the graph data. The graph data is then provided to the computer system.
Methods and systems are presented for providing a graph-based framework for evaluating feature candidates for a machine learning model. A production graph is generated to represent relationships among various assets of an organization. The production graph is used by various machine learning models for obtaining input data to perform the corresponding tasks. When it is determined that data corresponding to a feature candidate selected for the machine learning model is missing from the graph, instead of modifying the production graph, a new graph schema that defines one or more additional vertex types or one or more additional edge types is generated. New graph data is also generated based on the new graph schema. In response to a query corresponding to the feature candidate, a merged graph is generated by incorporating the new graph data into the production graph. A query result is obtained based on traversing the merged graph.
There are provided systems and methods of bot detection through explainable deep learning and rule violation codebooks from generative AI. A service provider, such as an electronic transaction processor for digital transactions, may provide computing services to users for processing various requests and interactions with those users. However, malicious users may utilize bots, such as automated scripts and software applications, that attempt to conduct fraud, compromise systems and data, and the like. To provide better bot and bot activity detection, the service provider may implement an explainable deep learning system that may generate rule violations of rules indicating bot activity or presence in computing logs and interactions using a generative AI. The violations may have a corresponding explanation in codebooks to automate bot detection. When bot activity is detected, the explanation may provide a reason for the bot activity detection.
Methods and systems are presented for providing a large language model-based query optimizer to interface between program developers and database systems. The query optimizer receives programming code corresponding to a set of queries intended for a database system from a program developer. The query optimizer then uses a machine learning model to analyze the programming code and to determine a set of strategies for executing the set of data queries corresponding to the programming code. To determine the set of strategies, the machine learning model analyzes dependencies among the set of data queries and retrieves sample data from the database system. The machine learning model implement the set of strategies by incorporating additional instructions in the programming code for the database system such that the database system would execute the set of data queries according to the set of strategies.
There are provided systems and methods for extraction of communication insights from optimal AI model selection during computing service issue handling. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include live agent and self-service assistance features.
There are provided systems and methods for extraction of communication insights from optimal AI model selection during computing service issue handling. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include live agent and self-service assistance features.
To provide more comprehensive and accurate customer service and assistance to users, a service provider may provide optimized AI model selection for handling of customer service requests. The AI models may correspond to AI agents that perform extraction of communication insights and determination of recommendations for responding to the requests. When selecting the AI models, a pipeline of deep learning and large language models may be used to classify requests and generate support tickets. The support tickets may then be assigned to AI agents using a load optimization mechanism, which may consider current load by each AI agent and model performance.
There are provided systems and methods for intelligent detection and acquisition of authentic product reviews for cross-platform availability. A service provider may provide computing services to merchants and users for processing various interactions, such as purchasing items electronically. When items or other products are purchased, users may leave reviews. To determine an authenticity of the reviews, the service provider may utilize an intelligent system that may include an LLM or other generative AI. The system may automatically generate questions for users that may be designed by the LLM to elicit responses that verify whether a review is authentic and/or relevant. This may include receiving responses and scoring those responses to verify the user is providing an authentic review. If so, the review may be written to a blockchain, which may allow the review to be pushed to users and/or automatically injected to product pages and checkout flows.
Methods and systems are presented for providing a graph-based framework for evaluating feature candidates for a machine learning model. A production graph is generated to represent relationships among various assets of an organization. The production graph is used by various machine learning models for obtaining input data to perform the corresponding tasks. When it is determined that data corresponding to a feature candidate selected for the machine learning model is missing from the graph, instead of modifying the production graph, a new graph schema that defines one or more additional vertex types or one or more additional edge types is generated. New graph data is also generated based on the new graph schema. In response to a query corresponding to the feature candidate, a merged graph is generated by incorporating the new graph data into the production graph. A query result is obtained based on traversing the merged graph.
A plurality of summaries is generated by a summary generator module. A plurality of negative samples is generated by a disruptor module. Each of the plurality of negative samples is tailored to one or more specified criteria. The plurality of summaries and the plurality of negative samples are combined into a dataset. The dataset is evaluated via a summary evaluator module. Based on the evaluating, a plurality of scores is calculated for the plurality of summaries and the plurality of negative samples. Via a recursive auto prompt tuning module, at least one of the summary generator module or the summary evaluator is tuned. The tuning is automatically performed based on the calculated scores. At least the evaluating, the calculating, and the tuning are performed for one or more cycles.
There are provided systems and methods for extraction of communication insights from optimal AI model selection during computing service issue handling. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include live agent and self-service assistance features. To provide more comprehensive and accurate customer service and assistance to users, a service provider may provide optimized AI model selection for handling of customer service requests. The AI models may correspond to AI agents that perform extraction of communication insights and determination of recommendations for responding to the requests. When selecting the AI models, a pipeline of deep learning and large language models may be used to classify requests and generate support tickets. The support tickets may then be assigned to AI agents using a load optimization mechanism, which may consider current load by each AI agent and model performance.
Methods and systems described herein may implement operations for identification of computing issues on computing platforms using social media comments and other available data in a variety of environments. An online transaction processor may provide operations for electronic transaction processing and/or other online computing services. The online transaction processor may monitor social media posts in order to determine if context and sentiments from such posts may indicate that there is a potential issue or complaint by users with computing services provided by the online service provider. This may be done by processing the posts using a machine learning engine for sentiment analysis and correlating sentiments with corresponding computing signals occurring with computing platforms of the service provider. Thereafter, computing anomalies may be detected and output notifications may be provided to users based on the corresponding computing anomalies.
There are provided systems and methods for browser extensions and applications for cross-platform item data identifications. A service provider server may provide website and application tools that may track user navigations, inputs and selections, and other operations with merchant websites and/or online merchant marketplaces. Further, the service provider may provide discounts and offers during purchases and transactions with the online merchants, which may further provide reward points or value based on use of the service provider's services. However, transactions may be canceled by the user and/or merchant, which may prevent distribution of such rewards. The service provider may provide operations to detect canceled transactions and thereafter determine the same or similar item from the transaction with different online merchants. The service provider may then automatically provide links and navigations to such items with the different online merchants using a browser extension and/or software application.
There are provided systems and methods for managing data dependencies in an N-layer architecture for data loading optimizations. A service provider, such as an electronic transaction processor for digital transactions, may utilize different decision services that implement rules and/or artificial intelligence models for decision-making of data including data in production computing environment. Decision services may be used for data processing and decision-making, where multiple decision services may be invoked during run-time in order to complete a data processing request. When processing data, data loads may be required by decision services, where multiple data loads that are the same or similar may be utilized by different data services. Thus, the service provider may provide data loading optimization by making these data loads available across multiple decision services. This may be done based on an intelligent and/or algorithmic process based on data storage requirements.
A method includes defining a first data vector of a first entity based on a set of data records associated with representative activities of the first entity, wherein the set of data records includes product data associated with the first entity, and an activities relationship between the first entity and a plurality of second entities. The method further includes defining a second data vector of the first entity based on supply chain topological connections between the second entities and the first entity, utilizing, a clustering space machine learning model to generate an entity vector representing the first entity based on the first data vector and the second data vector, and utilizing a classification machine learning model to generate an entity-specific classification of the first entity based on the entity vector.
Systems, methods, and computer program products for identifying a fraudulent device. A device analytics engine receives device data from a computing device, the device data including parameters associated with the computing device. The device analytics engine selects a set of rules in a plurality of rules that indicate at least one parameter in the plurality of parameters in the device data for determining a device identifier. The set of rules are evaluated in order until the device identifier is determined from the at least one parameter indicated in the set of rules, the device data, and previously stored data from multiple computing devices. A score is generated for the computing device using one or more of the device identifier, device data, a set of rules, and previously received device data that corresponds to the device identifier. A computing device is identified as a fraudulent computing device based on the score.
An example method of configuring a plurality of aspects of a system includes providing, by a computing system, a control smart contract and a plurality of subordinate smart contracts on a blockchain, wherein each subordinate smart contract receives a respective input regarding a respective one of the plurality of aspects and outputs a respective decision, and wherein the control smart contract controls a configuration process incorporating the subordinate contracts according to the decisions of the subordinate contracts. The method further includes conducting, by a computing system, the configuration process according to the control smart contract; and configuring the aspects of the system according to the decisions of the subordinate smart contracts.
