期刊文献+

基于Web的课程知识图谱的构建方法研究 被引量:2

Research on construction method of curriculum knowledge graph based on Web
下载PDF
导出
摘要 教育信息化的大趋势使得互联网中积累了丰富的教育资源,“信息过载”“知识迷航”给学习者带来了困难,构建课程的知识图谱可以为知识学习提供更好的服务支持。文章对课程知识图谱提出了构建方法,首先基于Web获取数据源,构建课程语料库;其次应用基于TF-IDF与互信息MI权值的方法抽取关键词,利用基于词向量的K-means聚类和基于规则的方法提取分类关系,然后将知识存储于neo4j图数据库。最后利用Protégé工具完成课程知识图谱的构建,为课程知识图谱的构建提供一种思路和方法。 The general trend of education informatization has accumulated rich educational resources on the Internet.“Information Overload”and“Knowledge Trek”have caused difficulties for learners.Constructing a knowledge graph of courses can provide better service support for knowledge learning.This paper proposes a construction method for the curriculum knowledge graph.First,based on the Web to obtain data sources,construct a curriculum corpus;apply methods based on TF-IDF and mutual information MI weights to extract keywords,and use K-means clustering based on word vectors and based on the rule method extracts the classification relationship,then stores the knowledge in the neo4j graph database,and finally uses the Protégétool to complete the construction of the curriculum knowledge graph.This research provides an idea and method for the construction of the curriculum knowledge graph.
作者 胡茹艳 Hu Ruyan(Institute of Information,Yunnan Normal University,Kunming 650500,China)
出处 《无线互联科技》 2020年第19期145-146,共2页 Wireless Internet Technology
关键词 知识图谱 课程 构建方法 knowledge graph curriculum construction method
  • 相关文献

参考文献3

二级参考文献18

  • 1[1]中国社会科学研究评价中心.中文社会科学引文索引[EB/OL].[2008-08-25].http://cssci.nju.edu.cn/introduce.htm.
  • 2[1]Chien Lee-Feng.PAT-tree-based keyword extraction for Chinese information retrieval[C]//Proceedifigs of the ACM SIGIR Intemational Conference on Information Retrieval,1997:50-59
  • 3[2]Yang Wenfen,Li Xing.Chinese keyword extraction based on max-duplicated strings of the documents[C]//Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval,2002
  • 4[3]Zhang Kuo,Xu Hui.Tang Jie,et al.Keyword extraction usingsupport vector machine[C]//Proceedings of the 7th International Conference on Web-Age Information Management,Hong Kong,China,2006:85-96
  • 5[4]Olena M,Witten I H.Thesaurus-based index term extraction for agricultural documents[C]//Proceedings of the 6th Agricultural Ontology Service Workshop at EFITA/WCCA.Vila Real;IEEE Press,2005:11-22
  • 6[5]Peter T.Learning to extract keyphrases from text[R].OTTAWA:National Research Council,1999:1-43
  • 7[7]俞鸿魁,张华平,刘群.基于角色标注的中文机构名识别[C]//Proceedings of the 20th International Conference on Computer Processing of Oriental Languages(ACOL),2003
  • 8[9]中国科学院计算技术研究所.汉语词法分析系统ICTCLAS[EB/OL].[2008-03-10].http://www.i3s.ac.err/index.htm
  • 9[10]詹卫东.中文信息处理基础[EB/OL].[2008-03-10].http://ccl.pku.edu.cn/doubffire/Course/Chinese%20 Information%20Processing/2002_2003_1.htm
  • 10[11]吕震宇.SharplCTCLAS分词系统[EB/OL].[2008-03-10].http://www.cnblogs.com/zhenyulu/category/85598.html

共引文献150

同被引文献15

引证文献2

二级引证文献3

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部