A multi-user-based video recommendation method and device

Abstract

Embodiments of the present invention provide a multiuser-based video recommendation method and apparatus, favorite videos can be recommended for each user of multiple users according to demand and interest of each user, and recommendation accuracy can be improved. The method comprises the steps of calculating first similarity and second similarity between any two videos according to video information and preset user operation type weights; obtaining comprehensive similarity between the any two videos according to the first similarity and the second similarity between the any two videos; clustering the videos according to the comprehensive similarity between the any two videos, and obtaining a plurality of interest points; counting the interest points to which history operation videos of each user belong in a divided time period according to video history operation information of the users; and generating a recommendation list for each user according to distribution of the interest points.

Description

technical field [0001] The present invention relates to the technical field of recommendation, in particular to a multi-user-based video recommendation method and device. Background technique [0002] With the development of information technology and the Internet, people have gradually entered the era of information overload from the era of information scarcity, and the recommendation system came into being. The recommendation system is either based on the video content or the user's historical behavior records to find interesting videos outside the known scope of the user to expand their viewing experience. [0003] Existing recommendation systems usually make recommendations for a single device and a single user, and multiple users may be involved in a single device. Take TV as an example. In a family, there are usually multiple users who watch TV, and their viewing interests are different in different time periods. Each member will actively choose related videos to watc...

AI Technical Summary

Problems solved by technology

Four members of the same family share a TV and mark it as the same user in the history of the recommendation system. Then, the recommendation system will recommend similar videos such as action movies, romance movies, Peking opera, and cartoons at the same time, which will lead to The recommendation results for each family member are mixed with a large number of useless videos, resulting in the inability to make recommendations based on the interests and hobbies of each family member, the recommendation accuracy is not high, and the user experience is poor

Images