System and methods for predicting content items using a neural network model and performing reinforcement learning as continual learning for training the neural network model includes obtain a first dataset of user actions of a plurality of users at a plurality of user devices and a second dataset of historical data for the plurality of users, extract a first set of embeddings and a second set of embeddings from the first dataset and the second dataset, output a trained model based on applying the first and second set of embeddings, determine a set of candidate content items by the trained model, determine a prediction value for each respective candidate content item of the set of candidate content items by the trained model, and output one or more content items of the set of candidate content items based on the prediction value determined for each respective first candidate content item.
H04N 21/25 - Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication or learning user preferences for recommending movies
There are provided systems and methods for procedural pattern matching in audio and audiovisual files using voice prints. A user may utilize a computing device to interact with online service providers via voice communications. Based on audio and/or audiovisual data provided during the voice communications, voice prints may be generated, such as by determine audio signals from audio and/or audiovisual data, extracting audio features from such signals, and identifying voice and other audio dimensions in the audio and/or audiovisual data. The voice print may be generated based on an algorithmic calculation or other function that hides or obscures personal data for the corresponding user and/or masks the users voice and identity. The voice print may then be stored and used as a key for data associated with the user, which allows the data to be scrubbed or masked of the user's personal data to protect their privacy.
G10L 17/04 - Training, enrolment or model building
G10L 17/02 - Preprocessing operations, e.g. segment selectionPattern representation or modelling, e.g. based on linear discriminant analysis [LDA] or principal componentsFeature selection or extraction
G10L 17/06 - Decision making techniquesPattern matching strategies
27.
HOT WALLET PROTECTION USING A LAYER-2 BLOCKCHAIN NETWORK
Methods and systems for digital hot wallet protection are provided. A payment channel is established via a Layer-2 network of a cryptocurrency blockchain for transferring a cryptocurrency balance from a first digital wallet of a service provider to a second digital wallet of a trusted entity over a plurality of commitment transactions. A transaction receipt for each commitment transaction is transmitted to the trusted entity via a secure communication channel previously established between the service provider and the trusted entity outside of the Layer-2 network. A transaction log of the service provider is modified so that it no longer represents the current transaction state of the payment channel. Responsive to detecting a breach of the first wallet, a transaction is broadcast to a Layer-1 network of the blockchain for transferring the total cryptocurrency balance from the first wallet to the second wallet.
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
H04L 9/00 - Arrangements for secret or secure communicationsNetwork security protocols
28.
Cross-Graph Transitions for Graph Database Queries
Techniques are disclosed for enabling cross-graph querying in graph databases using a transition operator within a traversal context. In some embodiments, a computing system receives a query containing a transition operator that facilitates transitioning from a first graph to a second graph. The system processes a traversal operation within the first graph, retrieves intermediary data, and transitions to the second graph to perform subsequent traversal operations. The query engine can utilize confidence scores associated with edges in the graphs to filter or prioritize results, ensuring the reliability of returned data. Additionally, data validation techniques using a mirror graph are disclosed, where new data is validated before integration into a production graph. These techniques streamline cross-graph data analysis, improve query efficiency, and maintain graph database integrity while supporting applications such as fraud detection, recommendation systems, and account linking.
Techniques are disclosed for a computer system performing batch processing on graph data using an offline mirrored graph database store synchronized from an online graph database store. The computer system includes a user service that receives a batch processing request and submits a batch job creation request. A batch processing service triggers the batch job based on the request and coordinates execution. A graph execution engine retrieves input data, initiates a query to the offline mirrored graph database store, and performs computations on the retrieved graph data to generate a result set. The result set is stored in a cloud storage system for retrieval by downstream systems or services. The offline graph database enables complex graph computations, including multi-hop traversals and graph variable calculations, with relaxed latency requirements compared to the online graph database.
A system may perform operations including, for a given seed file, obtaining a first graph query to extract a first set of feature values from a first dataset, extracting, based on a feature calculation time, a sub-graph from the first dataset, obtaining, based on a second logic, a second graph query to extract a second set of feature values from a second dataset, and calculating a parity between the first set of feature values and second set of feature values. The operations may also include obtaining the events from a first data store, the events being filtered based on the given seed file, replaying the events backwards and extracting a third set of feature values, determining whether any of the second set of feature values do not match the second set of feature values, and updating the second set of feature values based on third set of feature values.
Techniques are disclosed for a computer system performing batch processing on graph data using an offline mirrored graph database store synchronized from an online graph database store. The computer system includes a user service that receives a batch processing request and submits a batch job creation request. A batch processing service triggers the batch job based on the request and coordinates execution. A graph execution engine retrieves input data, initiates a query to the offline mirrored graph database store, and performs computations on the retrieved graph data to generate a result set. The result set is stored in a cloud storage system for retrieval by downstream systems or services. The offline graph database enables complex graph computations, including multi-hop traversals and graph variable calculations, with relaxed latency requirements compared to the online graph database.
G06F 16/27 - Replication, distribution or synchronisation of data between databases or within a distributed database systemDistributed database system architectures therefor
Techniques are disclosed relating to automatically determining whether an entity is malicious. In some embodiments, a server computer system generates a feature vector for an unknown website, where generating the feature vector includes preprocessing a plurality of structural features of the unknown website. In some embodiments, the system inputs the feature vector for the unknown website into a trained neural network. In some embodiments, the system applies a clustering algorithm to a signature vector for the unknown website and signature vectors for respective ones of a plurality of known websites output by the trained neural network. In some embodiments, the system determines, based on results of the clustering algorithm indicating similarities between signature vectors for the unknown website and one or more of the signature vectors for the plurality of known websites, whether the unknown website is suspicious. Determining whether the entity is suspicious may advantageously prevent malicious (fraudulent) activity.
A method includes partitioning a set of historical device keys into a set of clusters, embedding the set of clusters to generate a set of device lockers, and receiving a request including an application identifier and metadata. The application identifier corresponds to an application installed on the second computing system and the metadata corresponds to the second computing system. The method also includes combining the application identifier and the metadata to generate a device key, determining that the set of device lockers includes a device locker that matches the device key, and, in response to determining that the set of device lockers includes the device locker that matches the device key, adding the device key to a cluster of the set of clusters corresponding to the device locker.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06F 16/353 - ClusteringClassification into predefined classes
G06F 18/23213 - Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Techniques are disclosed for updating an operating system (OS) on a computing system. In some embodiments, a computer system receives an instruction to update a first operating system (OS) of the computer system to a second OS. The computer system loads the second OS into a volatile memory of the computer system and initiates a backup of the non-volatile memory of the computer system while the second OS is loaded into the volatile memory. In response to a completion of the backup, the computer system moves the second OS from the volatile memory to the non-volatile memory of the computer system. The computer system then boots the second OS from the non-volatile memory. This provides data integrity, minimizes risk of data loss, and reduces disruptions during the OS update process.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
35.
SCALABLE ERROR ALERT THRESHOLDS BASED ON CONVERSION METRICS FOR DATA PROCESSING FLOWS
Accuracy, efficiency, and speed improvements for error alerting are provided herein, particularly in the context of error detection and alerting. There are provided systems and methods for scalable error alerts threshold based on conversion metrics for data processing flows. A service provider may utilize different computing services for data processing to provide different computing services to users, such as via websites and/or applications of the service provider. Due to timeouts, failures, and other errors, users may be unable to complete a data processing flow. To provide dynamic error alerting, thresholds for reporting of the errors may be adjusted based on conversion metrics for users abandoning the processing flow at different steps. A threshold for a number of users that fail to complete the flow at certain steps may be adjusted to account for users that may abandon due to errors or other reasons.
The present invention relates to interconnection of Point of Sale, POS, terminals and card reader terminals. Especially, interconnection of POS terminals and card reader terminals via a cloud-based connection server is presented. A unique wireless connection, identified by a link ID, is established between each card reader terminal and the cloud-based connection server. The card reader terminals are configured to address the POS terminals using a channel ID concept. The POS terminals are configured to establish one connection to the cloud-based connection server per combination of link ID and channel ID.
