公开(公告)号：US11995121B2

公开(公告)日：2024-05-28

申请号：US18216372

申请日：2023-06-29

Applicant: THE TORONTO-DOMINION BANK

Inventor： Maksims Volkovs ,  Cheng Chang ,  Guangwei Yu ,  Chundi Liu

IPC: G06K9/60 ,  G06F16/58 ,  G06F16/583 ,  G06F16/901 ,  G06F16/903 ,  G06F16/9032 ,  G06V10/75 ,  G06V10/764 ,  G06V10/84

CPC classification number: G06F16/583 ,  G06F16/5866 ,  G06F16/9024 ,  G06F16/9032 ,  G06F16/90348 ,  G06V10/751 ,  G06V10/764 ,  G06V10/84

Abstract: An image retrieval system receives an image for which to identify relevant images from an image repository. Relevant images may be of the same environment or object and features and other characteristics. Images in the repository are represented in an image retrieval graph by a set of image nodes connected by edges to other related image nodes with edge weights representing the similarity of the nodes to each other. Based on the received image, the image traversal system identifies an image in the image retrieval graph and alternatively explores and traverses (also termed “exploits”) the image nodes with the edge weights. In the exploration step, image nodes in an exploration set are evaluated to identify connected nodes that are added to a traversal set of image nodes. In the traversal step, the relevant nodes in the traversal set are added to the exploration set and a query result set.

公开(公告)号：US20240160671A1

公开(公告)日：2024-05-16

申请号：US18420235

申请日：2024-01-23

Applicant: Elumus, LLC

Inventor： Matthew M. Kelly

IPC: G06F16/9038 ,  G06F8/38 ,  G06F9/451 ,  G06F9/455 ,  G06F16/21 ,  G06F16/903 ,  G06F16/9032 ,  G06F16/907

CPC classification number: G06F16/9038 ,  G06F8/38 ,  G06F9/451 ,  G06F9/45529 ,  G06F16/211 ,  G06F16/90332 ,  G06F16/90335 ,  G06F16/907

Abstract: A system includes a controller, a database controlled by the controller, and a memory including an end-user executable code and a business software management code. The controller receives a user update to modify the end-user executable code, converts the user update to a machine language input, and, in response to the machine language input, modifies one or more of the end-user executable code, the database structure, and a documentation of the end-user executable code. In response to executing the program instructions associated with the modified end-user executable code on the end-user device, the controller generates a data collection GUI according to the modified end-user executable code and stores data in the database structure according to the modified end-user executable code.

公开(公告)号：US11983554B2

公开(公告)日：2024-05-14

申请号：US17726258

申请日：2022-04-21

Applicant: X Development LLC

Inventor： Rebecca Radkoff ,  David Andre

IPC: G06F16/242 ,  G06F3/0482 ,  G06F3/0488 ,  G06F9/455 ,  G06F40/30 ,  G06F3/16 ,  G06F16/33 ,  G06F16/332 ,  G06F16/9032 ,  G06F16/9535 ,  G06F40/35 ,  G06F40/40 ,  G06F40/58

CPC classification number: G06F9/45529 ,  G06F3/0482 ,  G06F40/30 ,  G06F3/167 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/90332 ,  G06F16/9535 ,  G06F40/35 ,  G06F40/40 ,  G06F40/58

Abstract: Disclosed implementations relate to automating semantically-similar computing tasks across multiple contexts. In various implementations, an initial natural language input and a first plurality of actions performed using a first computer application may be used to generate a first task embedding and a first action embedding in action embedding space. An association between the first task embedding and first action embedding may be stored. Later, subsequent natural language input may be used to generate a second task embedding that is then matched to the first task embedding. Based on the stored association, the first action embedding may be identified and processed using a selected domain model to select actions to be performed using a second computer application. The selected domain model may be trained to translate between an action space of the second computer application and the action embedding space.

