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

User purchase behavior prediction method based on graph neural network and user intention perception

A technology of user intent and neural network, which is applied in the field of data mining and recommendation system, can solve the problems of poor recommendation effect and achieve good recommendation ability

Pending Publication Date: 2022-04-12
HANGZHOU DIANZI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in actual scenarios, there are usually a large number of items, and each user will only interact with a few of them, so the user-item interaction matrix in matrix decomposition will become very sparse, this very sparse data will lead to poor recommendations

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
  • User purchase behavior prediction method based on graph neural network and user intention perception
  • User purchase behavior prediction method based on graph neural network and user intention perception
  • User purchase behavior prediction method based on graph neural network and user intention perception

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] The item recommendation method based on graph neural network and user intent perception provided by the present invention will be described in detail below, as follows: figure 1 As shown, the present invention provides a user purchase behavior prediction method based on graph neural network and user intent perception, comprising the following steps:

[0056] Step 1, input the user's historical purchase data, wherein the purchase data includes the user's ID, item ID, and the timestamp of the purchase;

[0057] Step 2, read and process the user purchase behavior data; for the original user purchase behavior records, each record contains the user ID, the ID of the purchased item and the timestamp of the purchase; the purchase records of each user are sequenced according to the timestamp Sort to get each user behavior sequence file; each of them is a user’s item purchase sequence, in each sequence, the user’s ID is at the beginning of the row, and the user’s purchased item ...

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

According to the method, articles in historical purchase data of a user serve as behavior sequences, then a directed graph is constructed based on the sequences, each node represents one article purchased by the user, and each directed edge represents that the user purchases a pointed article after purchasing a source article of the edge. On the basis of the graph, the relation between the articles and the relation between the articles and the user are captured through a graph neural network, vector representation of the articles is accurately generated, and the current intention of the user is accurately captured through a user intention perception module and serves as the vector representation of the user. And based on the vector representations of the articles and the vector representation of the user, combining the vector representations with an attention mechanism to recommend articles which may be interested in for the user.

Description

technical field [0001] The invention belongs to the technical field of data mining and recommendation systems, and in particular relates to a user purchase behavior prediction method based on a graph neural network and user intention perception. Background technique [0002] In recent years, with the rapid growth of online shopping platforms such as Taobao, JD.com, and Pinduoduo, more and more users search, view, and purchase the products they need through shopping platforms. The purchase data of these users provides a good opportunity to analyze the user's behavior pattern. We can analyze and predict the next possible purchase of the user based on the user's historical purchase sequence. In addition, the e-commerce platform can capture the user's preferences and current intentions from the user's historical purchase data, and recommend content that users may be interested in, thereby improving the user experience and increasing the revenue of the e-commerce platform. A win...

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): G06Q30/02G06Q30/06G06N3/04G06N3/08
Inventor 俞东进王兴亮王东京
Owner HANGZHOU DIANZI UNIV
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