Vehicular Trip Classification Using Telematics Feature Similarity

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems struggle to accurately classify vehicular trips as personal or non-personal use based on driving data, which is crucial for insurance and business reporting.

Innovation Solution

A computer-implemented method and system that classifies vehicular trips by training a classification model on historic telematics data from work and personal trips, identifying representative operation features, and comparing them against baseline features to determine trip purpose.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a classification model is trained on historic telematics data to classify vehicular trips, then classification accuracy is improved, but device complexity increases

Engineering Contradiction:

Improvetrip classification accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system segments the classification task by separating telematics data collection, feature extraction, model training, and classification validation into distinct modules. Historic telematics data is collected and stored separately, then processed through feature extraction to create baseline operation features, which are subsequently used to train classification models independently from the actual classification validation process.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-training classification models on historic telematics data before actual trip classification is needed. Baseline operation features are extracted and stored in advance, allowing the classification model to be ready for immediate use without requiring complex real-time processing during actual trips.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If operation features are compared against baseline features to validate trip classification, then classification reliability is improved, but measurement precision requirements increase

Engineering Contradiction:

Improvetrip classification reliabilityVSAvoidoperation feature measurement precision

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The system changes parameters by transforming raw telematics data into standardized operation features through feature extraction. Baseline operation features are derived by analyzing historic data patterns, and these standardized features are then compared against new trip data using defined deviation thresholds, allowing reliable classification without requiring extremely precise measurements.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system implements feedback by comparing operation features from unlabeled trips against baseline features and using the results to validate or correct user classifications. The deviation between expected and actual operation features provides feedback that reinforces or challenges the user's trip classification, improving overall reliability through iterative validation.

Inventive Principle:

Principle #23Feedback

3Loss of information

If user classification is validated against model classification, then information accuracy is improved, but loss of time increases

Engineering Contradiction:

Improveclassification information accuracyVSAvoidvalidation time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system applies partial validation by comparing operation features against baseline features and using deviation thresholds to quickly identify clear cases. Not all trips require full validation - the system can accept user classifications when operation features show sufficient deviation from baseline patterns, reducing validation time while maintaining accuracy for ambiguous cases.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12505410B1Systems and methods for validating a vehicular trip classification as for personal use or for work based upon similarity in operation features

Publication Date: 2025.12.23 QUANATA LLC

AI summary

Method, system, device, and non-transitory computer-readable medium for classifying a vehicle trip. In one aspect, a computer-implemented method includes: obtaining a user classification associated with an unlabeled vehicular trip; obtaining a first set of historic telematics data associated with work; obtaining a second set of historic telematics data associated with personal use; training a classification model based at least in part upon the first set of historic telematics data and the second set of historic telematics data; obtaining a set of unlabeled telematics data associated with the unlabeled vehicular trip; identifying and comparing a first set of baseline operation features, a second set of baseline operation features, a set of representative operation features; classifying the unlabeled vehicular trip; and validating the user classification based at least in part upon the user classification and the classification made using the classification model.