Personalized recommendation method and system integrating implicit feedback and user social status

Abstract

The invention discloses a personalized recommendation method and system integrating implicit feedback and user social status. The method comprises the steps: determining a user project interaction matrix according to implicit feedback information; according to the user project interaction matrix, calculating social status values of the user in each field in combination with implicit feedback information and social network information; calculating the trust degree between the users according to the social network information; performing matrix decomposition according to the social position value and the trust degree to obtain a user feature matrix and a project feature matrix; constructing a pseudo scoring matrix according to the user feature matrix and the project feature matrix; And performing user recommendation through the pseudo scoring matrix. According to the method, the matrix is constructed by combining the implicit feedback data and the social position value of the user, the matrix scoring accuracy is improved, and then the recommendation reliability and the recommendation quality are improved; In addition, the recommendation process is optimized by combining the credibility between the users, the reliability of the recommendation result is further improved, and the method can be widely applied to the technical field of computers.

Description

Technical field [0001] The invention relates to the field of computer technology, in particular to a personalized recommendation method and system integrating implicit feedback and user social status. Background technique [0002] With the rapid development of social technology, the era of big data has arrived, and information overload exists in every aspect of life. In order to help users quickly and effectively obtain the information they really need, recommendation systems are increasingly developed. [0003] However, most of the current recommendation systems are based on display feedback. User feedback data is the key to constructing the recommendation system. Recommendations based on user ratings and other display feedback information often affect the quality of recommendations due to the sparseness of the rating matrix. The implicit feedback with rich information is easier to obtain, and can reflect the user's attitude more naturally, which can effectively alleviate the pro...

AI Technical Summary

Problems solved by technology

However, recommendations based on social networks are generally based on the assumption that user preferences are influenced by the preferences of trusted users, but do not take into account that users have different social status in different fields, that is, users influence others in different degrees in different fields and Influenced by others, existing recommendation methods are not accurate and reliable enough

Images