Trip Reconstruction from Fare Data for Urban Mobility Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current transportation infrastructure planning in urban areas is time-consuming and costly due to reliance on partial and outdated data from custom studies, which limits the precision and effectiveness of simulations for traffic congestion and pollution management in rapidly growing cities.
Innovation Solution
A system and method utilizing automatic fare collection data to learn transportation models by reconstructing trips, estimating origins and destinations, and generating demand models, which includes a trip reconstruction module, origin and destination estimator, time estimator, and simulator to enhance infrastructure planning with more accurate and up-to-date information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If custom studies with traveler surveys are used to build transportation models, then the models can be constructed with expert analysis, but the process becomes very time-consuming and expensive
Solution Approach 1:
The patent creates a virtual copy of the transportation system by reconstructing individual trips from fare validation data. Instead of conducting expensive custom studies, the system copies real travel behavior patterns from automated fare collection data, preserving accuracy while eliminating the time-consuming survey process. The trip reconstruction module creates synthetic trip records that mirror actual passenger behavior.
Solution Approach 2:
The system enables the transportation data to serve itself by automatically extracting trip information from fare validation records. The data speaks for itself through automated trip reconstruction algorithms that infer origins, destinations, and trip purposes without requiring expert analysts to conduct separate studies. The fare data inherently contains the mobility information needed.
2Loss of information
If custom studies with traveler surveys are conducted, then some mobility data can be collected, but the data is partial and outdated due to the limited scope and duration of studies
Solution Approach 1:
The patent makes the automated fare collection system multi-functional by extracting not only payment information but also detailed mobility patterns, trip purposes, and origin-destination data. The same infrastructure that collects fares universally serves multiple purposes: revenue collection, trip reconstruction, demand modeling, and infrastructure planning analysis, eliminating the need for separate data collection efforts.
Solution Approach 2:
The system enables continuous data collection by leveraging the ongoing fare validation process. Instead of periodic surveys, every fare validation event continuously generates mobility data. The trip reconstruction module processes ongoing fare data streams to continuously update trip patterns, ensuring the model remains current without interruption.
3Device complexity
If data is aggregated to a high level of granularity for macro simulation, then the modeling process becomes manageable, but the precision and detail of mobility dynamics are lost
Solution Approach 1:
The patent segments the transportation system into individual trip units, each with its own origin, destination, purpose, and temporal characteristics. Instead of aggregating all mobility into macro zones, the system maintains discrete trip-level granularity throughout the modeling process. The trip reconstruction module creates segmented trip records that preserve detailed information while remaining computationally manageable through modular processing.
4Quantity of substance
If more intelligent transportation systems are deployed to collect ticketing data, then vast amounts of detailed mobility information become available, but the data remains underutilized for understanding city mobility patterns
Solution Approach 1:
The system implements feedback by using reconstructed trip data to continuously refine the demand model and validate the trip reconstruction algorithms. The simulated trips are compared against actual fare validation patterns, and the model parameters are adjusted based on this feedback loop. This automated feedback mechanism ensures the system learns from the vast data volume without requiring manual intervention.
Data Source
AI summary
A method and system are disclosed for learning a demand model and simulation parameters from validation information. Validation information is received from automatic fare collection systems and trips are reconstructed from the validation information. Origins, destinations, and arrival/departure times are estimated from the reconstructed trips. A demand model is then generated from the origins, destinations, and times. Assignment model parameters are then learned from the received validation information and demand model via iterative simulations. Infrastructure changes are made to a simulated transportation network based on the assignment and demand model using the learned parameters. A simulated response of the transportation network to the infrastructure change is then output.