Social recommendation method for dynamic fusion of social information

Abstract

The invention relates to a social information dynamic fusion socialized recommendation method, which comprises the following steps of: receiving a commodity recommendation request of a user, and generating a short-term interest vector of the user according to an interaction list of the user; meanwhile, obtaining an interaction list of friends of the user by utilizing social information of the user, and generating a short-term interest vector of the friends of the user; the short-term interest vectors of the users being fused with the short-term interest vectors of the friends, and dynamic user interest features fused with short-term social information are generated; and meanwhile, the short-term interest vector of the user is fused with the long-term interest vector of the friend to generate static user interest characteristics fused with long-term social information, and finally, the dynamic user interest characteristics and the static user interest characteristics are combined to generate final user interest characteristics at the current moment. According to the technical scheme, the problem of data sparseness in the recommendation method is relieved, and the time information of article interaction of the user is fully applied, so that the recommendation effect is improved.

Description

technical field [0001] The invention relates to the technical field of social recommendation, in particular to a social recommendation method for dynamic integration of social information. Background technique [0002] With the rapid development of science and information technology, society has entered a highly informatized era. The rapid development of the Internet and the emergence of the Internet of Things have made the information in the network grow exponentially. Due to the limited energy of users, they often feel helpless in the face of the data impact brought by the era of big data, and more and more energy is required to find useful information on the Internet, resulting in the so-called "information overload" problem. [0003] The emergence of search engines and recommendation systems provides very important technical means to solve the problem of "information overload". For search engines, users need to input query keywords, and search engines provide informatio...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a social recommendation method for dynamic fusion of social information, which alleviates the problem of sparse data sets required by existing collaborative filtering and matrix decomposition algorithms by introducing user social relations, and makes social recommendation more time-effective sex

Images