Comment recommendation method of heterogeneous graph attention neural network based on meta-learning

A neural network and recommendation method technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as less interaction and difficult data sets

Pending Publication Date: 2022-04-22
SUN YAT SEN UNIV +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] (2) Graph-based methods (for example: LightGCN, HetGNN, HGT, GAT) have made great progress in recommendation, and can easily solve the problem of triple interaction, but it is still difficult to deal with extremely sparse data sets, among which Most review nodes feel that other nodes have very little interaction

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
  • Comment recommendation method of heterogeneous graph attention neural network based on meta-learning
  • Comment recommendation method of heterogeneous graph attention neural network based on meta-learning
  • Comment recommendation method of heterogeneous graph attention neural network based on meta-learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The accompanying drawings are for illustrative purposes only and cannot be construed as limiting the patent;

[0064] In order to better illustrate this embodiment, some parts in the drawings will be omitted, enlarged or reduced, and do not represent the size of the actual product;

[0065] For those skilled in the art, it is understandable that some well-known structures and descriptions thereof may be omitted in the drawings.

[0066] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0067] Such as Figure 2-3 As shown, the present invention provides a kind of comment recommendation method based on meta-learning heterogeneous graph attention neural network, comprising the following steps:

[0068] S1: construct metadata;

[0069] S2: Perform context mining;

[0070] S3: perform personality sorting;

[0071] S4: Perform meta-learning.

[0072] In step S1, use all the i...

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 provides a comment recommendation method of a heterogeneous graph attention neural network based on meta-learning, and the method constructs original data into a required metadata mode through a meta-learning process and a graph neural network model. And constructing a relationship among three types of user-commodity-comment nodes through a designed local graph extraction algorithm, and expanding a graph attention network structure taking each user as a new task for capturing preference information of corresponding comments of the users.

Description

technical field [0001] The present invention relates to the field of recommendation systems, more specifically, to a method for recommending comments based on meta-learning heterogeneous graph attention neural networks. Background technique [0002] At present, many Internet applications provide a comment function, and users usually share their views on commodities in the comments. At the same time, other users find what they are interested in by browsing these comments, and will vote on these comments. Because reviews are more authentic and subjective than product descriptions. Comments are an important part of the current content platform. They can not only provide reference for user decision-making, but also enhance the activity of the community and attract more users to join. Due to the activeness of the platform community, product reviews may experience explosive growth. The existing methods of sorting comments are all sorted by time or popularity. At the same time, ...

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): G06F16/335G06F16/338G06F16/38G06F16/9535G06F16/9538G06N3/04G06N3/08G06Q30/02
CPCG06F16/335G06F16/338G06F16/38G06F16/9535G06F16/9538G06N3/08G06Q30/0282G06F2216/03G06N3/044G06N3/045
Inventor 印鉴王书为刘威高静
Owner SUN YAT SEN UNIV
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