Driving risk identification method, electronic device and readable storage medium

Abstract

The present invention relates to the technical field of intelligent decision-making, and discloses a driving risk identification method. The method includes: performing first and second processing on the first driving data of each user in a preset user group to obtain the first Characteristic factor sequence, the third process is performed on the risk data of each user to obtain the historical risk value of each user, and the first characteristic factor and historical risk value are input into the neural network model based on the preset sorting algorithm for training to obtain the driving risk In the identification model, the second characteristic factor sequence of the specified user is input into the driving risk identification model to obtain the driving risk level of the specified user. The invention also provides an electronic device and a computer-readable storage medium. The invention can improve the accuracy of driving risk identification.

Description

technical field [0001] The invention relates to the technical field of intelligent decision-making, in particular to a driving risk identification method, an electronic device and a readable storage medium. Background technique [0002] Driving risk identification is an important topic in the field of road traffic safety. It is of great significance in providing targeted reminders to driving behaviors, improving driving behaviors, and preventing road traffic accidents. [0003] The current driving risk identification system is usually based on selected driving risk factors, through simple rules or the establishment of a linear regression model to achieve risk identification. The industry usually selects driving risk factors based on traditional human factors and vehicle factors, such as the driver’s gender, age, model of driving vehicle, and age of the vehicle, while some hidden factors, such as the driver’s behavioral characteristics (habitual rapid acceleration , rapid de...

AI Technical Summary

Problems solved by technology

The industry usually selects driving risk factors based on traditional human factors and vehicle factors, such as the driver’s gender, age, model of driving vehicle, and age of the vehicle, while some hidden factors, such as the driver’s behavioral characteristics (habitual rapid acceleration , rapid deceleration, sharp turns, often driving at night, etc.) also have a certain impact on driving risk, and the industry usually uses simple rules or traditional linear model modeling to identify driving risk, so the current driving risk factor selection is not sufficient. The model is too simple, resulting in low driving risk identification accuracy, and there is an urgent need for a method that can improve the accuracy of driving risk identification

Images