An anti-fraud resolution method and system

A technology with solutions and attributes, applied in the field of anti-fraud solutions and systems, can solve problems such as the inability to achieve dynamic confrontation between fraudulent gangs or black intermediaries, and achieve the effects of reducing query costs, reducing fraud rates, and protecting fund security.

Inactive Publication Date: 2019-01-08
深圳微言科技有限责任公司
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The risk features obtained by supervised learning are often old attack routines, which cannot achieve dynamic confrontation with fraudulent gangs or black intermediaries

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
  • An anti-fraud resolution method and system
  • An anti-fraud resolution method and system
  • An anti-fraud resolution method and system

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0146] Such as Figure 4As shown in the figure, the original data is input to the crawler program, and the crawler program crawls relevant information such as phone number, address latitude and longitude, and address type. In the "sql program 1", the user's pre-loan application data is cleaned and processed, and the "python program 1" is input to construct a complex network and calculate network attributes. Input the calculated complex network-related data, routing data, overdue data, and mobile phone number information crawled by crawlers into "sql program 3", and label the ID number and ID card attributes according to the rules in the label system, and mark risks Level, validity period, expiration date and other information, you can get the first part of the blacklist data. Clean and process the address data crawled by the crawler, input "python program 2" for clustering, calculate the community data obtained by clustering and the first part of blacklist data according to t...

example 2

[0148] like Figure 5 As shown, if the overdue data is missing, the overdue data may not be used, and this solution is still feasible. In this case, the blacklist obtained lacks tags related to post-loan overdue, and the others are the same as in Example 1.

example 3

[0150] like Figure 6 As shown, if the crawler data is missing, the crawler may not be used, and this solution is still feasible. In this case, address clustering cannot be performed, and the obtained blacklist lacks risk tags related to crawler data. Others are the same as Example 1.

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 an anti-fraud solution method and system. The method includes: obtaining sample feature information; constructing a complex network and calculating network attributes, whereinthe complex network comprises a first network and a second network; the first network takes the ID card number as a node and establishes a connecting edge between different ID card numbers with the same ID card attribute; the second network takes the ID card number and the ID card attribute as nodes, and each ID card number and each ID card attribute owned by each ID card number are respectively set up with connecting edges; the network attributes include association strength, user similarity, user bridge point value, and / or attribute bridge point value; the attribute of ID card includes communication telephone, bank card information and so on; according to the preset rules of network attribute and label system, obtaining the first part of the blacklist by putting corresponding risk labelson each ID card and ID card attribute respectively. The invention can accurately and effectively identify gang risk, individual risk, black intermediary and batch attack behavior and the like, thereby effectively reducing fraud rate.

Description

technical field [0001] The invention relates to the financial field, in particular to an anti-fraud solution method and system. Background technique [0002] At present, anti-fraud solutions in the field of consumer finance usually use supervised learning methods to train models based on historical data, and then judge the risk level of samples. The risk features obtained by supervised learning are often old attack routines, which cannot achieve dynamic confrontation with fraudulent gangs or black intermediaries. Contents of the invention [0003] The purpose of the present invention is to provide an anti-fraud solution method and system for discovering group risks, individual risks, black intermediaries, batch attacks, etc. in the field of consumer finance, so as to effectively reduce the fraud rate and reduce the cost of external blacklist inquiries , to protect the safety of funds. [0004] For reaching this purpose, the present invention adopts following technical sc...

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): G06Q40/02G06K9/62
CPCG06Q40/03G06F18/23213
Inventor 黄卫苏树清韩彧
Owner 深圳微言科技有限责任公司
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