A Collaborative Filtering Recommendation Method Combining Information Entropy Similarity and Dynamic Trust

Abstract

The invention discloses a collaborative filtering recommendation method that combines information entropy similarity and dynamic trust. The method is based on two similarity calculation methods of information entropy similarity and trust implicit similarity of score difference, and constructs a comprehensive similarity calculation model. Alleviate the problem that the similarity of cold-start users is difficult to calculate; then, comprehensively measure the scoring credibility and recommendation reliability, build direct, indirect and global trust calculation models, and reduce false recommendations from unreliable users; then, build similarity and trust Finally, evaluate the validity of the recommended user's rating, propose a trust reward and punishment strategy, dynamically update the trust neighbor set for the target user, and restrain the user from arbitrarily false ratings. Negative impact on recommended performance. The experimental results show that this method can improve the recommendation accuracy and reliability of the recommendation system, and effectively alleviate the problems of data reliability, data sparsity and cold start.

Description

Technical field [0001] The present invention relates to a personalized recommendation technique, in particular a synergistic filtering recommendation method for fusion information entropy similarity and dynamic trust. Background technique [0002] With the rapid development of information technology and social network, data resource explosion growth, information overload issues need to be resolved. In response to how to assist users from high-efficiency filtering and personalized recommendation useful information from massive data, the recommendation system came into being. At present, the recommended system can be divided into 5 categories: content based on content, collaborative filtration recommendation, knowledge-based recommendation, social recommendation and mixing recommendation. As a valid strategy for resolving information overload issues, the recommended system is in e-commerce (Amazon.com, Alibaba, etc.), social networks (Facebook, Twitter, Weibo, etc.), information re...

AI Technical Summary

Problems solved by technology

These classic recommendation algorithms provide key algorithm theories for research in this field. However, with the development of social networks and recommendation systems, the above algorithms cannot well meet the personalized recommendation needs of users. The reasons are as follows:

[0013] 1) There are random or malicious false ratings of users in the recommendation system. Most of the existing methods are based on the assumption that user ratings are authentic, and do not fully consider data reliability and recommendation effectiveness, resulting in low recommendation accuracy of the recommendation system;

[0014] 2) Trust is dynamic, and most of the existing trust calculation models describe static trust relationships, which do not fully consider the dynamic evolution of trust relationships between users, resulting in low recommendation reliability for recommendation systems

Images