A similar person recommendation method based on knowledge graph representation learning

Abstract

The present invention relates to a similar person recommendation method based on knowledge map representation learning, adopting a new design strategy, including social user information processing, representation learning model training, cluster index of character point vectors in entity relationship vectors, and similar person recommendation, wherein, The TransD representation learning algorithm is used to learn the knowledge representation of all entities and relationships in the knowledge graph, and to dig deeper into the hidden semantic information in the graph; for large-scale character point vectors, the Annoy fast calculation distance algorithm is used to cluster similar characters, Since the entity relationship vector considers the semantics in the graph, it provides a strong information support for clustering; and for the incremental update of the social knowledge graph, a representation learning recommendation algorithm is designed for periodic training to keep the freshness of the recommendation results; The whole design method can effectively improve the accuracy of character similarity detection and obtain more accurate similar character recommendation effect.

Description

technical field [0001] The invention relates to a method for recommending similar characters based on knowledge graph representation learning, and belongs to the technical field of knowledge graph representation learning. Background technique [0002] With the rise of mobile Internet, social network has become a typical product of mobile Internet, which strengthens the close communication between people, and character recommendation also plays a vital role in social network. [0003] There are some character recommendation methods in the prior art: [0004] 1. Network personalized recommendation method based on PageRank algorithm: obtain the friendship relationship between the group and its members from the web page configuration file, and establish the personal preference model of each group member. The PageRank algorithm is used to iteratively calculate the influence of group members on the group, so as to obtain the preference model of the entire group, and use this mode...

AI Technical Summary

Problems solved by technology

[0006] Nowadays, with the development of big data, the interpersonal network is getting bigger and bigger. The existing technology has low applicability for large-scale social networks. There are a lot of semantic information in the huge social network. The existing technology fails to capture the social network. Semantic connections in human beings, and the development of artificial intelligence has entered the stage of cognitive intelligence. Cognitive intelligence requires machines to learn to process human complex language and perform knowledge reasoning, which is very difficult for machines

Images