Allocation Server Optimizing Taxi Dispatch via Driver Compliance Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing allocation systems for moving objects, such as taxis, face inefficiencies due to drivers not following instructions, leading to reduced allocation success probability and potential request stealing, which affects the overall allocation plan's effectiveness.
Innovation Solution
An information processing apparatus and method that acquires information about transport objects and moving objects' tendencies to follow instructions, generating movement instructions based on this data to optimize allocation and reduce request stealing by prioritizing taxis with high allocation system dependence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an allocation system instructs moving objects (taxis) to follow predetermined routes, then allocation efficiency is improved, but drivers may not follow instructions and steal requests, reducing reliability
Solution Approach 1:
The system performs preliminary actions by predicting driver behavior and request stealing patterns before they occur. The allocation server uses machine learning models to anticipate which drivers may deviate from instructions and which requests may be stolen, then proactively adjusts allocation decisions to compensate for these predicted actions, thereby maintaining allocation efficiency despite non-compliance.
Solution Approach 2:
The system implements feedback loops where the allocation server continuously monitors actual driver behavior and request outcomes, compares them with predictions, and uses this information to refine future allocation decisions. The machine learning models are trained on historical data about driver compliance and request stealing patterns, creating a feedback mechanism that improves reliability while maintaining productivity.
2Reliability
If the allocation system accounts for driver non-compliance behavior, then reliability is improved, but system complexity increases due to additional prediction and adjustment mechanisms
Solution Approach 1:
The system uses self-service by leveraging the drivers' own behavioral patterns and historical data to train machine learning models that predict their actions. The allocation server automatically adjusts allocations based on these predictions without requiring external intervention or complex manual monitoring, thereby improving reliability while keeping the system relatively simple and self-regulating.
Data Source
AI summary
There is provided a system for more efficiently transporting transport objects using a moving object. An information processing apparatus (100) that generates a movement instruction for a moving object that carries a transport object includes a first acquisition unit (141) configured to acquire information about the transport object for each space, a second acquisition unit (135) configured to acquire information representing a tendency of whether the moving object moves in accordance with the movement instruction, and a generation unit (143) configured to generate the movement instruction for the moving object on the basis of the information about the transport object and the information representing the tendency.