中国科技核心期刊

中文核心期刊

CSCD来源期刊

空间控制技术与应用 ›› 2020, Vol. 46 ›› Issue (2): 49-55.

• 论文与报告 • 上一篇    下一篇

航天控制软件知识图谱构建方法研究
#br#

航天控制软件知识图谱构建方法研究#br#

#br#
  

  1. 北京控制工程研究所,北京 100090.


  • 出版日期:2020-04-25 发布日期:2020-05-21
  • 作者简介:作者简介:赵明(1995年—),男,硕士研究生,研究方向为知识图谱;顾斌(1968—),男,研究员,研究方向计算机控制,可信软件;钟睿明(1985—),男,工程师,研究方向为嵌入式软件开发,进化计算,分布式存储,深度学习;李振松(1983—),男,高级工程师,研究方向为嵌入式软件设计,航天器在轨软件维护;李声涛(1988—),男,工程师,研究方向为模型检验.
  • 基金资助:
    国家自然科学基金资助项目(90405017).

Construction Method of Aerospace Control Software Knowledge Graph

Construction Method of Aerospace Control Software Knowledge Graph   

  1. Beijing Institute of Control Engineering, Beijing 100090,China. 
  • Online:2020-04-25 Published:2020-05-21
  • Supported by:
    National Nature Science Foundation of China(90405017).

摘要: 摘要: 近些年,知识图谱构建技术快速发展,但对于领域知识图谱构建的研究还处于起步阶段.知识图谱的构建主要包括自顶向下、自底向上两种方法.当前大多采用自顶向下的方法进行领域知识图谱的构造,首先构建本体,然后通过本体学习得到实体,再将实体加入到知识图谱中.但这种做法有一个缺点,本体学习的过程过分依赖人工,不支持构建专业性强、数据量大的领域知识图谱.针对这一缺点,本文提出一种自顶向下和自底向上法相结合的领域知识图谱构建方法.提出一种改进的骨架法来进行本体构建,保证构建本体的准确率和覆盖率;利用基于规则与半监督的知识抽取技术,提高知识图谱的构建速度;并以某航天控制软件为例,详细说明了领域知识图谱的整体构建流程.实验结果表明,该领域知识图谱的构建方法是可行的.

关键词: 关键词: 领域知识图谱, 知识图谱构建, 本体构建, 知识抽取

Abstract: Abstract: Knowledge graph technology has developed rapidly in recent years. However, the research on domain knowledge graph construction is preliminary. There are mainly two methods to construct a knowledge graph, one is the topdown, and the other is the bottomup. The former method is more common. However, the topdown has a disadvantage, that ontology learning is too artificial, so that it does not support the construction of a domain knowledge graph which is strong professional and massive. In order to solve this problem, this paper proposes a novel domain knowledge graph construction method, which combining the topdown and the bottomup. We also propose an improved skeletal methodology to ensure the accuracy and coverage in ontology construction. We use rulesbased and semisupervision technology to improve the speed of knowledge extraction. After that, we illustrate the procedure of construction in detail. Moreover, instances prove that the method in this paper is feasible.


Key words: Keywords: domain knowledge graph, knowledge graph construction, ontology construction, knowledge extraction

中图分类号: 

  • TP18