基于案例挖掘的农村自建房安全风险致因分析  

Analysis of the Causes of Safety Risks of Rural Self-built Houses Based on Case Mining

作　　者：申建红 王思冉[1] 张茜 孟子祥 SHEN Jianhong;WANG Siran;ZHANG Qian;MENG Zixiang(College of Management Engineering,Qingdao University of Technology,Qingdao 266520,China;Research Institute of Construction Credit and Risk Management,Qingdao University of Technology,Qingdao 266520,China)

机构地区：[1]青岛理工大学管理工程学院,山东青岛266520 [2]青岛理工大学城乡建设信用与风险管理研究中心,山东青岛266520

出　　处：《工程管理学报》2024年第3期71-75,共5页Journal of Engineering Management

基　　金：国家自然科学基金青年科学基金项目(72304161)。

摘　　要：为深入分析农村自建房安全风险,探究影响农村自建房安全事故的关键致因,收集2014—2022年间的典型农村自建房建筑安全事故调查报告共86份。利用文本挖掘技术对事故调查报告进行分析,通过数据驱动的方式提取了36个影响农村自建房安全生产的风险因素。利用Apriori算法挖掘风险因素间的强关联关系,并在此基础上建立贝叶斯网络模型。通过贝叶斯网络推理及敏感性分析,明确了农村自建房安全事故的关键致因、敏感因素及最大概率致因链。该方法克服了专家主观意愿的影响,采用客观数据对农村自建房安全事故进行深入分析,为建立健全农村自建房安全风险长效管理机制提供参考。In order to gain a comprehensive understanding of the safety risks associated with rural self-built houses and identify the key causal factors influencing rural self-built house safety accidents,a total of 86 typical rural self-built house construction safety accident investigation reports were collected between 2014 and 2022.Text mining technology was employed to analyze the accident investigation report,resulting in the extraction of 36 risk factors affecting the safety production of self-built houses in rural areas in a data-driven manner.The Apriori algorithm was employed to identify the significant correlation between risk factors,and a Bayesian network model was constructed on this foundation.Through critical link analysis and sensitivity analysis,the primary causes,sensitive factors,and the most probable cause chain of rural self-built house safety accidents were elucidated.The method overcomes the influence of subjective will on the part of experts by using objective data to analyze rural self-built house safety accidents in depth.It thereby provides a reference for the establishment of a sound long-term management mechanism for rural self-built house safety risks.

关 键 词：农村自建房 安全风险 文本挖掘 APRIORI算法 贝叶斯网络 

分 类 号：TU714[建筑科学—建筑技术科学]