图书情报工作 ›› 2021, Vol. 65 ›› Issue (14): 138-148.DOI: 10.13266/j.issn.0252-3116.2021.14.016

• 知识组织 • 上一篇    下一篇

基于事件本体的疫情知识库构建策略

熊励1, 王成文1, 王锟1,2   

  1. 1 上海大学管理学院 上海 200444;
    2 悉尼科技大学澳大利亚人工智能研究所 悉尼 2007
  • 收稿日期:2021-01-06 修回日期:2021-02-28 出版日期:2021-07-20 发布日期:2021-07-21
  • 通讯作者: 王成文(ORCID:0000-0002-7353-472X),博士研究生,通讯作者,E-mail:woncwen@163.com
  • 作者简介:熊励(ORCID:0000-0002-6527-0517),教授,博士,博士生导师;王锟(ORCID:0000-0003-2711-6233),博士研究生。
  • 基金资助:
    本文系国家社会科学基金国家应急管理体系建设研究专项项目"基于人工智能机器学习和区块链技术支撑的疫情监测防控研究"(项目编号:20VYJ064)研究成果之一。

Construction Strategy of Epidemic Knowledge Base Based on Event Ontology

Xiong Li1, Wang Chengwen1, Wang Kun1,2   

  1. 1 School of Management, Shanghai University, Shanghai 200444;
    2 Australian Artificial Intelligence Institute, University of Technology Sydney, Sydney 2007
  • Received:2021-01-06 Revised:2021-02-28 Online:2021-07-20 Published:2021-07-21

摘要: [目的/意义] 疫情信息碎片化和非结构化给应急决策带来了挑战。为支撑应急决策数字化和促进应急管理智能化,结合自然语言处理、事件本体实现疫情信息管理和知识表示的自动化。[方法/过程] 提出一种基于网络爬虫、自然语言处理、事件本体的领域本体知识库自动构建策略。首先,运用网络爬虫和自然语言处理进行信息采集和事件要素自动提取,在此基础上构建疫情事件本体模型。然后,设计本体构建与更新算法,通过该算法完成事件本体的自动构建与扩充。[结果/结论] 研究结果表明,该策略具备疫情信息动态管理与自动更新的可行性,且事件本体能够有效描述事件,并为知识的拓展创造条件。本研究为应急管理决策的相关研究与实践提供一定的参考。

关键词: 事件本体, 疫情信息与知识, 知识库

Abstract: [Purpose/significance] The fragmented and unstructured information of the epidemic brings challenges to emergency decision-making. To support the digitization of emergency decision-making and to promote intelligent emergency management, combining natural language processing and event ontology to realize the automation of epidemic information management and knowledge representation. [Method/process] An automatic construction strategy of domain ontology knowledge base based on web crawler, natural language processing, and event ontology was proposed. First, web crawlers and natural language processing were used for information collection and automatic extraction of event elements, and an epidemic event ontology model was built on this basis. Then, the algorithms for the ontology construction and update were designed, and the automatic construction and expansion for the event ontology was completed by them. [Result/conclusion] The results show that the proposed strategy has the feasibility of dynamic management and automatic update of epidemic information, and event ontology can describe events effectively and create conditions for knowledge expansion. This study also provides a reference for the research and practice of emergency decision-making.

Key words: event ontology, epidemic information and knowledge, knowledge base

中图分类号: