Crowdsourced Parking Recommendation via Mobile Geolocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for calculating parking space availability require specialized equipment in parking lots and do not effectively account for real-time user behavior and multi-modal commute scenarios, leading to inefficiencies in finding available spaces during travel.
Innovation Solution
A computer-implemented method using crowdsourced data from geolocation-aware mobile devices to recommend parking spaces based on availability, user behavior patterns, and desired arrival times, which adjusts parking facility layouts and traffic flow without relying on imaging equipment or designated sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors or image capturing devices are deployed in parking lots to detect parking space availability, then parking space information can be captured, but the device complexity and cost increase significantly
Solution Approach 1:
The patent leverages the mobile devices themselves to perform the detection function. Users' smartphones with existing GPS and sensor capabilities are used to report their location and parking status, eliminating the need for dedicated detection infrastructure in parking lots. The system self-organizes by having users naturally contribute data during their normal commuting activities.
Solution Approach 2:
The patent repurposes universally available mobile devices for a specialized function (parking detection). Instead of requiring dedicated sensors in each parking lot, any mobile device can contribute to detecting parking availability by reporting its location and whether the user has successfully parked, making the detection capability universal across all areas covered by mobile device usage.
2Measurement precision
If traditional parking calculation methods are used without considering user behavior patterns, then simple computation is possible, but the accuracy of parking recommendations deteriorates
Solution Approach 1:
The system pre-calculates and stores user behavior patterns, historical parking success rates, and route characteristics during off-peak times. This preliminary processing allows the recommendation engine to quickly retrieve and combine pre-analyzed data during real-time queries, maintaining both high accuracy and computational efficiency.
Solution Approach 2:
The system continuously learns from actual user outcomes by incorporating feedback loops where parking success/failure data is fed back into the model. This feedback mechanism refines the behavior patterns and improves recommendation accuracy over time without requiring complex real-time computation for each query.
3Reliability
If parking lots are outfitted with specialized equipment to capture vehicle usage information, then real-time parking data can be obtained, but the ease of operation and deployment is reduced
Solution Approach 1:
The system uses users' existing mobile devices to automatically collect and report parking data without requiring any specialized equipment deployment. Users simply use their phones as normal during commuting, and the system passively collects location and parking status information, making deployment trivial while maintaining reliable real-time data collection.
Solution Approach 2:
The patent introduces a software intermediary layer that runs on users' mobile devices, acting as a mediator between the physical parking environment and the central system. This intermediary app on mobile devices captures vehicle usage information and transmits it to the server, eliminating the need for physical sensors in parking lots while maintaining real-time data reliability.
4Adaptability or versatility
If the system considers multiple factors including user behavior patterns and multi-modal commute scenarios, then the quality of parking recommendations improves, but the computational complexity increases
Solution Approach 1:
The patent divides the complex recommendation problem into separate modular components: route planning module, parking suitability evaluation module, user behavior analysis module, and multi-modal transport integration module. Each module handles a specific aspect independently, allowing the system to support multi-modal commutes with high adaptability while keeping individual computational tasks manageable and efficient.
Data Source
AI summary
Recommending a parking space to a target vehicle is provided. Current crowdsourced data corresponding to a plurality of vehicles geographically located at a plurality of parking facilities in geographic proximity to an intermediary parking destination of the target vehicle for travel mode change between a starting location and a final destination during a multi-modal commute is received. A parking space recommendation is generated for the target vehicle at the intermediary parking destination based on parking space availability information that includes the current crowdsourced data corresponding to the plurality of vehicles geographically located at the plurality of parking facilities. The parking space recommendation is transmitted to a mobile device of a user corresponding to the target vehicle.