A crowd evacuation method based on hybrid algorithm

By combining genetic, gray wolf, and sociomechanical models with a hybrid algorithm, the problems of low computational efficiency and inaccurate simulation results in existing evacuation models are solved, and efficient and accurate multi-exit crowd evacuation simulation is achieved.

CN117010487BActive Publication Date: 2026-06-16SHAANXI UNIV OF SCI & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHAANXI UNIV OF SCI & TECH
Filing Date
2023-05-23
Publication Date
2026-06-16

AI Technical Summary

⚠Technical Problem

Existing evacuation models are computationally inefficient when simulating large-scale crowd evacuations, and the simulation results are poor compared to reality. They fail to effectively consider the influence of individual psychological and environmental factors, and especially in multi-exit scenarios, they cannot accurately simulate crowd behavior.

⚗Method used

A hybrid algorithm is adopted, combining genetic algorithm, gray wolf algorithm and social mechanics model. By classifying the population, monitoring the spread of panic and macro and micro regulation, the global and local search of the population evacuation is realized. The accuracy of the evacuation results is improved by combining the panic spread model.

🎯Benefits of technology

It improves computational efficiency, enabling more realistic simulation of crowd evacuation processes, accurately reflecting individual behavior and environmental impacts, and is suitable for multi-exit scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117010487B_ABST
    Figure CN117010487B_ABST
Patent Text Reader

Abstract

The application discloses a kind of crowd evacuation methods based on hybrid algorithm, including the following steps;Using genetic algorithm to classify crowd;Danger source distance walker is judged by panic propagation model of monitoring system;By grey wolf algorithm, macro-control is carried out, and leader is selected by fitness;Microscopic guidance is carried out by social dynamics model, and each colony leader receives instruction from system, then commands the evacuation of the pedestrians of this colony, when pedestrian receives the information of leader, the expected motion direction of social dynamics model is updated to the direction of the leader;The fitness of each group is monitored and iterated, whether the replacement of leader is needed is observed, and the panic value of pedestrian is iterated and updated;Whether crowd is evacuated is observed, if evacuated, the evacuation task is ended, otherwise, return.The application has the characteristics of macro-micro combination, simple algorithm, strong global and local search ability, and can achieve the purpose of real simulation of crowd evacuation.
Need to check novelty before this filing date? Find Prior Art