Video recommendation method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to a video recommendation method and apparatus, an electronic device, a storage medium and a program product. The method comprises the steps of obtaining video vectors of a plurality of candidate videos and a user vector of a target user; according to a plurality of historical videos watched by the target user, obtaining a historical sequence of the target user formed by video vectors of the plurality of historical videos; the user vector of the target user and the historical sequence are input into a first neural network, a personalized sequence of the target user is obtained, and the personalized sequence of the target user comprises the ratio of the interest of the target user in each historical video to the total interest of the target user in the multiple historical videos; and inputting the video vectors of the plurality of candidate videos and the personalized sequence of the target user into a video recommendation system to obtain a recommended video of the target user determined from the plurality of candidate videos. The personalized sequence disclosed by the invention can reflect the interest distribution of the user in the historical sequence, so that the video which better conforms to the interest distribution of the user can be recommended based on the personalized sequence.

Description

technical field [0001] The present disclosure relates to the technical field of video recommendation, and in particular, to a video recommendation method, apparatus, electronic device, storage medium and program product. Background technique [0002] The video recommendation system predicts the user's interest and preference for the candidate video according to the characteristics of the candidate video, the characteristics of the historical videos that the user has watched, etc., so as to recommend the video for the user. In the related art, when a video recommendation system adopts the features of historical videos watched by a user, the features of multiple historical videos are usually summed globally with the same weight, so that the summed video features represent the user's interest preference. [0003] However, each user may have different video viewing habits. For example, user A likes to watch similar types of videos repeatedly, while user B refuses to watch simila...

AI Technical Summary

Problems solved by technology

[0003] However, each user may have different habits of watching videos. For example, user A likes to watch similar types of videos repeatedly, while user B rejects repeated viewing of similar types of videos.

Therefore, user A will tend to watch videos similar to "top videos in history", and user B will be less interested in videos similar to "top videos in history"

However, the global sum of the features of multiple historical videos with the same weight does not consider the distribution of user interests. Therefore, the accuracy of video recommendation for users needs to be improved.

Images