Knowledge graph construction method and device based on video subtitles, and computing equipment

Abstract

Embodiments of the invention relate to the technical field of video processing, and disclose a knowledge graph construction method and device based on video subtitles, and computing equipment. The method comprises the following steps: acquiring a video entity uploaded by a user, and extracting video subtitles according to the video; acquiring keywords of the video entity according to the video entity and the video subtitles to form a keyword group; and transmitting a data set formed by a video entity identifier, the video entity name and the keyword group to a server side so as to obtain an entity relationship between the video entity and other video entities in the knowledge graph according to the keyword group, and constructing a new knowledge graph. Through the above mode, the class and the theme of the video can be accurately positioned, accurate video classification data can be provided, accurate video association data can be provided, and video recommendation capability can be provided.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of video processing, and in particular to a video subtitle-based knowledge map construction method, device, and computing equipment. Background technique [0002] There are three commonly used video relationship methods for existing video recommendation, public opinion analysis and other services: 1) Classify according to the keywords, video titles and other information provided by the video submitter, when the user browses, searches, watches or collects similar keywords , video title, the user’s preference weight will be adjusted, and then the user preference model will be updated, or the public opinion model will be updated based on information such as real-time hotspots or rising hotspot videos in real time. When recommending videos to users, the user preference model and public opinion model are used to calculate the categories / keywords that users are most interested in at present, ...

AI Technical Summary

Problems solved by technology

Due to the above data problems, the follow-up results are biased or wrong, which will cause unforeseen results in actual use, such as pushing inappropriate content to children, related videos that cannot arouse user interest and lead to user loss, grasping hot spots of public opinion Mistakes cause social problems, etc.

[0004] In addition, in the existing technology, all computing processes are performed on the server side. When large-volume, high-concurrency user behavior occurs, it will bring a lot of operating pressure to the background, which needs to test the computing power of the background server, which will increase the user's overhead. Great possibility to affect user perception

Images