Trip Reconstruction via Multi-Trip Journey Decomposition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current transportation planning systems inaccurately distinguish between multi-segment trips and separate trips due to incorrect assumptions, leading to poor transportation planning when aggregating data into origin-destination matrices.
Innovation Solution
A method and system that classify route sequences using transaction data from automatic ticketing validation devices, employing a trip planner to identify and decompose multi-trip journeys into separate trips, distinguishing between multi-segment trips and multi-trip journeys based on transfer patterns and heuristics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If heuristics are used to infer alighting information and identify multi-segment trips, then trip reconstruction can be performed with available data, but incorrect assumptions lead to inaccurate distinction between multi-segment trips and separate trips
Solution Approach 1:
The patent introduces an intermediary classification step between raw transaction data and final trip reconstruction. A classifier is trained to distinguish between multi-segment trips and separate trips by analyzing patterns in transaction data, transfer times, and route sequences. This intermediary classification mechanism resolves the contradiction by providing a more reliable basis for trip reconstruction without making incorrect assumptions.
Solution Approach 2:
The patent applies preliminary action by training a classification model in advance using historical transaction data and ground truth trip information. The trained classifier then automatically distinguishes between multi-segment trips and separate trips in new data, eliminating the need for incorrect heuristic assumptions during actual trip reconstruction. This preliminary preparation ensures accurate and reliable trip identification.
2Productivity
If traditional time threshold methods are used to segment trips, then processing is simple and fast, but multi-trip journeys are incorrectly classified as multi-segment trips
Solution Approach 1:
The patent replaces the mechanical time threshold-based segmentation system with a machine learning classification system. Instead of using fixed time rules to divide trips, the system uses a trained classifier that analyzes multiple features including transaction patterns, transfer times, and route sequences. This substitution maintains processing efficiency while dramatically improving trip segmentation accuracy by correctly identifying multi-trip journeys as separate trips rather than single multi-segment trips.
3Ease of manufacture
If aggregate data is used for transportation planning, then planning can be performed with available information, but incorrect trip assumptions lead to poor planning decisions
Solution Approach 1:
The patent implements feedback by using the trained classification model to continuously improve trip reconstruction accuracy. The classifier learns from historical data and provides accurate distinctions between multi-segment trips and separate trips, which then feeds into more reliable origin-destination matrices. This feedback loop ensures that transportation planning is based on accurate trip information, improving planning quality while maintaining feasibility through automated classification.
Data Source
AI summary
A computer-implemented system and method for identifying passenger trips on a transportation network are described. The method includes acquiring transaction data for a collection of passengers boarding at stops on a transportation network. The network includes a plurality of routes. Route sequences are identified, based on the transaction data, each route sequence including at least two trip segments by a passenger. Each pair of trip segments of an identified route sequence are spaced by a transfer. For each identified route sequence, using a trip planner, the route sequence is classified as a multi-segment trip that includes at least one transfer or a multi-trip journey. A route sequence which is classified as a multi-trip journey is partitioned into at least two trips, each trip being a multi-segment trip or a single-segment trip.