基于贝叶斯网络的智慧城市建设影响因素研究  

Research on Influencing Factors of Smart City Construction Based on Bayesian Network

作　　者：张宁 盛武[1] ZHANG Ning;SHENG Wu(School of Economics and Management,Anhui University of Science and Technology,Huainan,Anhui 232001,China)

机构地区：[1]安徽理工大学经济与管理学院,安徽淮南232001

出　　处：《城市学刊》2018年第6期70-75,共6页Journal of Urban Studies

基　　金：国家自然科学基金项目(71371014);安徽高校省级自然科学研究重点项目(KJ2016A205);安徽省哲学社科规划项目(AHSKY2016D20)

摘　　要：大数据时代,智慧城市建设已经成为城市发展的关键性战略目标。在选取与智慧城市建设水平相关的因子基础上,结合样本数据及贝叶斯网络结构学习,构建贝叶斯网络结构模型。借助贝叶斯网络参数学习,对各节点变量的条件概率分布和后验概率进行分析,从而挖掘出各变量间的相互影响程度以及影响智慧城市建设水平的关键因素。结果表明:城市经济发展水平和基础设施建设情况是影响智慧城市建设水平的主要因素,创新型人才和科技创新能力对智慧城市建设起着不可忽略的影响作用,在智慧城市建设过程中,各评价指标变量间存在密切的因果关系和逻辑关系,共同构成影响智慧城市建设水平的复杂关系网络。In the era of the big data,the construction of smart cities has become a key strategic goal of urban development.Based on the factors related to the level of smart city construction,combined with sample data and the Bayesian network structure learning,the Bayesian network structure model is constructed.By means of the Bayesian network parameter learning,the conditional probability distribution and posterior probability of each node variable are analyzed,so as to explore the mutual influence degree of each variable and the key factors affecting the construction level of smart city.The results show that the level of urban economic development and infrastructure construction are the main factors affecting the construction level of smart cities;innovative talents and technological innovation capabilities play an indispensable role in the construction of smart cities;in the process of smart city construction,there are close causal and logical relationships between the evaluation index variables,which together constitute a complex relationship network that affects the level of smart city construction.

关 键 词：贝叶斯网络 智慧城市 EM算法 参数学习 

分 类 号：F291.1[经济管理—国民经济]