Collaborative recommendation model construction method based on knowledge graph preference propagation

Abstract

A collaborative recommendation model construction method based on knowledge graph preference propagation comprises the following steps: (1) performing knowledge modeling by using an ontology modeling tool, extracting entities and relationships to obtain a triple, and constructing a domain knowledge graph; (2) obtaining multi-layer preferences of the user through the preference propagation model, and calculating vector representation of the user preferences according to the multi-layer preferences of the user; (3) learning the vector representation of the article based on the user-article interaction matrix, and performing dot product operation on the preference vector representation of the user and the implicit vector representation of the article to calculate the click probability of the user on the article; and (4) recalling articles interested by the user according to the click probability, comparing a recall result with a user interaction list, and performing descending sorting after excluding the articles operated by the user to obtain a recommendation list. According to the recommendation model provided by the invention, the path structure information of the knowledge graph can be fully utilized, and the interpretability and diversity of recommendation results are improved.

Description

technical field [0001] The invention relates to the fields of knowledge graph, machine learning, personalized recommendation, etc., and specifically provides a collaborative recommendation model construction method based on knowledge graph preference propagation. Background technique [0002] The rapid development of Internet technology has brought a lot of convenience to people's work and life, but it has also brought about the problem of information overload. Recommendation technology can provide users with personalized services and solve the problem of information overload by connecting users and items. [0003] Traditional recommendation technology is mainly divided into content-based recommendation technology, collaborative filtering-based recommendation technology and hybrid recommendation technology. Content-based recommendation technology uses historical behavior content to recommend similar objects for users by analyzing the discrete features of purchased and evalu...

AI Technical Summary

Problems solved by technology

[0009] In order to overcome the problems of data sparsity and cold start in traditional recommendation algorithms, the present invention introduces knowledge graph into recommendation, and proposes a collaborative recommenda

Images