Recommendation method and system based on knowledge graph and graph convolutional network

A knowledge graph and convolutional network technology, which is applied in the field of recommendation methods and systems based on knowledge graphs and graph convolutional networks to ensure prediction, improve performance, and enhance user representation.

Active Publication Date: 2021-05-25
NORTHEAST NORMAL UNIVERSITY
View PDF8 Cites 3 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
  • Recommendation method and system based on knowledge graph and graph convolutional network
  • Recommendation method and system based on knowledge graph and graph convolutional network
  • Recommendation method and system based on knowledge graph and graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040]Such asfigure 1 It is a recommended method provided by the recommendation system based on knowledge map and graph volume network, which includes the following sub-steps:

[0041]Step S110: Get high-order embedding representation of the user.

[0042]Among them, it is assumed that the two users have interactions with the same item, indicating that these two users have higher dependence, so the weights of user relevance are large. The user's item interaction is constructed as a diagram, and the user features are constantly aggregated using the map volume network, and finally obtain the high order representation of the user.

[0043]Specifically, such asfigure 2 As shown in the user's item interactive matrix y∈RM × n As the input; then extracting the user's Layer 0 user representation in the user's item interactive matrix, after the multilayer map volume network is polymerized, the high-order user representation is obtained, and the feature embedded representation of all users is generate...

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 recommendation method and system based on a knowledge graph and a graph convolutional network. The recommendation method based on the knowledge graph and the graph convolutional network specifically comprises the following steps of obtaining a high-order embedded representation of a user; according to the high-order embedded representation of the user, obtaining an article embedded representation; and predicting the user according to the obtained high-order embedded representation and the article embedded representation of the user. According to the application, user representation can be enhanced, and article features are aggregated and propagated through different relation weights in the knowledge graph, so that remote interests of users are explored.

Description

Technical field[0001]The present application relates to the field of large data, and more particularly to a recommendation method based on a knowledge map and a map volume network and its system.Background technique[0002]In the prior art, the recommended system has become the most important way to overcome the information overload problem in the information explosion era. How to accurate, quickly predict the hobbies of users, recommend the most important items most important to the user, not only important research topics in the scientific research It has also gradually become a core technology that is successful in various e-commerce fields in real life. In numerous recommendations, collaborative filtration methods are predicted from user historical data to predict user preferences, have validity and universality, and are received by many researchers. However, the collaborative filtering method cannot model auxiliary information, such as item properties, user profiles, contexts, so...

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): 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
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap