Journey Time Estimation Using Historical Data and Error Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current journey time estimation methods, particularly in urban areas, are prone to inaccuracies due to traffic congestion and fluctuations, leading to inefficient route planning and increased costs for logistics and emissions.
Innovation Solution
A method utilizing a database of historical journeys to estimate journey times by selecting nearest neighbors based on origin and destination, calculating an average journey time with error estimation, and adjusting for time of day and vehicle type, providing a more accurate prediction than static models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If static route planning algorithms are used to calculate journey time, then the routing process is simple and fast, but the journey time estimation accuracy deteriorates due to traffic congestion and fluctuations
Solution Approach 1:
The system performs preliminary actions by collecting and storing historical journey time data from multiple sources (GPS devices, traffic sensors, user feedback) before actual route planning occurs. This historical data is pre-processed and stored in databases, allowing the system to quickly retrieve and analyze past journey patterns without performing complex real-time calculations during actual route planning, thus improving accuracy without proportionally increasing real-time system complexity
Solution Approach 2:
The system introduces historical journey time data as an intermediary element between the route planning algorithm and the final journey time estimate. Instead of relying solely on static route planning algorithms or complex real-time traffic analysis, the system uses historical data as a mediator to provide more accurate journey time predictions by comparing planned routes with historically similar routes, thereby improving accuracy without requiring the full complexity of real-time traffic modeling
2Measurement precision
If historical journey data from nearest neighbors is used to estimate journey time, then the prediction accuracy improves, but the calculation time and processing complexity increase
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing characteristics of historical journeys including origin-destination pairs, journey times, and traffic conditions in databases. When a route planning query is received, the system quickly retrieves pre-processed historical data matching the origin and destination, rather than performing complex calculations on raw historical data, thus improving prediction accuracy while minimizing additional calculation time
Solution Approach 2:
The system extracts only the essential and relevant features from historical journey data needed for accurate prediction, such as origin-destination pairs, journey times, and key traffic conditions. By extracting and utilizing only these critical elements rather than processing complete historical journey records, the system achieves high prediction accuracy while reducing calculation time and processing requirements
3Measurement precision
If real-time traffic data and historical data are integrated for journey time estimation, then the accuracy improves, but the system complexity and data processing requirements worsen
Solution Approach 1:
The system segments the journey time estimation process into distinct components: route planning using static algorithms, historical data retrieval based on origin-destination pairs, and integration of real-time traffic adjustments. Each segment handles specific data types and processing tasks independently, allowing the system to achieve high estimation accuracy through coordinated segments without requiring a single complex processing system to handle all data types simultaneously
Data Source
AI summary
Embodiments relate to calculating a journey time for a planned journey between a chosen origin and a chosen destination over a network of roads in a region. A first journey time for the journey is estimated using a route scheduling algorithm and a second journey time for the journey is estimated using selected historical journeys characterized by journey origins and destinations. The historical journeys are selected based on their vicinity to the planned journey. An error in the second journey time is calculated based on the standard deviation in the selected historical journeys. The second journey time is selected as the estimated journey time from the planned journey if this error is below a defined threshold, otherwise the first journey time is selected as the estimated journey time for the planned journey.