Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fraudulent case identification model training method and device and computer equipment

A technology for identifying models and training methods, applied in computer parts, computing, character and pattern recognition, etc., can solve problems such as differences and low classification accuracy of classifiers, achieve high classification accuracy, improve sample imbalance, increase effect of quantity

Pending Publication Date: 2020-12-04
CHINA PING AN PROPERTY INSURANCE CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a training method, device and computer equipment for a fraud case identification model, aiming to solve the problem that the distribution of fraud cases in historical data is different from the actual distribution, thus affecting the low classification accuracy of the constructed classifier technical 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
  • Fraudulent case identification model training method and device and computer equipment
  • Fraudulent case identification model training method and device and computer equipment
  • Fraudulent case identification model training method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not intended to limit the present application.

[0052] refer to figure 1 , the embodiment of the present application provides a method for training a fraud case identification model, including:

[0053] S1. Obtain case samples with fraud labels from the preset original data set to form the first positive sample set, and case samples without fraud labels to form the first unlabeled sample set;

[0054] S2. In the first unlabeled sample set, use the method of replacement to collect case samples without fraud labels to form a second unlabeled sample set, and combine the second unlabeled sample set with the first The posi...

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 relates to the field of artificial intelligence, and discloses a fraudulent case identification model training method and device and computer equipment, which can more accurately identify fraudulent cases which are not marked in historical claim settlement cases under the condition of fewer fraudulent samples so as to increase the number of positive samples, and have the effect of filtering dirty data at the same time, the condition that samples in an original data set are unbalanced is improved, and then the fraudulent case classifier is constructed through the obtained data set, so that the classification accuracy of the obtained fraudulent case classifier is higher.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to a training method, device and computer equipment for a fraud case identification model. Background technique [0002] Traditional car insurance claim fraud identification often uses machine learning methods to mark fraud cases judged by humans in historical data as positive samples, and other cases are considered non-fraud cases, that is, negative samples, based on positive samples and negative samples in historical data Train a binary classifier. However, the proportion of fraudulent cases in historical data is very small, and the samples of non-fraudulent cases are actually impure, that is, there may be omissions in human judgment, resulting in some fraudulent cases mixed in non-fraudulent samples, which means The distribution of fraud cases in historical data is different from the actual distribution, and the unidentified fraud samples are dirty data, which will affe...

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): G06K9/62G06Q40/08
CPCG06Q40/08G06F18/241G06F18/214
Inventor 陈超群
Owner CHINA PING AN PROPERTY INSURANCE CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com