Information Processing Apparatus for Predictive Transportation Dispatch
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face inconvenience when trying to access transportation services as they need to manually input their schedules, which can be cumbersome and may not accurately reflect their intentions or behaviors.
Innovation Solution
An information processing apparatus and method that calculates the likelihood of a user's future movements based on their behavior, using machine learning to determine the probability of going out and dispatching appropriate transportation services, such as taxis or bicycles, without requiring explicit user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the user manually inputs their schedule to a timetable, then the system can grasp the user's schedule information, but the user experiences trouble and inconvenience
Solution Approach 1:
The system automatically collects schedule information from multiple sources (messaging apps, calendars, browsing history, location data) without requiring user input. The server performs self-service by gathering, processing, and storing schedule data autonomously, eliminating the need for manual user entry while ensuring accurate schedule information is captured
Solution Approach 2:
The system performs preliminary actions by pre-collecting and processing schedule information from various sources before the user needs it. The server proactively gathers data from messaging applications, calendars, and other sources in advance, preparing the schedule information ready for use when needed
2Reliability
If the system waits for explicit user input to provide transportation services, then the service can be provided accurately, but the user experiences delay and inconvenience
Solution Approach 1:
The system performs preliminary actions by calculating the likelihood of user movement in advance based on collected behavior data. The server continuously analyzes patterns from messaging apps, calendars, and location data to predict future movements, so when the user actually needs transportation, the service can be provided immediately without waiting for explicit input
Solution Approach 2:
The system uses feedback from multiple data sources (messaging applications, calendars, browsing history, location information) to continuously refine and update the likelihood calculation. This feedback loop ensures accurate prediction of user movement while enabling timely service provision, as the system learns from past behavior patterns to improve future predictions
Data Source
AI summary
There is provided a controller that executes: calculating, based on information about behavior of a user, likelihood about future movement of the user; and outputting information about a service for the movement of the user based on the calculated likelihood.