Virtual Vehicle Tagging Using Mobile Sensor Fingerprints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining vehicle use by a driver often rely on user input, which may not accurately reflect actual usage, leading to inconsistencies in policies such as insurance rates.
Innovation Solution
A method using a mobile device with sensors like accelerometers and magnetometers to collect data, which is processed by a machine-learning model to identify the vehicle in use, allowing for accurate tracking of vehicle usage patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user input is used to determine vehicle use, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The system uses sensor data from the mobile device to automatically identify vehicle usage without requiring user input. The machine learning model processes accelerometer, magnetometer, and GPS data to self-determine whether the device is in a vehicle and which vehicle, eliminating the need for manual user reporting while improving accuracy.
Solution Approach 2:
The patent replaces the mechanical system of manual user input with an automated sensor-based detection system. Mobile device sensors (accelerometer, magnetometer, GPS) and machine learning algorithms substitute for human reporting, transforming the process from user-driven to system-driven vehicle usage identification.
2Measurement precision
If sensor data collection is implemented to identify vehicle use, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent leverages the mobile device's existing multi-functional sensors (accelerometer, magnetometer, GPS) that serve multiple purposes. These sensors are already part of the device for other functions, and the system repurposes them for vehicle usage identification, avoiding additional hardware complexity while improving measurement precision.
Solution Approach 2:
The machine learning model acts as an intermediary that processes raw sensor data and translates it into meaningful vehicle usage information. This intermediary layer simplifies the complexity by automatically handling data processing and interpretation, making the system manageable despite using multiple sensors.
3Productivity
If machine-learning models are trained with sensor measurements, then productivity is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary action by continuously collecting and pre-processing sensor data in the background, even when the device is not actively being used for vehicle identification. This allows the machine learning model to be pre-trained and ready for rapid vehicle usage determination, improving productivity while minimizing perceived time loss for the user.
Solution Approach 2:
The patent implements continuous data collection and processing, maintaining the useful action of vehicle usage identification constantly rather than on-demand. Sensors continuously monitor the environment, and the machine learning model continuously processes data, ensuring that vehicle usage information is always available without requiring additional time when needed.
Data Source
AI summary
Techniques are disclosed for virtual tagging of vehicles that include generating an association between a user of a mobile device and the mobile device. The techniques include receiving a first set of measurements from one or more sensors of the mobile device while the mobile device is positioned in a first vehicle during a trip and training a machine-learning model using the first set of measurements. The techniques further include receiving a second set of measurements from the one or more sensors of the mobile device and determining, by executing the machine-learning model using the third set of measurements, that the mobile device is positioned in the first vehicle or a second vehicle.