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G07F 7/08 - Mechanisms actuated by objects other than coins to free or to actuate vending, hiring, coin or paper currency dispensing or refunding apparatus by coded identity card or credit card
G07G 1/14 - Systems including one or more distant stations co-operating with a central processing unit
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
38 - Telecommunications services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable electronic commerce computer programs for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms using blockchain technology; Downloadable software for automating the synchronization of product data, pricing, and inventory information across multiple e-commerce marketplaces, online retailers, and social commerce platforms; artificial intelligence-based product content optimization and catalog management for e-commerce; Downloadable application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; Downloadable software for data mapping, data transformation, and data standardization for use in e-commerce operations; managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automating financial reconciliation and accounts receivable management in connection with electronic commerce; Downloadable mobile applications for automating the management of product listings, inventory, and orders across online retail channels, marketplaces, and social commerce platforms Order fulfillment services; Inventory management; Inventory management in the field of e-commerce; Business research and data analysis services in the field of e-commerce and online retail sales performance; Accounts receivable billing services; Business management services, namely, managing logistics, reverse logistics, supply chain services, supply chain visibility and synchronization, supply and demand forecasting and product distribution processes for others; Computerized on-line ordering services in the field of e-commerce; Electronic commerce services, namely, providing information about products via telecommunication networks for advertising and sales purposes; Business management of retail enterprises for others; Supply chain management services; Data processing services; Electronic catalog services featuring goods sold via e-commerce and online retail channels Electronic data interchange (EDI) services; Electronic transmission of data and documents via computer terminals and electronic devices; Communication services, namely, providing electronic transmission of information stored in a database via interactively communicating computer systems Software as a service (SAAS) services featuring software for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms; automating dropship operations between brands and retail partners; data mapping, data transformation, and product catalog standardization for use in electronic commerce; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for product content generation and optimization for e-commerce platforms; enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Platform as a service (PAAS) featuring computer software platforms for integrating brand and retailer systems for multichannel e-commerce operations across online retail channels, marketplaces, and social commerce platforms; Providing temporary use of online non-downloadable computer software for managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automated financial reconciliation and accounts receivable management in connection with electronic commerce; real-time inventory synchronization across online retail channels, marketplaces, and social commerce platforms; automated order management and fulfillment tracking in the field of e-commerce; Cloud computing featuring software for use in automating operations connecting brands and retailers for dropship, marketplace, and social commerce; Application service provider featuring application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; connectivity and integration of e-commerce platforms and retail information systems; Computer services, namely, integration of computer software into multiple systems and networks; Consulting services in the field of software implementation for others; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Providing temporary use of online non-downloadable chatbot software using large language models (LLMs) for automating product discovery and purchase transactions through artificial intelligence platforms and social commerce interfaces
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
38 - Telecommunications services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable electronic commerce computer programs for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms using blockchain technology; Downloadable software for automating the synchronization of product data, pricing, and inventory information across multiple e-commerce marketplaces, online retailers, and social commerce platforms; artificial intelligence-based product content optimization and catalog management for e-commerce; Downloadable application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; Downloadable software for data mapping, data transformation, and data standardization for use in e-commerce operations; managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automating financial reconciliation and accounts receivable management in connection with electronic commerce; Downloadable mobile applications for automating the management of product listings, inventory, and orders across online retail channels, marketplaces, and social commerce platforms Order fulfillment services; Inventory management; Inventory management in the field of e-commerce; Business research and data analysis services in the field of e-commerce and online retail sales performance; Accounts receivable billing services; Business management services, namely, managing logistics, reverse logistics, supply chain services, supply chain visibility and synchronization, supply and demand forecasting and product distribution processes for others; Computerized on-line ordering services in the field of e-commerce; Electronic commerce services, namely, providing information about products via telecommunication networks for advertising and sales purposes; Business management of retail enterprises for others; Supply chain management services; Data processing services; Electronic catalog services featuring goods sold via e-commerce and online retail channels Electronic data interchange (EDI) services; Electronic transmission of data and documents via computer terminals and electronic devices; Communication services, namely, providing electronic transmission of information stored in a database via interactively communicating computer systems Software as a service (SAAS) services featuring software for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms; automating dropship operations between brands and retail partners; data mapping, data transformation, and product catalog standardization for use in electronic commerce; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for product content generation and optimization for e-commerce platforms; enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Platform as a service (PAAS) featuring computer software platforms for integrating brand and retailer systems for multichannel e-commerce operations across online retail channels, marketplaces, and social commerce platforms; Providing temporary use of online non-downloadable computer software for managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automated financial reconciliation and accounts receivable management in connection with electronic commerce; real-time inventory synchronization across online retail channels, marketplaces, and social commerce platforms; automated order management and fulfillment tracking in the field of e-commerce; Cloud computing featuring software for use in automating operations connecting brands and retailers for dropship, marketplace, and social commerce; Application service provider featuring application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; connectivity and integration of e-commerce platforms and retail information systems; Computer services, namely, integration of computer software into multiple systems and networks; Consulting services in the field of software implementation for others; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Providing temporary use of online non-downloadable chatbot software using large language models (LLMs) for automating product discovery and purchase transactions through artificial intelligence platforms and social commerce interfaces
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
38 - Telecommunications services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable electronic commerce computer programs for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms using blockchain technology; Downloadable software for automating the synchronization of product data, pricing, and inventory information across multiple e-commerce marketplaces, online retailers, and social commerce platforms; artificial intelligence-based product content optimization and catalog management for e-commerce; Downloadable application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; Downloadable software for data mapping, data transformation, and data standardization for use in e-commerce operations; managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automating financial reconciliation and accounts receivable management in connection with electronic commerce; Downloadable mobile applications for automating the management of product listings, inventory, and orders across online retail channels, marketplaces, and social commerce platforms Order fulfillment services; Inventory management; Inventory management in the field of e-commerce; Business research and data analysis services in the field of e-commerce and online retail sales performance; Accounts receivable billing services; Business management services, namely, managing logistics, reverse logistics, supply chain services, supply chain visibility and synchronization, supply and demand forecasting and product distribution processes for others; Computerized on-line ordering services in the field of e-commerce; Electronic commerce services, namely, providing information about products via telecommunication networks for advertising and sales purposes; Business management of retail enterprises for others; Supply chain management services; Data processing services; Electronic catalog services featuring goods sold via e-commerce and online retail channels Electronic data interchange (EDI) services; Electronic transmission of data and documents via computer terminals and electronic devices; Communication services, namely, providing electronic transmission of information stored in a database via interactively communicating computer systems Software as a service (SAAS) services featuring software for automating operations for managing product listings, inventory, and order processing across online retail channels, marketplaces, and social commerce platforms; automating dropship operations between brands and retail partners; data mapping, data transformation, and product catalog standardization for use in electronic commerce; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for product content generation and optimization for e-commerce platforms; enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Platform as a service (PAAS) featuring computer software platforms for integrating brand and retailer systems for multichannel e-commerce operations across online retail channels, marketplaces, and social commerce platforms; Providing temporary use of online non-downloadable computer software for managing electronic data interchange (EDI) transactions in the field of retail and e-commerce; automated financial reconciliation and accounts receivable management in connection with electronic commerce; real-time inventory synchronization across online retail channels, marketplaces, and social commerce platforms; automated order management and fulfillment tracking in the field of e-commerce; Cloud computing featuring software for use in automating operations connecting brands and retailers for dropship, marketplace, and social commerce; Application service provider featuring application programming interface (API) software for integration of e-commerce platforms with third-party retail and marketplace systems, including EDI, enterprise resource planning systems, order management systems, product information management systems, and e-commerce platforms; connectivity and integration of e-commerce platforms and retail information systems; Computer services, namely, integration of computer software into multiple systems and networks; Consulting services in the field of software implementation for others; Software as a service (SAAS) services featuring software using artificial intelligence (AI) for enabling automated purchasing transactions initiated by artificial intelligence assistants and large language model platforms; Providing temporary use of online non-downloadable chatbot software using large language models (LLMs) for automating product discovery and purchase transactions through artificial intelligence platforms and social commerce interfaces
A computer-implemented method includes calculating a respective availability score for each of a plurality of backup computing action processing channels based on respective responses of the plurality of backup computing action processing channels to one or more of a plurality of test computing actions or a plurality of historical computing actions, receiving a requested computing action from a user, determining that a primary computing action processing channel cannot successfully process the requested computing action within one or more of a reliability threshold or a latency threshold, in response to determining that the primary computing action processing channel cannot successfully process the requested computing action, selecting a backup computing action processing channel from the plurality of backup computing action processing channels according to the availability scores, and transmitting the requested computing action to the selected backup computing action processing channel.
