Patents Assigned to Services
-
Patent number: 12175378Abstract: Systems, methods, and other embodiments associated with decision tree machine learning native to a graph database are described. In one embodiment, a method includes receiving an objective property value of a training graph for a graph-native decision tree to be trained to predict; determining feasible ranges of values from the training graph; automatically generating a graph query language grammar for graph-native decision trees based on the feasible ranges; progressively evolving output decision trees in a graph query language from the graph query language grammar to generate a final decision tree that accurately predicts the objective property value; and storing the final decision tree for subsequent execution against a target graph.Type: GrantFiled: March 5, 2021Date of Patent: December 24, 2024Assignee: Oracle Financial Services Software LimitedInventor: Richard Anthony McQueary, III
-
Patent number: 12173573Abstract: Provided, in one aspect, is an anchoring subassembly, a well system, and a method. The anchoring subassembly, in one aspect, includes a mandrel, and an isolation element positioned about the mandrel, the isolation element configured to move between a radially retracted state, a fully radially expanded state, and a relaxed radially expanded state. The anchoring subassembly, in one aspect, further includes a ratch latch body coupled to the isolation element, the ratch latch body configured to hold the isolation element in the fully radially expanded state, and a relief feature coupled to the ratch latch body, the relief feature configured to shear to release stored energy in the isolation element and thereby allow the isolation element to move from the fully radially expanded state to the relaxed radially expanded state.Type: GrantFiled: September 29, 2022Date of Patent: December 24, 2024Assignee: Halliburton Energy Services, Inc.Inventors: Aihua Liang, Wesley P. Dietz, Alireza Yazdanshenas
-
Patent number: 12175477Abstract: A non-fungible token (NFT) representing title to property may be received. A search of the title to the property may be conducted. A title confidence may be determined based on the search of the title to the property. A premium may be determined based on the title confidence. The premium may be redetermined based on changes to the title confidence.Type: GrantFiled: May 27, 2022Date of Patent: December 24, 2024Assignee: United Services Automobile Association (USAA)Inventors: Christopher E. Flores, Jennifer M. Chandler-Bradley, Elena M. Carrasco, Keegan P. Hayes, Nikhil Dama, Yibin Xu, Neetu Jain
-
Patent number: 12175310Abstract: Perceptive scaling of computing resources is disclosed. News sources can be analyzed to identify a future event as well as an occurrence date and type of the event. A computing resource affected by the event can be determined based on the type of event. A scaling strategy can be formulated for the computing resource, such as scaling up or out, to address resource load introduced by the event. The extent of scaling can be determined based on the predicted impact of the event on the computing resource. Subsequently, the scaling strategy can be scheduled for execution before the occurrence date. The scaling strategy can later be terminated or deactivated after the event terminates.Type: GrantFiled: February 21, 2022Date of Patent: December 24, 2024Assignee: Capital One Services, LLCInventors: Joshua Edwards, Michael Mossoba, Abdelkader M'Hamed Benkreira
-
Patent number: 12174897Abstract: Aspects described herein may relate to methods, systems, and apparatuses for generating synthetic data based on time series predictions and plural machine learning models. Generating the synthetic data may include receiving one or more data records that include transaction data of a user, categorizing and/or segmenting the one or more data records, determining a first predicted time step based on the categorizing and/or segmenting, and performing an iterative process that determines further predicted time steps. The first predicted time step may be determined using one model of a plurality of machine learning models. The iterative process may determine the further predicted time steps using the plural machine learning models. Based on iterations of the iterative process, potential time series may be determined. The synthetic time series may be determined from the potential time series. The synthetic time series may be used by additional processes, such as additional machine-learning processes.Type: GrantFiled: December 15, 2023Date of Patent: December 24, 2024Assignee: Capital One Services, LLCInventors: Austin Walters, Jeremy Goodsitt
-
Patent number: 12172074Abstract: Methods and systems described in this disclosure are directed at gamification. In some embodiments, the present disclosure relates to methods and systems for tracking actions taken by a user at predetermined gaming levels in a gaming application, the gaming application also facilitating users to interact with the gaming application in the form of questions and answers. If the user is unable to provide a minimum number of correct responses to the questions presented, the gaming application displays actions that are to be performed by the user to continue playing the game. In some embodiments, a game is paused temporarily by a pause signal sent to the gaming application. The game resumes when a resume signal is sent to activate the gaming application.Type: GrantFiled: November 3, 2021Date of Patent: December 24, 2024Assignee: United Services Automobile Association (USAA)Inventors: David Hancock, Sharon M. Sirizzotti, Joe R. Martin
-
