Text-driven AI-assisted short-form video creation in an ecommerce environment

    公开(公告)号:US12100028B2

    公开(公告)日:2024-09-24

    申请号:US18528850

    申请日:2023-12-05

    摘要: Disclosed embodiments describe text-driven AI-assisted short-form video creation. Text from a website is extracted to generate extracted text. Possible summary sentences are formed from the extracted text. The forming is based on natural language processing. The summary sentences are ranked according to an engagement metric. Summary sentences from the possible summary sentences are picked based on a threshold engagement metric value. A list of video scenes is generated based on the summary sentences. Each video scene is associated with a summary sentence. A media asset from a media asset library is chosen for each video scene within the list of video scenes. The choosing is accomplished by machine learning. The list of video scenes, including the media asset that was chosen for each video scene, is compiled into a short-form video. Media is extracted from the website included into the short-form video. The compiling includes a dynamically generated image.

    Method and apparatus for providing user interface for video retrieval

    公开(公告)号:US12045281B2

    公开(公告)日:2024-07-23

    申请号:US17985115

    申请日:2022-11-10

    申请人: Twelve Labs, Inc.

    摘要: Provided is a method of providing a user interface for video retrieval performed by a computing device, the method including: receiving a search query, providing a search result interface displaying at least one search video content and search section searched by the search query, wherein the search video content and the search section are related with at least one of a plurality of video semantic search attributes corresponding to the search query, and providing a timeline view interface for the search video content when it is determined to display the search result interface according to a timeline view mode, wherein the timeline view interface has a visual characteristic indicating the degree of relevance to at least one of the plurality of video semantic search attributes corresponding to the search query.

    SYSTEMS AND METHODS FOR IDENTIFYING WHETHER TO USE A TAILORED PLAYLIST

    公开(公告)号:US20240214652A1

    公开(公告)日:2024-06-27

    申请号:US18532114

    申请日:2023-12-07

    申请人: Rovi Guides, Inc.

    发明人: Reda Harb

    摘要: Systems and methods are provided herein for identifying a playlist of highlights to use for refreshing a user on a plot related to a media asset the user has requested to access based on how long it has been since the user last saw related programming. The media guidance application may receive a request from a user to access a media asset and may determine whether the user previously consumed a related media asset to the media asset. The media guidance application may determine whether a period of time between receiving the request and a time when the user previously consumed the related media asset exceeds a threshold period of time. If the period of time does not exceed the threshold, the media guidance application may play back a predefined playlist of highlights, and if it exceeds the threshold, the media guidance application may play back a customized playlist of highlights.