G06F 11/14 - Error detection or correction of the data by redundancy in operation, e.g. by using different operation sequences leading to the same result
Techniques are disclosed for enabling cross-graph querying in graph databases using a transition operator within a traversal context. In some embodiments, a computing system receives a query containing a transition operator that facilitates transitioning from a first graph to a second graph. The system processes a traversal operation within the first graph, retrieves intermediary data, and transitions to the second graph to perform subsequent traversal operations. The query engine can utilize confidence scores associated with edges in the graphs to filter or prioritize results, ensuring the reliability of returned data. Additionally, data validation techniques using a mirror graph are disclosed, where new data is validated before integration into a production graph. These techniques streamline cross-graph data analysis, improve query efficiency, and maintain graph database integrity while supporting applications such as fraud detection, recommendation systems, and account linking.
The disclosed computer-implemented method may include receiving transaction data of an online transaction that has a pending security authentication requirement and determining a risk score and a conversion score from the transaction data. The method may also include assessing combinations of authentication factors for the security authentication requirement based on applying the risk score and the conversion score to determine probabilities of the online transaction being completed with the combinations of the authentication factors. In addition, the method may further include requesting a combination of authentication factors, selected based on the assessing, to satisfy the security authentication requirement for the online transaction. Various other methods, systems, and computer-readable media are also disclosed.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
43.
DEVICE VERIFICATION USING A DEEP-LEARNING-BASED KEY-LOCKER FRAMEWORK
A method includes partitioning a set of historical device keys into a set of clusters, embedding the set of clusters to generate a set of device lockers, and receiving a request including an application identifier and metadata. The application identifier corresponds to an application installed on the second computing system and the metadata corresponds to the second computing system. The method also includes combining the application identifier and the metadata to generate a device key, determining that the set of device lockers includes a device locker that matches the device key, and, in response to determining that the set of device lockers includes the device locker that matches the device key, adding the device key to a cluster of the set of clusters corresponding to the device locker.
A method includes receiving a request designating an endpoint and triggering a function of a kernel extension. The function includes determining a permission of the endpoint to receive unmodified data and modifying at least part of the request based on the determined permission. The method also includes routing the request to a third computing system associated with the endpoint designated by the request.
Methods and systems are presented for providing a data storage optimization system. The data storage optimization system determines a data storage schema for storing data in one or more data storages. The data storage optimization system then monitors computer resources usage efficiency associated with accessing the data stored in the one or more data storages. When it is detected that the computer resources usage efficiency is below a threshold, the data storage optimization system determines modification recommendations for modifying the data storage schema. The data storage optimization system causes an implementation of the modification recommendations, and monitors the improvements to the computer resources usage efficiency.
The present invention relates to interconnection of Point of Sale, POS, terminals and card reader terminals. Especially, interconnection of POS terminals and card reader terminals via a cloud-based connection server is presented. A unique wireless connection, identified by a link ID, is established between each card reader terminal and the cloud-based connection server. The card reader terminals are configured to address the POS terminals using a channel ID concept. The POS terminals are configured to establish one connection to the cloud-based connection server per combination of link ID and channel ID.
H04L 67/12 - Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
H04W 76/38 - Connection release triggered by timers
Techniques are disclosed relating to determining whether input data is authentic. A system detects input data, that includes text data and typing data, at a computing device. The system may generate, using a string model, a string-level prediction for the input data, where the string model is trained to increase a similarity between embeddings of authentic text data and corresponding sequences of typing data. Using a character model, the system may generate a character-level prediction for the set of input data, where the character-level model predicts an intended sequence of characters based on the text data and a sequence of typing actions included in the input data. Using machine learning, the system determines, based on the string-level prediction and the character-level prediction, whether the input data is authentic input. The system transmits, to the device, a decision that is generated based on determining whether the input data is authentic.
Techniques are disclosed for dynamically managing token limits in Large Language Models (LLMs) using a Retrieval-Augmented Generation (RAG). In some embodiments, a computing system receives a query and retrieves relevant context articles via RAG. The system tokenizes the query and context articles to generate a set of input tokens for inclusion in an LLM prompt. A dynamic threshold is determined based on the input token quantity, which is used to truncate or adjust the token count if necessary. The threshold can be applied such that the total number of input and output tokens does not exceed the LLM's limit. Additionally, a lookup table can be generated from training data that correlates input token ranges with corresponding truncation thresholds. The system improves token usage by dynamically adjusting thresholds based on the input data, improving LLM performance and scalability in handling diverse data inputs.
There are provided systems and methods for a machine learning model and narrative generator for prohibited transaction detection and compliance. A service provider server, such as an electronic transaction processor, may generate a machine learning model using a supervised training technique, which may detect transactions that may be money laundering. The model may be iteratively trained by detecting flagged transactions and outputting those transactions to an agent for identification of false positives, which may be used to retrain the model. When outputting the flagged transactions, a narrative may be generated using an explainer graph and a machine learning prediction explainer that identifies the features of the transaction data that caused the transactions to be flagged. Further, once the model is trained additional transactions may be processed to determine whether the features of those transactions indicate prohibited behavior.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06F 18/21 - Design or setup of recognition systems or techniquesExtraction of features in feature spaceBlind source separation
The disclosed computer-implemented method may include receiving transaction data of an online transaction that has a pending security authentication requirement and determining a risk score and a conversion score from the transaction data. The method may also include assessing combinations of authentication factors for the security authentication requirement based on applying the risk score and the conversion score to determine probabilities of the online transaction being completed with the combinations of the authentication factors. In addition, the method may further include requesting a combination of authentication factors, selected based on the assessing, to satisfy the security authentication requirement for the online transaction. Various other methods, systems, and computer-readable media are also disclosed.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/42 - Confirmation, e.g. check or permission by the legal debtor of payment
Techniques are disclosed for dynamically managing token limits in Large Language Models (LLMs) using a Retrieval-Augmented Generation (RAG). In some embodiments, a computing system receives a query and retrieves relevant context articles via RAG. The system tokenizes the query and context articles to generate a set of input tokens for inclusion in an LLM prompt. A dynamic threshold is determined based on the input token quantity, which is used to truncate or adjust the token count if necessary. The threshold can be applied such that the total number of input and output tokens does not exceed the LLM’s limit. Additionally, a lookup table can be generated from training data that correlates input token ranges with corresponding truncation thresholds. The system improves token usage by dynamically adjusting thresholds based on the input data, improving LLM performance and scalability in handling diverse data inputs.
Quantum computers with a limited number of input qubits are used to perform machine learning processes having a far greater number of trainable features. A list of features of a field are divided into a plurality of feature groups. Each of the feature groups includes a respective group of some, but not all, of the features. A first machine learning process is performed to train a first instance of a quantum computer model, where the feature groups are used as inputs. Based on the first machine learning process being performed, a subset of the feature groups is selected for a second machine learning process. Thereafter, the second machine learning process is performed to train one or more second instances of the quantum computer model. The individual features of the selected subset of the feature groups are used as inputs for the second instances of the quantum computer model.
Systems and methods for validating electronic transaction requests are described, including monitoring electronic transactions from a plurality of first requests from one or more target accounts, the electronic transactions being between a plurality of first computing devices and a plurality of second computing device, each first computing device associated with a respective target account, generating, for each target account, a graph including nodes representative of one or more electronic transactions associated with the each target account, each node including at least one attribute representative of a respective electronic transaction, receiving a second electronic transaction request from a first computing device associated with a target account, classifying the second request as a first or a second request type based on the graph, predicting a validity of the second request based on the classification, and in response to the second request being valid, sending the second request to a second computing device.
