检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:朱纯 郑伟华 王玖凯 张文 朱军 ZHU Chun;ZHENG Weihua;WANG Jiukai;ZHANG Wen;ZHU Jun(State Grid Shanghai Electric Power Company,Shanghai 200120,China;Nanjing Nari Information&Communication Technology Co.,Ltd.,Nanjing 211899,China)
机构地区:[1]国网上海市电力公司,上海200120 [2]南京南瑞信息通信科技有限公司,江苏南京211899
出 处:《微型电脑应用》2024年第10期148-151,共4页Microcomputer Applications
摘 要:目前常规的基建工程知识库主要采用自下而上的方式对工程数据进行存储,由于对基建工程知识数据的融合程度较低,导致知识库的数据调度性能不佳。对此,提出基于语义概率图与关联规则的基建工程知识库构建方法。将电网基建工程数据转换为事件数据,对其进行关联分析,并结合关联分析结果以及语义概率图对基建工程知识图谱实体进行构建。通过计算文本词汇相似度,实现基建工程知识数据的深度融合,并对知识图谱进行复用,结合知识概念以及属性的抽取结果,实现知识库的构建。在实验中,对提出的知识库进行数据抽取性能的检验。经实验结果表明,采用所提方法构建的基建工程知识库,单位时间内可调度工程资源数据量较高,具备较为理想的数据调度性能。The current conventional infrastructure engineering knowledge base mainly adopts a bottom-up approach to store en-gineering data,which leads to poor data scheduling performance due to the low degree of integration of infrastructure engineer-ing knowledge data.In this regard,the method of constructing infrastructure engineering knowledge base based on semantic probability graph and association rule is proposed.The power grid infrastructure engineering data are converted into event da-ta,association analysis is performed on the data and the infrastructure engineering knowledge graph entity is constructed by combining the association analysis results and semantic probability graph.The deep fusion of infrastructure engineering knowl-edge data is realized by calculating the text lexical similarity,the knowledge graph is reused,and the knowledge base is con-structed by combining the extraction results of knowledge concepts and attributes.In the experiment,the data extraction per-formance of the proposed knowledge base is examined.The experimental results show that the infrastructure engineering knowledge base constructed by the proposed method has a high amount of schedulable engineering resource data per unit time and has a more desirable data scheduling performance.
分 类 号:TP392[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:18.119.110.206