公开(公告)号：US20240176820A1

公开(公告)日：2024-05-30

申请号：US18072614

申请日：2022-11-30

申请人： GOOGLE LLC

发明人： Ramprasad Sedouram ,  Daniel V. Klein

IPC分类号： G06F16/738 ,  G06F16/783

CPC分类号： G06F16/739 ,  G06F16/7834 ,  G06F16/7837

摘要： An example method includes presenting an item of third-party video content via a user interface, wherein the item of third-party video content is presented prior to presenting an item of primary content or is presented to interrupt the presenting of the item of primary content; providing a user-selectable option associated with an interactive summary of the third-party video content; receiving an indication that the user of the user device has selected the user-selectable option associated with the interactive summary of the third-party video content; and based on receiving the indication that the user of the user device has selected the user-selectable option associated with the interactive summary of the third-party video content: (i) ceasing, by the user device, presentation of the third-party video content, (ii) providing, by the user device, an interactive summary of the third-party video content, and (iii) presenting the item of primary content.

公开(公告)号：US11977579B2

公开(公告)日：2024-05-07

申请号：US18107724

申请日：2023-02-09

申请人： Rovi Guides, Inc.

发明人： Ashleigh Miller ,  Mario Sanchez ,  Phillip Teich ,  Carla Mack

IPC分类号： G06F16/00 ,  G06F3/04847 ,  G06F16/738 ,  G06F16/78 ,  G06Q10/0631 ,  H04N21/25 ,  H04N21/258 ,  H04N21/472 ,  H04N21/482

CPC分类号： G06F16/7867 ,  G06F3/04847 ,  G06F16/738 ,  G06Q10/0631 ,  H04N21/251 ,  H04N21/25883 ,  H04N21/472 ,  H04N21/4821

摘要： Systems and methods are disclosed herein for resolving a meaning of an ambiguous calendar entry and recommending broadcast media based on the meaning. To this end, a media guidance application may detect a calendar entry specific to a user, and determine that the calendar entry is ambiguous with respect to an associated period of time. In response to determining that the calendar entry is ambiguous with respect to the associated period of time, the media guidance application may determine characteristics of the calendar entry and the user, and compute an estimated range of time corresponding to the calendar entry based on the characteristic of the calendar entry and the characteristic of the user. The media guidance application may then generate for display a recommendation of broadcast media based on the estimated range of time.

公开(公告)号：US11972099B2

公开(公告)日：2024-04-30

申请号：US18299200

申请日：2023-04-12

申请人： Matroid, Inc.

发明人： Reza Zadeh ,  Dong Wang ,  Deepak Menghani ,  John Goddard ,  Ryan Tobin

IPC分类号： G06F3/048 ,  G06F3/00 ,  G06F3/04842 ,  G06F16/2457 ,  G06F16/738 ,  G06F16/74 ,  G06F16/783 ,  G06F18/241 ,  G06V10/764 ,  G06V20/40 ,  G11B27/34 ,  G11B27/36 ,  G06F3/0484

CPC分类号： G06F3/04842 ,  G06F3/00 ,  G06F16/24578 ,  G06F16/738 ,  G06F16/74 ,  G06F16/7837 ,  G06F18/241 ,  G06V10/764 ,  G06V20/41 ,  G11B27/34 ,  G11B27/36 ,  G06F3/0484

摘要： Described herein are systems and methods that search videos and other media content to identify items, objects, faces, or other entities within the media content. Detectors identify objects within media content by, for instance, detecting a predetermined set of visual features corresponding to the objects. Detectors configured to identify an object can be trained using a machine learned model (e.g., a convolutional neural network) as applied to a set of example media content items that include the object. The systems provide user interfaces that allow users to review search results, pinpoint relevant portions of media content items where the identified objects are determined to be present, review detector performance and retrain detectors, providing search result feedback, and/or reviewing video monitoring results and analytics.

公开(公告)号：US20240134597A1

公开(公告)日：2024-04-25

申请号：US17967714

申请日：2022-10-17

申请人： Adobe Inc.

发明人： Lubomira Assenova DONTCHEVA ,  Anh Lan TRUONG ,  Hanieh DEILAMSALEHY ,  Kim Pascal PIMMEL ,  Aseem Omprakash AGARWALA ,  Dingzeyu Li ,  Joel Richard BRANDT ,  Joy Oakyung KIM

IPC分类号： G06F3/16 ,  G06F3/0482 ,  G06F3/0484 ,  G06F16/735 ,  G06F16/738

CPC分类号： G06F3/167 ,  G06F3/0482 ,  G06F3/0484 ,  G06F16/735 ,  G06F16/738

摘要： Embodiments of the present invention provide systems, methods, and computer storage media for a question search for meaningful questions that appear in a video. In an example embodiment, an audio track from a video is transcribed, and the transcript is parsed to identify sentences that end with a question mark. Depending on the embodiment, one or more types of questions are filtered out, such as short questions less than a designated length or duration, logistical questions, and/or rhetorical questions. As such, in response to a command to perform a question search, the questions are identified, and search result tiles representing video segments of the questions are presented. Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.

公开(公告)号：US11960538B2

公开(公告)日：2024-04-16

申请号：US18142394

申请日：2023-05-02

申请人： Rovi Guides, Inc.

