A knowledge graph processing method and device for commodity recommendation

Abstract

The embodiment of the invention discloses a knowledge graph processing method and device for commodity recommendation, relates to the technical field of Internet, and can construct a knowledge graph between a commodity and a user. The method includes: according to the initial user vector and the initial commodity vector, carrying out training and learning on a first neural network model, and obtaining a vector result of a hidden layer in a calculation result of the first neural network model and taking the vector result as vector representation of a user and vector representation of a commodity; Calculating the distance between the vector representation of the user and the vector representation of the commodity, and taking the calculated distance as the similarity; Constructing a second neural network model by using the initial user vector representation and the initial commodity vector representation, and taking a vector result of a hidden layer in a calculation result of the second neural network model as a neighborhood vector representation of a commodity; Calculating the relevancy between the commodities according to the obtained neighborhood vector representation; And constructing a knowledge graph between the user and the commodity.

Description

technical field [0001] The present invention relates to the technical field of the Internet, in particular to a knowledge map processing method and device for product recommendation. Background technique [0002] As a method of representing entities or concepts and the relationship between entities / concepts, knowledge graphs have many applications in search, natural language processing, question answering and other fields, and their applications in retail or e-commerce are still in their infancy. In the current e-commerce field, knowledge graph-related technologies mainly focus on how to extract product / user tags, and directly apply them to the search or recommendation fields through the newly extracted tag features. [0003] In the field of e-commerce, due to the need to deal with massive and real-time changing data, the main research in the industry is how to train the labels of knowledge graphs, or how to extract labels from data sources such as pictures and web pages. H...

AI Technical Summary

Problems solved by technology

However, the processing scheme after label extraction is rarely studied, and the association relationship between labels is usually maintained manually.

However, limited by labor costs and data volume, there is no systematic quantitative representation scheme for product / user systems, and it is difficult to achieve relationship extraction that serves retail relationships.

[0004] The development of knowledge graph technology in the field of e-commerce retail is slow, and the scope of use is not large

Images