Dynamic Transit Routing Using Telematics and Rider Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current transit systems, such as bus routing and carpooling, are inefficient due to manual design processes that fail to adapt to changing commuter needs, leading to suboptimal routes that do not maximize accessibility, ridership, or environmental efficiency.
Innovation Solution
A transit analytics system that utilizes telematics data from mobile devices and connected vehicles to generate and update dynamic transit routes in real-time, optimizing for factors like length, transit time, and fuel efficiency, using machine learning and AI to build user models and predict transit behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual bus routing design is used, then route planning can be implemented, but the routes become obsolete quickly and fail to adapt to changing commuter needs
Solution Approach 1:
The patent implements dynamic routing by continuously collecting telematics data from mobile devices and connected vehicles, then using machine learning models to generate updated routes in real-time. This transforms static manual routes into dynamic adaptive routes that automatically adjust to changing commuter patterns, directly resolving the contradiction between route adaptability and obsolescence time
Solution Approach 2:
The system establishes a feedback loop where telematics data from users is continuously collected, analyzed by transit behavior models, and used to generate updated routes. This closed-loop feedback mechanism ensures routes continuously adapt to actual commuter behavior, preventing obsolescence while maintaining high adaptability
2Productivity
If ad hoc carpooling is used, then carpool routes can be formed, but potential riders are left out and efficiency is not optimized
Solution Approach 1:
The patent creates a universal carpooling system that serves multiple functions: it identifies potential riders through telematics data analysis, optimizes routes using machine learning models, and coordinates multiple vehicles. This multi-functional approach simultaneously increases ridership capacity and efficiency, resolving the contradiction between these two parameters
Solution Approach 2:
The system performs preliminary actions by pre-identifying potential riders through telematics data analysis and pre-optimizing carpool routes using transit behavior models before actual carpooling occurs. This advance preparation maximizes both ridership capacity and efficiency by ensuring optimal matching before trips begin
3Adaptability or versatility
If real-time telematics data processing is implemented, then dynamic routes can be generated, but system complexity increases
Solution Approach 1:
The patent introduces intermediary components including pre-trained machine learning models and transit behavior models that act as mediators between raw telematics data and route generation. These intermediaries simplify the processing complexity by handling data analysis and pattern recognition, while enabling real-time adaptability through automated model-based decision making
Data Source
AI summary
The present embodiments may relate to generating dynamic transit routes based at least in part upon telematics data of users. For instance, a transit analysis (TA) computing device may be configured to: (1) receive telematics data from the plurality of user mobile devices, each user mobile device of the plurality of user mobile devices corresponding to one user identifier of a plurality of user identifiers; (2) build, for each user identifier of the plurality of user identifiers, a transit model; (3) generate, for each user identifier of the plurality of user identifiers, based at least in part upon the transit model associated with the user identifier, one or more transit predictions; and/or (4) generate, based at least in part upon the one or more transit predictions, for each user identifier of the plurality of user identifiers, a dynamic transit route.