Boarding Alighting Prediction Device Using Real-Time Position Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dispatch management devices inaccurately estimate the number of passengers expected to alight by relying on clothing or belongings, which are unrelated to alighting.
Innovation Solution
A boarding and alighting number prediction device that predicts the number of boarding or alighting passengers based on real-time position information and past result values, using a prediction unit that weights these values for accurate forecasting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If clothing or belongings are used to estimate the number of passengers expected to alight, then the estimation can be performed, but the accuracy of the estimation deteriorates
Solution Approach 1:
The system incorporates feedback mechanisms by continuously updating the prediction model with actual boarding and alighting data. The prediction unit compares predicted values with actual values and adjusts the model parameters accordingly, improving accuracy over time while maintaining reliable estimation through iterative optimization
Solution Approach 2:
The system changes parameters by switching from using unrelated features (clothing, belongings) to using directly relevant features (position information, past boarding/alighting numbers). This parameter change fundamentally improves both the accuracy and reliability of the estimation by focusing on causally related variables
2Measurement precision
If real-time position information and past result values are used for prediction, then the prediction accuracy improves, but the device complexity increases
Solution Approach 1:
The prediction system is segmented into distinct functional units: an acquisition unit for gathering data, a prediction unit for processing, and a notification unit for output. This segmentation allows the complex task of prediction to be divided into manageable components, reducing overall system complexity while maintaining high accuracy
Solution Approach 2:
The prediction unit acts as an intermediary that processes raw position information and past result values, transforming them into accurate predictions. This intermediary layer simplifies the system architecture by centralizing the complex processing logic in a dedicated component rather than distributing it throughout the entire system
Data Source
AI summary
An object is to predict the number of boarding passengers or the number of alighting passengers that is more accurate. A boarding and alighting number prediction device (1) includes a prediction unit (12) predicting a boarding and alighting number prediction value that is a predicted value of a boarding and alighting number that is the number of boarding passengers or the number of alighting passengers at a stop on the basis of a real-time prediction value that is a predicted value of the boarding and alighting number based on position information relating to current positions of at least some of the passengers and past result values that are values based on result values of past boarding and alighting numbers. The prediction unit (12) may predict the boarding and alighting number prediction value by respectively weighting the real-time prediction value and the past result values.