Malicious user identification method, device and equipment
The invention provides a malicious user identification method, device and equipment. The method comprises the steps of obtaining feature attribute information of a to-be-identified user; inputting thefeature attribute information into a target classifier to obtain an identification result, the ident...
Saved in:
Main Authors | , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
19.03.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention provides a malicious user identification method, device and equipment. The method comprises the steps of obtaining feature attribute information of a to-be-identified user; inputting thefeature attribute information into a target classifier to obtain an identification result, the identification result being used for representing whether the to-be-identified user is a malicious useror not, and enabling the target classifier to generate a new training sample through the first classifier after the first classifier and the second classifier are obtained according to the multiple training samples; and training the second classifier by using the new training sample; outputting recognition results. Through the method, the efficiency of identifying malicious users can be improved.
本申请提供一种恶意用户的识别方法、装置和设备,该方法包括:获取待识别用户的特征属性信息;将特征属性信息输入目标分类器中,得到识别结果,识别结果用于表征待识别用户是否为恶意用户,目标分类器为根据多个训练样本得到第一分类器和第二分类器后,再通过第一分类器生成新的训练样本,并采用新的训练样本对第二分类器进行训练后得到的;输出识别结果。通过该方法能够提高识别恶意用户的效率。 |
---|---|
Bibliography: | Application Number: CN202011467982 |