Publication number: 20240420215Abstract: Unlike visual similarity, visual compatibility is a complex concept. Existing approaches for outfit compatibility prediction does not focus on methods with personalization. The present disclosure proposes a novel approach to model the user's preference for different styles. The outfit compatibility prediction module is a critical component of an outfit recommendation system. An outfit is said to be compatible if all the items are visually compatible and match the user's preferences. The present disclosure represents the outfit as a graph and uses Graph Neural Network (GNN) with attention mechanism to capture the inter-relationship between the items. A graph read-out layer generates the final outfit embedding. The proposed approach efficiently models the preferences of the users for different styles. Finally, the outfit compatibility score is generated by computing the similarity between the outfit embedding and the user embedding.Type: ApplicationFiled: May 17, 2024Publication date: December 19, 2024Applicant: Tata Consultancy Services LimitedInventors: Vivek Bangalore SAMPATHKUMAR, Jayavardhana Rama GUBBI LAKSHMINARASIMHA, Gaurab BHATTACHARYA, Bagya Lakshmi VASUDEVAN, Arpan PAL, Balamuralidhar PURUSHOTHAMAN
-
Publication number: 20240420045Abstract: A graphical user interface and a system are provided which include a route identification interface element which specifies a new route for a vehicle, a plurality of route type buttons, a vehicle type interface, a stop order interface, a map, a control button, and an assignment button. The stop order interface identifies one or more stops for a vehicle in a fleet of vehicles. The map identifies the new route and the one or more stops graphically on the graphical user interface. The control button provides a utilization view for the one or more vehicles in the fleet of vehicles from which a vehicle from the one or more vehicles in the fleet of vehicles that are available can be assigned to the new route.Type: ApplicationFiled: April 4, 2024Publication date: December 19, 2024Applicant: Zum Services, Inc.Inventors: Abhishek Garg, Rohit Jain, Sidi Liu, Andrew Mormysh, Gustavo Ocasio, Niket Sanghvi, Melissa Shiu
-
Publication number: 20240420464Abstract: The disclosure addresses problems associated with a systematic integration of multi-modal data for effective training, and handling of large volume of data because of high resolution of the multiple modalities. Embodiments herein provide a method and a system for a distributed training of a multi-modal data fusion transformer. Herein, a distributed training approach called a Distributed Architecture for Fusion-Transformer Training Acceleration (DAFTA) is proposed for processing large multimodal remote sensing data. DAFTA is enabled to handle any combination of remote sensing modalities. Additionally, similarity of feature space is leveraged to optimize the training process and to achieve the training with reduced data set which is equivalent to a complete data set. The proposed approach provides a systematic and efficient method for managing large sensing data and enables accurate and timely insights for various applications.Type: ApplicationFiled: June 13, 2024Publication date: December 19, 2024Applicant: Tata Consultancy Services LimitedInventors: Shruti Kunal KUNDE, Ravi Kumar SINGH, Chaman BANOLIA, Rekha SINGHAL, Balamuralidhar PURUSHOTHAMAN, Shailesh Shankar DESHPANDE
-
Publication number: 20240417765Abstract: The present invention relates to a fermented milk-based product comprising a combination of low levels of lactose and stable levels of galacto-oligosaccharides (GOS) produced in-situ and methods thereof.Type: ApplicationFiled: March 10, 2022Publication date: December 19, 2024Applicant: Kerry Group Services International LtdInventors: Maria Elina Sundberg, Vojislav Vojinovic, Hans Raj
-
Publication number: 20240420395Abstract: A method for generating a dynamic virtual representation of an event or an object is disclosed. The method includes obtaining one or more of first data or first metadata associated with the first data from one or more data sources, generating a virtual object, setting a state of the adjustable aspect such that the adjustable aspect is a visual representation of one or more aspects of the one or more of the first data or the first metadata, causing a user device to output the virtual object via a user interface, determining a change in one or more of the first data or the first metadata, modifying the state of the adjustable aspect based on the determined change, and causing the user device to modify the output of the virtual object based on the modified state of the adjustable aspect.Type: ApplicationFiled: June 15, 2023Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Amy Jean LA, Kevin OSBORN
-
Publication number: 20240419827Abstract: A method and related system may analyze metadata associated with a first set of transactions to determine whether to perform a second set of transactions. The method and related system may include determining a data category based on first device-provided data of a first database transaction indicating a first record associated with a second record, and may further include obtaining, based on whether the data category satisfies a first set of criteria, an identifier and an amount based on image data using a prediction model. The method may further include querying a database based on the identifier to obtain an indication that the identifier is mapped to an object category, validating the amount based on a result indicating whether the object category satisfies a second set of criteria, and causing a second transaction that changes fields of the first and second records.Type: ApplicationFiled: June 16, 2023Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Lawrence DOUGLAS, Jeffrey RULE, Jackson MACOMBER
-
Publication number: 20240418522Abstract: A system and method that includes a ride requestor device, a driver device, a server device, and a user device is disclosed. The ride requestor device provides rider information and stop location information for a plurality of riders. The driver device provides location information, navigation information, and stop timing information for a particular vehicle in a fleet of vehicles. The server device includes an artificial intelligence engine which generates and optimizes a plurality of routes for service by the fleet of vehicles to provide a ride to each one of the plurality of riders.Type: ApplicationFiled: July 8, 2024Publication date: December 19, 2024Applicant: Zum Services, Inc.Inventors: Abhishek Garg, Rohit Jain, Sidi Liu, Andrew Mormysh, Gustavo Ocasio, Niket Sanghvi, Melissa Shiu
