Global Journey Planning Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Journey planning systems face challenges in efficiency and comfort despite advancements in transport data, as they fail to effectively optimize travel plans considering multiple users' preferences and interactions within a shared travel space.
Innovation Solution
A computer-implemented method that generates a global recommended travel plan by optimizing user preferences using a combination of transport data, including real-time and historical traffic, weather, and organizational data, to provide personalized route, mode, and start time recommendations, taking into account the impact of other users' plans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If journey planning systems use more transport data and become more sophisticated, then the quality of travel recommendations improves, but the system complexity and computational requirements increase
Solution Approach 1:
The system segments the journey planning problem into multiple independent optimization iterations, where each user's travel plan is optimized separately in successive iterations. This divides the complex multi-user optimization into manageable single-user sub-problems that can be solved independently and then aggregated to form the global solution.
Solution Approach 2:
The system implements dynamic iteration where the global recommended travel plan is updated through multiple rounds of optimization. In each iteration, user preferences and transport data are re-evaluated with updated information from previous iterations, allowing the system to adapt and converge toward an optimal solution dynamically rather than using a static approach.
2Ease of operation
If the system optimizes for individual user preferences, then user satisfaction improves, but overall travel efficiency and congestion management deteriorates
Solution Approach 1:
The system merges individual user optimizations with global congestion considerations by integrating both objectives into a unified iterative optimization process. Each user's preferences are optimized while simultaneously considering the impact on overall travel efficiency and congestion, balancing individual and collective interests through the global recommended travel plan.
Solution Approach 2:
The system implements feedback loops where the global recommended travel plan is continuously updated based on the aggregated results of individual user optimizations. The transport data and user preferences are re-evaluated in subsequent iterations with feedback from previous optimizations, allowing the system to adjust and improve overall efficiency while maintaining user satisfaction.
3Adaptability or versatility
If the system provides detailed personalized recommendations, then the usefulness of the travel plan increases, but the computational time and processing resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing user preferences and transport data in structured databases before the actual optimization process. This preparation work is done in advance to enable faster retrieval and processing during the iterative optimization, reducing computational time while maintaining detailed personalization.
Solution Approach 2:
The system implements partial optimization by focusing computational resources on optimizing each user's travel plan incrementally across multiple iterations rather than attempting to optimize all parameters simultaneously. This approach provides detailed personalized recommendations through successive approximations, balancing personalization quality with computational efficiency.
Data Source
AI summary
A computer-implemented method includes accessing a user database, accessing a transport database, and generating a global recommended travel plan. The user database includes travel preferences and a metric preference for each user. The travel preferences include an origin, and a destination. The transport database includes transport data. The global recommended travel plan includes, for each user, a recommended route from the user's origin to the user's destination, a recommended mode, and a recommended start time. Generating the global recommended travel plan includes simultaneously optimizing each user's metric preference based on the transport data and the travel preferences. The computer-implemented method further includes returning each user's recommended route, recommended mode, and recommended start time. A corresponding computer program product and computer system are also disclosed.