User behavior clustering analysis method and terminal, and computer readable storage medium

A cluster analysis and behavior technology, applied in computer parts, computer security devices, computing, etc., can solve problems such as inability to accurately and quickly distinguish user types, and low accuracy of user behavior clustering.

Inactive Publication Date: 2017-12-01
NUBIA TECHNOLOGY CO LTD
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main purpose of the present invention is to provide a user behavior clustering analysis method, terminal, and computer-readable storage medium, aiming to solve the p

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 behavior clustering analysis method and terminal, and computer readable storage medium
  • User behavior clustering analysis method and terminal, and computer readable storage medium
  • User behavior clustering analysis method and terminal, and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0066] In the traditional user behavior analysis, it is judged through the pre-established user behavior model, and only the user's behavior operation is the same or similar to the operation specified by the user behavior model, then the user behavior operation is considered to be legal, but this It is only to judge the operation itself, and there is no corresponding induction for the user behavior operation after the judgment is completed, or the corresponding user is classified, which leads to the need for repeated comparison operations in the prior art, and The accuracy rate of the judgment is not high. In order to solve the above problems, the embodiment of the present invention provides a user behavior cluster analysis method. The category of user groups is convenient for quickly locating bad users.

[0067] Such as figure 2 as shown, figure 2 It is a flow chart of the user behavior cluster analysis method provided by this embodiment of the present invention, which is...

no. 2 example

[0116] Such as image 3 As shown, it is another flow chart of the user behavior clustering analysis method provided by Embodiment 2 of the present invention. This method is based on the operation plan proposed by the specific website, for example, the Alibaba sales platform, which specifically includes the following steps:

[0117] S301. The system collects user behavior. Develop a user behavior recording module to record the behavior of all users on the website and record these behaviors to the database.

[0118] S302, extracting user behavior. Analyze the user behavior in the database and extract various behaviors of the user. For example, user A's behavior includes: whether to log in from another place, log in time, log in location, stay time, query sales data, change password, etc.

[0119] S303, feature item extraction. Based on the feature item extraction algorithm, the behavior that best represents a certain user is extracted to form a feature item. For example, in...

Embodiment 3

[0142] refer to Figure 7 , Figure 7The structural block diagram of the user behavior distance analysis terminal provided in Embodiment 3 of the present invention, the device provided in this embodiment includes: a processor 71, a memory 72, and a communication bus 73, wherein:

[0143] The communication bus 73 is used to realize the communication connection between the processor 71 and the memory 72;

[0144] The processor 71 is configured to execute the user behavior cluster analysis program stored in the memory 72, so as to realize the following steps:

[0145] Obtain user data of all users operating on the website, where each user data includes at least one user behavior operation;

[0146] Extracting at least one valid user behavior operation from the at least one user behavior operation to form a feature item set;

[0147] Converting feature item sets of all users into vector space model data, the vector space model data is a multi-dimensional data table;

[0148] C...

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 provides a user behavior clustering analysis method and terminal, and a computer readable storage medium. The method includes: obtaining user data operated by all users on a website, extracting effective user behavior operations from the user data to form a characteristic item set, converting the characteristic item set of all the users to vector space model data, performing clustering operation on characteristic items in the vector space model data according to a clustering analysis algorithm, obtaining clustering analysis results, and determining the legality of each user behavior operation according to the clustering analysis results. According to the user behavior clustering analysis method and terminal, and the computer readable storage medium, the legality of the user behaviors operated by the users on the website is analyzed according to the clustering analysis algorithm, whether the user behaviors are legal is determined according to the analysis results, classified display of illegal user behaviors and the corresponding users is realized, the performance of the website is enhanced, interception processing of malicious operations of a certain kind of users is performed, and malicious operations of the website by the users can be solved from the operation source.

Description

technical field [0001] The present invention relates to the technical field of user behavior analysis, and more specifically, to a user behavior cluster analysis method, a terminal, and a computer-readable storage medium. Background technique [0002] For an e-commerce web site, user behavior analysis is very important, especially for a site with a huge user base. By analyzing user behavior, it is possible to distinguish whether a user is friendly or malicious. If there are bad hackers attacking the site , you can analyze the user's behavior records, make deviations, and finally locate whether the user is a malicious user. This is of great significance for improving the security of a website. [0003] The behavior of bad users is completely different from that of ordinary friendly users. For example, aggressive users often try to find loopholes in the website through various methods, often know various uncommon website operations, or often Abnormal operation of the website...

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): H04L29/06H04L12/24G06K9/62G06F21/55
CPCH04L41/14H04L63/1466G06F21/552G06F18/2135G06F18/23
Inventor 李志晖
Owner NUBIA TECHNOLOGY CO LTD
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