Road Priority Determination Using Vehicle Speed and Count
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining road priority levels are resource-intensive and slow, requiring machine learning or AI programs that need extensive training and are not scalable across different regions.
Innovation Solution
A method and system that determine road priority levels based on the total number of vehicles and their speeds, using GPS data to calculate a position and assign priority levels without the need for retraining across different areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning or AI programs are used to determine road priority levels, then measurement precision is improved, but use of energy and device complexity increase significantly
Solution Approach 1:
The patent replaces complex machine learning/AI systems with a simpler mathematical formulation that uses GPS trajectory data and vehicle speed information to calculate road priority levels through deterministic algorithms, eliminating the need for resource-intensive training models while maintaining determination accuracy
Solution Approach 2:
The patent extracts only the essential features needed for road priority determination (vehicle count, speed, GPS trajectories) from the broader context of road network data, processing only these key parameters through straightforward calculations rather than comprehensive AI analysis, thereby reducing computational resource requirements
2Measurement precision
If machine learning or AI programs are used to determine road priority levels, then measurement precision is improved, but loss of time increases due to training requirements
Solution Approach 1:
The patent performs preliminary data collection and processing of GPS trajectories and vehicle speed information in advance, pre-calculating road priority levels using straightforward mathematical formulas that require no training time, enabling immediate application across different regions without model retraining
Solution Approach 2:
The patent substitutes time-consuming AI training processes with instantaneous mathematical calculations based on extracted features, allowing road priority determination to be performed in real-time without the latency inherent in training and adapting machine learning models
3Device complexity
If a single machine learning or AI model is used, then device complexity is reduced, but adaptability worsens across different areas or regions
Solution Approach 1:
The patent creates a universal road priority determination method based on fundamental traffic flow principles and mathematical relationships that apply consistently across all regions, eliminating the need for region-specific models while maintaining high adaptability through location-independent calculations
Solution Approach 2:
The patent uses parameter transformations that normalize road characteristics across different regions by calculating priority levels based on relative vehicle counts and speed patterns rather than absolute values, allowing the same algorithm to adapt to various geographic areas without model modification
Data Source
AI summary
The present disclosure provides methods and systems for determining a priority level of a road. In some examples, there is provided a method comprising: determining, by a processor, a position associated with a road relative to one or more roads based on a total number of one or more vehicles that travelled on the road and a speed of the one or more vehicles on the road; and determining, by the processor, a priority level of the road based on whether a position associated with a priority level relative to one or more priority levels for the one or more roads matches the position associated with the road.