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

A vehicle collision detection method based on active learning

A technology of collision detection and active learning, applied in machine learning, vehicle components, vehicle safety arrangements, etc., can solve the problems of low accuracy of collision detection technology, achieve the effect of controlling the risk of claims and reducing the false alarm rate

Active Publication Date: 2019-11-05
重庆得润汽车电子研究院有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] A vehicle collision detection method based on active learning proposed by the present invention can solve the technical problem of low accuracy of traditional vehicle collision detection technology

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
  • A vehicle collision detection method based on active learning
  • A vehicle collision detection method based on active learning
  • A vehicle collision detection method based on active learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with accompanying drawing:

[0035] like figure 1 , figure 2 and image 3 As shown, the vehicle collision detection method based on active learning described in the first embodiment, the specific steps are as follows:

[0036] 1. Filter abnormal collision reports: for example, collision reports with ASI=0. Due to hardware problems, the acceleration values ​​of some collision reports cannot be collected or uploaded to the background. This part of the collision report has no reference significance for judging whether it is a real collision.

[0037] 2. Filter collision reports of frequent collisions: by observing the time period of vehicle collision reports generated on the system platform and the distribution of the number of reports, the time period T is predetermined 5 If the vehicle collision report exceeds the predetermined frequency F, it is considered that the vehicle-mounted terminal equipme...

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 an automobile collision detection method based on active learning and may solve the technical problem that traditional vehicle collision detection techniques are of low accuracy. The automobile collision detection method based on active learning employs a vehicular terminal device installed on a vehicle; longitudinal, transverse and vertical triaxial accelerations X, Y and Z of a vehicle are monitored in real time through acceleration sensors; if any of the trial accelerations is greater than preset value A within predetermined continuous time T1, the vehicular terminal device uploads a collision report to a system platform for the purpose of further inquiry, wherein vehicle collision detection is performed based on the collision report uploaded by the device. The automobile collision detection method based on active learning employs a mathematical model to construct objective indicators for reflecting vehicle collision severities, corresponding collision detection rules are made based on these indicators, vehicle collision types are depicted, and accordingly, false report rate of the device is decreased and the claim settlement risk is effectively controlled for an insurance company.

Description

technical field [0001] The invention relates to the field of automobile collision detection, in particular to an automobile collision detection method based on active learning. Background technique [0002] With the increasing popularity of automobiles and the improvement of people's awareness of vehicle insurance, vehicle insurance has become a very important part of property insurance, and the premium income of vehicle insurance business is naturally the most important part of property insurance business. However, with the vigorous development of the vehicle insurance business, fraudulent insurance behaviors such as falsely reporting vehicle accidents and forging false collisions also occur from time to time, which virtually increases the potential risks of the insurance company's vehicle insurance business. [0003] The on-board terminal equipment installed on the vehicle can obtain information such as the vehicle's geographical location and driving conditions. Based on ...

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): B60R21/013G06N99/00G06Q40/08
CPCB60R21/013G06N20/00G06Q40/08
Inventor 杨晙丁建栋郭恒
Owner 重庆得润汽车电子研究院有限公司
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