Page 78 - 2021年第52卷第8期

［ 21］ 蔡阳，谢文君 . 全国水利一张图建设与应用［J］. 水利信息化，2020（1）：1-5 .
［ 22］ 陈思源，陆丹丹，程海梅 . 基于科技文本挖掘的我国水资源研究知识图谱分析［J］. 水文，2019，39（2）：
61-66 .
［ 23］ 金 菊 良 ，陈 鹏 飞 ，陈 梦 璐 ，等 . 基 于 知 识 图 谱 的 水 资 源 承 载 力 研 究 的 文 献 计 量 分 析［J］. 水 资 源 保 护 ，
2019，35（6）：14-24，57 .
［ 24］ 刘晓君，杨兴，付汉良 . 再生水研究的发展态势与研究热点分析-基于 CiteSpace 的图谱量化研究［J］. 干旱
区资源与环境，2019，33（4）：68-75 .
［ 25］ 张紫璇，陆佳民，姜笑，等 . 面向水利信息资源的智能问答系统构建与应用［J］. 计算机与现代化，2020，
（3）：65-71 .
［ 26］ 王新龙，薛晓鹏，孙如飞 . 基于粒子群与知识图谱的突发水污染事件溯源方法［J］. 水力发电，2020，46
（2）：17-21 .
/
［ 27］ AMIT S . Introducing the Knowledge Graph［EB/OL］.（20120501）［ 20190315］.http：/googleblog .blogspot . pt/
2012/ 05/introducing-knowledge-graphthings-not .html .）
［ 28］ LAMPLE G，BALLESTEROS M，SUBRAMANIAN S，et al . Neural architectures for named entity recognition
［C］/Proceedings of Conference of the North American Chapter of the Association for Computational Linguistics，
/
2016 .
［ 29］ 王昊奋，漆桂林，陈华钧 . 知识图谱方法、实践与应用［M］. 北京：电子工业出版社，2019 .
［ 30］ 唐杰，梁邦勇，李涓字，等 . 语义 Web 中的本体自动映射［J］. 计算机学报，2006，29（11）：1956-1976 .
［ 31］ OGREN P，SAVOVA G，CHUTE C . Constructing evaluation corpora for automated clinical named entity recogni⁃
/
tion［C］/Proceedings of the 12th World Congress on Heath（Medical）Informatics，Marrakech，2008 .
［ 32］ 刘峤 . 基于知识图谱的关系推理算法研究［D］. 成都：电子科技大学，2018 .
［ 33］ ARTSTEIN R，POESIO M . Inter-coder agreement for computational linguistics［J］. Computational Linguistics，
2008，34（4）：555-596 .

Research on water conservancy comprehensive knowledge graph construction

DUAN Hao，HAN Kun，ZHAO Hongli，JIANG Yunzhong，LI Hao，MAO Wenshan
（China Institute of Water Resources and Hydropower Research， Beijing 100038，China）

Abstract：Based on the analysis of water conservancy knowledge characteristics，this research proposed the
description method of water conservancy comprehensive knowledge graph， including the definition， composi⁃
tion and relevancy of water conservancy knowledge. The construction framework and key technologies of wa⁃
ter conservancy knowledge graph were built. With the help of Bi-directional Long Shot-Term Memory Neu⁃
ral Network （BiLSTM） and Conditional Random Fields （CRF） models， the entities transformed from struc⁃
tured data were used to identify the entities in semi-structured and structured text knowledge and internet
data. The relationships between entities were extracted with pattern matching and co-occurrence network
analysis methods to supplement water related objects and attributes. RiMoM model was used to fuse the wa⁃
ter conservancy entities and disciplinary knowledge. Through the graph construction，136 million water con⁃
servancy entities were extracted and more than 300 million relationships were established. The annotation ac⁃
curacy of water conservancy objects was higher than 80 percent. Based on the graph constructed in this re⁃
search，both knowledge and relationships could be searched and the hidden relations between different enti⁃
ties could be found.
Keywords：knowledge graph；water conservancy comprehensive knowledge；water resource management；dis⁃
ciplinary knowledge；BiLSTM；CRF

（责任编辑：韩 昆）

— 958 —