Vehicle loss determination method based on neural network, server and medium

Abstract

The invention is applicable to the technical field of artificial intelligence, and provides a vehicle loss determination method based on a neural network, a server and a computer-readable storage medium. The invention comprises the following steps: obtaining a loss determination evaluation image sequence of an accident vehicle to be determined; obtaining a loss determination evaluation image sequence of the accident vehicle to be determined. Feature extraction layer of a preset neural network model performs feature extraction on each of the fixed-loss evaluation images in the fixed-loss evaluation image sequence to obtain feature vectors of each of the fixed-loss evaluation images; determining a damage level probability vector of the accident vehicle based on a feature vector of all the constant loss evaluation images at a probability calculation layer of the preset neural network model; the preset damage level corresponding to the element with the largest median value of the damage level probability vector is determined as the damage level of the accident vehicle, thereby realizing the intellectualization of the vehicle damage determination, saving the labor cost and improving theaccuracy of the vehicle damage determination.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a neural network-based vehicle damage assessment method, a server and a computer-readable storage medium. Background technique [0002] In the process of auto insurance claims, it is usually necessary to determine the damage of the accident vehicle first, and then determine the compensation amount for the accident vehicle based on the damage determination results. [0003] In the existing technology, the vehicle loss assessment personnel usually manually assess the damage of the accident vehicle based on their own past experience, and the damage assessment standards and experience of different loss assessment personnel are different, which leads to the accuracy of the final damage assessment results. Low, and the progress of manual vehicle damage assessment is slow, and the labor cost is high. Contents of the invention [0004] In view of this, an e...

AI Technical Summary

Problems solved by technology

[0004] In view of this, an embodiment of the present invention provides a neural network-based vehicle damage assessment method, a server, and a computer-readable storage medium to solve the problem of low damage assessment accuracy and high labor costs in existing vehicle damage assessment methods. The problem

Images