Personalized recommendation method based on knowledge graph

Abstract

The invention discloses a personalized recommendation method based on a knowledge graph. The method has the advantages that the link relations among conceptual entities in the knowledge graph are utilized to measure the semantic association between every two optional nodes, a network representation learning method is used to obtain the representation vectors of the nodes in a network structure, and items are precisely recommended for users by calculating node similarity; the item recommendation based on knowledge graph feature learning is used for efficiently mining the entity features in theknowledge graph, user and recommendation object features can be well modelled, and multi-dimensional features are sufficiently utilized.

Description

technical field [0001] The invention relates to the technical fields of knowledge graph and machine learning, in particular to a personalized recommendation method based on knowledge graph. Background technique [0002] With the rapid development of Internet-related technologies, extensive data sharing has brought about exponential growth of data. However, it is becoming more and more difficult for users to find the information they need in the massive data. Therefore, for users, they need results that are more in line with personal preferences. Therefore, various factors jointly promote the research process of personalized recommendation technology. [0003] In traditional research on personalized recommendation, most works make rule-based recommendations based on user historical data to predict new user interests. Among them, recommendation algorithms can be divided into the following categories: content-based recommendation, association rule-based recommendation, and c...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a personalized recommendation method based on knowledge graphs for the existing personalized recommendation methods that rarely use user and recommended object features and recommend fewer feature dimensions.

Images