一种从新闻报道中构建突发事件应急处置过程的方法  

A Method of Constructing Emergency Response Process from News Report

在线阅读下载全文

作  者:王学贺[1] 李晓磊 成洪豪 赵华[2] WANG Xuehe;LI Xiaolei;CHENG Honghao;ZHAO Hua(Division of Computer Science,Heze Medical College,Heze Shandong 274000,China;College of Computer Science and Engineering,Shandong University of Science and Technology,Qingdao Shandong 266590,China)

机构地区:[1]菏泽医学专科学校计算机教研室,山东菏泽274000 [2]山东科技大学计算科学与工程学院,山东青岛266590

出  处:《新疆大学学报(自然科学版中英文)》2024年第4期444-451,共8页Journal of Xinjiang University(Natural Science Edition in Chinese and English)

基  金:山东省自然科学基金面上项目“基于定制感知与流程比对的突发事件网络舆情异常定量分析研究”(ZR2021MG038).

摘  要:为了让民众更加清楚地了解突发事件的应急处置过程,提高政府公信力,提出并实现了一种从新闻报道中构建突发事件应急处置过程的方法.将应急措施看作三元组,构建训练语料,采用条件随机场(CRF)模型抽取三元组的元素,然后将应急措施按时间排序得到应急处置过程.所设计的基于CRF的三元组抽取模型的准确率为99.6%、精确率为93.8%、召回率为76.2%、F1值为84.1%.同时,通过对比抽取的应急处置过程和人工构建的应急处置过程可知抽取效果完全达到了实用水平.所提出的方法能自动准确地生成突发事件应急处置过程,为突发事件应急处置科学决策提供技术支持.In order to let the public know more about the emergency response process and improve the credibility of the government,this paper proposes and realizes a method of constructing the emergency response process from news report.The emergency measures were regarded as triples,the training corpus was constructed,the conditional random field(CRF)model was used to extract the elements of triples,and then the emergency measures were sorted in time order to get the emergency response process.The accuracy of CRF model was 99.6%,the accuracy was 93.8%,the recall was 76.2%,and the F1 value was 84.1%.At the same time,by comparing the extraction result of this paper and the manual extraction result,we can see that the extraction method of this paper achieves the practical level.This method can accurately generate emergency response process,and provide technical support for scientific decision-making in emergency response.

关 键 词:突发事件 应急处置过程 条件随机场 

分 类 号:TP274[自动化与计算机技术—检测技术与自动化装置]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象