A Study of Applying Multi-Agent in Innovation Technology Knowledge Services Recommendation on Industry Clusters
林志龍、楊豐兆
E-mail: 9422472@mail.dyu.edu.tw
ABSTRACT
Most modern industries are operated in industry cluster style. Only reinforcing the cluster forming factors could improve the performance of the cluster. Hence, this thesis is aim to build an innovation technology knowledge services recommendation sharing mechanism based on multi-agent technique under industry cluster environment, and this mechanism could suggest the right knowledge services at the right time to the right industry. The main tasks of this multi-agent system are knowledge acquirement and knowledge recommendation. Knowledge acquirement is that the extraction agent could automatically collect the knowledge service descriptions from the innovation knowledge base websites and then stored them in the knowledge repository. Knowledge
recommendation is that the register agent provides the industries with a register interface, in order to obtain the industrial technique requirement description. Further, the segmentation agent will separate the entire possible segment results from the industrial technique requirement description based on our proposed segmentation method which could separate out keywords from the industrial technique requirement description. Then the match agent will match the result of segmentation and the knowledge service description retrieved from knowledge base websites, the recommendation agent further recommends the innovation knowledge service to industries. The system development of this research is on JADE platform and its concrete contributions are as follows:
(1)We propose a novel platform of innovation knowledge services recommendation. (2)Applying the multi-agent technique to the industry cluster environment could promote the forming factors’ strength of cluster and reconstruct the structure of cluster.
(3)Reinforcing the forming factors of industry cluster by setting up an e-system is quite different from the other literatures which only discussed in the management domain. The obtainment of innovation technique information could speed up innovation research development, promote the level of industry and also let the cluster effect more conspicuous. Therefore, the design of innovation technology knowledge service recommendation mechanism is necessary and has its value.
Keywords : Industry cluster ; multi-agent system ; knowledge service recommendation ; segmentation ; innovation technique information
Table of Contents
封面內頁 簽名頁 授權書 ...iii 中文摘要 ...iv 英文摘要 ...v 誌謝 ...vii 目錄 ...viii 圖目錄 ...xi 表目錄
...xiii 第一章 緒論 ...1 1.1 研究背景 ...1 1.2 研究動機與目的 ...2 1.3 研究範圍與限制 ...3 1.4 研究流程 ...4 1.5 論文架構
...5 第二章 文獻探討 ...7 2.1 產業群聚(Industry Clusters) ...7 2.2 代理人(Agent) ...11 2.3 推薦系統(Recommendation System) ...14 2.4 資訊擷取(Information Retrieval) ...15 2.5 中文 斷詞(Chinese Segmentation) ...16 2.6 系統分析工具與方法論 ...17 2.7 JADE ...20 第三章 系統需求分析 ...23 3.1 系統架構 ...23 3.2 系統需求分析 ...25 3.3 斷詞方法 描述與擷取欄位說明 ...33 第四章 系統模型設計 ...37 4.1 代理人社群模型(Agent Society Model) ...37 4.2 代理人實作模型(Agent Implementation Model) .43 4.3 編碼模型(Code Model) ...47 4.4 部署模 型(Deployment Model) ...47 第五章 系統實作與評估分析 ...49 5.1 開發工具與平台 ...49 5.2 JADE代理人實作框架 ...51 5.3 系統操作介面 ...52 5.4 評估與分析 ...55 第 六章 結論與未來研究 ...59 6.1 研究貢獻 ...59 6.2 未來研究方向 ...60 參考文 獻 ...61 附錄A 代理人工作規範圖 ...65 附錄B 單一代理人結構定義圖 ...70 REFERENCES
1.中央研究院中文詞庫小組，“研究院語料庫的內容及說明”，中央研究院，1995。 2.王啟勳，“知識仲介下客戶問題與專家專長配對 之探討-以管理研究發展中心為例”，大葉大學 資訊管理系碩士論文，2005。 3.余明哲，“圖書館個人化館藏推薦系統”，交通大學資 訊科學研究所碩士論文，2003。 4.張陽隆，“產業群聚成因、廠商行為與組織績效之關聯性研究-以台灣高科技產業為例”，成功大學
