臺灣博碩士論文加值系統

本論文將研究的範圍著重在產生數位通訊應用的自主系統，利用人工智慧的技術及資料庫系統自主完成數位通訊硬體模組的代入與合成。在人工智慧中案例式推理技術是回憶和學習以往案例的解答，並推薦給目前問題案例當作解題參考答案，案例的儲存結構是使用標準關聯式資料庫設計流程。系統的操作程序一開始是由使用者在人機介面輸入設計條件，然後由交易單元產生對案例庫進行交談的查詢敘述，以擷取到解題的候選案例。最後，針對設計的規格，進行候選案例應用的可行性以及解答調整。案例式推理中，效能是最重要的部份，它會影響推論的結果，也就是在資料庫中搜尋到的案例數量。因此，為了提升擷取案例的正確性和效率的，許多比對函數也隨之產生，以達到實現自主系統世代為目標。

In this thesis, the research scope has focused on the autonomous system generation of the digital communication applications. We use the case-base reasoning of artificial intelligence technique and database system to retrieve the reusable digital communication hardware modules that are in turn used to synthesize a dedicated digital communication system referring to the designated system specification. The case-based reasoning technique uses the remembering and learning on existed solutions to solve new problems. The case library is constructed by a standard design flow of relational database to alleviate the implementation efforts. The system generation process is started from the specified design conditions from the graphical user interface, then a set of database query statements are derived to retrieve those candidate solution classes in case library that are built on a database system. Finally, the applicable evaluation and revision are applied on the candidate cases based on the designated system specification. The performance of case-based reasoning is important. It directly influences the amount of retrieved candidate cases from case library. Therefore, several matching functions are devised to promote the correctness and efficiency of the case retrieve that are applied to achieve the goal of autonomous system generation.

中 文 摘 要................i
Abstract................ii
致謝................iii
目 錄................iv
圖 目 錄................v
表 目 錄................vi

第一章 緒論................1
1-1 研究背景................1
1-2 研究動機................1
1-3 研究目的及方法................2
第二章 案例式推理理論................4
2-1 專家系統................4
2-1-1 規則式推理系統（Rule-based reasoning，RBR）................5
2-1-2 案例式推理系統（Case-based reasoning，CBR）................5
2-2 案例式推理系統（Case-based reasoning，CBR）................6
2-2-1 案例表示法（Representation of Cases）................6
2-2-2 案例式推理週期（CBR cycle）................8
2-3 案例式推理系統推論技術................10
2-3-1 索引編派................10
2-3-2 相似度衡量................11
第三章 系統設計方法................13
3-1 設計標準................14
3-2 系統架構................14
3-2-1 系統方塊功能設計................15
3-2-3 系統的學習與維護................34
第四章 實作驗證................36
4-1 開發環境................36
4-2 資料庫與C++ Builder 6.0的設定................37
4-3 系統操作流程及分析................38
第五章 結論................42
參考文獻................44
附錄................47
作者簡歷................50

圖 目 錄

圖2-1 問題與結果空間................7
圖2-2 系統PROTOS案例表示法................8
圖2-3 CBR流程................9
圖2-4 索引資訊................10
圖3-1 系統架構................15
圖3-2 案例庫形成步驟................16
圖3-3 表格形式................17
圖3-4 實體關係圖................18
圖3-5 關聯式資料綱要................18
圖3-6 案例庫架構和應用程式設計流程 20
圖3-7 通訊產品規格................21
圖3-8 通訊抽象階層圖................21
圖3-9 案例庫ER圖................24
圖3-10 Access表格架構................25
圖3-11 關聯式綱要Access格式................25
圖3-12 系統操作流程圖................26
圖3-13 案例收集器................27
圖3-14 屬性分級器................27
圖3-15 SQL產生器................28
圖3-16 案例式推理控制器................28
圖3-17 案例表示格式................29
圖3-18 案例的匹配................30
圖3-19 函數功能................31
圖3-20 數值型相似衡量函數................32
圖3-21 數值型屬性相似值計算範例................33
圖3-22 評論輸出報告框架................34
圖3-23 系統學習流程圖................35
圖4-1 C++ Builder 6.0整合開發環境 36
圖4-2 設定OLE DB提供者................37
圖4-3 連結資料庫................38
圖4-4 GUI介面................38
圖4-5 擷取候選案例................39
圖4-6 系統推理結果................40

表 目 錄

表3-1 需求表格................29
表3-2 解答表格................30
表4-1 屬性相關參數................39
表4-2文字型屬性相似度百分比................40
表4-3數值型屬性相似度百分比................41
表4-4總體相似度百分比................41

