Insurance fraud identification method and device based on telecommunication data

A technology of insurance fraud and identification method, which is applied in the field of insurance fraud identification based on telecommunication data, which can solve the problems of misjudgment and missed judgment in fraud case identification, and achieve the effects of avoiding innocent losses, reducing resources, and improving efficiency

Inactive Publication Date: 2017-11-28
云数信息科技(深圳)有限公司
View PDF4 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is mainly aimed at the data of the insurance case itself, using a single supervised learning algorithm, regression analys

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
  • Insurance fraud identification method and device based on telecommunication data
  • Insurance fraud identification method and device based on telecommunication data
  • Insurance fraud identification method and device based on telecommunication data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] see figure 1 , is a flow chart of a method for identifying insurance fraud based on telecommunication data provided in Embodiment 1 of the present invention; the method includes:

[0060] S101. Extract the mutual contact data between the persons involved in the case from the telecommunication data of the persons involved in the insurance case to be identified; wherein, the mutual contact data includes at least one of the number of calls, the duration of calls or the length of short messages;

[0061] S102. Calculate the correlation coefficient between the two persons involved in the case by using the pre-configured first data model according to the mutual relationship data between the persons involved in the case;

[0062] S103. According to the correlation coefficient, determine whether the persons involved in the case are closely related;

[0063] S104. Determine whether the insurance case to be identified is a fraud case according to whether the persons involved in ...

Embodiment 2

[0067] see figure 2 , is a flowchart of a method for identifying insurance fraud based on telecommunication data provided in Embodiment 2 of the present invention; the method includes:

[0068] S201. Extract the mutual contact data between the persons involved in the case from the telecommunication data of the persons involved in the insurance case to be identified; wherein, the mutual contact data includes at least one of the number of calls, the duration of calls or the length of short messages;

[0069] S202. According to the mutual relationship data between the persons involved in the case, calculate the correlation coefficient between the persons involved in the case by using the pre-configured first data model;

[0070] S203. According to the correlation coefficient, determine whether the persons involved in the case are closely related;

[0071] S204. Extracting a first characteristic variable from the original data of the insurance case to be identified and the telec...

Embodiment 3

[0103] see Figure 4 , is a structural diagram of an insurance fraud identification device based on telecommunication data provided by Embodiment 3 of the present invention.

[0104] Correspondingly, the present invention also provides an insurance fraud identification device based on telecommunication data, including:

[0105] The first extraction module 401 is used to extract the mutual contact data between two persons involved in the case from the telecommunication data of the persons involved in the insurance case to be identified; wherein, the mutual contact data includes the number of calls, the duration of calls or the length of short messages at least one of the

[0106] The first calculation module 402 is configured to calculate the correlation coefficient between the two persons involved in the case according to the mutual relationship data between the two persons involved in the case, using a pre-configured first data model;

[0107] The first judging module 403 i...

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 insurance fraud identification method based on telecommunication data, including the following steps: extracting interrelation data between every two people involved from telecommunication data of people involved in an insurance case to be identified; using a pre-configured first data model to calculate the correlation coefficient between every two people involved according to the interrelation data between every two people involved; determining whether the people involved are close according to the correlation coefficient; and determining whether the insurance case to be identified is a fraud case according to the whether the people involved are close. Accordingly, the invention discloses an insurance fraud identification device based on telecommunication data. According to the embodiments of the invention, insurance fraud can be quickly and accurately identified, insurance companies are prevented from suffering a loss innocently, and the efficiency of claim handling is improved.

Description

technical field [0001] The present invention relates to the field of fraud identification, in particular to a method and device for identifying insurance fraud based on telecommunication data. Background technique [0002] In recent years, the total premium income of auto insurance business of domestic insurance companies has increased year by year, but the profitability is worrying. Statistics from the China Insurance Regulatory Commission show that about 20% of auto insurance claims are fraudulent. A very important reason why auto insurance operations have been on the brink of loss is the proliferation of auto insurance fraud. Fraud is hailed as a silent catastrophe in the insurance industry, devouring the meager profit margins of the insurance industry all the time, causing insurance companies to suffer innocent losses. Therefore, the implementation of the anti-fraud system is of great significance for promoting the healthy development of the insurance industry and impr...

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): G06Q30/00G06Q40/08
CPCG06Q30/0185G06Q40/08
Inventor 谭浩宇肖文晗郭贤均
Owner 云数信息科技(深圳)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