Risk user identification method and system, storage medium and equipment

A user identification and user technology, applied in the field of webcasting, can solve the problem of low risk user identification accuracy

Active Publication Date: 2020-07-31
武汉斗鱼鱼乐网络科技有限公司
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In the existing technology, the risky users who may appear in new activities are usually identified based on the "blacklist" identified after historical activities, but the accuracy of identifying risky users in new activities is low

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
  • Risk user identification method and system, storage medium and equipment
  • Risk user identification method and system, storage medium and equipment
  • Risk user identification method and system, storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This implementation provides a method for identifying risky users, which is used on the webcast platform, see figure 1 , the method of this embodiment includes the following steps:

[0058] S101. According to the historical activity data of the webcast platform, obtain a historical risk user sample set in the historical activity and multiple characteristics of each user in the historical risk user sample set;

[0059] S102. Through risk interception, obtain a sample set of undetermined risk users composed of undetermined risk users participating in the current activities of the webcast platform;

[0060] S103. Iteratively update the weights of the users in the historical risk user sample set and the users in the undetermined risk user sample set, and based on the multiple characteristics of each user in the historical risk user sample set, obtain the user's iteration prediction label for each round Adjust the coefficient for the probability of risk and the weight of ea...

Embodiment 2

[0145] Based on the same inventive concept as in Embodiment 1, this embodiment provides a system for identifying risky users, which is used on a webcast platform, see figure 2 , the system includes:

[0146] The first obtaining module is used to obtain the historical risk user sample set in the historical activity and multiple characteristics of each user in the historical risk user sample set according to the historical activity data of the webcast platform;

[0147] The second acquisition module is used to obtain a sample set of undetermined risk users who participate in the current activities of the webcast platform through risk interception and constitute undetermined risk users;

[0148] The third obtaining module is configured to iteratively update the weights of the users in the historical risk user sample set and the users in the pending risk user sample set, and obtain users based on multiple characteristics of each user in the historical risk user sample set The pr...

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 risk user identification method. Firstly, a historical risk user sample set in historical activities and a plurality of features of each user in the historical risk user sample set are obtained; then, through risk interception, an undetermined risk user sample set formed by undetermined risk users participating in the current activity of a network live broadcast platformis obtained; weights are iteratively updated for the users in the historical risk user sample set and the users in the undetermined risk user sample set, and based on the multiple features of each user in the historical risk user sample set, the probability that a prediction label of each round of iteration of the user is a risk and a weight adjustment coefficient of each round of iteration of theuser are obtained; and based on the probability that the prediction label of each round of iteration of the user is a risk and the weight adjustment coefficient of each round of iteration of the user, a risk user is identified from the users participating in the current activity of the network live broadcast platform. According to the method, the identification accuracy of risk users in a new activity is higher.

Description

technical field [0001] The present invention relates to the technical field of webcasting, in particular to a method, system, storage medium, and equipment for identifying risky users. Background technique [0002] On the live webcast platform, in order to increase user activity, there are often many interactive activities. However, some abnormal risky users participated in these activities through cheating, causing the problem of live broadcast network congestion, which had a great impact on the live broadcast ecological environment of the platform, and at the same time damaged the relevant interests of other normal accounts. For the risk control system, it is hoped that these risky users' cheating behaviors can be effectively prevented after the activity starts. Therefore, an effective method is needed to identify such behaviors in the event. [0003] In the prior art, risky users who may appear in new activities are usually identified based on a "blacklist" identified af...

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): G06Q10/06G06Q30/00G06Q30/06H04N21/2187
CPCG06Q10/0635G06Q30/01G06Q30/0609H04N21/2187
Inventor 王璐
Owner 武汉斗鱼鱼乐网络科技有限公司
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