Electronic Map Parking Profiles from Full Parking-Search Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for generating parking-related data, such as parking probability or expected parking search time, for segments of an electronic map are not sufficiently accurate as they only consider the stationary period at the end of a trip, neglecting the preceding search for a parking space.
Innovation Solution
A method and system that analyze positional data from vehicle trips to identify parking space search portions, incorporating both successful and unsuccessful parking attempts, to determine parking-related parameters like probability and search time for each segment, considering the entire search process rather than just the final parked location.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only the stationary period at the end of a trip is considered for generating parking-related data, then the data generation process is simple, but the accuracy of parking probability and search time predictions is insufficient
Solution Approach 1:
The trip is segmented into multiple portions: a parking space search portion (from when the vehicle starts searching for parking until a stationary period begins) and a non-search portion. By analyzing only the search portion, the system captures actual parking search behavior while excluding irrelevant driving segments, thereby improving prediction accuracy without requiring analysis of the entire trip.
Solution Approach 2:
The method extracts and isolates the parking space search portion from the complete trip data. This extraction focuses the analysis specifically on the period when the vehicle is actively searching for parking, removing confounding factors from other driving activities and enhancing the precision of parking-related parameter calculations.
2Measurement precision
If the entire parking space search process is analyzed, then the accuracy of parking-related data improves, but the data processing complexity increases
Solution Approach 1:
The system performs preliminary identification of the parking space search portion within the trip before conducting the main analysis. By pre-segmenting the trip data to identify where the search begins and ends, the system prepares the data structure in advance, making the subsequent analysis of search time and probability more accurate while managing processing complexity through structured preprocessing.
Solution Approach 2:
The system uses the vehicle's own positional data and trip patterns to automatically identify and define the parking space search portion without requiring external manual annotation or intervention. The method leverages the inherent characteristics of the trip data itself (such as speed patterns, location changes, and stationary periods) to self-determine the search boundaries, improving accuracy while avoiding the complexity of external data collection methods.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A method is disclosed for generating profile data indicative of the time dependence of a time dependent parameter, such as a parking related parameter, in respect of one or more navigable elements of a navigable network within a geographic area, each navigable element being represented by a segment of an electronic map. The method comprises obtaining, for each one of at least one set of a plurality of different time periods, a relative value of the time dependent parameter associated with each one of a plurality of segments of the electronic map in respect of the time period. The method further comprises clustering, for the or each set of time periods, the segments into groups of segments based on the relative values of the time dependent parameter obtained for the segments in each time period of the set. The method further comprises using, for each group, relative time dependent parameter data associated with the segments of the group to obtain an aggregate profile indicative of the time dependence of the relative value of the time dependent parameter, the aggregate profile being applicable to each of the segments of the group.