Social robot detection method and system, storage medium and electronic equipment

A detection method and robot technology, applied in the field of social networks, can solve the problems of large impact on detection accuracy and low stability, and achieve the effects of high robustness, high recognition rate, and improved detection accuracy and detection efficiency.

Active Publication Date: 2021-03-12
北京智谱华章科技有限公司
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The quality of the data and feature selection for training the machine learning model has a great impact on the detection accuracy, the stability is not high, and there are certain limitations

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
  • Social robot detection method and system, storage medium and electronic equipment
  • Social robot detection method and system, storage medium and electronic equipment
  • Social robot detection method and system, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] like figure 1 As shown, the embodiment of the present invention provides a social robot detection method, including:

[0057] S101. Acquire a friend account of the target account to be detected and an associated post of the friend account, the associated post is a post referring to the target account;

[0058] Specifically, including:

[0059] Acquiring the first number (N) of friend accounts recently mentioned in the posting of the target account;

[0060] A second number (M) of associated posts recently published by the friend account are acquired.

[0061] For example, all friend accounts mentioned in the posting of the target account are obtained and sorted according to the time mentioned in descending order from the current time, and the first 100 friend accounts are taken. Obtain the related posts of the target account mentioned in the posts of the 100 friend accounts, sort the posting time from the current time in descending order, and take the first 200 relat...

Embodiment 2

[0105] Below to image 3 The social network relationship shown is taken as an example to illustrate the social robot detection method of the present invention.

[0106] exist image 3 In the shown social network relationship, taking the detection of twitter social robot account as an example, the node N0 of the target account to be detected has four neighbor nodes N1, N2, N3, and N4, which represent the four friend accounts recently mentioned by the target account, and the node Edges between nodes represent the existence of social relationships, and the value of the edges indicates the intimacy of the friendship between nodes. The calculation formula is:

[0107] (see embodiment one). In this embodiment, it is assumed that the values ​​of the sides are all 1.

[0108] First, obtain the account number and posting information of the user to be detected and its friends. Here, the twitter API is used for information acquisition. The obtained user information and posting info...

Embodiment 3

[0121] like Figure 4 As shown, another aspect of the present invention also includes a functional module architecture completely corresponding to the aforementioned method flow, that is, the embodiment of the present invention also provides a social robot detection system, including:

[0122] An acquisition module 41, configured to acquire a friend account of the target account to be detected and an associated post of the friend account, the associated post is a post referring to the target account;

[0123] A matrix construction module 42, configured to construct an account information matrix according to the target account and the friend account, and construct an article information matrix according to the posting of the target account and the associated posting of the friend account;

[0124] Graph construction module 43, for constructing social relation graph according to described account information matrix and article information matrix;

[0125] A classification modul...

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 social robot detection method and system, a storage medium and electronic equipment. The method comprises the steps of obtaining a friend account of a to-be-detected target account and an associated sent message of the friend account, wherein the associated sent message is a sent message referring to the target account; constructing an account information matrix accordingto the target account and the friend account, and constructing an article information matrix according to the sent message of the target account and the associated sent message of the friend account;constructing a social relation graph according to the account information matrix and the article information matrix; determining the category of each sent message of the target account; inputting themessage of the target account, the social relation graph and the article information matrix into a classification detection model corresponding to the category of the message to obtain a detection result based on the message; obtaining a final detection result of the target account according to the detection result of each message of the target account. The method has the advantages of low time delay, high robustness, high stability and high recognition rate.

Description

technical field [0001] The present invention relates to the technical field of social networks, in particular to a social robot detection method, system, storage medium and electronic equipment. Background technique [0002] In recent years, with the rapid development of information technology, social networks have been widely used by people, through which people can share news, opinions and make friends, etc., but there has been a social robot account of an abnormal user. Social robots have been applied to all aspects of people's lives (intelligent customer service, questionnaire robots, etc.), but the use of malicious social robots has led to more and more serious online fraud and false news, so the detection of social robot accounts has attracted more and more attention from governments and companies in various countries . [0003] Existing social robot detection technologies mainly use graph-based account detection, crowdsourcing account detection, and machine learning-...

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): G06F16/335G06F16/36G06Q50/00
CPCG06Q50/01G06F16/335G06F16/367
Inventor 周明唐杰刘德兵仇瑜
Owner 北京智谱华章科技有限公司
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