-
Publication number: 20240420690Abstract: Embodiments disclosed are directed to a computing system that performs steps to automatically generate fine-grained call reasons from customer service call transcripts. The computing system extracts, using a natural language processing (NLP) technique, a set of events from a set of text strings of speaker turns. The computing system then identifies a set of clusters of events based on the set of events and labels each cluster of events in the set of clusters of events to generate a set of labeled clusters of events. Subsequently, the computing system assigns each event in the set of events to a respective labeled cluster of events in the set of labeled clusters of events.Type: ApplicationFiled: June 25, 2024Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Adam FAULKNER, Gayle McELVAIN, John QIU
-
Publication number: 20240417446Abstract: Single-domain monoclonal antibodies (“nanobodies”) that specifically bind the S2 subunit of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) spike protein are described. The single-domain antibodies were isolated from shark variable domain of new antigen receptor (VNAR) and camel variant domain of heavy chain only antibody (VHH) phage display libraries panned against the S2 subunit of SARS-CoV-2 spike protein. The S2 subunit-specific nanobodies, and conjugates thereof, can be used for the diagnosis and treatment of a coronavirus infection.Type: ApplicationFiled: October 25, 2022Publication date: December 19, 2024Applicant: The U.S.A., as represented by the Secretary, Department of Health and Human ServicesInventors: Mitchell Ho, Zhijian Duan, Jesse D. Buffington
-
Publication number: 20240422239Abstract: A method, an apparatus, and a computer program product for subscription-based notifications of events in enterprise systems. A plurality of notification message delivery channels for delivery of one or more notification messages to one or more user devices is identified. The notification messages are received from one or more software applications and correspond to one or more events associated with the software applications. A first notification message delivery channel is selected from the plurality of notification message delivery channels for delivery of the received notification messages based on one or more subscriptions associated with the user devices to the events. The subscriptions are configured using one or more subscription preferences received from the user devices. The received notification messages are transmitted to the user devices using the selected first notification message delivery channel.Type: ApplicationFiled: August 29, 2024Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Milind Patel, Samin Bohara, Briana Vargas
-
Publication number: 20240420550Abstract: Disclosed herein is a transaction instrument and method for recording vibration information associated with a transaction at a point-of-service (POS) terminal. The vibration information can be used to determine whether the POS terminal is compromised (e.g., via a skimmer).Type: ApplicationFiled: August 22, 2024Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Molly JOHNSON, Adam VUKICH, James ZARAKAS
-
Publication number: 20240419567Abstract: Methods and systems for performing efficient integration tests on mobile device for contactless data transfers are described. Rather than performing contactless communications with a variety of test user devices (e.g., test smart cards), which may be time consuming and may present physical difficulty, a mobile device can simulate the result of these communications using a simulator application operating on the mobile device. A contactless communication application, also operating on the mobile device, can communicate with the simulator application in order to generate interaction payloads based on stored data records corresponding to the test user devices. These interaction payloads can then be transmitted by the mobile device to a processing computer. Later, the mobile device may receive a response from the processing computer or another computer system, indicating if the interaction payloads were successfully received and interpreted. This in turn may indicate if the integration test was successful.Type: ApplicationFiled: December 17, 2021Publication date: December 19, 2024Applicant: Visa International Service AssociationInventors: Yuexi Chen, Marc Kekicheff, Christian Aabye, Alexandre Pierre
-
Publication number: 20240420018Abstract: In some embodiments, a computing system may generate a prediction related to a new category (not included in a set of categories) using a machine learning model trained on a set of embeddings corresponding to the category set. As an example, the computing system may generate a set of hashes such that each hash of the hash set is mapped to an embedding of the embedding set. When a new category added to the category set, the computing system may generate a given hash for the new category and identify a first hash of the hash set that matches the given hash. Based on identifying the first hash as a matching hash, the computing system may use an existing embedding (e.g., mapped to the first hash) with the machine learning model in connection with the new category, thereby avoiding a need to add a new embedding to the embedding set.Type: ApplicationFiled: June 16, 2023Publication date: December 19, 2024Applicant: Capital One Services, LLCInventors: Samuel SHARPE, Christopher Bayan BRUSS, Senthil KUMAR, Nikita SELEZNEV, Fangxiang JIAO
-
Patent number: D1054856Type: GrantFiled: May 11, 2022Date of Patent: December 24, 2024Assignee: Albea ServicesInventors: Sylvain Defert, Franck Fritsch