发明人： Ankur Anil Aher ,  Charishma Chundi

IPC分类号： G06F16/73 ,  G06F16/735 ,  G06F16/738 ,  G06F16/74 ,  G06F16/783

CPC分类号： G06F16/739 ,  G06F16/735 ,  G06F16/745 ,  G06F16/7837

摘要： Systems and methods for generating a reply to a query are provided. A query about an event in a content recording during playback of the content recording is received. A type of the event based on the query is determined. A playback position in a timeline of the content recording is determined. Based on the type of the event, an event distribution table is obtained, the table comprising one or more event identifiers and one or more corresponding occurrence times for the one or more event identifiers in the timeline of the content recording. The playback position of the content recording to the one or more occurrence times is compared. A reply to the query is generated, for aural or visual presentation, the reply being based on a result of the comparing, the reply comprising data about at least one event corresponding to the one or more event identifiers.

公开(公告)号：US20240119089A1

公开(公告)日：2024-04-11

申请号：US18537291

申请日：2023-12-12

申请人： Microsoft Technology Licensing, LLC

发明人： Ganesh ANANTHANARAYANAN ,  Yuanchao SHU ,  Shadi NOGHABI ,  Paramvir BAHL ,  Landon COX ,  Alexander CROWN

IPC分类号： G06F16/71 ,  G06F16/738 ,  G06F16/783 ,  G06V20/40

CPC分类号： G06F16/71 ,  G06F16/738 ,  G06F16/7837 ,  G06V20/40

摘要： This document relates to performing live video stream analytics on edge devices. One example determines resources available to the system, and a video analytics configuration is selected that distributes work between edge devices and cloud devices in a cascading manner, where edge device processing is prioritized over cloud processing in order to conserve resources. This example can dynamically modify the allocation of processing depending on changing conditions, such as network availability.

公开(公告)号：US11954150B2

公开(公告)日：2024-04-09

申请号：US16369142

申请日：2019-03-29

申请人： SAMSUNG ELECTRONICS CO., LTD.

发明人： Jungmin Lee

IPC分类号： 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分类号： 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

摘要： 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：US11922563B2

公开(公告)日：2024-03-05

申请号：US17826059

申请日：2022-05-26

申请人： Dapper Labs, Inc.

发明人： Donald Dundas McEroy Flavelle ,  Catherine Marzi Tedman ,  Courtney McNeil ,  Denise Cascelli Schwenck Bismarque ,  Christopher Patrick Scott ,  Alan Carr ,  Eric Yu-Yin Lin

IPC分类号： G06T15/20 ,  G06F16/71 ,  G06F16/738 ,  G06F16/78 ,  G06F16/783 ,  G06T19/20

CPC分类号： G06T15/20 ,  G06F16/71 ,  G06F16/739 ,  G06F16/783 ,  G06F16/7867 ,  G06T19/20 ,  G06T2219/2016

摘要： A system and method for creating, managing, and displaying 3D digital collectibles comprising a virtual, three dimensional, n-sided structure including a digital media file or set of digital media files representing an event rendered on a representation of at least a first surface thereof, and data relating to the event rendered on at least a second surface thereof and other content on one or more other surfaces, where the digital media file may be video clip of the event that can be played automatically via a media player associated with the display.

公开(公告)号：US11917223B2

公开(公告)日：2024-02-27

申请号：US17967204

申请日：2022-10-17

申请人： Google LLC

发明人： Cagdas Evren Gerede ,  Vlad Berindei

IPC分类号： H04N21/235 ,  G06F16/735 ,  G06F16/738 ,  G06F16/78 ,  H04N21/23 ,  H04N21/231 ,  H04N21/239 ,  H04N21/262 ,  H04N21/43 ,  H04N21/431 ,  H04N21/433 ,  H04N21/466 ,  H04N21/845

CPC分类号： H04N21/2353 ,  G06F16/735 ,  G06F16/738 ,  G06F16/7867 ,  H04N21/23 ,  H04N21/23109 ,  H04N21/235 ,  H04N21/2393 ,  H04N21/26258 ,  H04N21/43 ,  H04N21/431 ,  H04N21/4332 ,  H04N21/4668 ,  H04N21/845

摘要： Methods, systems, and media for presenting media content items belonging to a media content group are provided. In some embodiments, the method comprises: retrieving metadata associated with video content segments, wherein the metadata includes user metadata, description metadata, and time metadata; generating subsets of video content segments from the video content segments based on the user metadata, wherein each of the subsets of video content segments is grouped into media content groups by: normalizing the description metadata; determining a similarity score between the normalized description metadata for a first video content segment and a second video content segment in the subset of video content segments; and determining whether to place the each of the first and second video content segments into a media content group based on the similarity score; arranging the video content segments within each of the media content groups based on time metadata; and causing at least one of the arranged media content groups to be presented in the video window in response to receiving a request for a video content item.

公开(公告)号：US11899706B2

公开(公告)日：2024-02-13

申请号：US17390308

申请日：2021-07-30

申请人： GOOGLE LLC

发明人： Justin D. Lewis ,  Scott Tadashi Davies

IPC分类号： G06F16/435 ,  G06F16/48 ,  G06F16/438 ,  G06F16/2458 ,  G06F16/33 ,  G06F16/738

CPC分类号： G06F16/435 ,  G06F16/2477 ,  G06F16/3349 ,  G06F16/438 ,  G06F16/489 ,  G06F16/738

摘要： Systems, apparatuses, and methods for providing content using notifications with content-specific keywords are provided. In one example embodiment, a method includes identifying, by one or more computing devices, a media content item for a user of a user device. The method includes generating, by the one or more computing devices, a keyword for the user of the user device based at least in part on data associated with the media content item. The keyword is indicative of the media content item. The method includes providing, by the one or more computing devices to the user device, for display a notification indicating that the media content is available for the user. The notification includes the keyword and the keyword is viewable by the user.