计算机与现代化

• 应用与开发 • 上一篇    下一篇

面向碳交易领域的知识图谱构建方法

  

  1. (安徽工业大学计算机科学与技术学院,安徽马鞍山243032)
  • 收稿日期:2018-02-28 出版日期:2018-09-11 发布日期:2018-09-11
  • 作者简介:王良萸(1992-),男,安徽芜湖人,安徽工业大学计算机科学与技术学院硕士研究生,CCF会员,研究方向:自然语言处理,知识图谱。
  • 基金资助:
    国家重点研发计划项目(2016YFF020440508)

Knowledge Graph Construction Method for Carbon Trading

  1. (School of Computer Science and Technology, Anhui University of Technology, Maanshan 243032, China)
  • Received:2018-02-28 Online:2018-09-11 Published:2018-09-11

摘要: 为解决碳交易领域数据集成问题,提出一种碳交易领域知识图谱的构建方法。针对碳交易领域的半结构化和非结构化数据,分别采用自定义的Web数据包装器和结合BiLSTM-CRF模型与依存句法分析的方法进行三元组抽取。然后将获取的知识转化为关联数据,得到完整的碳交易领域知识图谱,再利用基于Jena的fuseki实现对知识图谱的语义查询。实验结果表明,该方法能够为碳交易领域快速有效地构建知识图谱,并可以从碳交易领域的海量数据中检索出有用信息。

关键词: 碳交易, 知识图谱, 三元组抽取, 关联数据, 语义查询

Abstract: In order to solve the problem of data integration in carbon trading, a new method of constructing carbon trading knowledge graph is proposed. For processing the semi-structured and unstructured data in carbon trading, a self-defined Web data wrapper and a method by combining BiLSTM-CRF model with dependency parser are applied to extract triples from data respectively. Then a complete carbon trading knowledge graph can be obtained by transforming the acquired knowledge into linked data, and the semantic query of it can be achieved by fuseki based on Jena. The experimental results show that the proposed method can construct carbon trading knowledge graph rapidly and effectively, and can retrieve useful information from the massive data of carbon trading.

Key words:  carbon trading, knowledge graph, triple extraction, linked data, semantic query

中图分类号: