摘要
自新型冠状病毒疫情发生以来,全国有400多个城市通过多种渠道公布了包括确诊病例、疑似病例和无症状病例的住址或逗留场所等具体位置信息.这些信息不仅是公众的关注焦点,对防控工作也具有重要意义.以往这些信息的获取主要以人工方式为主,效率低下,缺乏时效性.针对这一现状,本文应用相关的自然语言处理方法分析疫情通报信息,构建疫情新闻信息提取系统.借助现有的NLP工具包和百度地图开发平台,结合疫情新闻的文本特点,设计相关规则,对疫情新闻网页中的文本进行分析,并提取3个方面的信息:病例的路线信息、居住地信息和交通搭乘信息.
Since COVID-19 took place in China,more than 400 cities have published specific location information about the residential areas or staying places of patients with COVID-19.Such information not only become the focus of public attention,but also has important significance on prevention work.In the past,the acquisition of these information was mainly in the manual way,which was inefficient and short of timeliness.In view of this situation,we use the relevant natural language processing methods to analyze the epidemic information,and construct the information extraction system about the COVID-19 news.With the help of the existing NLP toolkit and Baidu map development platform,combined with the text characteristics of news,we designed relevant rules to extract information from the text of news in three aspects:patient’s route information,residence or permanent residence information,and traffic information.Finally,we present the system in the form of a website.Users can access the system and use related functions through a web page.
作者
陈佳珊
黄景浩
杨坦
蔡志杰
CHEN Jiashan;HUANG Jinghao;YANG Tan;CAI Zhijie(School of Science,Harbin Institute of Technology(Shenzhen),Shenzhen,Guangdong 518055,China;School of Data and Computer Science,Sun Yat-sen University,Guangzhou,Guangdong 510006,China;School of Mathematical Sciences,South China Normal University,Guangzhou,Guangdong 510631,China;School of Mathematical Sciences,Fudan University,Shanghai 200433,China;Shanghai Key Laboratory for Contemporary Applied Mathematics,Shanghai 200433,China;Key Laboratory of Nonlinear Mathematical Models and Methods of Ministry of Education,Shanghai 200433,China)
出处
《数学建模及其应用》
2020年第4期94-100,共7页
Mathematical Modeling and Its Applications
