基于对水利知识特点的分析,提出了水利综合知识体系的描述方法,包括水利知识的定义、组成与关联;构建了水利知识图谱的构建框架和关键技术体系,以水利行业结构化业务数据的实体关系转换为基础,采用双向长短期记忆神经网络(Bi-directiona...基于对水利知识特点的分析,提出了水利综合知识体系的描述方法,包括水利知识的定义、组成与关联;构建了水利知识图谱的构建框架和关键技术体系,以水利行业结构化业务数据的实体关系转换为基础,采用双向长短期记忆神经网络(Bi-directional Long Shot-Term Memory Neural Network,BiLSTM)与条件随机场(Conditional Random Fields,CRF)方法识别半结构化、非结构化学科知识文本以及互联网数据中的水利实体,使用模式匹配和共现网络分析方法抽取各实体间关系,对涉水对象及其属性进行补充,基于风险最小化的最小风险映射模型(Risk Minimization based Ontology Mapping,RiMOM)进行了多源异构水利实体的融合,实现了涉水对象与水利学科知识的融合与关联,形成水利综合知识的建模和表达。在图谱构建过程中,累计抽取水利实体136万个,构建实体关系300余万条,抽取的水利实体对象的标注准确率在80%以上。基于该图谱可实现水利知识的跨域查询与检索,学科图谱与水网图谱间关系查询,挖掘不同水利实体间的隐含关系,提高水利知识检索的效率和知识挖掘发现的能力。展开更多
As the demands on limited water resources intensify, concerns are being raised about the human carrying capacity of these resources. However, few researchers have studied the carrying capacity of regional water resour...As the demands on limited water resources intensify, concerns are being raised about the human carrying capacity of these resources. However, few researchers have studied the carrying capacity of regional water resources. Beijing, the second-largest city in China, faces a critical water shortage that will limit the city’s future development. We developed a method to quantify the carrying capacity of Beijing’s water resources by considering water-use structures based on the proportions of water used for agricultural, industrial, and domestic purposes. We defined a reference structure as 45：22：33 （% of total, respectively）, an optimized structure as 40：20：40, and an ideal structure as 50：15：35. We also considered four domestic water quotas： 55, 75, 95, and 115 m 3 /（person·yr）. The urban carrying capacity of 10–12 million was closest to Beijing’s actual 2003 population for all three water-use structures with urban domestic water use of 75 m 3 /（person·yr）. However, after accounting for our underlying assumptions, the adjusted carrying capacity is closer to 5–6 million. Thus, Beijing’s population in 2003 was almost twice the adjusted carrying capacity. Based on this result, we discussed the ecological and environmental problems created by Beijing’s excessive population and propose measures to mitigate these problems.展开更多
文摘基于对水利知识特点的分析,提出了水利综合知识体系的描述方法,包括水利知识的定义、组成与关联;构建了水利知识图谱的构建框架和关键技术体系,以水利行业结构化业务数据的实体关系转换为基础,采用双向长短期记忆神经网络(Bi-directional Long Shot-Term Memory Neural Network,BiLSTM)与条件随机场(Conditional Random Fields,CRF)方法识别半结构化、非结构化学科知识文本以及互联网数据中的水利实体,使用模式匹配和共现网络分析方法抽取各实体间关系,对涉水对象及其属性进行补充,基于风险最小化的最小风险映射模型(Risk Minimization based Ontology Mapping,RiMOM)进行了多源异构水利实体的融合,实现了涉水对象与水利学科知识的融合与关联,形成水利综合知识的建模和表达。在图谱构建过程中,累计抽取水利实体136万个,构建实体关系300余万条,抽取的水利实体对象的标注准确率在80%以上。基于该图谱可实现水利知识的跨域查询与检索,学科图谱与水网图谱间关系查询,挖掘不同水利实体间的隐含关系,提高水利知识检索的效率和知识挖掘发现的能力。
基金supported by the Knowledge InnovationProject of the Chinese Academy of Sciences (No. KZCX2-YW-422)
文摘As the demands on limited water resources intensify, concerns are being raised about the human carrying capacity of these resources. However, few researchers have studied the carrying capacity of regional water resources. Beijing, the second-largest city in China, faces a critical water shortage that will limit the city’s future development. We developed a method to quantify the carrying capacity of Beijing’s water resources by considering water-use structures based on the proportions of water used for agricultural, industrial, and domestic purposes. We defined a reference structure as 45：22：33 （% of total, respectively）, an optimized structure as 40：20：40, and an ideal structure as 50：15：35. We also considered four domestic water quotas： 55, 75, 95, and 115 m 3 /（person·yr）. The urban carrying capacity of 10–12 million was closest to Beijing’s actual 2003 population for all three water-use structures with urban domestic water use of 75 m 3 /（person·yr）. However, after accounting for our underlying assumptions, the adjusted carrying capacity is closer to 5–6 million. Thus, Beijing’s population in 2003 was almost twice the adjusted carrying capacity. Based on this result, we discussed the ecological and environmental problems created by Beijing’s excessive population and propose measures to mitigate these problems.
