User interest representation intelligent session recommendation model based on multi-attention mechanism

Abstract

To solve the problem that it is difficult to take account of user behavior diversity and item features inherent in a limited sequence of user conversation behavior, and a single model cannot make full use of favorable feature information for recommendation matching, In this paper, we propose a User Interest Representation (UIR) session recommendation model (SR-UIAM) integrating Attention Mechanism (AM). Using project information, studies project representation from a multi-dimensional and fine-grained perspective and excavates deeper relationships between users and projects. Finally, some experiments are carried out on two real open benchmark data sets, and the experimental results show that the proposed method can improve the expressiveness of the model and improve the recommendation performance to some extent.