A video recommendation method, device, computer equipment and storage medium

Abstract

The invention discloses a video recommendation method, device, computer equipment and storage medium; acquiring a plurality of hidden state information of a video title of a target video; fusing the plurality of hidden state information to obtain title tendency characteristic information of a video title; acquiring Image tendency feature information of the target video; multiple hidden state information and image tendency feature information are fused to obtain the target title tendency information of the video title; the title tendency feature information and image tendency feature information are fused to obtain the target image of the target image Tendency information: the target title tendency information and the target image tendency information are fused to construct the target video tendency characteristic information of the target video, and based on the target video tendency characteristic information, the target video is recommended, wherein the target video tendency characteristic of the target video can be The information is stored in the cloud server for subsequent information reading. This scheme can improve the accuracy of video recommendation.

Description

technical field [0001] The present application relates to the field of communication technology, and in particular to a video recommendation method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of information technology, the video recommendation to users has also been developed rapidly in view of the excavated user's viewing tendency and the content tendency of the video itself. In real life, cloud servers can be used to assist in mining video content. Content tendency information to recommend videos and recommend videos to corresponding users. [0003] In the process of research and practice of related technologies, the inventors of the present application found that the current mining of video tendency information is mainly to mine the tendency information through a single modal information in the video, and the accuracy of the tendency information of the mined video is Poor, can not well characterize the content ...

AI Technical Summary

Problems solved by technology

[0003] In the process of research and practice of related technologies, the inventors of the present application found that the current mining of video tendency information is mainly to mine the tendency information through a single modal information in the video, and the accuracy of the tendency information of the mined video is Poor, can not represent the content tendency of the video very well, and when making video recommendation, the accuracy of video recommendation is low

Images