首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于交互式可视化的领域知识图谱构建研究
引用本文:岳丽欣,刘自强,许海云.基于交互式可视化的领域知识图谱构建研究[J].情报科学,2020,38(6):145-150.
作者姓名:岳丽欣  刘自强  许海云
作者单位:中国人民大学信息资源管理学院,北京100872;中国科学院成都文献情报中心,成都610041;中国科学院大学经济与管理学院图书情报与档案管理系,北京100190;中国科学院成都文献情报中心,成都610041
基金项目:国家自然科学基金;中国科学院青年创新促进会项目
摘    要:【目的/意义】基于文献数据的领域知识图谱构建有助于探测某学科领域的主要研究内容及其发展方向,是进行技术创新的基础情报工作,对于研究人员、企业都具有一定的意义。【方法/过程】提出基于交互式可视化技术的知识图谱构建方法,首先基于经典LDA模型进行主题识别,然后基于社会网络分析方法构建领域主题网络识别关键主题词;最后,基于JS(D3工具)绘制可交互的关键主题词关联与检索知识图谱,发现关键主题词的隐含联系,辅助进行领域知识挖掘与分析。【结果/结论】通过对我国医疗健康信息领域进行实证研究,验证了本文提出方法的准确性和有效性。

关 键 词:交互式  可视化  主题识别  D3  LDA

Domain Knowledge Mapping Construction Based on Interactive Visualization
YUE Li-xin,LIU Zi-qiang,XU Hai-yun.Domain Knowledge Mapping Construction Based on Interactive Visualization[J].Information Science,2020,38(6):145-150.
Authors:YUE Li-xin  LIU Zi-qiang  XU Hai-yun
Institution:(School of Information Resources Management,Renmin University of China,Beijing 100872,China;Chengdu Library of Chinese Academy of Sciences,Chengdu 610041,China;Department of Library,Information and Archives Management,School of Economics and Management,University of Chinese Academy of Sciences,Beijing 100190,China)
Abstract:【Purpose/significance】Domain knowledge map construction based on document data is helpful to explore the main research content and development direction of a certain discipline field. It is the basic information work for technological innovation, and has certain significance for researchers and enterprises.【Method/process】A method of knowledge map construction based on interactive visualization technology is proposed. Firstly, topic recognition is performed based on classical LDA model, and then domain topic network is constructed based on social network analysis method to identify important subject words. Then, interactive key subject word association and retrieval knowledge map are drawn based on JS(D3 tool), and hidden relation of core subject words is found to assist in leading domain knowledge mining and analysis.【Result/conclusion】Through the empirical research on the field of medical health information in China, it verifies the accuracy and effectiveness of the proposed method.
Keywords:interactive  visualization  topic identification  D3  LDA
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《情报科学》浏览原始摘要信息
点击此处可从《情报科学》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号