Mobile Device Usage State Detection for Driver Risk Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle monitoring systems fail to accurately distinguish and classify mobile device usage by drivers, leading to incorrect risk assessments and high false positives, as they do not account for various interaction types and device states effectively.
Innovation Solution
A method and system that assess device usage by receiving user device information, determining the device state, and classifying interactions using tap parameters, which includes processing data from sensors like accelerometers and proximity sensors to differentiate between device usage types, such as holding or mounting, and providing risk scores and feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional systems approximate mobile device presence in a vehicle, then device usage can be detected, but the accuracy of distinguishing different usage types is poor leading to high false positives
Solution Approach 1:
The patent segments device usage into distinct states (active, inactive, mounted, handheld) based on sensor data patterns. By dividing the detection space into discrete categories with specific criteria, the system achieves more precise classification of device usage types, reducing confusion between different usage scenarios and lowering false positives.
Solution Approach 2:
The system dynamically transitions between device usage states based on real-time sensor data analysis. Rather than using static thresholds, the patent employs dynamic state transitions that adapt to changing driving conditions and device handling patterns, improving detection accuracy while maintaining reliability across varied scenarios.
2Measurement precision
If multiple sensor data points are collected to improve classification accuracy, then device usage types can be distinguished better, but data processing complexity and resource consumption increase
Solution Approach 1:
The patent extracts only the most relevant features from sensor data for classification, rather than processing all available data points. By identifying and extracting key indicators (such as specific accelerometer patterns or proximity sensor readings) that most strongly correlate with device usage types, the system maintains high classification accuracy while reducing processing complexity.
Solution Approach 2:
The system changes parameters dynamically based on device state transitions. Rather than continuously processing all sensor data at full resolution, the patent adjusts processing intensity and parameter selection based on the current device state, optimizing the balance between classification accuracy and computational resource consumption.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system effectively reduces false positives by accurately distinguishing device usage types, providing actionable insights for insurance assessments and user feedback, and minimizing resource consumption by processing data efficiently.
Implementation Method 1
processing data from sensors like accelerometers and proximity sensors
Implementation Method 2
processing data from sensors like accelerometers and proximity sensors
Data Source
AI summary
A method for monitoring device usage includes: receiving user device information; based on the user interaction data, determining a state associated with the user device; and based on the state of the user device, determining a set of tap parameters. Additionally or alternatively, the method can include any or all of: determining a risk score based on at least on the set of tap parameters; determining an output based on the risk score; and/or any other suitable processes performed in any suitable order.