公开(公告)号：US20240362272A1

公开(公告)日：2024-10-31

申请号：US18647338

申请日：2024-04-26

申请人： Twelve Labs, Inc.

发明人： Seung Joon Lee ,  Raehyuk Jung ,  Seongyun Lee ,  Minjoon Seo ,  Jaehyuk Yi

IPC分类号： G06F16/735 ,  G06F40/40 ,  G06V20/40

CPC分类号： G06F16/735 ,  G06F40/40 ,  G06V20/46

摘要： A video analysis system receives one or more queries from users of client devices. The video analysis system trains a machine-learned video encoder and/or a decoder coupled to receive video data and a prompt including a user query and generate an output for responding to the user query. A set of video embeddings are generated by extracting frame data, audio data, or text data from the video content, and applying a machine-learned video encoder to the frame data, the audio data, or the text data to generate the set of video embeddings. The video analysis system also generates a set of prompt embeddings representing at least a portion of the query in a latent space. The video analysis system applies at least a component of a machine-learned decoder to the input tensor to generate an output including a set of output embeddings.

公开(公告)号：US20240346074A1

公开(公告)日：2024-10-17

申请号：US18637875

申请日：2024-04-17

申请人： Magnet Forensics Inc.

发明人： Christopher Sippel

IPC分类号： G06F16/735 ,  G06F16/783 ,  G06V10/74 ,  G10L15/10

CPC分类号： G06F16/735 ,  G06F16/7834 ,  G06V10/761 ,  G10L15/10

摘要： Systems and methods for video matching are provided. A video matching method includes receiving known video data comprising a first plurality of video frames and unknown video data comprising a second plurality of video frames, converting all pixel channel values of each video frame into buffer values, calculating a buffer distance value of each pixel of each video frame by comparing buffer values for all pixels of each video frame of the unknown video data to the known video data, and calculating an average buffer distance value, the average buffer distance value comprising the mean value of the buffer distance value of each pixel of all frames.

公开(公告)号：US20240289399A1

公开(公告)日：2024-08-29

申请号：US18628529

申请日：2024-04-05

申请人： Anup Tikku

发明人： Anup Tikku ,  Arsh Tikku

IPC分类号： G06F16/9535 ,  G06F3/01 ,  G06F16/735 ,  G06F16/908 ,  G06F16/9536 ,  G06N20/00 ,  H04L65/612

CPC分类号： G06F16/9535 ,  G06F3/011 ,  G06F16/735 ,  G06F16/908 ,  G06F16/9536 ,  G06N20/00 ,  H04L65/612

摘要： Methods, systems, and non-transitory computer programs configured to generate and present customized movie content to a user are disclosed, according to example embodiments. The customized movie content may be generated by an entertainment system from a plurality of content based on at least one or more of user criteria, device criteria, content criteria, and/or environment criteria. The user criteria, device criteria, content criteria and/or environment criteria may be obtained from public and/or private sources of information of a user. To provide an empirically compelling recommendation of the customized movie content, an artificial intelligence agent may be trained to accurately predict an optimized balance between user's interest, content criteria, network performance, device criteria and/or environment criteria. Then, an algorithm may be derived from the trained artificial intelligence agent so that the transmission of the appropriate customized movie content will seek to result in an improved overall relevance of content, avoid repeated requests and disruptions to the user, enhance the resolution, reliability and delivery of the audio and video content, optimize end user device capabilities, reduce communication disruption, interference and latency, and improve the overall entertainment experience for the user. The customized movie content may be presented to the user at an end user device.

公开(公告)号：US20240289381A1

公开(公告)日：2024-08-29

申请号：US18656217

申请日：2024-05-06

申请人： Rovi Guides, Inc.

发明人： Charishma Chundi ,  Reda Harb

IPC分类号： G06F16/735 ,  G06F16/732 ,  G06F16/738 ,  G06F16/783 ,  G06F16/9032 ,  H04N21/454 ,  H04N21/81

CPC分类号： G06F16/735 ,  G06F16/732 ,  G06F16/738 ,  G06F16/783 ,  G06F16/90324 ,  H04N21/454 ,  H04N21/812

摘要： Systems and methods are provided for preventing spoilers in autocompleted search queries. One example method includes, in response to detecting a user interaction at a computing device associated with a search query, identifying a media content history comprising one or more media content items. A predicted search query based on the user interaction and the media content history is generated, and the predicted search query is generated for output, at the computing device.

公开(公告)号：US20240211512A1

公开(公告)日：2024-06-27

申请号：US18596497

申请日：2024-03-05

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Tianyu WU ,  Rui Hua ,  Aihu Zhang ,  Yao Meng ,  Quan Wen ,  Chao Qi

IPC分类号： G06F16/738 ,  G06F16/732 ,  G06F16/735

CPC分类号： G06F16/738 ,  G06F16/7335 ,  G06F16/735

摘要： This application discloses a search result reordering method performed by a computer device. The method includes: displaying a search result page corresponding to a search session, the search result page displaying a first content sequence obtained based on a search keyword corresponding to the search session, and the first content sequence including a plurality of media contents; obtaining at least one real-time interactive behavior performed by a target object on the search result page; determining media contents other than a target media content associated with the at least one real-time interactive behavior as to-be-sorted media contents in the first content sequence; and reordering the to-be-sorted media contents to obtain a second content sequence when the at least one real-time interactive behavior satisfies a reordering trigger condition, and updating the search result page based on the second content sequence.