Automated rule set generation is disclosed. A computer generates a rule by selecting a feature of a dataset of training data having a plurality of features and by creating, based on the feature, a root node of a decision tree. The root node is associated with a root node decision condition. The computer associates, based on the root node decision condition, events in the dataset with one or more root-level branches from the root node. The computer selects one of the one or more root-level branches as a selected root-level branch, with any remaining root-level branches constituting unselected root-level branches. The computer creates nodes at (n−1) levels descending from the selected root-level branch without creating nodes descending from the unselected root-level branches. The computer evaluates information gains of nodes at a depth of n levels of the decision tree to determine a first n-condition rule of the rule set.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
The disclosed computer-implemented method may include preprocessing documents for indexing into different document databases for different content types, and prompting language models to retrieve relevant documents of the different content types from the document databases and generate document summaries for each of the different content types. The method may also include prompting the language models with a document template incorporating the different content types to generate a formatted document from the document summaries. Various other methods, systems, and computer-readable media are also disclosed.
A plurality of user segments is defined. Each user segment has a respective profile corresponding to one or more characteristics shared by one or more users. A plurality of elements of a user interface for a mobile application is defined. Each user segment is associated with a different subset of the elements. A first request is received to display the user interface on a first mobile device of a first user. In response to the first request, user data of the first user is analyzed. Based on the analysis, a first user segment to which the first user belongs is determined. The mobile application is then instructed to display the user interface according to a first customized layout on the first mobile device. The first customized layout includes a first subset of elements associated with the first user segment.
H04L 41/22 - Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks comprising specially adapted graphical user interfaces [GUI]
G06F 3/048 - Interaction techniques based on graphical user interfaces [GUI]
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
G06F 9/451 - Execution arrangements for user interfaces
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
Computer system security is improved by implementing zero-trust principles for management of source codes in a software development lifecycle. In some embodiments, a source code may be processed with a natural language processor to attribute the source code to its particular developer. Further, a machine learning algorithm may be applied to data related to the coding behavior of the code developer to identify any behavioral anomalies of the code developer in developing the source code. In addition, the interaction, of applications executing in an execution environment of an organization's network of managed compute facilities, with the various components of the network may be analyzed with a machine learning algorithm to identify code execution anomalies.
G06F 21/57 - Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
Computer security improvements relating to detection of social engineering attacks using a deep learning pipeline for account and communication correlations are disclosed. A service provider may utilize a framework having computing operations for detecting social engineering attacks, fraud, and other malicious or suspicious activities by malicious bots and other fraudsters. In this regard, the service provider may extract pattern data from communications using one or more AI models, which may include semantic information. Account assets for different accounts may be correlated using a relationship graph that links the assets based on the communication patterns shared between the assets. The relationship graph may then be used by additional AI models that classify if the communications are associated with social engineering attacks by classifying the communications using an attack classifier. The classification may be based on inferencing by the AI models from training on past social engineering attacks.
G06F 21/56 - Computer malware detection or handling, e.g. anti-virus arrangements
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06F 18/21 - Design or setup of recognition systems or techniquesExtraction of features in feature spaceBlind source separation
G06F 21/55 - Detecting local intrusion or implementing counter-measures
There are provided systems and methods for a dynamic user interface rendering engine for personalized data acquisition using intelligently created rules. An online transaction processor or other service provider may provide computing services and platforms to entities including merchants for electronic transaction processing and other account services. To onboard entities with the transaction processor, the transaction processor may provide a merchant or user-specific experience and interfaces, which may be dynamically created and rendered based on available data for the merchant and required data to iterate through and process the onboarding. A rendering engine may intelligently synthesize rules for interface element selection for personalized data acquisition based on policies regarding required data and/or verification during onboarding. Using these rules and known data for the merchant, interface elements may be selected and used for interface creation and rendering to reduce user inputs and repetitive processing during onboarding.
A system may include a processor and a non-transitory computer readable medium having stored thereon instructions that are executable by the processor to cause the system to receive a clearing house request that may include an amount owed to a first party by a second party and an indication of an account associated with the second party, and retrieve a risk score associated with the indicated account. The risk score may have been generated by a trained machine learning model configured to receive, as input, a plurality of account activities and to generate, as output, risk scores for a plurality of accounts indicative of a probability that the associated account is solvent. The system may further determine that the associated risk score exceeds a threshold value, and in response to the associated risk score exceeding the threshold value, execute a transfer of the amount to the first party via a clearing house.
G06Q 20/02 - Payment architectures, schemes or protocols involving a neutral third party, e.g. certification authority, notary or trusted third party [TTP]
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
61.
QUANTITATIVE ANALYSIS TOOL FOR INFERENCE SPEED AND PERFORMANCE OF ARTIFICIAL INTELLIGENCE MODELS
There are provided systems and methods for a quantitative analysis tool for inference speed and performance of AI models. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include services that utilize AI models including LLMs. To provide more efficient training and testing of AI models, a service provider may utilize a quantitative analysis tool that executes operations for algorithmic techniques utilized to calculate model throughput parameters include prefill latency, decoding latency, and other performance metrics. For LLMs, these metrics may be used to compute a time-to-first-token, which may be used to assess an inferencing speed. The tool may analyze the performance metrics and model throughput parameters using model configurations and hardware specifications and may do so without real testing so that system resource usage may be reduced, and performance may be more quickly assessed.
Methods and systems described herein may implement blockchain cryptocurrency transactions in a variety of environments. An online transaction processor may provide operations for ephemeral cryptocurrency wallets and platforms. The transaction processor may receive a request for an entity to establish an ephemeral digital wallet, which may correspond to a digital wallet that does not remain permanently open and usable for cryptocurrency transactions in contrast to conventional digital wallet address that are always active once a blockchain and its addresses have been established. The transaction processor may utilize a digital platform with a governor software function that may limit the usage of the wallet address on the blockchain to approved cryptocurrency key transfers and transactions. A whitelist may be established with the governor function that may designate allowable addresses that may deposit cryptocurrency through key transfers, as well as addresses or conditions for cryptocurrency payments or withdrawals.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
63.
AUTOMATED SCALABILITY AND PERFORMANCE OPTIMIZATION FOR CLOUD DATABASE SYSTEMS USING DYNAMIC POLICY MANAGEMENT
A method includes accessing a retention policy and a partitioning strategy for a database. The database includes a control table and a plurality of data tables, and each data table of the plurality of data tables includes one or more data entries. The method also includes populating the control table with control entries based on the retention policy and the partitioning strategy. The populated control entries in the control table represent the plurality of data tables. At each predetermined time interval, the method also includes purging data entries from a first data table of the plurality of data tables based on a retention policy of a first control entry of the populated control entries, and generating future partitions for a second data table of the plurality of data tables based on a partitioning strategy of a second control entry of the populated control entries.
There are provided systems and methods selective and personalized acquisition of user data using adaptive learning. An online transaction processor or other service provider may provide computing services and products to users and entities. For data collection required for computing service and/or product provision, users may be provided with selected data fields in dynamically created and customized UIs based on rules for data requirements and collection. The rules may be generated from policies of the service provider, which may be converted to conditional trees using an AI model and natural language processor. The trees may be merged based on shared conditions, and the rules may indicate what data may be collected for a specific service or product, as well as what other services or products may utilize overlapping data collection. As such, the data fields may be selectively chosen by an AI engine during data collection.
G06F 16/335 - Filtering based on additional data, e.g. user or group profiles
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
Methods and systems described herein may implement blockchain cryptocurrency transactions in a variety of environments. An online transaction processor may provide operations for ephemeral cryptocurrency wallets and platforms. The transaction processor may receive a request for an entity to establish an ephemeral digital wallet, which may correspond to a digital wallet that does not remain permanently open and usable for cryptocurrency transactions in contrast to conventional digital wallet address that are always active once a blockchain and its addresses have been established. The transaction processor may utilize a digital platform with a governor software function that may limit the usage of the wallet address on the blockchain to approved cryptocurrency key transfers and transactions. A whitelist may be established with the governor function that may designate allowable addresses that may deposit cryptocurrency through key transfers, as well as addresses or conditions for cryptocurrency payments or withdrawals.
