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

A label propagation anti-fraud detection method and system based on enterprise relationship graph

A label dissemination and detection method technology, applied in the field of financial credit, achieves the effect of strong theoretical foundation, broad application prospects, and rich applicable scenarios

Active Publication Date: 2022-06-28
浪潮卓数大数据产业发展有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical task of the present invention is to provide a label propagation anti-fraud detection method and system based on the enterprise relationship graph to solve how to effectively analyze complex network data to find valuable information and further mine the fraud risks reflected in complex network relationships The problem

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 label propagation anti-fraud detection method and system based on enterprise relationship graph
  • A label propagation anti-fraud detection method and system based on enterprise relationship graph
  • A label propagation anti-fraud detection method and system based on enterprise relationship graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] The label propagation anti-fraud detection method based on the enterprise relationship graph of the present invention comprises the following steps:

[0069] S1. Establish an enterprise blacklist database: data collection technology collects raw network data, which is stored in a relational database, filters the tables and fields in the relational database that can be included in the anti-fraud blacklist database, and extracts relevant data, Integrate and deduplicate preprocessing to establish an enterprise anti-fraud blacklist database; the specific steps are as follows:

[0070] S101. Data collection and storage: based on data collection technology, collect data covering enterprise information, blacklist information and information on various untrustworthy enterprises across the country, and store the collected data in a relational database; enterprise information includes enterprise name, social credit code, and listing Blacklist time.

[0071] S102. Screening of ob...

Embodiment 2

[0100] The label propagation anti-fraud detection system based on the enterprise relationship graph of the present invention includes,

[0101] The enterprise blacklist database establishment unit is used to establish the enterprise anti-fraud blacklist database through the preprocessing of extraction, fusion and deduplication of the original network data collected by the data collection technology;

[0102] The relational graph construction unit is used to extract the relational database object entities and entity relationships to construct the relational graph by screening the relevant tables and fields of the relational graph in the relational database;

[0103] The anti-fraud detection unit is used to perform anti-fraud detection on the enterprise based on the self-built blacklist database and the enterprise relationship graph, and estimate the probability of the enterprise being fraudulent.

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 tag propagation anti-fraud detection method and system based on enterprise relationship graph, which belongs to the field of financial credit, and the technical problem to be solved is how to effectively analyze complex network data to find valuable information and further mine complex The technical scheme of the fraud risk embodied by the network relationship is as follows: ①The steps of the method are as follows: S1. Establish a blacklist database of enterprises; S2. Build a relational map: filter the relevant tables and fields included in the relational map in the relational database, and extract relational database objects Entity and entity relationship; S3. Anti-fraud detection for enterprises based on self-built blacklist database and enterprise relationship graph: identify blacklist nodes in the relationship graph based on blacklist database, extract blacklist node connection subgraph, and use label propagation algorithm to identify each connection Fraudulent enterprise nodes in the subgraph, and estimate the probability of anti-fraud enterprises. ②The system includes the establishment unit of the enterprise blacklist database, the construction unit of the relationship graph and the anti-fraud detection unit.

Description

technical field [0001] The invention relates to the field of financial credit, in particular to a method and system for anti-fraud detection of label propagation based on an enterprise relationship graph. Background technique [0002] Under the current market environment of inclusive finance, online fraud risks change very frequently. In the past, single individual fraud has rapidly evolved into organized and large-scale group fraud and corresponding associated risks. However, traditional anti-fraud methods include identity verification, logical verification of customer information, comparison and verification of external information, and blacklist filtering. A network-based global risk identification capability is needed to cover this part of the risk vulnerabilities. Due to the intricate relationships of many large enterprises, traditional graphics monetization methods will no longer apply. In order to solve this problem, the patent document with the patent number of CN1...

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): G06Q40/02G06F16/28G06F16/23G06F16/36G06F16/2458
CPCG06F16/284G06F16/23G06F16/367G06F16/2465G06Q40/03
Inventor 尹盼盼崔乐乐郭宏毅
Owner 浪潮卓数大数据产业发展有限公司