面向非相关文献的知识关联检索系统的设计与实现
|
摘要
[目的/意义]面向非相关文献的知识关联能够促进新知识的产生,为科学研究提供了一种有效的辅助手段。[方法/过程]本文以《中国分类主题词表》为主题词受控词表,首先对文献摘要进行中文分词处理并提取主题词,利用计量分析技术和聚类技术分析文献间特征的相似、相异水平,然后基于该系统为用户检索并利用用TOP-K算法反馈用户精确结果。[结果/结论]设计了面向非相关文献的知识关联检索系统,从更细的粒度层面揭示文献之间的知识关联,为用户提供高质量的服务。
[Purpose/Meaning]Knowledge association for non-related literature can promote the generation of new knowledge and provide an effective aid for scientific research.[Methods/Processes]This paper used the"Chinese Classification Thesaurus"as the controlled word list of subject words.Firstly,the Chinese word segmentation of the document abstract was processed and the topic words were extracted.The econometric analysis technique and clustering technique were used to analyze the similarity between the documents.Different levels were then used to retrieve and utilize the TOP-K algorithm to feed back user accurate results based on the system.[Results/Conclusions]A knowledge-based retrieval system for non-related literature was designed to reveal the knowledge association between documents from a more granular level,and to provide users with high-quality services.
[Purpose/Meaning]Knowledge association for non-related literature can promote the generation of new knowledge and provide an effective aid for scientific research.[Methods/Processes]This paper used the"Chinese Classification Thesaurus"as the controlled word list of subject words.Firstly,the Chinese word segmentation of the document abstract was processed and the topic words were extracted.The econometric analysis technique and clustering technique were used to analyze the similarity between the documents.Different levels were then used to retrieve and utilize the TOP-K algorithm to feed back user accurate results based on the system.[Results/Conclusions]A knowledge-based retrieval system for non-related literature was designed to reveal the knowledge association between documents from a more granular level,and to provide users with high-quality services.
引文
[1]黄水清,马俊岭.汉语社会科学文献非相关文献知识发现的实证研究——以农业经济学文献为例[J].中国图书馆学报,2009,35(4):31-38.
[2]李勇,冷伏海,王林.基于非相关文献的三阶知识发现方法探讨[J].中国图书馆学报,2011,37(4):21-26,69.
[3]楼雯.馆藏资源语义化关键技术及实证研究[J].中国图书馆学报,2013,39(6):27-40.
[4]邱均平,余凡.基于计量分析的馆藏资源语义化理论研究[J].中国图书馆学报,2012,38(4):71-78.
[5]刘爱琴,王友林,尚珊.基于爬虫技术的关键词关联推荐算法优化与实现[J].情报理论与实践,2018,41(4):134-138.
[6]赵萍萍.从传记文献的主题标引谈文献主题标引规则[J].现代情报,2004,(6):137-139.
[7]吴雯娜.我国叙词表的编制历史与发展模式[J].情报理论与实践,2018,41(6):39-44.
[8]陈树年,刘惠敏.从网络信息组织看《中国分类主题词表》[J].国家图书馆学刊,2006,(2):21-27.
[9]余丰民.国内主题词表研究脉络初探[J].情报科学,2014,32(5):12-17.
[10]王曰芬,宋爽,卢宁,等.共现分析在文本知识挖掘中的应用研究[J].中国图书馆学报,2007,(2):59-64.
[11]邱均平,楼雯.基于共现分析的语义信息检索研究[J].中国图书馆学报,2012,38(6):89-99.
[12]刘迁,贾惠波.中文信息处理中自动分词技术的研究与展望[J].计算机工程与应用,2006,42(3):175-177.
[13]黄昌宁,赵海.中文分词十年回顾[J].中文信息学报,2007,(3):8-19.
[14]尹锋.基于神经网络的汉语自动分词系统的设计与分析[J].情报学报,1998,17(1):41-50.
[15]陈白雪,宋培彦.基于用户自然标注的TF-IDF辅助标引算法及实证研究[J].图书情报工作,2018,62(1):132-139.
[16]祝清松,冷伏海.非相关文献知识发现的融合评价方法构建研究[J].情报理论与实践,2013,36(7):106-109,105.
[2]李勇,冷伏海,王林.基于非相关文献的三阶知识发现方法探讨[J].中国图书馆学报,2011,37(4):21-26,69.
[3]楼雯.馆藏资源语义化关键技术及实证研究[J].中国图书馆学报,2013,39(6):27-40.
[4]邱均平,余凡.基于计量分析的馆藏资源语义化理论研究[J].中国图书馆学报,2012,38(4):71-78.
[5]刘爱琴,王友林,尚珊.基于爬虫技术的关键词关联推荐算法优化与实现[J].情报理论与实践,2018,41(4):134-138.
[6]赵萍萍.从传记文献的主题标引谈文献主题标引规则[J].现代情报,2004,(6):137-139.
[7]吴雯娜.我国叙词表的编制历史与发展模式[J].情报理论与实践,2018,41(6):39-44.
[8]陈树年,刘惠敏.从网络信息组织看《中国分类主题词表》[J].国家图书馆学刊,2006,(2):21-27.
[9]余丰民.国内主题词表研究脉络初探[J].情报科学,2014,32(5):12-17.
[10]王曰芬,宋爽,卢宁,等.共现分析在文本知识挖掘中的应用研究[J].中国图书馆学报,2007,(2):59-64.
[11]邱均平,楼雯.基于共现分析的语义信息检索研究[J].中国图书馆学报,2012,38(6):89-99.
[12]刘迁,贾惠波.中文信息处理中自动分词技术的研究与展望[J].计算机工程与应用,2006,42(3):175-177.
[13]黄昌宁,赵海.中文分词十年回顾[J].中文信息学报,2007,(3):8-19.
[14]尹锋.基于神经网络的汉语自动分词系统的设计与分析[J].情报学报,1998,17(1):41-50.
[15]陈白雪,宋培彦.基于用户自然标注的TF-IDF辅助标引算法及实证研究[J].图书情报工作,2018,62(1):132-139.
[16]祝清松,冷伏海.非相关文献知识发现的融合评价方法构建研究[J].情报理论与实践,2013,36(7):106-109,105.