Binding recommendation method and system based on graph convolutional neural network

A convolutional neural network and recommendation method technology, applied in the field of bundled recommendation methods and systems based on graph convolutional neural networks, can solve the problem of inability to balance the weight relationship between users, bundles and items, the decision reference relationship is not comprehensive enough, and the recommendation results are not accurate enough and objective problems, to achieve the effect of good recommendation performance

Pending Publication Date: 2020-09-01
TSINGHUA UNIV
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The embodiment of the present invention provides a method and system for bundling recommendation based on graph convolutional neural network, which is used to solve the problem that the weight relationship among users, bun

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
  • Binding recommendation method and system based on graph convolutional neural network
  • Binding recommendation method and system based on graph convolutional neural network
  • Binding recommendation method and system based on graph convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0109] Implementation mode one: if Figure 10 In the middle branch of , the user wants to use the user's interaction with the item and the bundle history tracked by the platform to recommend new bundles to the user. The platform here can be any e-commerce and content platform, corresponding to any items that can form a bundle, such as commodities, food, places, music, books, movies, news, etc.

[0110] First, the historical interaction between the user and the item, the historical interaction between the user and the bundle, and the composition information of the bundle are formalized into a matrix to obtain the user-bundle historical interaction matrix X M×N , user-item historical interaction matrix Y M×O and bundle-item affiliation matrix Z N×O , a unified heterogeneous graph can be described by three matrices. where node by user node The binding node b∈B and the item node i∈I are composed, and the edge E is composed of the corresponding x ub = 1 user-bundle interact...

Embodiment approach 2

[0113] Implementation mode two: if Figure 10 In the left branch, the user wants to recommend a new bundle to the user by using the interaction between the user and the bundle history tracked by the platform. The platform here can be any e-commerce and content platform, corresponding to any items that can form a bundle, such as commodities, food, places, music, books, movies, news, etc.

[0114] First, the historical interaction between the user and the bundle, and the composition information of the bundle are formalized into a matrix, and the user-bundle history interaction matrix X is obtained M×N and bundle-item affiliation matrix Z N×O , a unified heterogeneous graph can be described by two matrices. where node by user node The binding node b∈B and the item node i∈I are composed, and the edge E is composed of the corresponding x ub = 1 user-bundle interaction edge (u,b) and corresponding z bi Bundle = 1 - items are composed of dependent edges (b,i). For user and b...

Embodiment approach 3

[0117] Implementation mode three: if Figure 10 In the right branch of , the user wants to use the historical interaction between the user and the item tracked by the platform to recommend new bundles to the user. The platform here can be any e-commerce and content platform, corresponding to any items that can form a bundle, such as commodities, food, places, music, books, movies, news, etc.

[0118] First, the historical interaction between the user and the item and the composition information of the bundle are formalized into a matrix, and the user-item historical interaction matrix Y is obtained M×O and bundle-item affiliation matrix Z N×O , a unified heterogeneous graph can be described by two matrices. where node by user node The binding node b∈B and the item node i∈I are composed, and the edge E is composed of the corresponding y ui = 1 user-item interaction edge (u,i) and corresponding z bi Bundle = 1 - items are composed of dependent edges (b,i). For user and ...

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 embodiment of the invention provides a binding recommendation method and system based on a graph convolutional neural network. The method comprises the steps: acquiring historical interaction dataof a user and binding, historical interaction data of the user and an article and affiliation data of the binding and the article; inputting the data into the binding recommendation model to obtain auser and binding interaction possibility recommendation result output by the binding recommendation model, wherein the bundled recommendation model is obtained by constructing a unified heterogeneousgraph based on a user data set, a bundled data set and an article data set, extracting article hierarchical graph convolution propagation features and bundled hierarchical graph convolution propagation features, then performing joint prediction and feature connection, and performing training based on a difficult negative sample learning strategy. According to the embodiment of the invention, theinteraction relationship and subordination relationship among the user, the bundle and the article are reconstructed into the graph, and three associated entity representations are learned from a complex topological structure and high-order connectivity by utilizing the powerful capability of the graph neural network, so that better recommendation performance can be achieved.

Description

technical field [0001] The present invention relates to the technical field of bundling recommendation, in particular to a bundling recommendation method and system based on a graph convolutional neural network. Background technique [0002] Bundled recommendation is defined as a set of bundled items that are intended to be recommended for overall consumption by users. The prevalence of bundled items on e-commerce and content platforms makes bundled recommendation an important task, which can not only avoid users’ monotonous choices but also improve user experience. experience, but also increase business sales by scaling order sizes. Since a bundle consists of multiple items, the attractiveness of the bundle depends on the items within the bundle, with the attractiveness of each item within the bundle being affected by the other items displayed together in the bundle. In addition, users need to be satisfied with most items in the bundle, which means that the interaction bet...

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): G06F16/9535G06N3/04G06N3/08G06Q30/06
CPCG06F16/9535G06N3/084G06Q30/0631G06N3/045
Inventor 李勇常健新高宸金德鹏
Owner TSINGHUA 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