Recognition method of trusted and untrusted users based on feedforward neural network

A feedforward neural network and user identification technology, applied in the field of trusted and untrusted user identification based on feedforward neural network, can solve the problems of lack of intelligence, insufficient accuracy, and insufficient flexibility.

Inactive Publication Date: 2016-10-05
JILIN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The technical problem to be solved by the present invention is to overcome the problems of insufficient precision, insufficient flexibility, and lack of intelligence in the prior art, and to provide a credible and untrustworthy user identification method based on a feedforward neural network

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
  • Recognition method of trusted and untrusted users based on feedforward neural network
  • Recognition method of trusted and untrusted users based on feedforward neural network
  • Recognition method of trusted and untrusted users based on feedforward neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0151] refer to figure 1 , the steps of the credible and untrustworthy user identification method based on the feedforward neural network described in the present invention are as follows:

[0152] 1. Obtain special users and users included in the training set

[0153] (1) Use Web Crawler to crawl user level information, build an initial user set through user level information, and refer to the results Figure 4 ;

[0154] (2) Delete the initial user set by determining the user method to obtain special users. For the results, refer to Figure 5 ;

[0155] (3) Web Crawler is used to crawl user trust relationship, and the initial social network is constructed according to the trust relationship. For the results, refer to Image 6 ;

[0156] (4) Obtain seed users according to the topology structure of the initial social network and the method of determining users, and use Web Crawler to crawl the trust relationship of seed users to build a social network. For the results, re...

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 credible and untrustworthy user identification method based on a feedforward neural network, aiming to overcome the problems of insufficient precision, insufficient identification basis, lack of flexibility, and coarser granularity of social network analysis in the prior art. The steps of the method are: 1. Obtain special users and determine the users included in the training set; 2. Analyze and quantify user features, and represent users as user feature vectors; 3. Construct a feedforward neural network; 4. Train a feedforward neural network ; 5. Realize credible and untrustworthy user identification by the feed-forward neural network after training: its steps are: 1) obtain user information in the social network; 2) quantify user information and generate user feature vector; 3) user feature vector Input into the feed-forward neural network, and identify trusted and untrusted users according to the output value of the output node.

Description

technical field [0001] The invention relates to a method for identifying trusted and untrusted users in the field of social networks, more precisely, the invention relates to a method for identifying trusted and untrusted users based on a feedforward neural network. Background technique [0002] Nowadays, social networks provide network users with a more convenient and fast platform for information exchange and resource sharing. However, due to the openness and virtuality of social networks, a large amount of false information or even false information floods the network space, leading to the growing phenomenon of dishonesty. Seriously, it has adverse effects on society and disrupts social order. Therefore, identifying false information on the Internet has become a key and hot research issue. Given that network users are the media for information release and dissemination, the primary task of identifying information authenticity is to identify credible and untrustworthy user...

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 Patents(China)
IPC IPC(8): G06N3/02
Inventor 王英左万利田中生王鑫彭涛王萌萌赵秋月
Owner JILIN 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