Unsupervised driving style analysis method based on basic driving operation event

Abstract

The invention provides an unsupervised driving style analysis method based on a basic driving operation event. The unsupervised driving style analysis method comprises the steps that data are acquired and preprocessed; extracting a basic driving operation event; performing feature construction and extraction on each event in the basic driving operation events to obtain event intensity features; event intensity clustering is carried out through k-means, and event intensity category labels are marked; obtaining a dynamic time window, and constructing a time-varying event curve which represents a driving style in the dynamic time window and has an event intensity category label; and based on a curve clustering algorithm fused with DTW, the curves of the dynamic time windows are clustered to obtain various time window curves, and driving style types are labeled. According to the method, a basic driving operation event is taken as a basic unit, event intensity and event transfer characteristics are considered, a change curve of the event along with time is taken as a characteristic for describing a driving style, dynamic decision information, data continuity and time characteristics of a driving behavior are reflected, original data information is reserved, and driving style analysis accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of traffic analysis, in particular to an unsupervised driving style analysis method based on basic driving operation events. Background technique [0002] With the development of social science and technology, driving style analysis has become a research hotspot. Driving style plays an important role in road safety, vehicle economy, vehicle insurance, and smart car design: detection of driving style and real-time feedback to drivers can effectively reduce the occurrence of road traffic accidents; driving style greatly affects the The fuel economy of the vehicle, the more aggressive the driving behavior, the lower the fuel economy; the vehicle insurance fee also depends on the driving style of the vehicle user, and setting different insurance premiums for drivers with different driving styles can maximize the benefits of the insurance company; With the development of artificial intelligence, intelligent vehi...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides an unsupervised driving style analysis method based on basic driving operation events, so as to solve the existing driving style analysis methods that do not start from basic driving operation events, do not consider event intensity and event transfer characteristics; use discrete feature points To characterize the driving style, the continuity of natural driving data cannot be preserved, and the time characteristics are omitted; the clustering algorithm for continuous curves of different lengths is lacking, and it is impossible to perform efficient and accurate clustering analysis of driving styles based on continuous curve characteristics for data samples of different lengths The problem

Images