Target database construction method, target applicant identification method, target applicant identification device and target applicant identification system

A construction method and the applicant's technology, applied in the field of data processing, can solve problems such as resource waste, tedious manual verification work, and increased search time, and achieve the effects of small system processing capacity, fast judgment process, and improved verification efficiency

Pending Publication Date: 2021-01-15
南京星云数字技术有限公司
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When finding suspected loan gangs, the traditional data table structure needs to search and explore the entire amount of data, which is often extremely inefficient and takes up a lot of resources. With the increase of the amount of data, the search time will continue to increase. cause waste of resources
Moreover, when verifying the suspected list, the work of manual verification is very cumbersome, the cost is high, and it is prone to errors and omissions

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
  • Target database construction method, target applicant identification method, target applicant identification device and target applicant identification system
  • Target database construction method, target applicant identification method, target applicant identification device and target applicant identification system
  • Target database construction method, target applicant identification method, target applicant identification device and target applicant identification system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] combine figure 1 As shown, the present embodiment provides a method for constructing a target database, which at least includes the following steps:

[0064] S1. Construct the applicant relationship map based on the current full loan applicants and corresponding applicant information. Specifically, S1 includes the following sub-steps:

[0065] S11. Extract the applicant information of the current full loan applicant;

[0066] S12. Obtain the relationship between any two applicants according to the information of the applicants;

[0067] S13. Taking the applicant as the target node, and the relationship between applicants as the target relationship between the target nodes to construct an applicant relationship graph.

[0068] Specifically, the association relationships in this embodiment include at least suspected fraudulent relationships that can reflect a certain degree of aggregation, such as multiple applicants whose ID numbers come from the same region, the same...

Embodiment 2

[0101] combine figure 2As shown, this embodiment provides a method for identifying a target applicant, which is implemented based on the target database constructed in Embodiment 1, and at least includes the following steps:

[0102] S1'. Obtain the current application information of the current loan applicant.

[0103] The current application information includes at least one of the structured data and unstructured data in Embodiment 1. The structured data includes at least one of the application area, application address, IP address, application equipment, password, and application page stay time. One: the unstructured data includes at least one of recorded faces, recorded voices, video backgrounds, and audio backgrounds.

[0104] S2'. Match the current application information with the group features of each target malicious lending group in the target database according to preset matching rules.

[0105] Matching rules can be set in a variety of ways, such as including a...

Embodiment 3

[0111] In order to implement a loan identification method in the first embodiment above, this embodiment provides a corresponding loan identification device, such as image 3 As shown, the device includes at least:

[0112] The first building block is used to construct an applicant relationship graph based on the current full loan applicant and corresponding applicant information. The first building blocks include at least:

[0113] The first extracting unit is used to extract the applicant information of the current full loan applicant;

[0114] An acquisition unit, configured to acquire the association relationship between any two applicants according to the applicant information;

[0115] The first construction unit is configured to use the applicant as a target node, and the association relationship between the applicants is the target relationship between the target nodes to construct an applicant relationship graph.

[0116] The segmentation module is configured to se...

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 target database construction method, a target applicant identification method, a target applicant identification device and a target applicant identification system. The target database construction method specifically comprises the following steps: firstly, constructing an applicant relationship graph based on a current full loan applicant and corresponding applicant information; obtaining the applicant relationship graph, segmenting the applicant relationship graph based on preset suspected gang features to obtain a plurality of gang graphs, judging whether a loan gang is a target malicious loan gang or not according to the similarity between applicants in each gang graph, and finally constructing a target database based on the gang features of all target malicious loan gangs. The database comprising the gang features of all target malicious loan gangs can be constructed based on the current full-amount loan applicant, the loan gangs are directly segmented for the gang features and nodes which may have fraud in a relation graph mode and further verified and confirmed, and therefore the gang recognition time is shortened, and recognition efficiency is high.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a target database construction method, a target applicant identification method, device and system. Background technique [0002] With the development of Internet finance, many institutional loans can be completely applied and approved online, resulting in many malicious applications for loans and losing contact immediately after receiving the quota, which has brought great losses to financial institutions. How to identify malicious loans It has become a problem faced by various financial institutions. [0003] In the current technology, the identification of loans is mainly divided into two steps. The first step is to identify suspected loan gangs. Usually, certain conditions are used to directly search the applicant information data table to find applications with certain commonality and suspicious performance. people, as a suspected loan gang. Secondly, after finding out the l...

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): G06F16/36G06F16/41G06F16/45G06Q40/02
CPCG06F16/367G06F16/41G06F16/45G06Q40/03
Inventor 黄馨李怡文
Owner 南京星云数字技术有限公司
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