Collaborative filtering method of simultaneously integrating social relationship and user similarity

Abstract

The invention aims at solving the problem in the prior art, and provides a collaborative filtering method of simultaneously integrating friend characteristics and similar user characteristics. The accuracy of the collaborative filtering method is improved. The method comprises the steps of obtaining a user-object scoring matrix, calculating the similarity between users through a Pearson correlation coefficient and building a user similarity matrix; obtaining a user-user relationship matrix and carrying out normalization processing on an original user-user relationship matrix to obtain a normalized user-user relationship matrix; and integrating the similar user characteristics and the friend user characteristics into the user characteristics of a probability matrix decomposition model according to the user similarity matrix and the normalized user-user relationship matrix, obtaining prediction scores of users on objects according to the probability matrix decomposition model and recommending the objects for the users according to the prediction scores. The collaborative filtering method has the beneficial technical effects that the recommending result is affected by the friend user characteristics and the similar user characteristics, and the accuracy of the collaborative filtering method is improved.

Description

technical field [0001] The present invention relates to a collaborative filtering method, in particular to a collaborative filtering method that incorporates social relations and user similarity at the same time. Background technique [0002] In recent years, as the problem of information overload in Internet products has become more and more serious, there is an urgent need to provide personalized recommendation functions in many products. However, traditional recommendation techniques only consider two entities, namely "user" and "item", while ignoring the influence of the social relationship between friends on the recommendation results. For this reason, recommendation systems that integrate social relationships have gradually attracted attention. At present, many scientific research and engineering practices have proved that the introduction of social relationships can effectively improve the accuracy and degree of personalization of recommendation systems. [0003] At ...

AI Technical Summary

Problems solved by technology

[0004] The above two types of recommendation methods that integrate social relations can only integrate social relations or user similarity information respectively, and cannot model social relations and user similarity information at the same time. In real Internet product application scenarios, user interest preferences On the one hand, it will be influenced by friends, that is, the influence of social relations

Images