基于文本挖掘的煤矿安全隐患管理研究

为探寻安全隐患的内在特征，加深安全管理人员对安全隐患的理解，提升安全管理效率。以潞安集团司马煤业有限公司2009—2015年安全隐患记录为数据源，利用Word2Vec模型构建安全隐患词向量模型，从模型中获取各类安全隐患主要相关词，利用桑基图解释安全隐患在不同隐患地点、生产作业单位的特征分布，并进一步揭示相关安全隐患的细节特征。结果表明:词向量模型能有效发掘安全隐患特征，桑基图能突出呈现安全隐患的关键信息流动。上述措施有助于管理人员深刻理解安全隐患数据中蕴含的潜在规律，为煤矿安全隐患排查治理工作提供依据，指导安全管理实践。

Research on management of hidden danger in coal mine based on text mining

In order to explore the inherent characteristics of hidden danger,deepen the understanding of safety managers on the hidden danger,and improve the efficiency of safety management,taking the records of hidden danger in Sima Coal Industry Co.,Ltd.of Lu’an Group from 2009 to 2015 as the data source,a word vector model of hidden danger was constructed by using the Word2Vec model,and the main relevant words of various hidden danger were obtained from the model.The Sankey diagram was used to explain the characteristics and distribution of hidden dangers in different locations and operation units,and the detail characteristics of relevant hidden danger were revealed further.The results showed that the word vector model could effectively explore the characteristics of hidden danger,and the Sankey diagram could prominently present the key information flow of hidden danger.The above measures are helpful for the managers to deeply understand the potential rules contained in the data of hidden danger,and provide basis for the investigation and governance of hidden danger in the coal mine,as well as guiding the practice of safety management.