多词共现分析方法在暴雨-地质灾害应急任务研究中的应用

Application of Multi-word Co-occurrence Analysis Method inEmergency Tasks of Rainstorm-geological Disasters

为快速制定救援行动方案,提出了一种多词共现分析方法将灾害应急任务从历史发生的灾害案例中提取出来的方法。该方法首先利用K-means聚类算法将预处理好的文本进行聚类分析,归纳出应急任务集。然后利用关联规则挖掘Apriori算法提取案例文本中的频繁项集作为共现词集,分析解释共现词集与应急任务之间的关系。最后,运用Gephi软件将共现词语网络可视化,进一步分析应急任务中要素之间的相关关系。以暴雨引发的地质灾害事故为例,对该方法进行了实验,结果表明该方法能有效的将暴雨-地质灾害事故案例文本中的应急任务提取出来,并通过网络可视化分析发现,在救援过程中,应急任务之间是联动配合的一个体系,协调好各个应急任务能缩短应急响应的时间,为制定或完善救援行动方案提供参考。

To quickly formulate rescue action plans,a method of extracting emergency tasks from historical disaster cases using multi-word co-occurrence analysis is proposed.Firstly,the K-means clustering algorithm is used to cluster the preprocessed text and summarize the emergency task set.Then,the Apriori algorithm of association rule mining is used to extract frequent itemsets from the case text as co-occurrence word sets,and analyze the relationship between co-occurrence word sets and emergency tasks is analyzed.Finally,the Gephi software is used to visualize the co-occurrence word network,and further analyze the correlation between the elements in the emergency tasks.Taking the geological disaster accident caused by rainstorm as an example,the method is experimentally verified.The results show that this method can effectively extract the emergency tasks from the text of rainstorm-geological disaster accident,and through network visualization analysis,it is found that in the rescue process,the emergency tasks are a coordinated system that work together,and coordinating various emergency tasks can shorten the emergency response time,and provide reference for formulating or improving rescue action plans.