收稿日期: 2014-08-26
修回日期: 2014-09-19
网络出版日期: 2014-11-07
基金资助
本文系国家社会科学基金一般项目"知识构建范式演进及其服务创新研究"(项目编号:12BTQ044)研究成果之一。
Knowledge Extraction and Application Based on Web 2.0 Meta-Synthesis in Knowledge Architecture
Received date: 2014-08-26
Revised date: 2014-09-19
Online published: 2014-11-07
对于用户解决问题的智能活动,知识提炼与应用是相继而生的两个连续过程,知识构建(KA)也应对两者进行一体化建构,但已有的KA研究一般都将两者分开来进行,这就使知识内容很难与用户群体及其应用环境有机融合起来,势必严重影响KA的质量和效果。为了使知识提炼与应用在KA中得到一体化实现,以知识及其转化过程为对象,采用文献统计分析和比较研究方法,根据知识的生成机理、转化机制和问题解决的过程要求,在概括总结知识提炼与应用的基本原则基础上,通过对Web 2.0与传统知识生成方法的对比,提出Web 2.0与全信息Web(CI-Web)综合集成的知识提炼与应用方法。这种方法既能在宏观上保障KA系统中的知识得到自主、高效和适应性的定性提炼与应用,又能在微观上确保KA系统中每个用户实现对知识进行全义表示、全面关联、完整发现、准确获取、融合集成和共享应用的定量提炼与利用。
姜永常 , 王红露 . 知识构建中基于Web 2.0综合集成的知识提炼与应用[J]. 图书情报工作, 2014 , 58(21) : 116 -124 . DOI: 10.13266/j.issn.0252-3116.2014.21.017
For users to solve their problems in the intellectual activities, knowledge extraction and application (KEA) are two continuous processes, and should be integrated to knowledge architecture (KA). However, the previous KA's study separates them commonly so that it's really hard to make the knowledge content organically combined with community and context, and will severely reduce the quality and effect of KA. In order to integrate knowledge extraction and application in KA, this paper, using knowledge and its conversion process as the research object, based on documentary statistical analysis and comparative study, first summarizes the basic principles of KEA according to the mechanism of knowledge generation, conversion and the process demand of problem solving, and then puts forward the approach of KEA based on Web 2.0 and comprehensive Information Web (CI-Web) meta-synthesis via the comparison of Web 2.0 and the traditional knowledge generation method. This approach can not only ensure knowledge in KA system will be independently, efficiently, adaptively and qualitatively extracted and applied in macroscopic view, but also ensure each user in KA system will quantitatively extract and apply knowledge in terms of complete representation, correlation, discovery, acquisition, integration and application in microscopic view. This will certainly create a bright future for the integrated construction and innovative development of KA.
[1] 姜永常.知识构建成长的动力需求与能力生成[J].情报理论与实践,2014, 37(4):19-23.
[2] 朝乐门.基于语义Web的知识处理框架研究[J].档案学通讯,2011(4):52-54.
[3] 化柏林,张新民.从知识抽取相关概念辨析看知识抽取的特点和发展趋势[J].情报科学,2010,28(2):311-315.
[4] 化柏林.基于NLP的知识抽取系统架构研究[J].现代图书情报技术,2007(10):38-41.
[5] 温有奎,张卓奎,焦玉英.知识信息谱的分析与提取[J].情报学报,2008,27(5):677-682.
[6] 温浩,温有奎.主题成因的知识元本体转换模型研究[J].情报学报,2011,30(11):123-128.
[7] 温有奎,孙明,温浩,等.基于Web的情报知识元挖掘与语义集成地图[J].情报学报,2008,27(2):163-168.
[8] 赵宇翔,吴克文,朱庆华.基于IPP视角的用户生成内容特征与机理的实证研究[J].情报学报,2011,28(3):299-309.
[9] 朝乐门.大规模人机协同知识处理模式研究[J].中国图书馆学报,2011,37(5):101-114.
[10] 胡昌平,胡吉明.基于群体交互学习的知识创新服务组织分析[J].图书馆论坛,2009,29(6):54-57.
[11] 焦玉英,袁静.基于WIKI的群体知识共享与创 新服务研究[J].情报科学,2008,26(5):652-656.
[12] 张红兵,和金生.基于WIKI的知识共享系统研究[J].科学学研究,2010,28(5):727-731.
[13] Storey V C, Chiang R, Chen G Lily. Ontology creation:Extraction of domain knowledge from Web documents[M]//Lecture Notes in Computer Science.Berlin:Springer-Verlag, 2005: 256-269.
[14] Wu Qingxiang, Bell D. Multi-knowledge extraction and application[M]//Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing. Berlin: Springer-Verlag,2003: 274-278.
[15] Ittoo A, Bouma G. Minimally-supervised extraction of domain-specific part-whole relations using Wikipedia as knowledge-base[J]. Data & Knowledge Engineering, 2013, 85(2): 57-79, 23.
[16] Kurfess F J. Neural networks and structured knowledge: Rule extraction and applications[J]. Applied Intelligence, 2000, 12(1-2): 7-13.
[17] Zárate L E, Dias S M, Song M A J. FCANN:A new approach for extraction and representation of knowledge from ANN trained via formal concept analysis[J]. Neurocomputing, 2008, 71(13-15): 2670-2684, 15.
[18] Ultsch A, Guimaraes G, Korus D, et al. Knowledge extraction from artificial neural networks and applications[M]. Parallele Datenverarbeitung mit dem Transputer.Berlin:Springer-Verlag, 1994: 148-162.
[19] 钟义信.知行学引论——信息、知识、智能的统一理论[J].中国工程科学,2004,6(6):1-8.
[20] 钟义信.人工智能的突破与科学方法的创新[J].模式识别与人工智能,2012,25(3):456-461.
[21] 钟义信.高等智能·机制主义·信息转换[J].北京邮电大学学报,2010,33(1):1-6.
[22] 钟义信.信息转换原理:信息、知识、智能的一体化理论[J].科学通报,2013,58(14):1300-1306.
[23] 钟义信.机器知行学原理:信息、知识、智能的转换与统一理论[M].北京:科学出版社,2007:148-161.
[24] 马费成.Web 2.0信息序化机制[J].图书情报知识,2009(6):14-18.
[25] 朝乐门.基于语义的人机协同知识处理研究[J].图书情报工作,2009,53(24):115-119.
[26] 马费成.基于CAS理论的维基百科序化机制研究[J].图书馆论坛,2008,28(6):85-92.
[27] 赵宇翔,张苹,朱庆华.社会化媒体中用户体验设计的理论视角:动因支持模型及其设计原则[J].中国图书馆学报,2011,37(5):36-45.
[28] 马费成.网络信息序化原理——Web 2.0机制[M].北京:科学出版社,2012:55-75.
[29] 姜永常.基于用户体验的知识构建——Web 2.0环境下对知识构建原理的再认识[J].情报学报,2010,29(5):872-879.
[30] 朝乐门.基于语义Web的知识处理流程及其技术框架研究[J].中国图书馆学报,2009, 35(5):59-68.
/
| 〈 |
|
〉 |
