User trust relationship network link prediction method and system based on gating mechanism

A trust relationship and network link technology, which is applied in the field of user trust relationship network link prediction based on the gating mechanism, can solve the problems of unbalanced embedding results, no directed symbol network, and inability to learn negative relationships, etc., to reduce sparsity , maintain balance, and predict the effect that the accuracy rate does not change too much

Pending Publication Date: 2020-07-14
SHANDONG NORMAL UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the directed symbolic network does not have this excellent property, so it cannot learn the n...

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 trust relationship network link prediction method and system based on gating mechanism
  • User trust relationship network link prediction method and system based on gating mechanism
  • User trust relationship network link prediction method and system based on gating mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] This embodiment discloses a user trust relationship network link prediction method based on a gating mechanism, including:

[0059] Step 1: Obtain the comment interaction data between users and build a network model of user trust relationship;

[0060] In a trust relationship network, each user’s comments can be expressed by other users, that is, a user’s reaction to another user’s comments has the following two basic situations: trust the user’s speech and distrust the user’s speech , based on which the basic comment symbolic network model can be constructed.

[0061] Step 2: Extracting an adjacency matrix based on the user trust relationship network model, and converting the adjacency matrix into a directed activation propagation adjacency matrix;

[0062] Specifically, the step 2 includes:

[0063] Step 2.1: Use the symbol '1' to represent the trust relationship between users, and the symbol '-1' to represent the distrust relationship between users, construct a pre...

Embodiment 2

[0151] The purpose of this embodiment is to provide a user trust relationship network link prediction system based on the gating mechanism, including:

[0152] The symbolic network acquisition module acquires comment interaction data between users and builds a user trust relationship network;

[0153] A symbolic network processing module extracts an adjacency matrix based on the user trust relationship network, and converts the adjacency matrix into a directed activation propagation adjacency matrix;

[0154] The reachability matrix calculation module combines the symbolic network activation propagation adjacency matrix to calculate the symbolic network reachability matrix;

[0155] The gating mechanism module processes the symbolic network reachability matrix based on the gating mechanism;

[0156]The network embedding module takes the processed reachability matrix as the input of the graph convolutional network, uses the spectral domain graph convolution method to encode th...

Embodiment 3

[0159] The purpose of this embodiment is to provide a computer-readable storage medium in which a plurality of instructions are stored, and the instructions are suitable for being loaded and executed by a processor of a terminal device:

[0160] Obtain comment interaction data between users and build a user trust relationship network;

[0161] extracting an adjacency matrix based on the user trust relationship network, and converting the adjacency matrix into a directed activation propagation adjacency matrix;

[0162] Combining the symbolic network activation propagation adjacency matrix to calculate the symbolic network reachability matrix;

[0163] The symbolic network reachability matrix is ​​processed based on the gating mechanism;

[0164] The processed reachability matrix is ​​used as the input of the graph convolutional network, and the symbolic network is encoded using the spectral domain graph convolution method to obtain the network embedding result;

[0165] Base...

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 user trust relationship network link prediction method and system based on a gating mechanism, and the method comprises: obtaining comment interaction data between users, andconstructing a user trust relationship network; extracting an adjacency matrix based on the user trust relationship network, and converting the adjacency matrix into a directed activation propagationadjacency matrix; calculating a symbol network reachable matrix in combination with the symbol network activation propagation adjacency matrix; processing the symbol network reachable matrix based ona gating mechanism; taking the processed reachable matrix as input of a graph convolutional network to obtain a symbol network for encoding and a network embedding result; and taking the network embedding result as a code of the symbol network, and performing similarity measurement between nodes in the network by using an inner product decoding mode to obtain a reconstructed symbol network adjacency matrix, namely a user trust relationship network link prediction result. An accurate network embedding result is obtained through the graph convolution network, the speed of user trust relationship prediction is increased, and the prediction accuracy is ensured.

Description

technical field [0001] The invention belongs to the technical field of network link prediction, and in particular relates to a user trust relationship network link prediction method and system based on a gating mechanism. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Nowadays, most research data can be represented graphically, so there is a great demand for generalized neural network models for graphical data, such as research on user credibility in comment trust networks, and user preferences in e-commerce platforms. Recommendations and avoidance of disgust, research on user similarity in major traffic platforms and recommendation strategies. The more mature methods in the research of the above fields include matrix-based symbol prediction method and network embedding method. The former excavates the potential similarity between netw...

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): G06N3/04G06F17/16G06F17/14
CPCG06F17/16G06F17/14G06N3/045
Inventor 王红崔健聪庄慧相志杰李泽慧吴祖涛胡宝芳胡斌张伟闫晓燕
Owner SHANDONG NORMAL 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