Finding method and device for group fraud

A discovery method, gang technology, applied in other database retrieval, resource, network data retrieval and other directions to achieve the effect of improving security

Active Publication Date: 2017-09-22
深圳市分期乐网络科技有限公司
View PDF6 Cites 44 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This patented technology divides an internet dataset into smaller groups called communities that are used regularly during different times or days. These small clusters represent people who have been infected with malware. Based upon these characteristics, algorithms will be able to accurately identify any suspicious connections between them. By analyzing those connections over multiple periods, we aimed towards developing more efficient ways to detect and prevent credit card Fraud attacks by identifying specific patterns within their networks.

Problems solved by technology

The technical problem addressed in this patented text relates to prevention against credit card Fraud (CFO) attacks that involve multiple companies or different sources of debt through their own systems called CFO risk management system(CRM). Current solutions only allow people to monitor and investigate any issues related to these transactions before they can commit them again without being detected during later stages of the process itself.

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
  • Finding method and device for group fraud
  • Finding method and device for group fraud
  • Finding method and device for group fraud

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] figure 1 It is a flow chart of a method for discovering gang fraud provided by Embodiment 1 of the present invention. This embodiment is applicable to the situation of discovering gang fraud. The method can be executed by a gang fraud discovery device, which can be a server. Such as figure 1 Said, the method specifically includes the following steps:

[0050] Step 110, community-dividing the network relationship data in the network database every preset time period to obtain at least one first community.

[0051] Wherein, the preset time period can be set according to business requirements, for example, it can be set to 1 hour, 12 hours, or 1 day. The network database can be used to store network relationship data between network user nodes. In this application scenario, the network database is used to store network relationship data between user nodes involved in loan business. Network relationships may include social network relationships, communication network rel...

Embodiment 2

[0064] Figure 2a The flow chart of a method for discovering gang fraud provided by Embodiment 2 of the present invention is based on the above-mentioned embodiments, such as Figure 2a As shown, step 110 includes:

[0065] Step 111, acquiring node information in the network relationship data in the network database every preset time period.

[0066] Wherein, the node information may include the user name registered by the user in the network, the registered mobile phone number, the IP address and the device number used, etc. Specifically, the information of each node constituting the network relationship data in the network database is extracted every preset time period, and then the node information is analyzed.

[0067] Step 112, constructing relationship edges between node information according to network relationships.

[0068] Specifically, the way of constructing the relationship edge between node information according to the network relationship may be to construct ...

Embodiment 3

[0076] image 3 The flow chart of a method for discovering gang fraud provided by Embodiment 3 of the present invention is based on the above embodiments, such as image 3 As shown, step 130 includes:

[0077] Step 131, using the feature index information of the gang fraud community and the feature index information of the non-gang fraud community in the historical community to perform data training to obtain a training model.

[0078] Among them, the training model can choose a decision tree model or a logistic regression model. The process of using the characteristic index information of the gang fraud community and the characteristic index information of the non-gang fraud community in the historical community for data training can be as follows: respectively substituting the characteristic index information of the gang fraud community and the characteristic index information of the non-gang fraud community into the training model, Calculate parameter values ​​for the tra...

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 embodiment of the invention discloses a finding method and a finding device for group fraud. The method comprises the steps of performing community division on network relation data in a network database at regular intervals to acquire at least one first community; computing feature index information of the first community according to feature information of each node in the at least one first community; and predicting a group fraud risk of the first community according to the feature index information. In the prior art, when in anti-fraud, anti-fraud is performed by mainly performing all-round evaluation on individuals, and the method for effectively monitoring and investigating the group fraud risk is lacked. According to the finding method for group fraud provided by the embodiment of the invention, after the community division is performed on the network relation data, the group fraud risk of the divided community is predicted according to the feature index information, monitoring on the group fraud is achieved, and security of financial Internet can be improved.

Description

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

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
Owner 深圳市分期乐网络科技有限公司
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