Parking Availability Prediction via Crowd Forecast Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems and online databases have limited awareness of parking lots and often prioritize well-known, expensive options, neglecting uncatalogued parking spaces that may be more available and closer to destinations.
Innovation Solution
A computer-based system that identifies and groups parking spaces, distinguishes between private and public spaces, trains crowd forecast models using human and vehicle activity data, and predicts availability by creating geofences based on user preferences, refining models for accurate predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If navigation systems prioritize well-known parking lots, then users can access familiar parking options, but parking availability decreases and costs increase
Solution Approach 1:
The system performs preliminary actions by cataloging and pre-mapping uncatalogued parking spaces before users need them. Mobile devices continuously detect and map parking spaces in advance, building a comprehensive database of available parking options including uncatalogued spaces, so that when users search for parking, both well-known and hidden spaces are already identified and ready for selection.
2Ease of operation
If users search for parking closer to destinations, then convenience increases, but finding available spaces becomes more difficult
Solution Approach 1:
The system enables self-service by allowing mobile devices to automatically detect, map, and update parking space information without requiring manual user input. The system continuously monitors and updates the status of nearby parking spaces, automatically making this information available to users so they can easily find available spaces close to their destinations without manual searching or reporting.
3Measurement precision
If comprehensive parking data is collected, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The system introduces intermediary components including centralized servers that aggregate data from multiple mobile devices, machine learning models that process raw data into predictions, and database systems that organize parking space information. These intermediaries mediate between the complex data collection process and the user interface, managing the complexity while enabling accurate predictions through sophisticated data processing and analysis.
Data Source
AI summary
Embodiments of the present invention disclose a method, a computer program product, and a computer system predicting parking availability. A computer identifies parking spaces and groups the parking spacing into parking locations. In addition, the computer distinguishes private parking spaces from public parking spaces, and trains a crowd forecast model for each of the parking locations. The computer further receives a destination and preferences, from which the computer creates a geofence based on the destination and preferences. The computer then predicts parking availability based on the crowd forecast models and refines the crowd forecast model.