Sequence recommendation method fusing dynamic knowledge graph

Abstract

The invention designs a sequence recommendation method fusing a dynamic knowledge graph. The item sequence of the user in the latest session is utilized to predict the next item which is possibly interacted by the user, so that the short-term preference of the user is better captured according to the item sequence in the session. The feature representation of the item sequence and the operation sequence is learned by adopting a gating graph neural network and a recurrent neural network respectively; and meanwhile, related project knowledge (such as commodity brands, rating, categories and the like) is utilized to construct a dynamic knowledge graph, a dynamic knowledge graph method is fused, a graph convolutional network (GCN) is adopted for modeling in the time dimension to learn embedding of nodes, and parameters (weight matrixes) in the graph convolutional network are evolved by using long short-term memory (LSTM) so as to capture the dynamic state of a graph sequence, therefore, the next interaction item of the user can be predicted more effectively.

Description

technical field [0001] The present invention designs a method for sequence recommendation, and specifically relates to the method of utilizing neural network learning item embedding and operation embedding, and integrating dynamic knowledge maps as auxiliary information for sequence recommendation. Background technique [0002] The main challenge of recommender systems is how to learn effective user and item representations from historical interaction information, so as to better describe user preferences. Traditional algorithms such as collaborative filtering that mine user or item similarity based on historical behavior are difficult to meet business needs in some complex scenarios. Since a lot of user and item information has a graph structure, and graph neural networks are good at representation learning, some works have applied graph neural networks to recommender systems. Content-based recommender systems and collaborative filtering-based recommender systems usually m...

AI Technical Summary

Problems solved by technology

Most of the current knowledge graphs focus on static knowledge graphs, ignoring time information, but a lot of structured knowledge is only valid within a specific period of time, and the evolution of facts follows a time sequence

Images