Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Network water army behavior detection method and system based on mixed Dirichlet process

A detection method and behavior technology, applied in the field of network security, which can solve the problems affecting the accuracy of algorithm determination and difference

Active Publication Date: 2014-05-21
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF4 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing "network trolls" generally use algorithms such as decision trees, KNN, and neural networks. During the design process of these algorithms, it is necessary to set the values ​​of key parameters based on historical experience to reflect the impact of every aspect of user behavior. The degree of influence of the judgment results is different. This method has a lot of subjectivity and seriously affects the judgment accuracy of the algorithm.

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
  • Network water army behavior detection method and system based on mixed Dirichlet process
  • Network water army behavior detection method and system based on mixed Dirichlet process
  • Network water army behavior detection method and system based on mixed Dirichlet process

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The principles and features of the present invention are described below in conjunction with the accompanying drawings, and the examples given are only used to explain the present invention, and are not intended to limit the scope of the present invention.

[0054] Such as figure 1 As shown, a water army recognition method based on the fusion of behavioral features and content features includes the following steps:

[0055] A network troll behavior detection method based on a hybrid Dirichlet process, comprising the following steps:

[0056] Step 1: The raw data collection module collects raw data including user behavior characteristics and content characteristics, and quantifies the raw data of each dimension. The quantified raw data constitutes the user's historical behavior vector, and the set of historical behavior vectors of all users together constitute the user data set to be clustered;

[0057] Step 2: The clustering module receives the historical behavior vec...

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 relates to a network water army behavior detection method and a network water army behavior detection system based on a mixed Dirichlet process. The network water army behavior detection method includes: collecting original data comprising user behavior features and content features, performing quantization representation on the original data of each dimensionality so as to form history behavior vectors of a user, and forming a user data set to be clustered; clustering the history behavior vectors in the user data set to be clustered so as to obtain at least one classification user behavior set; converting data in the at least one classification user behavior set, and merging data with the same user identification in the data after being converted so as to obtain a sequence database; performing sequence pattern excavation on the sequence database through a pattern excavation module so as to obtain at least one affair sequence pattern corresponding to each classification user behavior set; judging out the classification user behavior set which is a water army username by comparing each affair sequence pattern through a water army judging module. The network water army behavior detection method and the network water army behavior detection system based on the mixed Dirichlet process can easily recognize which category belongs to the water army username.

Description

technical field [0001] The invention relates to the field of network security, in particular to a method and system for detecting network troll behavior based on a mixed Dirichlet process. Background technique [0002] The popularity and rapid development of social networks not only brought fundamental changes in information communication technology, but also changed people's production and lifestyle, interpersonal communication and way of thinking step by step, affecting all areas of social life and the survival of human beings. It has had a wide-ranging and profound impact on development. At present, social networks include all forms of network services centered on human social interaction. From a historical perspective, it will be a key force that will push the Internet closer to the real world. [0003] With the rapid development of social networks, the security problems it brings are becoming more and more prominent, among which the security problems originating from t...

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 Applications(China)
IPC IPC(8): H04L29/06G06F17/30
Inventor 李丹李倩牛温佳管洋洋黄超孙卫强胡玥郭莉
Owner INST OF INFORMATION ENG CHINESE ACAD OF SCI
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
Eureka Blog
Learn More
PatSnap group products