G06Q 20/06 - Private payment circuits, e.g. involving electronic currency used only among participants of a common payment scheme
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
66.
AUTOMATED SCALABILITY AND PERFORMANCE OPTIMIZATION FOR CLOUD DATABASE SYSTEMS USING DYNAMIC POLICY MANAGEMENT
A method includes accessing a retention policy and a partitioning strategy for a database. The database includes a control table and a plurality of data tables, and each data table of the plurality of data tables includes one or more data entries. The method also includes populating the control table with control entries based on the retention policy and the partitioning strategy. The populated control entries in the control table represent the plurality of data tables. At each predetermined time interval, the method also includes purging data entries from a first data table of the plurality of data tables based on a retention policy of a first control entry of the populated control entries, and generating future partitions for a second data table of the plurality of data tables based on a partitioning strategy of a second control entry of the populated control entries.
There are provided systems and methods for dynamic content security policies using webpage data loaded in webpage element proxies. A service provider may provide online digital computing services, such as electronic transaction processing, account, and the like through online platforms and digital content that may be loaded and served on external webpages. To secure such computing services, webpage data, and digital content from misuse, fraud, or abuse, the service provider may utilize and implement a set of utilities that provide dynamic and secure gateways to internal and/or hosted webpages, webpage content and data, or other digital content of the service provider on external third-party domains, such as websites of known or unknown third parties. This may be done through an iframe or proxy that allows for loading of the digital content on the third-party domain. Access tokens may establish allowable domains for loading the digital content.
Techniques for predicting whether a submission includes a forged image. A computer system receives a submission from a user that includes an image and image metadata, such as an identifier for the user and a User-Agent string value. An image pixel embedding is generated from the image, and a profile embedding is generated from the image metadata. The image embedding is indicative of whether the image is similar to known image forgeries. The profile embedding is generated from a user activity embedding indicative of User-Agent values associated with the user identifier. The profile embedding is generated using a machine learning model that uses stored parameters to associate user activity, device information, and forgery groups. The profile embedding thus indicates whether the user is associated with known image forgeries. The image pixel embedding and profile embedding are then used by a neural network to output a forgery prediction.
System and methods for determining high-impact, non-informative features in datasets can include obtaining a first dataset including a first set of features and first set of tags, determining a second dataset including a second set of features and the first set of tags, the second set of features transformed from the first set of features, and each of the second set of features including a binary value, predicting, by a model, a third dataset including a third set of features and second set of tags based on the second dataset, comparing the third dataset to the second dataset to determine a correlation therebetween, based on the comparison, filtering at least one feature having missing feature values from the first dataset, and determining a training dataset with the remaining features in the first dataset, wherein the model being trained using the training dataset improves the outcome prediction accuracy of the model.
There are provided systems and methods for a dynamic user interface rendering engine for personalized data acquisition using intelligently created rules. An online transaction processor or other service provider may provide computing services and platforms to entities including merchants for electronic transaction processing and other account services. To onboard entities with the transaction processor, the transaction processor may provide a merchant or user-specific experience and interfaces, which may be dynamically created and rendered based on available data for the merchant and required data to iterate through and process the onboarding. A rendering engine may intelligently synthesize rules for interface element selection for personalized data acquisition based on policies regarding required data and/or verification during onboarding. Using these rules and known data for the merchant, interface elements may be selected and used for interface creation and rendering to reduce user inputs and repetitive processing during onboarding.
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
G06Q 40/02 - Banking, e.g. interest calculation or account maintenance
71.
DEEP LEARNING PIPELINE FOR PROACTIVE IDENTIFICATION AND MITIGATION OF COMPUTING SYSTEM ATTACKS FROM SOCIAL ENGINEERING
Computer security improvements relating to detection of social engineering attacks using a deep learning pipeline for account and communication correlations are disclosed. A service provider may utilize a framework having computing operations for detecting social engineering attacks, fraud, and other malicious or suspicious activities by malicious bots and other fraudsters. In this regard, the service provider may extract pattern data from communications using one or more AI models, which may include semantic information. Account assets for different accounts may be correlated using a relationship graph that links the assets based on the communication patterns shared between the assets. The relationship graph may then be used by additional AI models that classify if the communications are associated with social engineering attacks by classifying the communications using an attack classifier. The classification may be based on inferencing by the AI models from training on past social engineering attacks.
Methods and systems are presented for providing a knowledge bot configurable to interact with users across multiple domains. The knowledge bot includes at least a text-based search engine and a semantic-based search engine. Each of the search engine is configured to retrieve documents from a corpus of documents based on the user query. The user query is in a natural language format. The retrieved documents may be ranked according to how relevant the documents are to the user query. A subset of the documents is used as the search results based on the ranking. The search results from the search engine are combined with the user query to generate a prompt for an artificial intelligence model. Based on the prompt, a response in the natural language format is generated by the artificial intelligence model.
Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.
Methods and systems are presented for providing multi-tiered cache system that works with an artificial intelligence (AI)-based conversation system for facilitating a conversation with users and processing transactions for the users. The multi-tiered cache system includes multiple tiers of cache modules that use different structures for caching and/or querying data. As a new utterance is received, the cache system uses each of the cache modules in sequence to determine whether a cache hit occurs. If a cache miss occurs at a first cache module, the cache system determines if a cache hit occurs at a second cache module. When a response is obtained from one of the cache modules and/or the AI model, the cache system updates the cache modules using the response.
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
Methods and systems for providing a stateless application framework are presented. The stateless application framework is utilized by different applications for implementing different workflows. Each workflow may be associated with one or more state machine configurations representing the different states within the workflow. Upon receiving an indication of an event from an application, a stateless application module transmits a job request to a data processing engine based on a current state of the event. When a response is received from the data processing engine, the state application module determines whether the state of the event has been updated since transmitting the job request. If it is determined that the state has been updated, the stateless application module is configured to transmit another job request to the data processing engine based on the updated state of the event.
There are provided systems and methods for on-device management of computing cookie placement for enforcement of user consents. A service provider, including an electronic transaction processor, may provide consent management and enforcement through an on-device consent storage and library of user consents. When a device interacts with a website, such as one provided by a service provider, the device may utilize the on-device storage to lookup a user consent. The user consent may indicate allowable computer cookie placement and/or usage of computer cookies by the website with the device. The consent may be used to generate a data string or other file that may be transmitted to the website's server to convey the user's consent to the server. The data string may include one or more parameters for the user's consent. The data string may be attached to a network call made to the server for website data.
Techniques are disclosed relating to maintaining a point in time (PIT) database. A database system updates a snapshot table included in the PIT database according to a snapshot table time-to-live (TTL) value of 3K/2. In some embodiments, the updated snapshot table is configured to provide accurate data for queries up to K years prior to points in time at which the queries are executed. The system may update a binlog table included in the PIT database according to a binlog table TTL value of K. The system may receive a request to access PIT data stored in the PIT database. Based on a timestamp specified in the request, the system may access the PIT database. The system transmits a set of PIT data that corresponds to the timestamp and includes accurate data for K years prior to the timestamp.
Techniques are disclosed relating to extracting data from a document, using a large language model (LLM), to populate fields in a data structure. A computer system may receive a request to populate multiple fields of a data structure with data extracted from text of a document. The computer system parses the text using an LLM (as well as regular expressions or other parsing techniques in some embodiments). The parsing includes issuing, to the LLM, a sequence of queries targeting individual ones of the multiple fields. The computer system applies a validation algorithm to results received from the LLM in response to the sequence of queries. The validation algorithm confirms the presence of results in the text of the document and populates the data structured with the validated results. In various embodiments, the computer system performs an optical character recognition (OCR) on the document to determine the text for parsing.
