An intelligent campus simulation system based on game

Abstract

As a densely populated place, the occurrence of accidents on campus causes serious concerns, while the construction of an intelligent and safe campus is also one of the hotly debated topics. Starting from the perspective of the development process of security events, this paper comprehensively perfects each stage and applies reasonable methods, hoping to reduce the cost of human and material resources in campus security. First, the abnormal behaviour data set and the identification model based on time and space fusion are constructed to identify the abnormal behaviours on campus. Further on, through the agent reward function construction and state transfer function solution and algorithm research, the multi-intelligent-agent tracking and cooperation based on the game idea are realised to provide efficient real-time security alarm and decision suggestion. Finally, the safety resource path planning platform is designed, and the simulation analysis is conducted combined with the traffic network of New Normal University. The results turn out to identify the abnormal behaviour, work out the optimal decision as well as figure out the optimal path of security resources planning and verify the effectiveness of the mathematical model in a simulation manner.