據世界智慧財產權組織（World Intellectual Property Organization, WIPO）的統計，發現有效率的運用專利文獻不僅獲得90%-95%的研發成果，更可以縮短及節省40%的研發費用。相對於其他技術文獻則僅含有5%-10%的研發成果，專利的重要性舉足輕重。
本研究為跨越習用以國際專利分利號所制定的分類號進行專利分類，提出先以在申請專利範圍進行檢索近10年關於太陽能集熱器之專利，進行文字解析以及統計其常出現之關鍵字，以利建構出太陽能集熱器之本體論，提供後續檢索太陽能集熱器之專利可利用此本體論進行資料的整理以及歸檔與組織，並且合理的利用專利內的技術內容劃分並且分群以利於檢索並且也節省時間，接著利用檢索專利進行專利分析以及探討，並且根據不同之技術以及應用進行趨勢分析之探討，接著利用其中關鍵專利結合資料探勘K-means之方法進行分群，將關鍵專利以技術分為五個群集，針對這五個群集產生技術功效矩陣，建構功效矩陣時，使用者只需由本體論之結構、材料或元件對照專利之功效。
本研究完成太陽能集熱器本體論之建構，並且在專利分析管理層面完成專利總表、生命週期分析、國家別、公司別、美國專利分類號分析，在技術層面針對不同之技術與應用完成之技術功效矩陣。由本研究將本體論與資料探勘對分析專利有別以往單純專利統計分析方法有更深入且更嚴謹之分析，以利提供產業可利用之專利資訊以及趨勢分析以利產業蓬勃發展。

According to the World Intellectual Property Organization (WIPO), efficient use of patent information not only results in 90% to 95% of research and developmental (R&D) results, but also can save 40% R&D costs. Compared to other technical literature containing only 5% to 10% of R&D results, patents are of vital importance.
This study introduces a novel approach in classifying patents instead of using conventional methods, such as International Patent Classification (IPC). We first retrieved patents established during the past ten years on solar collectors. Then, keyword analyses and numerations of frequently appeared keywords were performed to construct the ontology for solar collectors and to provide subsequent retrieval of patent data. Subsequently, we analyzed patents of various technologies and applications, along with each patent life cycle. Moreover, using key patent which combines data mining method, K-means are performed for dividing key patents into five technological clusters. These five clusters are then used to produce a technology-function matrix, which can show patent density in each technology-function node and give a good guidance for technical development.
This study lastly completed the ontology for solar collectors. Different management levels of patent analyses, including the patent summary table, patent life cycle analyses, categorization by country and company, and by United States Patent Classification (UPC), were examined. Also, the patent analysis in technical level such as technology-function matrix, with respect to different technologies and applications, was constructed. This study, combining ontology analysis and data mining, is more in-depth and rigorous when compared to the conventional method in patent analysis. This approach offers the solar industry usable patent analysis and technology trend analysis.

摘要I
ABSTRACTII
誌謝辭IV
目錄V
圖目錄VII
表目錄IX
第1章緒論1
1.1 研究背景1
1.2 文獻回顧2
1.3 研究動機與目的4
1.4 研究方法與進行步驟7
1.5 論文架構10
第2章太陽能之產業與專利分析11
2.1 太陽能產業發展11
2.1.1 太陽能集熱器吸熱原理12
2.1.2 全球太陽熱能之市場規模13
2.1.3 我國太陽能產業趨勢14
2.2 專利技術分析與佈局之理論16
2.2.1 相關的專利檢索策略20
2.2.2 專利分析與佈局方法21
第3章資料探勘之技術26
3.1 資料探勘介紹26
3.1.1 資料探勘的方式28
3.1.2 專利分類29
3.2 本體論35
3.3 資料探勘演算法36
第4章太陽能集熱器專利分析結果41
4.1 本體論建構41
4.1.1文件詞彙解析43
4.2 太陽能集熱器之專利地圖46
4.2.1 太陽能集熱器之發展趨勢47
4.2.2 太陽能集熱器之專利佈局57
4.2.3 太陽能集熱器之專利檢索65
4.3 探勘前資料處理67
4.3.1 探勘過程與結果69
第5章結論與未來展望88
5.1 結論88
5.2未來展望90
參考文獻91

