Driving Assessment Calibration for Missing Vehicle Trip Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for driving assessment inaccurately process missing vehicle data due to simple interpolation, failing to consider driving characteristics such as route and discontinuous driving, leading to significant errors in assessment.
Innovation Solution
A method for calibrating driving assessment by creating a time series of vehicle trip data, generating perception factor data for missing data, selecting candidate trip data with the highest matching degree, and restoring missing data based on candidate assessment factors, thereby improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If simple interpolation is used to correct missing vehicle data, then the processing is simple and fast, but the accuracy of driving assessment deteriorates due to significant errors
Solution Approach 1:
The system performs preliminary actions by creating a distribution map of perception factor data before missing data occurs, and pre-grouping candidate trip data according to numbers of trip misses. When missing data is detected, the system can immediately query and restore data based on the pre-established distribution and grouping, avoiding complex real-time calculations while maintaining high accuracy.
Solution Approach 2:
The system introduces perception factor data as an intermediary to bridge the gap between existing trip data and missing data. By creating a distribution of perception factors (such as sudden acceleration, sudden deceleration, route types) and using this distribution to guide the selection of candidate trip data, the system achieves accurate restoration without simple interpolation.
2Device complexity
If conventional correction methods are used, then the device complexity is low, but the reliability of driving assessment deteriorates due to failure to consider driving characteristics
Solution Approach 1:
The system segments the restoration process into distinct stages: creating perception factor distribution from existing data, grouping candidate trip data by number of trip misses, querying the distribution to determine the number of misses, selecting candidate data with highest matching degree, and restoring missing data. This segmentation allows each stage to be handled independently with appropriate complexity, achieving high reliability without excessive overall system complexity.
Solution Approach 2:
The system changes parameters by introducing perception factors (sudden acceleration, sudden deceleration, route types) as new dimensions for data analysis and grouping. By organizing candidate trip data according to numbers of trip misses and using perception factor distributions to guide selection, the system transforms the restoration process from simple value interpolation to multi-parameter matching, significantly improving reliability.
3Ease of operation
If simple interpolation is applied to missing data, then the ease of operation is high, but the accuracy of restoring driving characteristics deteriorates
Solution Approach 1:
The system creates copies of existing trip data and organizes them as candidate trip data grouped by numbers of trip misses. By copying and organizing historical data with similar characteristics (perception factors, route types, driving behaviors), the system can restore missing data with high accuracy while maintaining ease of operation through automated querying and matching processes.
Data Source
AI summary
A computing device may be configured to perform and/or use a method for calibrating a driving assessment. The method may comprise: creating vehicle trip data, comprising driving assessment data based on vehicle data, in a time series; based on missing trip data from multiple pieces of vehicle trip data, creating perception factor data based on the missing trip data; based on a distribution between the perception factor data and provisional trip data constituting pre-prepared provisional missing data, selecting candidate trip data that is grouped according to a number of trip misses among the provisional trip data; estimating the number of trip misses from the grouped candidate trip data that has a highest matching degree for the missing trip data; and restoring the missing trip data based on candidate assessment factor data that belongs to the candidate trip data corresponding to the estimated number of trip misses.