Recommendation system based on non-sampling collaborative knowledge graph network

Abstract

The invention provides a recommendation system based on a non-sampling collaborative knowledge graph network. The recommendation system comprises an embedding module which is set to obtain an initial embedding vector of a triple in a knowledge graph; a non-sampling knowledge graph convolution module which is set as a single-layer convolution network comprising a plurality of linear aggregators, and is used for performing non-sampling pre-calculation on an initial embedded vector to obtain deep information of a triple, and combining the embedded vector and the deep information as an updated embedded vector; a cooperative propagation module which is set to simultaneously encode cooperative signals in user and project interaction as initial preferences of a user and a project, and is combined with the updated embedded vector to serve as an input vector of the prediction module; a prediction module which is configured to obtain a recommendation result according to the input vector. According to the method, only by designing a relatively complex propagation matrix and pre-calculation operation, the performance which is not worse than that of a depth model, the speed is higher, and a more accurate prediction result is obtained.

Description

[0001] technology neighborhood [0002] The invention relates to the technical field of recommendation methods, in particular to a recommendation system based on a non-sampling collaborative knowledge graph network. Background technique [0003] The recommendation system uses e-commerce websites to provide customers with product information and suggestions, to help users decide what products to buy, and to simulate salespeople to help customers complete the purchase process. Personalized recommendation is to recommend information and products that the user is interested in based on the user's interest characteristics and purchase behavior. With the continuous expansion of the scale of e-commerce and the rapid growth of the number and types of commodities, customers need to spend a lot of time to find the commodities they want to buy. This process of browsing a large amount of irrelevant information and products will undoubtedly cause consumers who are submerged in the problem...

AI Technical Summary

Problems solved by technology

However, the introduction of GNN also faces the following problems: (1) The exponentially increasing number of nodes in the process of information dissemination leads to huge memory and time costs

However, the sampling operation may introduce errors in the optimization process

(2) Inherent problems such as gradient disappearance and feature smoothing in the deep graph neural network architecture make model training more difficult

Although some recent work has shown that these problems can be improved to some extent, extensive experiments have demonstrated that depth often does not bring significant benefits.

Images