Dispatch Platform Modification via Graph Neural Network Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The logistics industry faces challenges in efficiently matching available trucks to loads due to the large search space and the inability to automate the process effectively, leading to increased costs and suboptimal resource utilization.
Innovation Solution
A computer-implemented system using an optimization engine and artificial intelligence to determine optimal truck-load matches and routes, leveraging a graph neural network to consider constraints such as driver hour requirements and cost factors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual truck-load matching is performed by humans, then operational control and decision-making flexibility are maintained, but the process becomes impossible to complete in a timely manner due to the large volume of loads and trucks
Solution Approach 1:
The patent replaces the mechanical human decision-making system with an automated computer-based optimization system that uses algorithms to evaluate truck-load matches. This substitution enables rapid processing of large volumes of data that would be impossible for humans to handle manually, directly resolving the contradiction between maintaining operational control and achieving timely matching decisions.
2Productivity
If automation is implemented to evaluate vast combinations of trucks and loads, then matching speed and productivity improve, but the computational complexity and resource requirements increase significantly
Solution Approach 1:
The patent segments the complex optimization problem into manageable components by evaluating truck-load matches in batches or iterations rather than all at once. The system divides the vast search space into smaller subsets that can be processed efficiently, reducing the computational burden while maintaining the ability to evaluate comprehensive combinations.
Solution Approach 2:
The system performs preliminary filtering and preprocessing of truck and load data before conducting the full optimization evaluation. By pre-processing data to identify relevant candidates and constraints beforehand, the system reduces the complexity of the main evaluation process while maintaining comprehensive search capabilities.
3Reliability
If comprehensive constraints such as driver hour requirements and cost factors are considered in the optimization, then solution quality and operational compliance improve, but the computational time and processing requirements increase
Solution Approach 1:
The patent applies different levels of constraint evaluation to different parts of the optimization process. Critical constraints like driver hour requirements are enforced with strict local checks during the matching process, while other factors are evaluated with varying degrees of detail depending on their importance and computational cost. This allows comprehensive constraint compliance without uniformly high computational overhead throughout the entire system.
Data Source
AI summary
A server receives an input representing a new truck for addition to a set of load-truck matches stored in a match data repository. The server transforms the input into new truck data. The server generates a new load-truck match matching the new truck to at least one load based on the new truck data, the set of load-truck matches, and a set of global constraints. The server generates an output of multiple new edges for manual review. The output indicates information associated with each of the multiple new edges. The server transmits the output to the client device for display via the graphical user interface. The server receives an indication of a selection of one of the multiple new edges or a rejection of the new edges. The server adjusts the set of load-truck matches stored in a match data repository based on the indication.