公开(公告)号：US11983175B1

公开(公告)日：2024-05-14

申请号：US17497236

申请日：2021-10-08

Applicant: GOOGLE LLC

Inventor： Bruce Christensen ,  Pravir Kumar Gupta ,  Jan Kuipers

IPC: G06F16/2457 ,  G06F16/242 ,  G06F16/332 ,  G06F16/9032

CPC classification number: G06F16/2425 ,  G06F16/24578 ,  G06F16/3322 ,  G06F16/90324

Abstract: Methods and apparatus related to ranking modifications of a previous query. For example, modifications of a previous query may be generated based on a current query issued subsequent to the previous query by substituting one or more n-grams of the previous query with one or more n-grams of the current query. One or more measures of each of the modifications may be identified and, based on such measures, a ranking of each of the modifications may be determined. One of the modifications may be selected as a submission query based on the rankings of the modifications. The submission query may be selected for submission in lieu of, or in addition to, the current query.

公开(公告)号：US11974019B2

公开(公告)日：2024-04-30

申请号：US17536583

申请日：2021-11-29

Applicant: Google LLC

Inventor： Kevin Greene ,  Justin Lewis

IPC: G06F16/438 ,  G06F16/783 ,  G06F16/9032 ,  H04N21/45 ,  H04N21/466 ,  H04N21/472

CPC classification number: H04N21/4668 ,  G06F16/4387 ,  G06F16/7837 ,  G06F16/784 ,  G06F16/90328 ,  H04N21/4532 ,  H04N21/47217

Abstract: Systems and methods for identifying related videos based on elements tagged in the videos are presented. In an aspect, a system includes an identification component configured to identify tagged elements in a video, a matching component configured to identify other videos that include one or more of the tagged elements, and a recommendation component configured to recommend the other videos for viewing based on a current or past request to play the video.

公开(公告)号：US11966986B2

公开(公告)日：2024-04-23

申请号：US17878778

申请日：2022-08-01

Applicant: Meta Platforms, Inc.

Inventor： Shivani Poddar ,  Seungwhan Moon ,  Paul Anthony Crook ,  Rajen Subba

IPC: H04L67/306 ,  G06F3/01 ,  G06F9/451 ,  G06F9/48 ,  G06F9/54 ,  G06F16/332 ,  G06F16/9032 ,  G06F16/9536 ,  G06F18/2321 ,  G06F40/205 ,  G06F40/242 ,  G06F40/253 ,  G06F40/30 ,  G06F40/35 ,  G06F40/56 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06N20/00 ,  G06Q10/109 ,  G06Q50/00 ,  G06V10/20 ,  G06V10/764 ,  G06V10/82 ,  G06V20/00 ,  G06V20/20 ,  G06V20/30 ,  G06V40/16 ,  G06V40/20 ,  G10L15/06 ,  G10L15/08 ,  G10L15/16 ,  G10L15/18 ,  G10L15/22 ,  G10L15/30 ,  G10L15/32 ,  H04L51/18 ,  H04L51/212 ,  H04L51/222 ,  H04L51/224 ,  H04L51/52 ,  H04L67/75 ,  H04N7/14 ,  G06F3/16 ,  G06V20/40

CPC classification number: G06Q50/01 ,  G06F3/011 ,  G06F3/013 ,  G06F9/453 ,  G06F9/485 ,  G06F9/4881 ,  G06F9/547 ,  G06F16/3329 ,  G06F16/90332 ,  G06F16/9536 ,  G06F18/2321 ,  G06F40/205 ,  G06F40/242 ,  G06F40/253 ,  G06F40/30 ,  G06F40/35 ,  G06F40/56 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06N20/00 ,  G06Q10/109 ,  G06V10/255 ,  G06V10/764 ,  G06V10/82 ,  G06V20/00 ,  G06V20/20 ,  G06V20/30 ,  G06V40/16 ,  G06V40/25 ,  G10L15/063 ,  G10L15/08 ,  G10L15/16 ,  G10L15/1815 ,  G10L15/1822 ,  G10L15/22 ,  G10L15/30 ,  G10L15/32 ,  H04L51/18 ,  H04L51/212 ,  H04L51/222 ,  H04L51/224 ,  H04L51/52 ,  H04L67/306 ,  H04L67/75 ,  H04N7/147 ,  G06F3/017 ,  G06F3/167 ,  G06V20/41 ,  G06V40/174 ,  G06V2201/10 ,  G10L2015/088 ,  G10L2015/223 ,  G10L2015/227

Abstract: In one embodiment, a method includes receiving, at a client system, an audio input, where the audio input comprises a coreference to a target object, accessing visual data from one or more camera associated with the client system, where the visual data comprises images portraying one or more objects, resolving the coreference to the target object from among the one or more objects, resoling the target object to a specific entity, and providing, at the client system, a response to the audio input, where the response comprises information about the specific entity.

