Vehicle loss assessment method and device based on artificial intelligence, equipment and storage medium

Abstract

The invention relates to the technical field of machine learning of the artificial intelligence technology, and provides a vehicle loss assessment method and device based on artificial intelligence, equipment and a storage medium, and the method comprises the steps: querying a time period when a target vehicle is collided, obtaining a video clip of the target vehicle in a driving process, and storing the video clip in a database; intercepting a video clip of the target vehicle according to the time period to obtain a target video clip; and determining dynamic parameters and static parameters of the target vehicle according to the target video clip, inputting the dynamic parameters and the static parameters of the target vehicle into a pre-trained vehicle damage assessment model to obtain damage detail information of the target vehicle, and predicting a damage assessment value of the target vehicle according to the damage detail information. Compared with dynamic parameter analysis and static parameter analysis on the vehicle by analyzing a traditional static picture and a video clip with dynamic characteristics, the method is more in line with an actual accident scene, and the actual damage condition of the vehicle can be better predicted, so that the accuracy of the loss assessment value is improved.

Description

technical field [0001] The present application relates to the field of machine learning technology of artificial intelligence technology, in particular, the present application relates to a method, device, equipment and storage medium for assessing vehicle damage based on artificial intelligence. Background technique [0002] The current vehicle damage assessment method generally obtains a static image of the vehicle through a camera, processes the static image of the vehicle with the help of a model, and identifies the damaged area and parts of the vehicle. Since the external damage of the vehicle can only be estimated through static images, the damage assessment of the vehicle based on the external damage is easy to ignore the internal damage of the vehicle, resulting in a low accuracy rate of the final calculated damage value. Contents of the invention [0003] The main purpose of this application is to provide an artificial intelligence-based vehicle damage assessment ...

AI Technical Summary

Problems solved by technology

Since the external damage of the vehicle can only be estimated through static images, it is easy to ignore the internal damage of the vehicle if the vehicle is assessed based on the external damage, resulting in a low accuracy rate of the final calculated damage value

Images