Network payment anti-fraud system architecture design method based on suspected fraud transaction reference order

A network payment and system architecture technology, which is applied in the field of network payment anti-fraud system architecture design, can solve the problems that are difficult to meet the needs of the network payment anti-fraud field, and achieve the effect of good scalability and convenient addition and deletion

Active Publication Date: 2019-08-30
TONGJI UNIV
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Traditional financial anti-fraud methods are di...

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
  • Network payment anti-fraud system architecture design method based on suspected fraud transaction reference order
  • Network payment anti-fraud system architecture design method based on suspected fraud transaction reference order
  • Network payment anti-fraud system architecture design method based on suspected fraud transaction reference order

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] Such as figure 1As shown, the implementation of the present invention provides a complete fraud space division method based on the reference order of suspected fraudulent transactions (successor, middle and predecessor of suspected fraudulent transactions). Divide the fraudulent feature space into three corresponding subspaces, namely the precursor feature space of the fraudulent transaction, the successor feature space of the fraudulent transaction, and the median feature space of the fraudulent transaction, which correspond to the risk rating module, the subsequent analysis module and the association evaluation module respectively. Here, the "reference sequence of fraudulent transactions" in the present invention can be understood as, if there are 10 transaction data in total, assuming that the fifth transaction is a fraudulent transaction, then the feature space proposed by the present invention refers to the division of features before and after the occurrence of fra...

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 network payment anti-fraud system architecture based on suspected fraud transaction reference order, and relates to the field of network payment anti-fraud. According to themethod, a fraud feature subspace synthesis concept is creatively adopted, a complete fraud space division method based on a suspected fraud transaction reference order is provided for the first time,and a fraud feature space is divided into a fraud transaction predecessor feature space, a fraud transaction post-secondary feature space and a fraud transaction median feature space. Different feature subspaces refer to the order according to the transaction data generated in the transaction process of the user, several or all of the modules are used for analyzing whether the transaction is a fraudulent transaction or not, the results of the modules are integrated through the decision strategy of the voting method according to the results generated by the modules, and finally the decision result of the system is generated. According to the invention, the coupling property is reduced by utilizing the mutual independence of multiple modules, the multiple modules are combined by utilizing anintegration and coordination strategy, the expansibility and interpretability are good, the functions of the modules are complementary, and the anti-fraud system performance is improved.

Description

technical field [0001] The invention relates to the field of network payment anti-fraud, in particular to the architecture design of a network payment anti-fraud system. Background technique [0002] With the development of technology and service models such as mobile Internet and e-commerce, online payment has penetrated into people's daily life. Online payment can be used not only for online shopping, but also for fast offline payment, which greatly facilitates people's lives and improves efficiency. While online payment brings certain convenience, it also brings new risks, such as fraudulent issues such as fraudulent brushing and money laundering caused by identity theft or loss of mobile phones. For many online trading platforms, when fraudulent gangs break through the anti-fraud algorithm, they can cause huge economic losses (usually measured by the loss rate), so the anti-fraud work for online payment is particularly important. [0003] Most of the existing network p...

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): G06Q20/40G06K9/62
CPCG06Q20/4016G06F18/214G06F18/24
Inventor 王成胡瑞鑫
Owner TONGJI UNIV
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