城市级新冠肺炎(COVID-19)疫情预测和仿真模型  

City-Level Structured Prediction and Simulation Model of COVID-19

作　　者：王金恺 张虎 贾鹏 权益 陈梁港旭 王长波[1] Wang Jinkai;Zhang Hu;Jia Peng;Quan Yi;Chen Lianggangxu;Wang Changbo(School of Computer Science and Technology,East China Normal University,Shanghai 200062;General Department of System Confrontation and Intelligent Information System,The Third Academic of Aerospace and Technology Group of China,Beijing 100074)

机构地区：[1]华东师范大学计算机科学与技术学院,上海200062 [2]中国航天科工集团第三研究院体系对抗与智能信息系统总体部,北京100074

出　　处：《计算机辅助设计与图形学学报》2022年第8期1302-1312,共11页Journal of Computer-Aided Design & Computer Graphics

基　　金：上海市自然科学基金(19ZR1415800)。

摘　　要：传染病的传播分析对于社会公共安全与城市管理有着重要的意义.针对此次新冠肺炎(COVID-19)疫情的传播,构建了一个城市级结构化疫情预测和仿真模型.该模型基于最新的传染病动力学理论,综合地理信息网络,将易感者、潜伏者、感染者和康复者(SEIR)模型与社会网络模型相结合,对预测区域进行多层级划分;宏观上使用二分网络模拟公共设施与社区节点的关系;微观上使用改进的SEIR模型模拟节点内部的传染情况;节点间使用智能体追踪个体的传播过程.采用国家卫生健康委员会公开的2020年武汉市与北京市疫情确诊及治愈病例数进行对比实验,结果表明,所提模型在疫情仿真上更灵活,预测结果更准确,并能直观地体现不同人群的分布情况和流动趋势.It is important for social public security and urban management to explore the spread of infectious diseases.A city-level structured prediction and simulation model for COVID-19 is proposed.This model is consisted of SEIR and social network model on the basis of latest infectious disease dynamics theory and real geographic networks.The prediction region is divided into multiple levels.Specifically,a bipartite network is applied to simulate the relationship between public facilities and community nodes at the macro level,and a modified SEIR is applied to simulate the infection within nodes at the micro level.Besides,intelligent agent is applied to track the individual transmission process.The contrast experimental results based on the confirmed and cursed cases of Wuhan and Beijing in 2020 published by National Health Commission,show that the proposed model has better flexibility and higher accuracy,and reflects the distribution and movement of people more directly.

关 键 词：2019新型冠状病毒(COVID-19) 传染病 易感者、潜伏者、感染者和康复者(SEIR)模型 复杂网络模型 智能体 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]