企業管理系碩士論文，2001。 5.楊錦潭、蕭淳豐，“開發智慧型代理人軟體工程平台初探”，高師大電子月刊，pp. 138-157， 2001年11 月。 6.鍾政憲，“以代理人社群為基礎的主動式知識服務推薦系統之研究”，大葉大學資訊管理系碩士 論文，2004。 7.AgentBuilder, http://www.agentbuilder.com/AgentTools/. 8.Bettina Berendt, Bamshad Mobasher and Myra Spiliopoulou, “Web Usage Mining for E-Business Application,” http://gnu.univ.gda.pl/~tomasz/Download/z/Sem2002-3/berendt-2. pdf, 19 Aug. 2002. 9.David W. McDonald, “Ubiquitous Recommendation System,” Computer, Vol. 36, No. 10, pp. 111-112, Oct. 2003. 10.G. Cabri, L. Leonardi and F. Zambonelli, “Mobile-agent coordination models for Internet applications,” Computer, Vol. 33, pp. 82-89, Feb. 2000. 11.Hyacinth S. Nwana, “Software Agents: An Overview,” Knowledge Engineering Review, Vol. 11, No. 3, pp. 1-40, Sep. 1996. 12.J. Pokorny, “Web searching and information retrieval,”
Computing in Science & Engineering, Vol. 06, pp. 43-48, Jul./Aug. 2004. 13.Martin Gonzalez Rodriguez, “Automatic data-gathering agents for remote navigability testing,” IEEE, Software, Vol. 19, pp. 78 - 85, Nov. /Dec. 2002. 14.M.L. Griss and G. Pour, “Accelerating development with agent components,” Computer, Vol. 34, pp. 37 - 43, May 2001. 15.M.N. Huhns, “Agents as Web services,” IEEE, Internet Computing, Vol. 6, pp. 93 – 95, July-Aug. 2002. 16.PASSI Methodology, http://mozart.csai.unipa.it/passi/, 2004. 17.Paul Resnick, and Hal R. Varian,
“Recommendation systems,” Communication of ACM, Vol. 40, No. 3, pp. 56-58, 1997. 18.P. Burrafato and M. Cossentino, “Designing a multi-agent solution for a book store with the PASSI methodology,” in Fourth International Bi-Conference Workshop on Agent-Oriented Information System,27-28 May 2002. 19.Porter M. E, “The Competitive Advantage of Nations,” New York: Free Press, 1990. 20.Roger H.L.
Chiang, Cecil Eng Huang Chua and Veda C. Storey, “A smart web query method for semantic retrieval of web data,” Data and Knowledge Engineering Vol. 38, pp. 63-84, July, 2001. 21.Sabourin, V. and Pinsonneault, I., “Strategic Formation of Competitive High Technology Clusters,
” International Journal of Technology Management, pp. 165-178, 1997. 22.San Murugesan, ”Intelligent Agents on the Internet and Web,”
TENCON '98. 1998 IEEE Region 10 International Conference on Global Connectivity in Energy, Computer, Communication and Control, Vol.
1, pp. 97-102, 17-19 Dec. 1998. 23.S. Case, N. Azarmi, M. Thint and T. Ohtani, “Enhancing e-communities with agent-based systems,”
Computer, Vol. 34, pp. 64 - 69, Jul. 2001. 24.Scott A. Deloach, Mark F. Wood and Clint H. Sparkman, “Multiagent System Engineering,”
International Journal on Software Engineering and Knowledge Engineering, Vol. 11, No. 3, pp. 231-258, Mar. 2001. 25.Steven Willmott,
“Technical Input and Feedback to FIPA from Agentcities RTD and the Agentcities Initiative,”
http://www.agentcities.org/note/00003/actf-note-00003a.pdf, Mar. 2004. 26.Stuart Russell and Peter Norvig, “Artificial Intelligence: A Modern Approach,” Prentice Hall, Upper Saddle River, N.J., 1995. 27.The FIPA Agent UML Web Site, http://www.auml.org, 2004. 28.Tse-Ming Tsai, Han-Kuan Yu, Hsin-Te Shih, Ping-Yao Liao, Ren-Dar Yang and S.T. Chou, “Ontology-mediated integration of intranet Web services,”
Computer, Vol. 36 , pp. 63 - 71, Oct. 2003. 29.Web Services Activity, http://www..w3.org/2002/ws, 2004. 30.Weiming Shen, “Distributed manufacturing scheduling using intelligent agents,” IEEE, Intelligent Systems , Vol. 17, pp. 88-94, Jan./Feb. 2002. 31.Wooldridge Michael, Jennings N.R. and Kinny D., “The Gaia Methodology for Agent-Oriented Analysis and Design,” Journal of Autonomous Agents and Multi-Agent Systems, Vol. 3, No. 3, pp. 285-312, 2000. 32.Yue-Shan Chang, Min-Huang Ho and Shyan-Ming Yuan, ”A unified interface for integrating information retrieval,” Computer Standards and Interfaces, Vol. 23, pp. 325-340, September 2001.
