A user similarity-based sparse data collaborative filtering recommendation method

Abstract

The invention provides a user similarity-based sparse data collaborative filtering recommendation method and mainly aims to solves the problems in the prior art that the calculation of the values of similarity between users is in accurate for sparse data and further the recommendation quality is influenced. The method comprises the steps of (1) establishing a sparse matrix for item scores from users; (2) calculating the overall situation similarity between any two items; (3) calculating the local similarity between any two user scores; (4) calculating the similarity between any two users; (5) predicting scores; (6) generating a recommendation list; (7) completing collaborative filtering item recommendation for all the users. Experimental simulation results show that for sparse data sets, the method has the advantages of guaranteeing higher accuracy of the similarity between users, improving the recommendation quality and better meeting user requirements compared with conventional collaborative filtering recommendation methods.

Description

technical field [0001] The invention belongs to the field of physics technology, and further relates to a sparse data collaborative filtering recommendation method based on user similarity in the field of item recommendation technology. The present invention can calculate the similarity between users according to the scoring information of items by users, and then select a set of neighboring users for the user according to the similarity, thereby discovering the points of interest of the user, thereby guiding the user to find the items they need, and bringing the user Recommend items of interest to users, and solve the problem of personalized recommendation for users. Background technique [0002] With the further popularization of the Internet, the problem of information overload is becoming more and more serious. How to quickly and effectively obtain the information you are interested in from the massive amount of information has become an urgent problem to be solved. Fac...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it only uses the common rating item information between users when calculating the similarity between users. When the data is relatively sparse, the calculation of similarity is inaccurate, which will affect the final recommendation quality.

Although this method utilizes all the rating information between users, the inaccuracy of calculating the global similarity between items only by using the Bhattacharyya coefficient can be further improved, and it is inaccurate to only use the traditional similarity index when calculating the local similarity of user ratings. Therefore, it affects the calculation of user similarity and affects the final recommendation effect.

Images