作为知识经济时代出现的新兴管理方法,企业知识管理的一个重要的研究课题,是对组织成员和人力资源的知识管理。传统的知识管理方法基于封闭的企业管理历史数据,不能深入地挖掘企业管理知识。本文拟从网络数据的行为建模和多源数据融合的角度,探索新的企业知识管理方法。以企业知识管理为研究目标,以石化企业员工为研究对象,以自然语言分析和处理为模式表示方法,以统计机器学习为知识分析工具,重点研究如何通过网络行为建模和多源数据融合,从而更全方位地对企业员工的性格、日常行为建立一套行之有效的分析机制,实现在开放网络时代的企业知识管理和绩效管理。在石化企业内部的知识管理实验性尝试表明,所提知识管理方法,能够更深入地对企业员工的行为进行分析和理解,能够更有效地将员工行为和企业人力资源中的若干关键指标建立相关性模型,从而为企业的知识管理和决策人员提供强有力的技术支持。
Abstract
As a novel management theory of the knowledge-based economy, the key research problem of enterprise knowledge management is how to conduct management on organization members, human resources and customers. Traditional knowledge management approaches are based on the closed enterprise management history data. However, they are not able to discover the knowledge for modern enterprises more comprehensively. This paper studies the methodologies of behavior modeling on web data and heterogeneous information fusion for enterprise knowledge management. We serve enterprise knowledge management as the research objective, treat the employees of the petrochemical enterprises as the research target, and use the natural language processing techniques as the pattern representation method. We build our knowledge analytical method based on the statistical machine learning for heterogeneous information fusion mechanisms, in order to construct a comprehensive behavior understanding and knowledge discovery methodologies, and try to use big data and information fusion to construct the enterprise knowledge based management and performance management. Extensive knowledge management experiments in petrochemical enterprises validate the effectiveness of our approach, which is capable of analyzing and understanding the enterprise employees, and build the correlation model between the employee behavior and knowledge discovery objectives in enterprise human resource management. Therefore, our method provides strong technical support for enterprise knowledge management decision making.
关键词
知识管理 /
网络行为建模 /
多源知识融合 /
指标相关性模型
Key words
knowledge management /
online behavior modeling /
multi-source knowledge fusion /
correlation model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 汪克强. 企业知识管理运行体系研究[D].合肥:中国科学技术大学,2003. Wang Keqiang.Research of the operation system of knowledge management in enterprise[D].Hefei:University of Science and Technology of China,2003
[2] Romer P M.Endogenous technological change[J].Journal of Political Economy,1990,98(5):71-102.
[3] Lucas Jr R E.On the mechanics of economic development[J].Journal of monetary economics,1988,22(1):3-42.
[4] 郭君, 付群,刘宁.面向知识经济的企业组织管理[J].一重技术,2007(1):71-73. Guo Jun,Fu Qun,Liu Ning.The enterprise management to knowledge economy[J].CFHI Technology,2007(1):71-73.
[5] 李小艳. 基于改进BP神经网络的企业知识管理绩效评价研究[D].广州:华南理工大学,2013. Li Xiaoyan.Research on the performance evaluation of enterprise knowledge management based on improved BP neural network[D].Guangzhou:South China University of Technology,2013
[6] 廖玲. 基于数据库资源的长庆油田知识管理研究[D].西安:西安石油大学,2012. Liao Ling.Knowledge management research based on database resource for changqing oilfield[D].Xi'an:Xi'an Shiyou University,2012
[7] Liu S,Wang S,Jayarajah K,et al.TODMIS:Mining communities from trajectories[C].Proceedings of the 22nd ACM international conference on Conference on information & knowledge management.ACM,2013:2109-2118.
[8] Liu S,Wang S,Zhu F,et al.HYDRA:Large-scale social identity linkage via heterogeneous behavior modeling[C].SIGMOD,2014.
[9] 唐杰, 贾珈,杨洋等.社交网络数据的情感计算[J].中国计算机学会通讯,2014,10(5):18-24. Tang Jie,Jia Jia,Yang Yang,et al.The emotional calculation of social network data[J].Communications of the CCF,2014,10(5):18-24.
[10] Antenucci D,Cafarella M J,Levenstein M C,et al.Ringtail:Feature selection for easier nowcasting[C].WebDB,2013:49-54.
[11] Antenucci D,Cafarella M,Levenstein M C,et al.Using social media to measure labor market flows[R].Cambridge:National Bureau of Economic Research,2014.
[12] Culotta A.Estimating county health statistics with twitter[C].Proceedings of the SIGCHI Conference on Human Factors in Computing Systems,2014:1335-1344.
[13] Lazer D M,Kennedy R,King G,et al.The parable of google flu:Traps in big data analysis[J].Science,2014,343(6176):1203-1205.
[14] Wang S,Wang Z,Jiang S,et al.Cross media topic analytics based on synergetic content and user behavior modeling[C].Multimedia and Expo(ICME),2014 IEEE International Conference on,IEEE,2014:1-6.
[15] Liu S,Wang S,Krishnan R.Persistent community detection in dynamic social networks[C].Advances in Knowledge Discovery and Data Mining,2014:78-89
[16] Fellegi I P,Sunter A B.A theory for record linkage[J].Journal of the American Statistical Association,1969,64(328):1183-1210.
[17] Hall R,Fienberg S E.Privacy-preserving record linkage[C].Privacy in statistical databases,Springer Berlin Heidelberg,2011:269-283
[18] Bradley P S,Fayyad U,Reina C,et al.Scaling EM (expectation-maximization) clustering to large databases[R].Technical Report MSR-TR-98-35,Microsoft Research,1998.
[19] Duda R O,Hart P E,Stork D G.Pattern classification[M].John Wiley & Sons.,2012.
[20] Dhillon I,Guan Y,Kulis B.A unified view of kernel k-means,spectral clustering and graph cuts[M].UTCS Technical Report #TR-04-25,University of Texas at Austin,2005.
[21] Liu H, Yan S.Robust graph mode seeking by graph shift[C].Proceedings of the 27th International Conference on Machine Learning (ICML-10).2010:671-678.
[22] Krishnapuram B,Carin L,Figueiredo M A,et al.Sparse multinomial logistic regression:Fast algorithms and generalization bounds[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2005,27(6):957-968.
PDF(1 KB)
