POI Arrival Time Prediction Using Parking and Entry Wait Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Navigation systems fail to accurately predict the time of arrival at large-scale points of interest (POIs) due to the lack of consideration for parking times and entry wait times, especially in areas like underground parking lots where no road links are provided on geographic information systems.
Innovation Solution
Collect driving data and trajectory data using GPS to derive parking times and entry wait times, integrating these with real-time traffic information to provide an estimated time of arrival, including congestion levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If navigation systems calculate ETA based only on road link information from GIS, then the system complexity remains low, but the accuracy of ETA prediction deteriorates for large-scale POIs with parking lots
Solution Approach 1:
The patent segments the ETA calculation into multiple components: driving time on road links, entry wait time at parking lot entrances, and parking time within the parking lot. Each component is calculated separately using different data sources and methods, then summed to produce the total ETA. This segmentation allows the system to maintain simplicity for road navigation while adding complexity only where needed for accurate POI arrival prediction.
Solution Approach 2:
The system performs preliminary actions by pre-calculating and storing entry wait times and parking times based on historical trajectory data and driving data. These pre-computed values are then reused for ETA predictions, avoiding the need for complex real-time calculations and reducing system complexity during actual navigation operations.
2Reliability
If navigation systems collect and process additional data (driving data, trajectory data) to derive parking times and entry wait times, then the accuracy of traffic information improves, but the data processing complexity increases
Solution Approach 1:
The patent extracts only the necessary data elements from complex datasets. From trajectory data, it extracts entry times and exit times to calculate parking duration. From driving data, it extracts travel times on road links leading to parking lots. This selective extraction reduces data processing complexity while maintaining reliability of the derived traffic information.
Solution Approach 2:
The system uses existing GPS trajectory data and driving data that are already being collected for navigation purposes. Instead of requiring separate data collection systems, it leverages data already available in the navigation system to derive parking times and entry wait times, reducing overall system complexity while improving traffic information accuracy.
3Reliability
If navigation systems aggregate travel times of multiple vehicles to calculate entry wait times, then the reliability of congestion level prediction improves, but the time and computational resources required increase
Solution Approach 1:
The system performs preliminary aggregation of travel times from multiple vehicles and stores the results as pre-computed entry wait times. This historical aggregation is done in advance and stored for future reference, so that when a user needs congestion information, the system can quickly retrieve pre-aggregated data rather than performing time-consuming real-time aggregation, thus reducing time loss while maintaining reliability.
Solution Approach 2:
The system performs data aggregation periodically rather than continuously, collecting travel time data from vehicles over specific time periods and aggregating them at intervals. This periodic approach reduces the computational burden and time required compared to continuous real-time aggregation, while still providing reliable congestion level predictions based on sufficient sample sizes.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Accurately predicts the time required for parking and entry into POIs, providing optimal route guidance by analyzing patterns of vehicle arrival times and wait times, enhancing navigation system accuracy and reliability.
Implementation Method 1
trajectory data including information obtained through a global positioning system (GPS), with respect to trajectories of vehicles moving along a non-predefined route within a parking lot
Data Source
AI summary
Methods and apparatuses for providing an estimated time of arrival at a point of interest (POI) in a navigation system are described. According to one embodiment, the method includes collecting driving data and trajectory data, generating parking time data of the vehicles by deriving times required for the vehicles to park based on the trajectory data and integrating the times required for the vehicles to park, deriving travel times of the vehicles traversing links leading to an entrance to the parking lot based on the driving data, calculating the vehicles' entry wait times by aggregating the travel times, and generating entry wait time data by integrating the vehicles' entry wait times, and deriving estimated times of arrival of the vehicles by summing the times required for the vehicles to park and the entry wait times, and generating estimated arrival time data by integrating the vehicles' estimated times of arrival.