Vehicle damage identification method and server

A recognition method and server technology, applied in the computer field, can solve the problems of missing detection of damaged parts, unguaranteed recognition accuracy and recall, and recognition errors, so as to avoid detection omissions or recognition errors, and improve recognition. Accuracy and pass rate, the effect of improving accuracy and recall

Active Publication Date: 2018-08-31
PING AN TECH (SHENZHEN) CO LTD
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing automatic detection scheme is sometimes easier to miss or identify the damaged part, and the accuracy and recall of the identification cannot be guaranteed.

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
  • Vehicle damage identification method and server
  • Vehicle damage identification method and server
  • Vehicle damage identification method and server

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0038] In the first embodiment, the vehicle damage identification method includes:

[0039]Step S10, the server receives the damage assessment request sent by the user through the first terminal and includes the damage assessment photo, analyzes the damage assessment photograph using the preset first preset type model, and obtains the first damage assessment photo corresponding to the damage assessment photograph. classification information of damaged parts, and return the classified information of the first damaged parts to the first terminal for display.

[0040] In this embodiment, the server receives a photo sent by the user through the first terminal (such as a mobile phone, a tablet computer, a handheld device, etc.) that includes a damage assessment photo (for example, a close-up photo of the vehicle damage location) uploaded by the user and including the damaged part of the vehicle to be determined. ) request for loss determination. In one embodiment, the auto insuran...

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 vehicle damage identification method and a server. The method includes: receiving a damage determination request sent by a user through a first terminal, and using a preset first preset type model to analyze a damage determination photo to obtain the corresponding first classification information of damaged parts, and return the classified information of the first damaged parts to the first terminal for display; Using the preset first preset type model to analyze the damaged photos again to obtain the corresponding classification information of the second damaged parts, and return the classified information of the second damaged parts to the first terminal for display; The user sends an instruction of rejecting the classification information of the second damaged part through the first terminal, and then sends an instruction to manually identify the damaged part of the damaged photo to the predetermined second terminal. The invention improves the accuracy rate and recall rate of vehicle damage identification.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a vehicle damage identification method and a server. Background technique [0002] At present, one of the difficulties in the auto insurance business is that a lot of manpower and material resources are required to be invested in the auto insurance claims process. In order to effectively reduce the manpower and material resources in the process of auto insurance claims, some insurance companies currently use image detection and recognition technology to automatically detect damaged parts. However, the existing automatic detection scheme is sometimes relatively easy to miss or identify the damaged part, and the accuracy and recall of the identification cannot be guaranteed. Contents of the invention [0003] The main purpose of the present invention is to provide a vehicle damage identification method and server, aiming at improving the accuracy and recall rate of vehicle dam...

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 Patents(China)
IPC IPC(8): G06K9/62G06N3/08G06Q40/08
CPCG06N3/08G06Q40/08G06F18/24G06F18/214
Inventor 黄章成马进王健宗肖京
Owner PING AN TECH (SHENZHEN) CO LTD
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