Commute Time Estimation via Trajectory Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of accurately determining personal commute time periods is exacerbated by sparse positioning coordinate points generated during the commute process, making it difficult to calculate commute times effectively.
Innovation Solution
A method and device that perform cluster analysis on commute trajectories to identify similar patterns, allowing for the determination of commute speed and time periods by combining trajectories and using weighted time arrays to estimate accurate commute times.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cluster analysis is performed on commute trajectories to improve measurement accuracy, then commute time estimation accuracy is improved, but computational complexity increases
Solution Approach 1:
The commute trajectory is segmented into multiple coordinate points with associated time stamps. By dividing the continuous trajectory into discrete segments, the system can perform cluster analysis on individual segments rather than the entire trajectory at once, reducing computational complexity while maintaining measurement accuracy through point-by-point speed calculations and time accumulations.
Solution Approach 2:
The system performs preliminary clustering of commute trajectory points before calculating final commute times. By pre-processing the trajectory data to identify and group similar commute patterns, the system establishes a foundation for more accurate speed determinations without performing complex real-time calculations during actual commute monitoring.
2Ease of manufacture
If sparse positioning coordinate points are used during commute, then data collection is simplified, but commute time calculation accuracy deteriorates
Solution Approach 1:
The system creates a reference commute trajectory by copying and combining multiple actual commute trajectories through cluster analysis. This reference trajectory serves as a template that fills in gaps from sparse positioning data, allowing accurate commute time calculations even when individual trajectory points are sparse. The copying process preserves the simplicity of data collection while enhancing calculation accuracy.
Solution Approach 2:
Multiple sparse commute trajectories are merged through cluster analysis to create a denser, more complete reference trajectory. By combining data from multiple commutes, the system compensates for sparse positioning points in any single trajectory, maintaining data collection simplicity while improving the completeness and accuracy of commute time calculations.
Data Source
AI summary
Embodiments of the present disclosure provide a method and device for a personal commute time period. The method includes: obtaining data of at least one commute trajectory of a user within a preset time period; performing cluster analysis on the data of the at least one commute trajectory to obtain at least one commute trajectory cluster, and obtaining a combined trajectory according to the commute trajectories in each commute trajectory cluster; for each commute trajectory T of the at least one commute trajectory, determining a commute speed of the user according to a combined trajectory corresponding to a commute trajectory cluster to which the commute trajectory T belongs; and determining a commute time period corresponding to the commute trajectory T according to the commute speed.