Session-based recommendation system, method and device and storage medium

Abstract

The invention discloses a session-based recommendation system, method and device and a storage medium. The system comprises a session layer network, a user long-term preference memory unit and a userlayer network. The session layer network is realized based on a GGNN network model, a target session is decomposed into a plurality of sub-graph matrixes which are used for model training, and the information of the target session is mapped to the user long-term preference memory unit; the user long-term preference memory unit records the long-term preference of the user in the target session andfeeds back user preference information to the user layer network; the user layer network is realized based on a GRU cyclic network model, the preference changes of users in different sessions are tracked through state vectors, and the preference change information is fed to the session layer network. According to the method, the improved GGNN dual-cycle network model is applied to the recommendation system, the evolution rule of the user among multiple sessions can be learned, the relation among more articles can be found, and the recommendation effect of the recommendation system is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, and more specifically, to a session-based recommendation system, method, device and storage medium. Background technique [0002] Recommender system is an effective tool to solve information overload, aiming to capture user's interests to provide personalized recommendations. In recent years, the research and application of session-based recommender systems has received more and more attention in the recommender system research field. The session refers to the interaction between the user and the site within a given period of time. The main advantage of using the session log for recommendation is that it can infer the preferences of new users or anonymous users. [0003] The existing research on session-based recommendation algorithms is mainly divided into two categories. The first is a traditional session-based recommendation algorithm, which includes algorithms based on colla...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the present invention provides a session-based recommendation system, method, device and storage medium to solve the technical problem that the current session-based recommendation system has a poor recommendation effect

Images