公开(公告)号：US20240193934A1

公开(公告)日：2024-06-13

申请号：US18585637

申请日：2024-02-23

申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

发明人： Hui GUO

IPC分类号： G06V10/98 ,  G06F16/735 ,  G06V10/94 ,  G06V20/40 ,  G06V20/62

CPC分类号： G06V10/98 ,  G06F16/735 ,  G06V20/41 ,  G06V20/46 ,  G06V20/48 ,  G06V20/62 ,  G06V10/95

摘要： A video recognition method, performed by a computer device, including obtaining a target video and a series reference video in a video series, recognizing a series local similar clip in the target video relative to the series reference video according to a first matching result obtained by performing video frame matching on the target video and the series reference video, obtaining a platform reference video from a video platform to which the target video belongs, recognizing a platform global similar clip in the target video relative to the platform reference video according to a second matching result obtained by performing video frame matching on the target video and the platform reference video, and determining a comprehensive similar clip in the target video relative to the series reference video and the platform reference video based on positions of the series local similar clip and the platform global similar clip.

公开(公告)号：US20240187729A1

公开(公告)日：2024-06-06

申请号：US18440814

申请日：2024-02-13

申请人： Axon Enterprise, Inc.

发明人： Michael J. BOHLANDER ,  Raymond T. FORTNA ,  Anthony G. HUANG ,  Jeffrey P. JOLMA ,  Aerianna K. DELUCA ,  Julianne C. WEISS

IPC分类号： H04N23/661 ,  G06F16/735 ,  G08B13/196 ,  H04N5/77 ,  H04N23/63 ,  H04W76/50

CPC分类号： H04N23/661 ,  G06F16/735 ,  G08B13/19654 ,  H04N5/77 ,  H04N23/63 ,  H04W76/50

摘要： A method of automatic activation of a responder camera to begin capturing a video can be performed by a computing device. The computing device receives an indication of a location or an event. The computing device determines a geographic area associated with the location or event. The computing device receives a dispatch acknowledgement from a responder, where the dispatch acknowledgement indicates that the responder is at the geographic area or that the responder is en route to the geographic area. The computing device automatically sends a camera activation signal to a responder camera associated with the responder in response to receiving the dispatch acknowledgement from the responder. The responder camera is configured to begin capturing a video in response to receiving the camera activation signal.

公开(公告)号：US11995412B1

公开(公告)日：2024-05-28

申请号：US18482828

申请日：2023-10-06

申请人： Armada Systems, Inc.

发明人： Pragyana K. Mishra

IPC分类号： G06F40/40 ,  G06F16/732 ,  G06F16/735 ,  G06V10/77 ,  G06V20/40 ,  G06V20/70

CPC分类号： G06F40/40 ,  G06F16/7343 ,  G06F16/735 ,  G06V10/77 ,  G06V20/46 ,  G06V20/49 ,  G06V20/70

摘要： Disclosed are systems and methods that convert digital video data, such as two-dimensional digital video data, into a natural language text description describing the subject matter represented in the video. For example, the disclosed implementations may process video data in real-time, near real-time, or after the video data is created and generate a text-based video narrative describing the subject matter of the video. In addition, the disclosed implementations may also support a question and answer session in which a user may submit queries about the subject matter of one or more videos and the disclosed implementations will present natural language responses based on the subject matter of the video and any corresponding context.

公开(公告)号：US11966441B2

公开(公告)日：2024-04-23

申请号：US18164917

申请日：2023-02-06

申请人： CareerAmerica, LLC

发明人： Benjamin Beck ,  Kevin O'Shea ,  Timothy Kuminecz

IPC分类号： G06F16/9032 ,  G06F3/0482 ,  G06F16/735 ,  G06F16/9038 ,  H04L51/02 ,  H04L51/08

CPC分类号： G06F16/90328 ,  G06F3/0482 ,  G06F16/735 ,  G06F16/90332 ,  G06F16/9038 ,  H04L51/02 ,  H04L51/08

摘要： Methods, systems, and computer-readable media provide a real-time Q&A interface, such as an online chatbot, either standing alone or as a live agent assistant, with predicative Q&A and resource suggestions. In one embodiment, the real-time Q&A interface uses data extracted from a user inquiry to identify and display a primary response, identify suggested inquiries from a knowledgebase and provide a user-selectable suggested inquiries indicator, and identify suggested content items from related content libraries or webpages and provide user-selectable suggested content item indicators. In one embodiment, the suggested content items include related videos and links to webpages with related content.

公开(公告)号：US20240106973A1

公开(公告)日：2024-03-28

申请号：US18532784

申请日：2023-12-07

申请人： Cisco Technology, Inc.

发明人： Nathaniel Webster Storer

IPC分类号： H04N5/272 ,  G06F16/735 ,  G06F16/738 ,  G06T7/194 ,  G06T7/215 ,  G06T7/254 ,  G06T7/50

CPC分类号： H04N5/272 ,  G06F16/735 ,  G06F16/738 ,  G06T7/194 ,  G06T7/215 ,  G06T7/254 ,  G06T7/50 ,  G06F3/0482

摘要： Systems and methods provide for optimizing video review using motion recap images. A video review system can identify background image data of a video clip including an amount of motion satisfying a motion threshold. The video review system can generate foreground mask data segmenting foreground image data, representing a moving object in the video clip, from the background image data. The video review system can select a set of instances of the moving object represented in the foreground image data. The video review system can generate a motion recap image by superimposing the set of instances of the moving object represented in the foreground image data onto the background data.