A tag user identification method and related equipment

Abstract

Embodiments of the present invention provide a label user identification method and related equipment, which are used to quickly identify label users on a live broadcast platform, purify the network environment, and provide user experience on the platform. The method includes: constructing a target directed graph, the target directed graph indicating the information interaction relationship between any two users in the live broadcast platform; calculating the weight of an edge connected to a vertex corresponding to the target user in the target directed graph , the target user is the user of the label to be identified; determine the initial label score of the user corresponding to each vertex in the target directed graph; according to the initial label score and the weight of the edge connected to the vertex corresponding to the target user Iteratively calculating the label score of the target user; judging whether the label score of the target user is greater than a preset threshold when the preset iteration termination condition is reached; if so, determining that the target user is a label user.

Description

technical field [0001] The invention relates to the field of big data risk control, in particular to a tag user identification method and related equipment. Background technique [0002] With the advancement of network communication technology and the speed up of broadband network, live video technology has been more and more developed and applied. [0003] On the live broadcast platform, there is a social function that users on the live broadcast platform can send messages to each other. However, some black industries use in-site messages to send some pornographic and spam in-messages with advertising content to users on the live broadcast platform, which greatly damages the user experience on the platform. Therefore, there is a need for an effective method to quickly identify these malicious users who send spam messages. [0004] The existing methods generally use statistical methods directly to count the number of private messages sent by each private message user on th...

AI Technical Summary

Problems solved by technology

[0004] The existing methods generally use statistical methods directly to count the number of private messages sent by each private message user on the live broadcast platform, the proportion of replies, etc. A malicious private message user may send a large number of internal messages, but the proportion of replies received is very low, which makes it difficult to identify malicious users through the proportion of replies

Or to identify the content of the letter in the station, and find those that contain advertisements and pornographic content, but it is difficult to play a role in the case of using urls that do not have obvious abnormalities in the content.

Images