A kind of personalized video recommendation method and system

Abstract

The invention discloses a personalized video recommendation method and system, wherein the method includes: S1, constructing a user vector and a video vector, and storing the vector in Faiss; S2, judging whether the user needs to conduct interest exploration, and if so, executing the steps S3, if no, perform step S4; S3, update the user vector based on the user vector of the user and the IDs of his friends or users in the same region; S4, perform video recall in Faiss based on the user vector, and generate a recommended video for the user. The present invention can maintain high recommendation efficiency while avoiding the fixed problem of the recommended content type in the video recommendation process. At the same time, the recommendation is made based on the social network and its own characteristics, and the recommendation effect is good.

Description

technical field

[0001] The invention relates to the field of content recommendation, in particular to a personalized video recommendation method and system. Background technique

[0002] With the popularity of various applications, enterprises can collect more and more comprehensive user data. How to use this data to increase revenue is a problem that enterprises will face. The most common way is personalized recommendations, especially in e-commerce, video sites or other content platforms. Recommendation based on social network is a commonly used recommendation method. People with the same or similar interests are more likely to like the same content. Therefore, the recommendation based on the social network is based on the content that the friends who follow them like. However, in the recommendation process based on the social network, only the social relations among users are considered, but the characteristics of the users themselves are not considered, and the prefere...

Images