公开(公告)号：US11966433B1

公开(公告)日：2024-04-23

申请号：US17953305

申请日：2022-09-26

Applicant: Google LLC

Inventor： Justin Lewis ,  Kevin Greene

IPC: G06F16/48 ,  G06F16/435 ,  G06F16/9032

CPC classification number: G06F16/48 ,  G06F16/435 ,  G06F16/90324

Abstract: A computer-implemented method for enabling users to subscribe to people and other tagged entities is provided herein. Such a method includes maintaining subscription data specifying a plurality of entities subscribed to by a plurality of users, with each of the plurality of entities being a tagged entity associated with a tag. The method further includes identifying a media item associated with one or more tagged entities of the plurality of entities, determining, based on the subscription data, a user of the plurality of users that is subscribed to the tagged entities of the media item, and providing the media item to the user.

公开(公告)号：US20240119093A1

公开(公告)日：2024-04-11

申请号：US17961069

申请日：2022-10-06

Applicant: International Business Machines Corporation

Inventor： Susan Hallen ,  Rose Fleischman ,  Alan Daet Mejía Villaseñor ,  Diane Helen Wasserstrom

IPC: G06F16/9032 ,  G06F16/93 ,  G06F40/20

CPC classification number: G06F16/90332 ,  G06F16/93 ,  G06F40/20

Abstract: Methods, systems, and computer program products for enhanced document ingestion using natural language processing are provided herein. A computer-implemented method includes identifying, within a first document, terms unknown to a first natural language processing model by processing the first document using the first natural language processing model; identifying, within a second document, terms known to a second natural language processing model by processing the second document using the second natural language processing model; comparing the terms unknown to the first natural language processing model to the terms known to the second natural language processing model; and upon determining that at least one of the terms unknown to the first natural language processing model matches at least one of the terms known to the second natural language processing model, reprocessing the first document using the second natural language processing model.

公开(公告)号：US11954150B2

公开(公告)日：2024-04-09

申请号：US16369142

申请日：2019-03-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jungmin Lee

IPC: G10L15/22 ,  G06F16/33 ,  G06F16/332 ,  G06F16/73 ,  G06F16/738 ,  G06F16/9032 ,  G06N20/00 ,  G06V10/22 ,  G06V10/764 ,  G06V10/82 ,  G06V20/20 ,  G06V20/40 ,  G10L17/22

CPC classification number: G06F16/73 ,  G06F16/3329 ,  G06F16/3344 ,  G06F16/738 ,  G06F16/90332 ,  G06N20/00 ,  G06V10/235 ,  G06V10/764 ,  G06V10/82 ,  G06V20/20 ,  G06V20/40 ,  G06V20/41 ,  G10L15/22 ,  G10L17/22 ,  G10L2015/223

Abstract: An artificial intelligence (AI) system utilizing a machine learning algorithm such as deep learning for controlling an electronic device when a video is reproduced and a user's voice instruction is received, to acquire a frame corresponding to the time point when the input of the user's voice instruction is received, and obtain a search result for information on objects in the frame using an AI model trained according to at least one of machine learning, a neural network or a deep learning algorithm.

公开(公告)号：US11948058B2

公开(公告)日：2024-04-02

申请号：US16216296

申请日：2018-12-11

Applicant: Adobe Inc.

Inventor： Nedim Lipka ,  Nikhita Vedula

IPC: G06N3/02 ,  G06F16/9032 ,  G06F40/30 ,  G06N20/00

CPC classification number: G06N3/02 ,  G06F16/9032 ,  G06F40/30 ,  G06N20/00

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods that utilize recurrent neural networks to determine the existence of one or more open intents in a text input, and then extract the one or more open intents from the text input. In particular, in one or more embodiments, the disclosed systems utilize a trained intent existence neural network to determine the existence of an actionable intent within a text input. In response to verifying the existence of an actionable intent, the disclosed systems can apply a trained intent extraction neural network to extract the actionable intent from the text input. Furthermore, in one or more embodiments, the disclosed systems can generate a digital response based on the intent identified from the text input.