Driver Identification From Mobile Use During High-Attention Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems misattribute passenger mobile device usage to the vehicle driver, leading to inaccurate assessment of driving behavior and negative impacts on insurance ratings.
Innovation Solution
Analyze telematics and device interaction data during high attention driving events to determine the vehicle driver by calculating a ratio of mobile device usage to total driving events, comparing it to a threshold, and using machine learning techniques to differentiate between the driver and passenger.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems attribute all mobile device usage to the driver, then the system is simple to operate, but the measurement precision of driver behavior assessment deteriorates
Solution Approach 1:
The system segments mobile device usage events into driver-specific and passenger-specific categories by analyzing contextual data patterns. It divides the assessment into high-attention driving events and low-attention driving events, applying different attribution rules to each segment to improve measurement precision without overwhelming system complexity.
Solution Approach 2:
The system introduces an intermediary analysis layer that processes mobile device usage data through multiple data points (geofence location, time of day, driving events, device orientation) before attributing usage to driver or passenger. This intermediary processing layer enables accurate differentiation while maintaining manageable system complexity through automated pattern recognition.
2Measurement precision
If the system collects and analyzes multiple data points to differentiate driver and passenger usage, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The system performs preliminary actions by pre-establishing geofences, pre-categorizing driving events into high-attention and low-attention types, and pre-defining attribution rules before actual usage analysis. This preparation work enables more accurate driver identification during operation without requiring complex real-time processing of all data points simultaneously.
Solution Approach 2:
The system changes parameters dynamically based on context - adjusting the stringency of driver attribution criteria depending on whether it's a high-attention or low-attention driving event, the location within geofences, and the time of day. This parameter adaptation allows accurate driver identification while managing data processing complexity through context-aware decision rules.
Data Source
AI summary
Method and system for determining whether a user of a mobile device is a driver of a vehicle. For example, the method includes receiving telematics data and device interaction data collected by the mobile device during vehicle trip segments, analyzing the telematics data to determine first driving events of a predetermined type during the vehicle trip segments, determining second driving events of the predetermined type during which the user interacts with the mobile device by correlating the telematics data and the device interaction data, calculating a ratio of the number of the second driving events to the number of the first driving events, and determining whether or not the user of the mobile device is the driver of the vehicle during the vehicle trip segments by comparing the ratio to a predetermined threshold.