[1] J. Kolodner. Case-Based Reasoning. Morgan Kaufmann Publishers, San Mateo, CA, 1993
[2] F. Lorenzi and F. Ricci, “Case-Based Recommender Systems：a Unifying View”, LNCS/LNAI State-of-the-Art Survey book on Intelligent Techniques, 2005.
[3] A. Aamodt and E. Plaza, “Case-Based Reasoning：Foundational Issues, Methodological Variations, and System Approaches,” AI Communications, vol.7, no. 1, pp.39-59, March 1994.
[4] D. A. Waterman, A Guide to Expert System, Addison-Wesley, 1985.
[5] R. Bareiss, Exemplar-based knowledge acquisition：A unified approach to concept representation, classification, and learning. Boston, Academic Press, 1989
[6] B. Porter, R. Bareiss and R. Holte, “Concept learning and heuristic classification in weak theory domains,” Artificial Intelligence, vol. 45, no. 1-2, pp. 229-263, Sep 1990.
[7] H.-C. Chang, L. Dong, F.X. Liu and W.F. Lu, “Indexing and retrieval in machining process planning using case-based reasoning,” Artificial Intelligence in Engineering, vol. 13, no. 1, pp1-13, 2000.
[8] B.C. Jeng and T.-P. Liang, “Fuzzy indexing and retrieval in case-based systems,” Expert Systems with Application, vol.8, no.1, pp.135-142, 1995.
[9] H. Li, “Case-based reasoning for intelligent support of construction negotiation,” Information & Management, vol.30, pp231-238, 1996.
[10] J. Kolodner, “Maintaining Organization in a dynamic long-term memory,” Cognitive Science, vol.7, pp243-280, 1983
[11] J. Kolodner, “Reconstructive memory, a computer model,” Cognitive Science, vo1.7, pp281-328, 1983
[12] R. Schank, “Dynamic memory, a theory of reminding and learning in computers and people,” Cambridge University Press.
[13] I. Watson, “Case-based reasoning is a methodology not a technology,” Knowledge-based systems, vol.12, pp303-308, 1999.
[14] N.J. Yau and J.B. Yang, “Applying case-based reasoning technique to retaining wall selection,” Automation in construction, vol.7, pp271-283, 1998.
[15] G. Divr, G. Langholz and M. Schneider, “Matching Attributes in a Fuzzy Case-based Reasoning,” Fuzzy Information Processing Society, 1999. NAFIPS. 18th Int. Conf. of the North American, pp. 33-36.
[16] P. Juell and P. Paulson, “Using Reinforcement Learning for Similarity Assessment in Case-based Systems,” IEEE Intelligent Systems, vol.18, no.4, pp.60-67, January 2003.
[17] D. Xu. Li, “Case-based reasoning,” IEEE Potentials, pp.10-13, 1994
[18] C. Tsatsoulis, Q. Cheng and H.-Y. Wei, “Integrating Case-Based Reasoning and Decision Theory” IEEE Expert, pp.46-55, July/August 1997.
[19] J.Jarmulak, S. Craw and R. Rowe, “Self-Optimizing CBR Retrieval,” In Proceedings of the. 12th IEEE International Conf. On Tools with Artificial Intelligence (ICTAI-2000), pp. 376-383, 2000.
[20] 林耀珍（2004），『軟體架構師的成功秘訣』。民國96年1月。取自：http://www.microsoft.com/taiwan/msdn/columns/200410softdev.htm
[21] E.F. Codd, “Relational Model of Data for Large Shared Data Banks,”Communications of the ACM, vol.13, no.6, pp.377–387, June 1970.
[22] D. Hennessy and D. Hinkle, “Applying Case-based Reasoning to Autoclave Loading,” IEEE Expert, vol7, pp21-28, October 1992.
[23] T. Tanaka, M. Hattori and N. Sueda,“Use of Multiple Cases in Case-Based Design,” In Proceedings of. the IEEE Int. Conf. on AI Applications, pp. 233–239, 1992.
[24] L. Lifeng, M. Zengqiang, Z. Zhe and L. Baizhen, “Research on Case Organization and Retrieval of Case and Rule Based Reasoning Approaches for Electric Power Engineering Design,” Power System Technology, 1998. Proceedings. POWERCON '98. 1998 Int. Conf. on, vo1.7, pp.1082-1085.
[25] 姚修慎（1999），『資料庫系統概論』，揚智文化事業股份有限公司。
[26] 施威銘（1998），『Access 2000系統開發實務』，旗標出版股份有限公司。