Behavior-Model Traffic Simulation for Dynamic Route Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing traffic simulation methods fail to accurately account for dynamic states of transportation modes, such as congestion degrees, which affects the selection of travel routes by individuals.

Innovation Solution

A computer program that simulates traffic using a behavior model to predict route selection based on features indicating transportation mode states, allowing for the simulation of multiple travel routes and updating these features based on movement results to improve accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional traffic simulation methods are used, then the simulation process is simple, but the simulation accuracy is insufficient because dynamic states of transportation modes are not properly accounted for

Engineering Contradiction:
Improvesimulation accuracyVSAvoidsimulation process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies dynamics by making the transportation mode states dynamic rather than static. The behavior model continuously updates features indicating transportation mode states (such as congestion degrees) based on simulated movement results, allowing the simulation to reflect real-time dynamic conditions that affect route selection, thereby improving simulation accuracy without requiring overly complex infrastructure

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements feedback mechanisms where the behavior model uses updated features from movement results to continuously refine route selection predictions. The simulation process feeds back the actual movement outcomes into the behavior model, which then adjusts the features indicating transportation mode states for subsequent iterations, creating a closed-loop system that progressively improves accuracy

Inventive Principle:
Principle #23Feedback

2Measurement precision

If multiple travel routes are simulated with behavior model predictions, then the simulation accuracy improves, but the computational complexity increases

Engineering Contradiction:
Improveroute selection prediction accuracyVSAvoidcomputational resources
Core Design Contradiction:
Measurement precisionVSPower

Solution Approach 1:

The patent changes parameters by using a behavior model that predicts route selection based on features indicating transportation mode states rather than evaluating all possible routes exhaustively. The behavior model uses parameters such as congestion degrees and other state features to probabilistically determine route selections, reducing computational power requirements while maintaining prediction accuracy

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The patent applies partial action by having the behavior model predict and select only the most relevant travel routes based on current transportation mode states, rather than simulating all possible routes equally. The system focuses computational resources on predicting the actual selected route and its alternatives, rather than exhaustively analyzing every possible path

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4657023A1Computer program, traffic simulation method, and information processing apparatus
Publication Date: 2025.12.03 FUJITSU LTD
  • EP4657023A1 patent drawingFigure 1
  • EP4657023A1 patent drawingFigure 2
  • EP4657023A1 patent drawingFigure 3

AI summary

A computer searches for a plurality of travel routes along which a person moves from a departure point to a destination using one or more transportation modes among a plurality of transportation modes, the one or more transportation modes being different from each other among the plurality of travel routes, predicts a first travel route to be selected by the person from the plurality of travel routes by using a behavior model for predicting a selection behavior based on features indicating states of the plurality of transportation modes, simulates a first movement of the person along a time axis using the first travel route, and updates the features using a result of the first movement.