Probe Trace Parking Analysis for Non-Recurring Traffic Events
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems face challenges in predicting traffic increases that are not associated with regularly recurring patterns, as they rely heavily on web crawling techniques and struggle to identify sporadic or aperiodic events that affect traffic, limiting their ability to provide accurate real-time traffic management and route guidance.
Innovation Solution
A method and system that processes probe data to identify changes in vehicle numbers in specific areas, using artificial intelligence models to detect events prone to causing future traffic increases, allowing for predictive traffic management without relying on publicly available event calendars, and enabling operations such as route guidance, traffic flow control, and electronic map updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If web crawling techniques are used to identify events, then publicly available event information can be obtained, but the system cannot detect sporadic or aperiodic events that do not appear in public calendars
Solution Approach 1:
The patent introduces probe data as an intermediary source to bridge the gap between public event calendars and actual traffic conditions. By using probe data from navigation devices as a mediator, the system can detect sporadic events that do not appear in public calendars, thereby improving both information completeness and prediction reliability
Solution Approach 2:
The patent replaces the mechanical web crawling approach with an AI-based analysis system that processes probe data. This substitution enables the system to automatically detect event patterns and predict traffic increases without relying on public event calendars, resolving the contradiction between information availability and prediction accuracy
2Productivity
If navigation systems rely on regularly recurring traffic patterns, then predictable traffic conditions can be managed, but aperiodic traffic increases cannot be anticipated
Solution Approach 1:
The patent implements a dynamic system that adapts to different traffic conditions by using AI analysis of probe data. The system can identify both regularly recurring patterns and aperiodic events, making it versatile enough to handle varying traffic conditions while maintaining management efficiency through automated detection and prediction
Solution Approach 2:
The patent changes the parameters used for traffic analysis from static, pre-defined event calendars to dynamic, real-time probe data. By analyzing changes in probe data patterns, the system can detect both recurring and aperiodic traffic conditions, improving adaptability while maintaining productivity through automated parameter monitoring
3Reliability
If probe data processing is used to identify events, then sporadic events can be detected, but the system complexity increases compared to web crawling methods
Solution Approach 1:
The patent makes the probe data processing system multi-functional by using the same data source for both event detection and traffic pattern analysis. The AI system performs multiple functions including detecting sporadic events, identifying recurring patterns, and predicting traffic increases, thereby improving detection accuracy without proportionally increasing system complexity
Data Source
Figure 1
Figure 2~3
Figure 4~5
AI summary
A processing system (20) processes probe data to determine a change in a number of vehicles (51, 52) parked in an area (50), the probe data comprising information on probe traces for a plurality of probes. The processing system (20) identifies occurrence of an event based at least on the determined change in the number of vehicles (51, 52) parked in the area (50). The processing system (20) causes the identified occurrence of the event to be used for performing one or several operations.