Graph model intelligent commodity recommendation method fusing knowledge graph and user interaction

Abstract

The invention discloses a graph model intelligent commodity recommendation method fusing a knowledge graph and user interaction, and the method comprises the steps: 1, collecting the historical interaction record data of a user for a commodity, constructing a user commodity interaction matrix Y for training a recommendation model, and constructing a user commodity interaction bipartite graph; 2, collecting commodity attribute features and association features between attributes, and constructing a knowledge graph by using priori knowledge; 3, constructing a recommendation model fusing the knowledge graph and user interaction, and selecting a proper loss function to optimize model parameters and feature vectors; and 4, predicting the probability that the user interacts with the non-interacted commodities in the future by using the recommendation model, and selecting the commodity with the maximum interaction probability to recommend to the user, thereby completing a commodity recommendation task. According to the method, graph convolution operation on the knowledge graph and the interactive bipartite graph is combined, and semantic and structural information carried by the knowledge graph can be more sufficiently captured, so that a more accurate recommendation effect is realized.

Description

technical field [0001] The invention belongs to the field of data mining recommendation system based on graph convolution, and mainly relates to a product recommendation method that integrates knowledge factors of knowledge graphs. Background technique [0002] In recent years, with the rapid development of Internet technology, people have access to a large amount of data information on the Internet. However, with the gradual development of information volume, people inevitably fall into the dilemma of how to obtain information while enjoying the convenience brought by the Internet. Quickly find the part you need from a lot of information, that is, the problem of information overload. In order to solve the impact caused by information overload, personalized recommendation systems have gradually attracted extensive interest from researchers at home and abroad. , to reduce the troubles brought by a wide variety of information to users. The core of the personalized recommenda...

AI Technical Summary

Problems solved by technology

However, there are often some problems in the recommendation method based on collaborative filtering: for new users who join the system, because there is no historical record in the database, their interests and preferences cannot be excavated and personalized recommendations cannot be accurately made, which is called cold Start-up problem; due to the large increase in the number of users and the number of products, the number of products that a single user can interact with is limited, making the interaction matrix contain a large number of blank elements, which is called the data sparse problem

The embedding-based method mainly uses the graph embedding method to carry out vector modeling of various entities and associations in the map, and then expands the semantic information expressed by the original products and users. However, this method focuses on building strict semantic associations. The model often ignores the attribute information of the node itself in the knowledge graph, so that it is impossible to accurately model the user's preference for the node content attribute, resulting in a decrease in the accuracy of the recommendation; the path-based method focuses on mining the various information between users and products based on the graph. Connect the relationship, extract the path carrying high-level information and input it into the prediction model, but because the choice of the path has a great impact on the final performance, and the definition of the path requires a lot of manual operation and certain domain knowledge, in practical situations , it is difficult to get the optimal connection path, so that the role of the knowledge map in the recommendation algorithm cannot be fully utilized

The recommendation model needs to model users and products at the same time, and the existing methods usually only gather knowledge graph information on the product side. There is a certain degree of information gap between the user feature vector and the product feature vector trained by the model, which leads to model prediction. It is difficult for the function to accurately calculate the user's preference for the knowledge information contained in the product vector, which reduces the quality of the recommendation model

Images