Item recommendation method, system and device based on implicit feedback

Abstract

The invention discloses an implicit feedback-based article recommendation method, system and device. The method comprises the following steps of: constructing an information matrix and an information network according to information between a user and an article and information between articles; learning a user implicit factor vector, an article implicit factor vector, an article auxiliary feature vector and a user auxiliary feature vector according to the information matrix and the information network; and according to the user implicit factor vector, the article implicit factor vector, the article auxiliary feature vector and the user auxiliary feature vector, constructing a prediction vector for prediction, and generating a recommended article. The system comprises a construction module, a learning module and a prediction module. The device comprises a memory and a processor used for executing the implicit feedback-based article recommendation method. By using the method and the device, article recommendation is simply and accurately realized. The article recommendation method, system and device based on implicit feedback can be widely applied to the field of article recommendation.

Description

technical field [0001] The present invention relates to the field of item recommendation, in particular to an item recommendation method, system and device based on implicit feedback. Background technique [0002] With the rapid development of information technology, the information on the Internet is increasing exponentially, and users on the Internet are gradually facing the serious problem of "information overload", that is, it is often difficult for users to effectively find the content they are interested in from the massive amount of information. As an effective method to solve the problem of "information overload", the recommendation system has attracted extensive attention from both academia and industry. It has not only become a hot spot in academic research, but also has been widely used in various Internet platforms. [0003] Commonly used methods in recommendation systems include collaborative filtering recommendation methods and content-based recommendation meth...

AI Technical Summary

Problems solved by technology

[0003] Commonly used methods in recommendation systems include collaborative filtering recommendation methods and content-based recommendation methods. Collaborative filtering recommendation methods are implemented using historical interaction information of users. However, in real life, users often rarely actively rate or evaluate items. Therefore, collaborative filtering recommendation methods Faced with serious "cold start" and "data sparse" problems; content-based recommendation methods need to extract effective features from the original content, which is difficult

Images