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

Loan intermediary agent identification method, system and device and storage medium

A recognition method and intermediary technology, applied in the field of Internet information, can solve problems such as low recognition accuracy, complicated actual operation, and inability to learn knowledge, and achieve the effect of improving recognition accuracy

Active Publication Date: 2020-03-17
铭迅(北京)信息技术有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The above methods all belong to known users as intermediaries. The main action is to collect manual annotations combined with traditional naive Bayesian and other supervised classification models to train artificially labeled data to identify black intermediaries. Supervised learning methods can only learn sample knowledge, but cannot learn samples. This puts higher requirements on the training samples, the training samples directly determine the generalization effect of the model, the actual operation is more complicated, and the recognition accuracy is low

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
  • Loan intermediary agent identification method, system and device and storage medium
  • Loan intermediary agent identification method, system and device and storage medium
  • Loan intermediary agent identification method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 1 As shown, Embodiment 1 of the present invention provides a loan intermediary identification method, the identification method includes:

[0044] S110. Construct a text feature vector of the first bookkeeping data.

[0045] In this embodiment, the first accounting data may include accounting data of multiple users.

[0046] Exemplarily, the first text data of user A includes "90,000 rebates for Jia Yu Youxin's approval", "50,000 C rebates for B's loan" and "5,100,000 and 250 intermediary fees for D's loan". Get user A's words "A", "Yuyouxin", "approval", "90,000", "rebate", "B", "loan", "50,000", "C", "rebate", " Ding", "loan", "5 thousand", "1 thousand", "fee", "250" and "intermediary fee", for example, "number of Chinese names" and "number of loan intermediary words" can be constructed Dimension feature vector, in which there are 4 Chinese names and 6 loan intermediary words, then the text feature vector of user A is [4,6].

[0047] S120. Cluster t...

Embodiment 2

[0054] Such as figure 2 As shown, Embodiment 2 of the present invention provides a loan intermediary identification method. Embodiment 2 of the present invention is further optimized on the basis of Embodiment 1 of the present invention. The identification method includes:

[0055] S210. Acquire the accounting behavior pattern and first accounting data of the intermediary user.

[0056] In this embodiment, it is first necessary to analyze and obtain the accounting behavior pattern of the intermediary user and the first accounting data. The intermediary user’s accounting behavior pattern is significantly different from that of the general user, mainly in the intermediary user’s accounting behavior pattern. The noun part of speech in the data has a higher weight than the name of the person, and the accounting content in the accounting data has a single structure, and there are intermediary-related keywords, such as "empty" and the frequency of words is significantly higher than...

Embodiment 3

[0077] Such as image 3 As shown, the third embodiment of the present invention provides a loan intermediary identification system 100, the loan intermediary identification system 100 provided by the third embodiment of the present invention can execute the loan intermediary identification method provided by any embodiment of the present invention, and has The corresponding functional modules and beneficial effects of the execution method. The recognition system 100 includes a vector construction module 200 , a user set clustering module 300 and a user set extraction module 400 .

[0078] Specifically, the vector construction module 200 is used to construct the text feature vector of the first accounting data; the user set clustering module 300 is used to cluster the first intermediary user set from the text feature vector based on the K-Means algorithm; The set extraction module 400 is configured to extract a second set of intermediary users from the first set of intermediar...

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 loan intermediary agent identification method, system and device and a storage medium. The loan intermediary agent identification method comprises the following steps of constructing the text feature vectors of the first accounting data; clustering a first intermediary agent user set from the text feature vectors based on a K-Means algorithm; and extracting a second intermediary agent user set from the first intermediary agent user set through an LDA model. According to the embodiment of the invention, the identification accuracy of the loan intermediary agents is improved.

Description

technical field [0001] Embodiments of the present invention relate to Internet information technology, and in particular to a method, system, device and storage medium for identifying black loan intermediaries. Background technique [0002] With the rapid development of Internet finance, there are more and more lending businesses based on the Internet. Due to information asymmetry, there are more and more intermediary agency behaviors. With the attraction of intermediary high rebates, more and more Black intermediary gang fraudulent behavior. It is reported that the current bad debt rate in the financial technology field is about 10%-15%, of which 60%-70% of the bad debts are "created" by black intermediaries; even among the loan applicants of many financial technology platforms, 10%-15% It is "manipulated behind the scenes" by black intermediaries. The "2018 Intelligent Anti-Fraud Insight Report" released by 360 Finance pointed out that black intermediaries exist to recom...

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): G06F16/35G06Q30/00G06Q40/02
CPCG06F16/35G06Q30/0185G06Q40/03
Inventor 韦雪碧
Owner 铭迅(北京)信息技术有限公司