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

Attribute reasoning and product recommendation method based on adaptive graph convolutional network

A convolutional network and self-adaptive technology, applied in reasoning methods, neural learning methods, biological neural network models, etc., can solve problems such as the need to improve the accuracy of attribute reasoning

Active Publication Date: 2020-06-16
HEFEI UNIV OF TECH
View PDF6 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing attribute reasoning works use semi-supervised graph learning (label propagation, graph regularization, deep models, etc.) to predict missing attributes, but the accuracy of attribute reasoning needs to be improved

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
  • Attribute reasoning and product recommendation method based on adaptive graph convolutional network
  • Attribute reasoning and product recommendation method based on adaptive graph convolutional network
  • Attribute reasoning and product recommendation method based on adaptive graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0105] In order to verify the effectiveness of this method, the present invention uses three public datasets commonly used in recommendation systems: Amazon-Video Games, Movielens-1M, and Movielens-20M. Each dataset screens users with less than 5 rating records, and randomly deletes 90% of the records for each attribute as training data.

[0106] For the product recommendation task, the present invention uses Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG) as evaluation criteria. In the present invention, 5 methods are selected for effect comparison, namely BPR, FM, BLA, NGCF, and PinNGCF. Specifically, Table 1, Table 2, and Table 3 respectively show the experimental results on the Amazon-Video Games, Movielens-1M, and Movielens-20M data sets. It can be seen that on the three data sets, the method proposed by the present invention is better than HR Both indicators of NDCG and NDCG are better than the five comparison methods.

[0107] Table 1 The product recom...

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 an attribute reasoning and product recommendation method based on an adaptive graph convolutional network. The method comprises the following steps: 1, constructing heterogeneous data: a scoring matrix of a user to a product, a user attribute matrix, a product attribute matrix, a user attribute index matrix and a product attribute index matrix; 2, performing missing value filling preprocessing on the user attribute matrix and the product attribute matrix; 3, obtaining a cooperative matrix through one-hot coding; 4, constructing a feature fusion layer according to the attribute matrix and the collaborative matrix; 5, carrying out feature propagation through a graph convolution layer; 6, constructing a prediction layer to perform attribute reasoning and product recommendation; 7, updating the node attribute matrix according to the output result of the prediction layer; and 8, repeating the steps 4-7 until the attribute reasoning and product recommendation effectsare optimal. According to the method, the high-order structure information of the graph, the internal interaction between the node attributes and the potential association between the node attributesand the link relationship can be fully mined, so that more accurate attribute reasoning and product recommendation are realized.

Description

technical field [0001] The present invention relates to the field of attribute reasoning and product recommendation, in particular to an attribute reasoning and product recommendation method based on an adaptive graph convolutional network. Background technique [0002] The recommendation system effectively alleviates the problem of information overload, and has been successfully applied to platforms such as e-commerce, music, movies, and social networking. The model based on collaborative filtering is one of the most mainstream recommendation systems, which mines the user's historical records to make personalized product recommendations. The recommendation system based on collaborative filtering is widely used, but its performance is often limited by the sparsity of user behavior data. [0003] Attribute-enhanced collaborative filtering system uses rich attribute features of users (gender, age, occupation, etc.) and products (price, quality, category) to model users and pr...

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
IPC IPC(8): G06F16/9535G06F16/9536G06F17/16G06K9/62G06N3/04G06N3/08G06N5/04
CPCG06F16/9535G06F16/9536G06F17/16G06N3/08G06N5/04G06N3/045G06F18/253
Inventor 吴乐杨永晖张琨汪萌洪日昌
Owner HEFEI UNIV OF TECH
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