Element abnormal structure detection model construction method based on complex network

A technology of abnormal structure and detection model, which is applied in the fields of instruments, finance, and data processing applications, and can solve problems such as neglect

Active Publication Date: 2020-02-14
TIANJIN UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Often, these conne

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
  • Element abnormal structure detection model construction method based on complex network
  • Element abnormal structure detection model construction method based on complex network
  • Element abnormal structure detection model construction method based on complex network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] The detection method of illegal fund-raising behavior based on complex network proposed in this paper is mainly applied to discover illegal fund-raising behavior and find out its operation rules. When unearthing an illegal money syndicate, follow the steps described below.

[0036] Step 1: First, we obtain the bank's transaction data, and we mainly clean the bank's transaction flow.

[0037] Step 2: Further pre-process the data and remove redundant data. In order to protect the privacy of customers in the bank, we perform decryption processing, such as the customer's id (the card number in the bank).

[0038] Step 3: Construct a transaction network according to the ternary relationship model. The transaction network is G=(V, E, M, T). In its meaning, nodes are transaction nodes between customers, and the attributes on the edge include transaction time and trans...

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 element abnormal structure detection model construction method based on a complex network. The element abnormal structure detection model construction method mainly comprises the following steps: firstly constructing a transaction relation network through employing an extracted transaction relation according to a dependent bank transaction flow, finding out an outbreak time interval of a transaction, and calculating an abnormal value of each customer; and then, finding out a suspicious customer in the transaction burst interval and detecting a suspicious maximum communication sub-graph. The element abnormal structure detection model construction method provided by the invention describes the suspicion degree of each client in a more formalized manner, and is usedfor detecting fraud of a real world transaction network with large edge attributes. According to the element abnormal structure detection model construction method, the inherent characteristics of the nodes are mined from the client node behavior information, and the behaviors of the nodes are researched on the time sequence, and the characteristics of the nodes are described more accurately, andthe essence of clients is mined.

Description

technical field [0001] The invention belongs to the field of data mining, and is a method for constructing an element abnormal structure detection model based on a complex network, and then constructs a transaction relationship network according to the extracted transaction relationship, and mines trigger events of illegal fund-raising in transaction information according to the network. Background technique [0002] Banks and insurance companies lose billions of dollars each year to fraud. Traditional methods of fraud detection play an important role in reducing these losses. But fraudsters use all sorts of sophisticated methods to evade detection and various other ways to construct false identities. While the specifics of fraudulent behavior vary from operation to operation, the following pattern illustrates how fraudulent syndicates typically operate: (1) two or more individuals form a syndicate; (2) syndicates share a subset of legitimate contact information , such as ...

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): G06F30/18G06Q10/06G06Q40/02G06Q40/04
CPCG06Q10/0635G06Q40/02G06Q40/04Y02A90/10
Inventor 王文凯何东晓武南南孙越恒潘林王文俊
Owner TIANJIN 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