Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and system for improving user authentication accuracy

An accurate and user-friendly technology, applied in the direction of neural learning methods, instruments, biological neural network models, etc., can solve the problems of insufficient authentication accuracy, loss information, model information, etc., and achieve the effect of improving the effect and stability

Active Publication Date: 2021-03-12
索信达(北京)数据技术有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the undersampling method will detract from information, and although oversampling generates more negative samples, these extra negative samples are still generated based on known negative samples and cannot bring more negative samples to the model. In the end, the accuracy of authentication will be insufficient, and users who should have been given permission are prohibited from accessing, while users who should not be given permission can access freely and enjoy corresponding resources. This is obviously what we don’t want to see Arrived

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
  • A method and system for improving user authentication accuracy
  • A method and system for improving user authentication accuracy
  • A method and system for improving user authentication accuracy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 1 As shown, the present invention discloses a method for improving user authentication accuracy, comprising the following steps:

[0049] Collect massive historical user data based on local database and third-party database;

[0050] Building a variational autoencoder based on the massive historical user data;

[0051]Based on the label, the massive historical user data is divided into three categories, namely the first type of user data, the second type of user data and the third type of user data, the third type of user represents the negative sample label user, and the sample increment Operation refers to generating more and different third-class user data based on existing third-class user data;

[0052] performing a sample increment operation on the third type of user data based on the variational autoencoder and the third type of user data;

[0053] Based on massive historical user data and the third type of user data obtained by sample increment...

Embodiment 2

[0057] A method for improving user authentication accuracy, comprising the following steps:

[0058] Collect massive historical user data based on local database and third-party database;

[0059] Building a variational autoencoder based on the massive historical user data;

[0060] Based on the label, the massive historical user data is divided into three categories, namely the first type of user data, the second type of user data and the third type of user data, the third type of user represents the negative sample label user, and the sample increment Operation refers to generating more and different third-class user data based on existing third-class user data;

[0061] performing a sample increment operation on the third type of user data based on the variational autoencoder and the third type of user data;

[0062] Based on massive historical user data and the third type of user data obtained by sample incremental operations, a binary classification model is established...

Embodiment 3

[0082] Historical data preparation for modeling:

[0083] A large amount of user data has been accumulated in the business process to form a historical data set for model building. For each user, the present invention collects information including the user's gender, age, occupation information, educational background, residential area, etc., information associated with mobile phones, such as IP address, number of mobile APPs, mobile phone brands, etc., and under the authorization of the user Query the user's data, as well as the user's third-party data, such as communication data, etc.

[0084] Among these users who have used a certain type of APP, such as shopping APP, video browsing APP, RPG game APP, chess and card game APP, etc., they can get their labels, that is, whether they are good users or bad users, and the value is 1 or 0. Bad users are users with low integrity or reputation, because these users are a small number of users, so they are marked as 0.

[0085] And...

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 method and system for improving user authentication accuracy. The method includes: constructing a variational autoencoder based on a local database and a third-party database; and dividing a large amount of historical user data into three categories based on tags, namely the first category user data, the second category user data and the third category user data. User data; based on the variational autoencoder and the third type of user data, performing a sample incremental operation on the third type of user data; based on the massive historical user data and the third type of user data obtained by the sample incremental operation, Establishing a binary classification model; receiving user requests; and authenticating the user based on the binary classification model. The method proposed by the present invention can make full use of known information to generate more negative samples, and these generated negative samples can bring more information to the model. At the same time, the variational autoencoder VAE also makes full use of the information of the rejected samples, and its encoder part can realize the dimensionality reduction of the feature dimension to improve the effect and stability of the model.

Description

technical field [0001] The invention belongs to the field of big data analysis and data mining, and in particular relates to a method and system for improving user authentication accuracy. Background technique [0002] The rapid development of the mobile Internet has given birth to the rapid development of mobile phone business. Users only need to submit application materials on the mobile APP to enjoy the functions of the corresponding application at a very high speed. At the same time, the operator's server will deploy a set of authentication measures to ensure the rights and interests of legitimate users and prevent bad users from causing losses to the operator. Due to the fierce market competition, it is very important whether the server can quickly and accurately feed back the results. [0003] Generally speaking, the following method is used for authentication: receiving application data of mobile phone users, including user's gender, age, occupation information, educ...

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 Patents(China)
IPC IPC(8): H04W12/30H04W12/69H04W12/06G06K9/62G06N3/04G06N3/08
CPCH04W12/06G06N3/08G06N3/045G06F18/24G06F18/214
Inventor 邵俊
Owner 索信达(北京)数据技术有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com