Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Graph neural network recommendation method integrated with label information

A neural network and label information technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as single interactive data and cold start, achieve reasonable and more accurate recommendations, and alleviate the effect of cold start problems

Pending Publication Date: 2021-10-12
ANHUI AGRICULTURAL UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a graph neural network recommendation method that incorporates label information to solve the problem of single interactive data and cold start in the prior art recommendation system based on collaborative filtering

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Graph neural network recommendation method integrated with label information
  • Graph neural network recommendation method integrated with label information
  • Graph neural network recommendation method integrated with label information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0030] Such as figure 1 As shown, a graph neural network recommendation method incorporating label information of the present invention includes the following steps:

[0031] Step 1. Construct a user-item interaction graph based on the user's historical purchase records, and an item-item association graph based on the item label, where the user and item are used as nodes in the user-item interaction graph, and the item is used as a node in the item-item association graph. node.

[0032] Step 2, such as figure 2 As shown, the feature representation of nodes in the user-item interaction graph is learned by using the attention network in the first graph. The learning process of the attention network in the first graph is as follows:

[0033] Step 2.1. Calculate the attention score of the neighbor node j of any node i in the user-item interaction graph ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a graph neural network recommendation method integrated with label information. The method comprises the following steps: step 1, constructing a user-article interaction graph and an article-article association graph; 2, learning feature representation of nodes in the user-article interaction graph; step 3, learning feature representation of nodes in the article-article association graph; step 4, constructing a multi-layer perceptron to predict an interaction preference value of the user to the article by utilizing the feature representation of the nodes in the user-article interaction graph and the feature representation of the nodes in the article-article association graph; and 5, recommending articles to the user based on the interaction preference value. Compared with a traditional recommendation method using single interaction data, the invention can carry out more reasonable and more accurate recommendation, and alleviates the cold start problem of articles to a certain extent.

Description

technical field [0001] The invention relates to the field of recommendation methods based on graph neural networks, in particular to a graph neural network recommendation method incorporating label information. Background technique [0002] With the advent of the information age, it is becoming more and more convenient for people to obtain information from the Internet. However, the explosive growth of information on the Internet has also brought the problem of information overload to users. The massive amount of information makes it difficult for users to filter and find out the information they are interested in. The emergence of recommendation systems has alleviated this type of problem. The recommendation system mines the user's preference information from the user's historical behavior, and actively recommends items that the user may be interested in, so that the user no longer needs to search for it from massive information. [0003] Traditional recommendation method...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06F18/253
Inventor 吴国栋刘玉良涂立静杨宇汪菁瑶范维成毕海娇
Owner ANHUI AGRICULTURAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com