There are provided systems and methods for a secure data erasure framework using individualized encryption key management. A service provider, including an electronic transaction processor, may provide data management and secure erasure through individualized encryption keys that may be managed and deleted to render encrypted data unreadable. When a device interacts with a service provider and provides or generates user data, the user data may be stored in accordance with an encryption process that encrypts the data using an encryption key for a corresponding account. Thereafter, the encryption key may be stored by a key store and not replicated elsewhere. When data is needed, the key store may be used by a trusted decryption platform and not shared. As such, when data is required to be erased or deleted, the data may be removed from availability with the service provider by implementing a secure key deletion process.
There are provided systems and methods for on-device management of computing cookie placement for enforcement of user consents. A service provider, including an electronic transaction processor, may provide consent management and enforcement through an on-device consent storage and library of user consents. When a device interacts with a website, such as one provided by a service provider, the device may utilize the on-device storage to lookup a user consent. The user consent may indicate allowable computer cookie placement and/or usage of computer cookies by the website with the device. The consent may be used to generate a data string or other file that may be transmitted to the website's server to convey the user's consent to the server. The data string may include one or more parameters for the user's consent. The data string may be attached to a network call made to the server for website data.
Methods and systems are presented for providing a framework that improves the logic induction capabilities of an artificial intelligence (AI) model. Under the framework, different logics are encapsulated in a logic knowledge graph. Embeddings are extracted from different portion of the logic knowledge graph, and guiding questions are generated for each logic that is encapsulated within the graph based on the embeddings. A logic database is constructed using the embeddings and the guiding questions. In order for the AI model to perform a task, the logic database is queried to obtain a set of guiding questions corresponding to the task. The guiding questions, along with other information associated with the task, are incorporated into a prompt, which is then provided to the AI model. Based on the guiding questions included in the prompt, the AI model can generate content that follows a particular logic.
System and methods for determining high-impact, non-informative features in datasets can include obtaining a first dataset including a first set of features and first set of tags, determining a second dataset including a second set of features and the first set of tags, the second set of features transformed from the first set of features, and each of the second set of features including a binary value, predicting, by a model, a third dataset including a third set of features and second set of tags based on the second dataset, comparing the third dataset to the second dataset to determine a correlation therebetween, based on the comparison, filtering at least one feature having missing feature values from the first dataset, and determining a training dataset with the remaining features in the first dataset, wherein the model being trained using the training dataset improves the outcome prediction accuracy of the model.
Techniques are disclosed relating to maintaining a point in time (PIT) database. A database system updates a snapshot table included in the PIT database according to a snapshot table time-to-live (TTL) value of 3K/2. In some embodiments, the updated snapshot table is configured to provide accurate data for queries up to K years prior to points in time at which the queries are executed. The system may update a binlog table included in the PIT database according to a binlog table TTL value of K. The system may receive a request to access PIT data stored in the PIT database. Based on a timestamp specified in the request, the system may access the PIT database. The system transmits a set of PIT data that corresponds to the timestamp and includes accurate data for K years prior to the timestamp.
Methods and systems are presented for providing an artificial intelligence (AI) framework for navigating through electronic user interfaces (UIs). The AI framework includes a navigation module that communicates with various components of a computer system for accessing an interacting different UI pages. After accessing a first UI page, the navigation module analyzes an image of the first UI page, and generates a prompt for an AI model. The prompt instructs the AI model to generate a set of navigation instructions for interacting with the first UI page that enables the navigation module to navigate to a predetermined target UI page. The navigation module interacts with the first UI page according to the set of navigation instructions. The interactions trigger an access of a second UI page. The navigation module iteratively uses the AI model to continue to navigate through various UI pages until the target UI page is accessed.
G06F 9/451 - Execution arrangements for user interfaces
G06F 3/0483 - Interaction with page-structured environments, e.g. book metaphor
G06F 3/0484 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
G06F 16/954 - Navigation, e.g. using categorised browsing
85.
SECURE DATA ERASURE FRAMEWORK USING INDIVIDUALIZED ENCRYPTION KEY MANAGEMENT
There are provided systems and methods for a secure data erasure framework using individualized encryption key management. A service provider, including an electronic transaction processor, may provide data management and secure erasure through individualized encryption keys that may be managed and deleted to render encrypted data unreadable. When a device interacts with a service provider and provides or generates user data, the user data may be stored in accordance with an encryption process that encrypts the data using an encryption key for a corresponding account. Thereafter, the encryption key may be stored by a key store and not replicated elsewhere. When data is needed, the key store may be used by a trusted decryption platform and not shared. As such, when data is required to be erased or deleted, the data may be removed from availability with the service provider by implementing a secure key deletion process.
Methods and systems are presented for providing a framework for facilitating storage and querying of vectors. Under the framework, different portions of a vector database are stored in different types of memories to improve storage and querying efficiency. One or more index portions of the vector database is stored in a volatile memory, and one or more vector portions of the vector database is stored in a non-volatile memory. Each index portion includes an index that represents multiple levels of vector partitions, including a first level of vector partitions and a second level of vector partitions. Each vector partition in the first level of vector partitions is linked to a different subset of vector partitions in the second level of vector partitions, and each vector partition in the second level of vector partitions corresponds to a group of vectors.
Computer security improvements relating to defenses using behavior pattern identification and extraction from unique traits of activities in time-series data are disclosed. A service provider may utilize a framework having computing operations for detecting and protecting from fraud and other behaviors indicative of risk, account takeovers, or other malicious activity. In this regard, the service provider may utilize a pattern analysis tool that may analyze computing log histories for account activities performed by devices using digital accounts. The activities may be correlated based on their traits having the same or similar data values, where sharing of these traits for activities at or over a threshold with a target account group in contrast to another account group may indicate a particular behavior. Behavior patterns may be extracted by comparing the activities by their traits in the target group, and the behavior patterns may be used for AI model training.
Computer security improvements relating to fraud detection and data correlations through large-scale graph clustering of graph transformations and embeddings are disclosed. A service provider may utilize a framework having computing operations for detecting fraud and other malicious or suspicious activities by groups of accounts and fraudsters. In this regard, the service provider may transform relationship graphs of account networks and relationships between accounts and account data captured in the nodes and edges of such graphs. The service provider may merge nodes that edges connecting to other nodes of a certain type of account data, while other types of account data and nodes may not be merged. Edges may also be merged and weighted, and the resulting transformed graph may undergo graph embedding to generate vectors that may be clustered using an AI clustering algorithm. The clusters may then be used for AI model training and inferencing.
Disclosed methods and systems include monitoring, by a computer system, online activity associated with a plurality of entities and a plurality of user devices that have respective pluralities of tokens provided by the token management system. The computer system may detect particular online activity related to a first token of a first of the pluralities of tokens, associated with a first user device. The computer system may determine that the particular online activity affects a status of the first token. In response to the determining, the computer system may modify data within the first token using information within the particular online activity. In response to identifying a second token of the first plurality of tokens, the computer system may determine that the particular online activity also affects a status of the second token, and modify, without receiving input from the first user device, the second token using the information.
The disclosed computer-implemented method may include detecting a user authentication request from a user device for a session, determining a confidence score for identifying a device fingerprint of the user device, and authenticating the user device in response to the user authentication request. The authenticating may be based on the confidence score satisfying a confidence threshold. The method may also include identifying other active sessions for other devices associated with the user device, and providing session management for the other active sessions. Various other methods, systems, and computer-readable media are also disclosed.
Methods and systems are presented for providing a framework that configures a machine learning model to be insensitive to changes in input features. A computer modeling system determines data sources from which attribute values associated with transactions can be obtained. Instead of configuring the machine learning model to accept the attribute values as inputs, the computer modeling system may configure the machine learning model to accept a vector representation in a multi-dimensional space as input values. The computer modeling system then generates an encoder for each data source. Each encoder is configured to encode attribute values from a corresponding data source to a representation representing the attribute values. Further, each encoder is trained to minimize a variance between outputs of the different encoders. The computer modeling system determines a vector representation based on the representations generated by the encoders and provide the vector representation to the machine learning model.
