Video recommendation method and system

Abstract

The invention belongs to the field of data processing, and provides a video recommendation method and system. The method comprises the following steps of: establishing a relationship between users and videos according to score data of the users; mining cluster center points according to the relationship between the users and the videos, establishing association between a user cluster center and the videos so as to carry out a collaborative filtering algorithm on the basis of all the cluster center points and then obtain a recommendation result; and recommending a video to an appointed user according to result obtained by the collaborative algorithm. Through the collaborative filtering algorithm on the basis of all the cluster center points, the problem that the existing collaborative filtering algorithm encounters sparse features is overcome, and the recommendation correctness and the ability of being adapted to large-scale data are improved.

Description

technical field [0001] The invention belongs to the field of data processing, and in particular relates to a video recommendation method and system. Background technique [0002] At present, the personalized recommendation system has been widely used in the recommendation of goods and content such as books, papers, music and movies, and the internal structure of the personalized recommendation system has also undergone tremendous changes. The existing recommendation method is to generate a personalized recommendation list based on the user's interests and hobbies on different items, and recommend objects such as videos, books, and commodities that the user has never touched to the user. [0003] In academia, many researches on personalized recommendation rely on collaborative filtering methods. The idea of ​​collaborative filtering is mainly divided into two types: user-based collaborative filtering and item-based collaborative filtering. The biggest difference between the ...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present invention provide a video recommendation method and system to better deal with the data sparsity problem encountered by existing video recommendation systems, thereby recommending videos to users more accurately

Images