Vehicle Vocation Classification Using Telematics Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fleet owners struggle to distinguish between different driving patterns of similar and dissimilar vehicles within their fleet, limiting their ability to benchmark vehicle performance effectively across different industries and vehicle types.
Innovation Solution
A telematics system that classifies vehicle vocation independently of fleet, industry, and vehicle type groupings by analyzing historical data using machine learning techniques to identify predominant behavioral execution patterns, allowing for the benchmarking of vehicles with similar usage patterns regardless of their operational context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vehicles are grouped by fleet, industry, or vehicle type, then traditional classification methods are simple to implement, but the ability to distinguish different driving patterns and benchmark performance is limited
Solution Approach 1:
The patent segments vehicle classification into multiple independent dimensions: fleet groupings, industry groupings, vehicle type groupings, and usage pattern groupings. This segmentation allows the system to analyze driving patterns independently from traditional categorizations, enabling more precise performance benchmarking by comparing vehicles with similar usage patterns regardless of their fleet, industry, or type.
Solution Approach 2:
The patent introduces a new classification dimension based on usage patterns that operates independently from traditional fleet, industry, and vehicle type groupings. This additional dimension allows vehicles to be classified and benchmarked based on actual driving behavior rather than administrative or physical categories, significantly improving measurement precision for performance evaluation.
2Adaptability or versatility
If traditional fleet-based classification is used, then data organization is straightforward, but performance benchmarking across different vehicle types and industries is not possible
Solution Approach 1:
The patent creates a universal classification framework that works across multiple fleets, industries, and vehicle types simultaneously. The usage pattern-based classification system is designed to be fleet-agnostic, allowing performance benchmarking to be applied universally across diverse vehicle populations without requiring fleet-specific customization, thereby enhancing adaptability and versatility.
Solution Approach 2:
By adding the usage pattern dimension independent of traditional fleet-based classification, the system enables cross-fleet, cross-industry, and cross-vehicle-type benchmarking. This dimensional addition allows the same classification and benchmarking methodology to be applied universally across different contexts while maintaining the ability to handle diverse data types and structures.
3Measurement precision
If usage pattern analysis is added to traditional classification, then vehicle performance benchmarking precision is improved, but the system complexity increases
Solution Approach 1:
The system segments the classification task into distinct layers: traditional categorizations (fleet, industry, vehicle type) and usage pattern analysis. This segmentation allows each component to be processed independently, with usage patterns extracted and analyzed separately from traditional metadata. The modular structure manages complexity by breaking down the overall classification problem into manageable, independent segments that can be processed and combined systematically.
Data Source
AI summary
System for automatically classifying vehicle vocation and benchmarking vehicle performance relative to other vehicles having the same vocation classification, independent of vehicle fleet groupings, industry vehicle application groupings and vehicle type groupings, is disclosed. The system includes a vehicle vocation classifier in communication with a data management system to store historical vehicle data including recurring vehicle usage data, and assign one or more predicted vocations for each vehicle based on the recurring vehicle usage data using a machine learning technique. The system also includes a benchmarking management system for grouping the historical vehicle data for vehicles of same determined predicted vocation, determining therefrom benchmarking vehicles having better performance characteristics than other vehicles of the same determined predicted vocation, and benchmarking performance of the other predicted vocation vehicles relative to the benchmarking vehicles.