Supercharge Your Innovation With Domain-Expert AI Agents!

A recommendation method and system based on knowledge graph and graph convolutional network

A technology of knowledge graph and convolutional network, applied in the recommendation method and system field based on knowledge graph and graph convolutional network, to achieve the effect of guaranteeing prediction, improving performance, and enhancing user representation

Active Publication Date: 2022-02-11
NORTHEAST NORMAL UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above methods have achieved good results in the recommendation system, due to the heterogeneity of the knowledge graph, it is still very challenging to fully exploit the inherent high-level semantic information of the knowledge graph and explore the relationship features with users.

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
  • A recommendation method and system based on knowledge graph and graph convolutional network
  • A recommendation method and system based on knowledge graph and graph convolutional network
  • A recommendation method and system based on knowledge graph and graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] Such as figure 1 It is the recommendation method provided by the recommendation system based on knowledge graph and graph convolutional network in this application, which specifically includes the following sub-steps:

[0041] Step S110: Obtain the user's high-order embedding representation.

[0042] Among them, assuming that two users interact with the same item, it indicates that the correlation between the two users is high, so the weight of user correlation is relatively large. Construct user-item interaction features into a graph, use graph convolutional network to continuously aggregate user features, and finally obtain a high-level representation of users.

[0043] Specifically, as figure 2 As shown, the user-item interaction matrix Y∈R m×n As input; then extract the user’s 0th-layer user representation map from the user-item interaction matrix, and aggregate through a multi-layer graph convolutional network to obtain a high-level user representation map, gen...

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 present application discloses a recommendation method based on a knowledge map and a graph convolutional network and a system thereof, wherein a recommendation method based on a knowledge map and a graph convolutional network specifically includes the following steps: obtaining a high-order embedded representation of a user; The high-order embedded representation of the item is obtained to obtain the embedded representation of the item; according to the obtained high-order embedded representation of the user and the embedded representation of the item, the user is predicted. This application is able to enhance user representation and propagate item features through aggregation of different relation weights in the knowledge graph, thereby exploring users' long-range interests.

Description

technical field [0001] This application relates to the field of big data, in particular, to a recommendation method and system based on knowledge graphs and graph convolutional networks. Background technique [0002] In the existing technology, the recommendation system has become the most important method to overcome the problem of information overload in the era of information explosion. How to accurately and quickly predict the user's hobbies and recommend the most desired items to the user is not only an important research topic in the field of scientific research , It has gradually become the core technology that determines the success or failure of various e-commerce fields in real life. Among many recommendation methods, the collaborative filtering method predicts user preferences from user historical data, which is effective and universal, and has attracted the attention of many researchers. However, collaborative filtering methods cannot model auxiliary information...

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 Patents(China)
IPC IPC(8): G06F16/9535G06F16/958G06F16/2455G06F16/36G06N3/04G06N3/08
CPCG06F16/9535G06F16/958G06F16/24556G06F16/367G06N3/04G06N3/08
Inventor 张邦佐张利飒蒲东兵
Owner NORTHEAST NORMAL UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com