Vehicular Trip Classification Using Device Interaction Similarity
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 device interaction data from personal and work trips, identifying representative features, and comparing them to baseline features to determine trip purpose.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a classification model is trained on historic device interaction data to classify vehicular trips, then classification accuracy is improved, but device complexity increases
Solution Approach 1:
The system segments the classification task by separating device interaction data collection from trip classification. Device interaction features (music playback, navigation, messaging) are collected and stored separately, then fed into the classification model. This segmentation allows the model to focus on pattern recognition without managing all data processing complexity internally.
Solution Approach 2:
Device interaction features serve as an intermediary between raw driving data and trip classification. Instead of directly analyzing complex driving behavior patterns, the system uses device interaction features as a mediator that captures contextual information about trip purpose, simplifying the classification process while maintaining accuracy.
2Reliability
If device interaction features are collected and analyzed to validate trip classification, then classification reliability is improved, but loss of information increases
Solution Approach 1:
The system extracts specific device interaction features (music playback, navigation usage, messaging activity) from the broader set of available driving data. By selectively extracting only the most relevant features for trip classification, the system maintains high reliability while minimizing information loss from unnecessary data processing.
Solution Approach 2:
The system applies partial action by analyzing only the most pertinent device interaction features rather than processing all possible driving data. This selective approach ensures sufficient information for reliable classification without the excessive processing overhead that would result from analyzing every conceivable data point.
Data Source
AI summary
A computer-implemented method can include receiving a user classification associated with an unlabeled vehicular trip as for work or for personal use. The method can also include determining a classification using a classification model, for the unlabeled vehicular trip as for work or for personal use by at least: determining a first set of baseline device interaction features associated with the first set of historic vehicular trips, determining a second set of baseline device interaction features associated with the second set of historic vehicular trips, determining a set of representative device interaction features associated with the unlabeled vehicular trip, receiving a set of weights associated with the first set of baseline device interaction features, the second set of baseline device interaction features, and the set of representative device interaction features, comparing the set of representative device interaction features against the first set of baseline device interaction features and the second set of baseline device interaction features, and classifying the unlabeled vehicular trip. The method can further comprise validating the user classification. Other embodiments are disclosed.