[1]經濟部能源局，中華民國一百零一年能源統計手冊，台北，2012。
[2]S. C. Morris, D. Yong, Z. Wu, S. Salman, and D. Yemenu, “DIVA: a Visualization System for Exploring Document Databases for Technology Forecasting,” Computer & Industrial Engineering, Vol. 43, pp. 841-862, 2002.
[3]C. H. Lee, “A Study of Applying Data Mining Classification Techniques to Patent Analysis,” Chung Yuan Christian University, Master thesis, 2002.
[4]C. C. Kao, “A Study of Combining Automatic Document Classification-Example on Patent Document,” Chung Yuan Christian University, Master thesis, 2004.
[5]C. W. Wang, “Times Series Visualization of Patents,” National Chiao Tung University, Master thesis, 2005.
[6]M. L. Hsu, “A Study of Mining the Change of Patent Trend,” National Chiao Tung University, Master thesis, 2005.
[7]L. C. Lin, “Automatic Classification of Patent Documents,” National Chiao Tung University, Master thesis, 2005.
[8]K. Borner, E. Hardy, B. Herr, T. Holloway, and W. B. Paley, “Taxonomy Visualization in Support of the Semi-automatic Validation and Optimization of Organizational Schemas,” Journal of Informetrics, Vol. 1, pp. 214–225, 2007.
[9]A. Mogoutova, A. Cambrosio, P. Keatingc, and P. Mustar, “Biomedical Innovation at the Laboratory, Clinical and Commercial Interface: A New Method for Mapping Research Projects, Publications and Patents in the Field of Microarrays,” Journal of Informetrics, Vol. 44, pp. 341–353, 2008.
[10]W. W. Yi, S. Yong, S. K. Zhang, Y. F. Wu, and Z. H. Chu, “The Application and Research of Ontology Construction Technology,” First International Workshop on Knowledge Discovery and Data Mining, pp. 618 – 623, 2008.
[11]T. Nielsen, C. Cruickshank, S. Foged, J. Thorsenc, and F. Krebsa, “Business, Market and Intellectual Property Analysis of Polymer Solar Cells,” Solar Energy Materials and Solar Cells, Vol. 94, pp. 1553–1571, 2010.
[12]莊雯菱，運用專利共詞分析探討太陽能電池之發展趨勢，國立台灣科技大學，科技管理研究所碩士班，碩士學位論文，2010。
[13]F. M. Tseng, C. H. Hsieh, Y. N. Peng, and Y. W. Chu, “Using Patent Data to Analyze Trends and the Technological Strategies of the Amorphous Silicon Thin-Film Solar Cell Industry,” Technological Forecasting & Social Change, Vol. 2, pp. 332–345, 2011.
[14]C. V. Trappey, H. Y. Wu, F. Taghaboni-Dutta, and J. C. Trappey, “Using Patent Data for Technology Forecasting: China RFID Patent Analysis,” Advanced Engineering Informatics, Vol. 1, pp. 53–64, 2011.
[15]W. M. Wang, C. F. Cheung, “A Semantic-based Intellectual Property Management System (SIPMS) for Supporting Patent Analysis,” Engineering Applications of Artificial Intelligence, Vol. 24, pp. 1510–1520, 2011.
[16]L. Gao, L. J. Wang, S. F. Xian, Z. T. Mae, W. P. Wang, and H. Lu, “Technology Life Cycle Analysis Method Based on Patent Documents,” Technological Forecasting and Social Change, Vol. 80, pp. 398–407, 2013.
[17]陳明君，台灣熱水器產業競爭分析，工業技術研究院產業經濟與趨勢研究中心，台北，2013。
[18]社團法人中華替代能源協會，台灣綠能新願景，台北，2012
[19]經濟部能源局，2012年能源產業技術白皮書，台北，2012。
[20]羅運俊、何梓年、王長貴，太陽能發電技術與應用，新文京出版社，台北，2007。
[21]趙佳飛，駱仲泱，蔡潔聰，王輝，倪明江，太陽能電熱聯產技術研究綜述，中國電機工程學報，第29卷，第17期，浙江省，中國，2009。
[22]陳明君，被遺忘的能量來源-太陽熱能，工業技術研究院產業經濟與趨勢研究中心，新竹，2012。
[23]陳明君，太陽能熱水器領導廠商策略及技術趨勢分析，工業技術研究院產業經濟與趨勢研究中心，新竹，頁1-4，2008。
[24]陳明君，台灣太陽能熱水器產業競爭力分析，工業技術研究院產業經濟與趨勢研究中心，新竹，頁6，2010。
[25]Global Market Outlook for Photovoltaic until 2015：European Photo Voltaic Industry Association (EPIA), 2010.
[26]World Intellectual Property Organization, Importance of using patent information.
http://www.wipo.int/edocs/mdocs/sme/en/wipo_wasme_ipr_ge_03wipo_wasme_ipr_ge_03_5-main1.pdf 上網日期2014/01/02。
[27]H. Ernst, “Patent Portfolios for Strategic R&D Planning,” Journal of Engineering and Technology Management, Vol. 15, pp. 279-308, 1998.
[28]陳達仁、黃慕萱，專利資訊檢索分析與策略，華泰文化事業股份有限公司，台北，頁266，2009。
[29]魯明德，解析專利資訊，全華圖書股份有限公司，台北，頁374，2010。
[30]黃慕萱，資訊檢索，台灣學生書局，台北，頁209，1996。
[31]劉尚志，中小企業專利管理的策略與方法，產業科技研究發展管理研討會論文集，台北，頁20-25，1998。
[32]賴榮哲，專利分析總論，翰蘆圖書出版社，台北，頁426，2002。
[33]廖述賢、溫志浩，資料探勘理論與應用 : 以IBM SPSS Modeler為範例 = Data Mining Theories and Applications : in Case of IBM Spss Modeler，博碩文化，台北，頁30-50，2012。
[34]World Intellectual Property Organization, “International Patent Classification Guide” Eighth Edition, 2006.
[35]R. Studer, V. R. Benjamins and D. Fensel, “ Knowledge Engineering: Principles and Methods,” Data and Knowledge Engineering, Vol. 1, pp. 161-197, 1998.
[36]S. William, and T. Austin, "Ontologies," IEEE Intelligent Systems Vol. 14, pp. 18-19, 1999.
[37]N. Guarino, “Formal Ontology and Information Systems,” Formal Ontology in Information Systems. Proc. of the 1st International Conference, pp. 3-15, 1998.
[38]Microsoft, http://msdn.microsoft.com/zh-tw/library/ms175595. aspx,
Microsoft developer network, 2013. 上網日期2013/10/02。
[39]J. B. M. Queen, “Some Methods for Classification and Analysis of Multivariate Observations,” Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, Vol. 1, pp. 281-297, 1967.
[40]陳鍾誠，http://ccckmit.wikidot.com/ai:kmeans，陳鍾誠的網站，2010。.
[41] R. N. Foster, “Working the S-Curve: Assessing Technological Threats,” Research Management, Vol. 29, No.4, pp.17-20. 1986.
[42]H. Ernst, “The Use of Patent Data for Technological Forecasting- The Diffusion of CNC-Technology in the Machine Tool Industry,” Small Business Economics, Vol. 9, pp. 361-381. 1997.