User name sample labeling method and device, electronic equipment and storage medium

A user name, sample technology, applied in the field of network security, can solve the problem of inaccurate model recognition results

Pending Publication Date: 2021-07-30
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present disclosure provides a user name sample tagging method, device, and electronic equipment, a user name recognition model training method, device, electronic device, and storage medium, and a user name recognition method, device, and user

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 name sample labeling method and device, electronic equipment and storage medium
  • User name sample labeling method and device, electronic equipment and storage medium
  • User name sample labeling method and device, electronic equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0082] figure 1 is a flow chart of a method for labeling user name recognition samples according to an exemplary embodiment, as shown in figure 1 As shown, this method can improve the accuracy of the recognition results of the username recognition model.

[0083] The execution subjects of the method include but are not limited to servers, personal computers, notebook computers, tablet computers, smart phones and other intelligent electronic devices that can execute predetermined processing procedures such as numerical calculations and / or logic calculations by running predetermined programs or instructions. Wherein, the server may be a single server or multiple servers. The method may include the steps of:

[0084] In step S101, based on the acquired semantic features of each user name sample, the user name samples are clustered to obtain a plurality of sample clusters.

[0085] In an implementation manner, before step S101 is performed, acquiring a user name sample may also...

Embodiment 2

[0150] figure 2 is a flow chart of a method for labeling user name samples according to an exemplary embodiment, as shown in figure 2 As shown, in step S102, according to the specified characteristics of the multiple sample clusters, the sample clusters that meet the predetermined sample cluster selection conditions are selected from the multiple sample clusters, including the following steps S201 to S202:

[0151] The specified features of the sample cluster include: the average similarity of semantic features between different username samples in the sample cluster;

[0152] The sample cluster selection conditions include: the average semantic feature similarity between different user name samples in the sample cluster is greater than the semantic similarity threshold.

[0153] In step S201, calculate the semantic feature average similarity between user name samples in each sample cluster;

[0154] In an optional implementation manner, calculating the average semantic fe...

Embodiment 3

[0166] image 3 is a flow chart of a method for labeling user name samples according to an exemplary embodiment, as shown in image 3 As shown, in step S102, according to the respective specified characteristics of the multiple sample clusters, the sample clusters that meet the predetermined sample cluster selection conditions are selected from the multiple sample clusters, including the following steps S301 and S302:

[0167] Among them, the specified characteristics of the sample cluster include: the similarity of the positive and negative sample types marked by the user name sample in the sample cluster;

[0168] Predetermined sample cluster selection conditions include: the positive and negative sample type similarity of the user name sample marked in the sample cluster is less than the type similarity threshold.

[0169] In step S301, the labeled positive and negative sample type similarities between user name samples in each sample cluster are calculated.

[0170] In a...

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 relates to a user name sample labeling method, and the method comprises the steps of carrying out the clustering of user name samples based on the obtained semantic features of all user name samples, so as to obtain a plurality of sample clusters; according to respective specified features of the plurality of sample clusters, screening the sample clusters meeting a predetermined sample cluster selection condition from the plurality of sample clusters, wherein the specified features are used for representing whether user name samples in the sample clusters are in a negative sample type, and the sample cluster selection condition is determined based on a specified feature statistical result of a sample cluster formed by the user names which are identified as abnormal user names in advance; and marking the user name samples in the screened sample clusters as negative user name samples.

Description

technical field [0001] The present disclosure relates to the technical field of network security, and in particular to a method, device, electronic equipment and storage medium for labeling user name samples. Background technique [0002] Username (English name: Username), also known as account name, can use Chinese characters, letters, character codes, etc., such as Everest, zmlmf, 12345, etc., can be used as a user name. Abnormal user names, for example, are typically generated and registered by malicious users using scripts in large quantities. Such user names either contain pornographic and reactionary information themselves, or spread pornographic information, phishing website links, advertisements, etc. , will have adverse effects on legitimate users, and may easily lead to network security issues. [0003] In order to prevent abnormal user names from appearing on the network platform, it is necessary to identify the registered user names, and then restrict the succes...

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): G06F16/33G06F16/35G06F40/30
CPCG06F16/3344G06F16/35
Inventor 周亚林张子琦
Owner BEIJING DAJIA INTERNET INFORMATION TECH 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