Methods and systems are presented for signed document image analysis and fraud detection. An image of a document may be received from a user's device. A first layer of a machine learning engine is used to identify a signature and a name of the user within different areas of the received image. A second layer of the machine learning engine is used to extract a plurality of features from the different areas of the image. The plurality of features includes at least one visual feature representing the signature and at least one textual feature representing the name. A combined feature representation of the signature and the name is generated based on the plurality of features extracted from the image. A third layer of the machine learning engine is used to determine whether the signature of the user has been digitally altered, based on the combined feature representation.
System and methods for providing stand-in services at a domain can include obtaining a service request at a domain, determining one or more services at the domain to fulfill the service request, in response to determining a service of the one or more services is unavailable, providing a model as a stand-in service for the service, determining, by the one or more services and the model, a decision based on the service request, and sending, in response to the service request, the decision as output by the domain level. The model can provide the stand-in service by obtaining data for the service based on the service request context, identifying one or more keys based on the obtained context data, retrieving, based on the one or more keys, data from a cache, and applying the data to the model, the decision being based on the data applied to the model.
There are provided systems and methods for automated updating of computing code for software platform integrations with computing services. An online transaction processor or other service provider may provide computing services and platforms to entities including merchants for electronic transaction processing and other account services. To provide for code integrations of the computing services with software platforms, the service provider may provide a tool where merchants may update legacy code integrations of the computing services on their software platforms to new computing code for new code integrations, such as to facilitate the use of new APIs, endpoints, and the like. The tool may provide mappings for legacy code parameters to new code parameters, which may each be associated with code limitations in the legacy code and new code integrations. Further, the tool may provide an automatic converter of the legacy code to the new code using these mappings.
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
95.
FRAMEWORK FOR GENERATING RELEVANT QUERIES FOR ARTIFICIAL INTELLIGENCE MODEL
Methods and systems are presented for providing a framework that provides information associated with a particular domain to an artificial intelligence (AI) model. The framework includes a query condenser model that reformulates user-generated queries, such that the reformulated query can be used to retrieve a set of documents that can be used by the AI model to generate a response to the user-generated query. The query condenser model is trained using outputs generated by a teacher model. When the reformulated query generated by the query condenser model does not satisfy a set of criteria, the teacher model is configured to generate an improved version of the reformulated query for retraining the query condenser model.
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
36 - Financial, insurance and real estate services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Downloadable software for processing electronic payments and
for transferring funds to and from others; downloadable
software for facilitating money transfer services,
electronic funds transfer services, bill payment remittance
services, electronic processing and transmission of payments
and payment data; downloadable computer software and
downloadable mobile application software for facilitating
electronic commerce transactions; downloadable software for
use as a digital wallet; downloadable software for
connecting digital wallets; downloadable software for
connecting, integrating, and enabling transfer of funds
between digital wallets and financial accounts; downloadable
software for linking independent financial accounts and
digital wallets, enabling migration of data and transfers of
funds between independent third party financial accounts and
digital wallets, and establishing secure connections between
independent financial accounts and digital wallets;
downloadable computer software for use for financial account
management, namely, software for managing and facilitating
financial transactions and funds transfers for bank
accounts, credit card accounts, debit card accounts, and
digital wallets; downloadable authentication software for
controlling access to and communications with computers and
computer networks; downloadable software for currency
conversion. Providing business information regarding money transfer
services; business consulting services in the field of
online payments; business managing and tracking credit card,
debit card, ACH, prepaid cards, payment cards, and other
forms of payment transactions via electronic communications
networks for business purposes; business information
management, namely, electronic reporting of business
analytics relating to payment processing, authentication,
tracking, and invoicing. Electronic payment services involving electronic processing
and subsequent transmission of bill payment data; payment
transaction processing services; providing electronic
processing of electronic funds transfer, ACH, credit card,
debit card, electronic check and electronic payments;
financial information processing; money transfer services;
electronic funds transfer services; bill payment services;
providing payment services via a network for facilitating
transactions from digital wallets; providing financial
services, namely, bill payment services provided via a
digital wallet and providing secure commercial transactions;
transaction processing services for bank accounts, debit
cards, and credit cards on embedded digital wallets,
cross-border money transfers to banks and mobile wallets
with real time currency exchange rates; clearing financial
transactions via a global computer network and wireless
networks; credit card and debit card transaction processing
services; processing of electronic wallet payments; currency
exchange services; electronic commerce payment services,
namely, establishing funded accounts used to facilitate
transactions and purchases on the internet. Providing temporary use of online non-downloadable software
for processing electronic payments and for transferring
funds to and from others; application service provider (ASP)
featuring application programming interface (API) software
for facilitating payment transactions and financial
information processing; providing temporary use of online
non-downloadable software for facilitating money transfer
services, electronic funds transfer services, bill payment
remittance services, electronic processing and transmission
of payments and payment data; providing temporary use of
online non-downloadable software for facilitating electronic
commerce transactions; providing temporary use of online
non-downloadable software for use as a digital wallet;
providing temporary use of online non-downloadable software
for connecting digital wallets; providing temporary use of
online non-downloadable software for connecting,
integrating, and enabling transfer of funds between digital
wallets and financial accounts; providing temporary use of
online non-downloadable software for linking independent
financial accounts and digital wallets, enabling migration
of data and transfers of funds between independent third
party financial accounts and digital wallets, and
establishing secure connections between independent
financial accounts and digital wallets; providing temporary
use of online non-downloadable software for use for
financial account management, namely, software for managing
and facilitating financial transactions and funds transfers
for bank accounts, credit card accounts, debit card
accounts, and digital wallets; providing temporary use of
online non-downloadable authentication software for
controlling access to and communications with computers and
computer networks; providing temporary use of online
non-downloadable software for currency conversion.
97.
DYNAMICALLY CUSTOMIZING A USER INTERFACE OF AN ELECTRONIC PLATFORM VIA MACHINE LEARNING
Via one or more electronic communication channels of an electronic platform, a request is detected from a user to interact with the electronic platform. Via a Natural Language Processing (NLP) model, an intent of the user behind the request to interact with the electronic platform is predicted. Via an Explainable Artificial Intelligence (XAI) model, one or more features associated with the user that contributed to the predicted intent are determined. Via a Large Language Model (LLM), a personalized message is generated for the user. The personalize message refers to the intent predicted by the NLP model or the one or more features associated with the user determined by the XAI model that contributed to the predicted intent. The personalized message is provided to the user via the one or more electronic communication channels.
G06F 40/58 - Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
98.
SEARCH AND ANSWER GENERATION ENGINE FOR DATA SUMMARIZATION FROM MULTIPLE DATA SOURCES
There are provided systems and methods for a search and answer generation engine for data summarization from multiple data sources. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include live agent and self-service assistance features for answering users'questions. To provide more comprehensive searching and automated answer generation, the service provider may utilize an answer engine that may search multiple data sources in different data formats. Keywords may be extracted from a natural language question using an embedding LLM, and API calls to search features of each data source may be executed to retrieve relevant content. A summarization LLM may then concisely summarize the different content in different formats so that an answer may be provided. The user may then refine their question with further questions or requests, which may adjust the keywords and/or summarization.
A computer system performs a processing operation in real time on an aggregated value stored in a counter of a set of counters corresponding to time periods associated with events. The computer system maintains the set of counters usable to store aggregated values of an event metric. In response to detection of the events, the computer system stores, in a database, event details for the received events and updates those counters of the set of counters that correspond to time periods associated with the received events. In response to receipt, in a current time period, of an update to a particular event of the received events associated with a previous time period, the computer system, in real time, retrieves, from the set of counters, a particular aggregated value of the event metric for the previous time period and performs a processing operation based on the particular aggregated value.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
Methods and systems are presented for identifying different users who share a user account with an online service provider and dynamically processing transactions for the user account differently based on which user initiates the transaction request. In some embodiments, an account decomposition system may decompose the user account into distinct users who share the user account. The account decomposition system may identify different users who are sharing a user account by analyzing past transactions associated with the user account and different user devices that were used to conduct the past transactions. The account decomposition system may determine different user profiles for the different users, and may use the different user profiles to process incoming transaction requests initiated by different users of the user account.
G06F 18/23213 - Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
