Video recall method and device, electronic equipment and storage medium

Abstract

The invention relates to a video recall method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to a video obtaining request sent by target equipment, and detecting whether the target equipment authorizes to obtain application program information on the target equipment, wherein the platform account of the target equipment is an account of which the video interaction behavior occurring on the current platform does not meet a preset condition; when the target equipment authorizes to acquire the application program information on the target equipment, acquiring target application program information of an installed application program in the target equipment; and at least based on the target application program information, screening a video set matching the platform account from a video library, with the screened video set being used for determining a video sent to the target equipment.

Description

technical field [0001] The present disclosure relates to the field of video recall, in particular to a video recall method, device, electronic equipment and storage medium. Background technique [0002] In a video playback application, recommending videos that a user is interested in targetedly for a target device can effectively increase the playback rate of the recommended video. Before recommending videos for the target device, it is necessary to determine the video set in the video library through video recall, and then filter out the videos sent to the target device from the video set. [0003] In related technologies, recall methods such as behavioral recall, visual recall, and semantic recall usually require historical data such as the viewing records of the target device’s logged-in platform account to complete video recall. When historical data does not exist or cannot be obtained, it is often difficult to know the viewing preferences of users corresponding to the ...

AI Technical Summary

Problems solved by technology

[0003] In related technologies, recall methods such as behavioral recall, visual recall, and semantic recall usually require historical data such as viewing records of the target device's logged-in platform account to complete video recall. When historical data does not exist or cannot be obtained, it is often difficult to know the viewing preferences of users corresponding to the target device, resulting in poor accuracy of video recall and low user retention rate

In addition, for semantic recall, this recall method also needs to be based on metadata information highly semantically related to the video to be recalled, which requires high video information in the video library, so the recall logic is more complicated, and the large amount of calculations leads to recall efficiency. lower

Images