本研究提出修正式FUZZY DEMATEL方法，其主要為收集LED自行車車燈之相關技術領域中針對一技術領域與另一技術領域間重複定義或定義相同的專利技術字所佔之常態化數值比例，依所計算的常態化數值比例值進而應用三角形歸屬函數之模糊理論公式及α-cut的觀念評估各技術領域間的相互影響程度0~4之值，以取代傳統的專家問卷方式。接著再依照修正式DEMATEL運算步驟求出總關係影響矩陣、直接/間接關係圖及(D+R)值與(D-R)值之因果圖。此(D+R)值與(D-R)值之因果圖可協助判斷LED自行車車燈之各技術領域間的相互受影響程度。本研究提出創新之修正式FUZZY DEMATEL方法，應用在以LED自行車車燈為載具，收集相關專利，利用斷詞斷字系統計算各相關專利之關鍵技術字、零組件元件字及功能字之常態化數值，分析歸納各第一層技術類別之技術字及零組件元件字字群，定義其第一層技術類別之第二層技術類別及功能類別，進而建立技術/功能矩陣。再依前述之FUZZY DEMATEL方法計算，最後得到各技術領域的因果圖來判斷LED自行車車燈之本研究亦進行LED自行車車燈專利生命跨距及LED自行車車燈專利之技術生命週期分析，並進行DEMATEL因果圖、技術活動力趨勢表、專利生命跨距與專利技術生命週期之合併分析。
接著以LED投射燈為載具，計算LED投射燈之相關技術領域中針對一技術領域與另一技術領域間重複定義或定義相同的專利技術字占之常態化數值比例，及應用三角形歸屬函數之模糊理論公式依照修正式DEMATEL以及修正式FUZZY DEMATEL方法得到評估各技術領域間的相互影相程度0~4之值，進而計算得到總關係影響矩陣、直接/間接關係圖及(D+R)值與(D-R)值之因果圖。判斷LED投射燈之各技術領域間的相互受影響程度。此外亦進行LED投射燈之專利生命跨距及專利技術生命週期分析。本研究亦應用結合改良式餘弦相似度及機率方法進行LED投射燈之新投入專利之專利歸屬判別，先以改良式餘弦相似度做篩選再以機率方法計算出專利可能歸屬之技術或功能類別。最後提出藉由合併分析DEMATEL因果圖、技術活動力趨勢表、專利生命跨距與技術生命週期之分析方法，探討LED投射燈技術領域相關專利發展空間。本研究亦進行IPC分析、發明人分析、各公司核心競爭力及技術活動力趨勢分析，上述分析之結果可提供給企業及工程師，作為新專利產生之參考。此外亦可使企業了解競爭者之核心競爭力。

The study develops a modified fuzzy DEMATEL method, which mainly finds the ratio of normalized numerical values of the collected patent technical words having repeated definitions or the same definition between a technical category and another technical category in the related technical category of LED bicycle light. According to the calculated ratio of the normalized numerical values, the study applies fuzzy theoretical equation of triangular membership function and the concept of α-cut to evaluate the value of the extent of mutual influence 0~4 among various technical categories so as to replace the conventional way of professional questionnaire survey. After that, following the computing steps of the modified DEMATEL, the study establishes the general relational influence matrix, the direct/indirect relationship diagram, and the causal diagram between (D+R) value and (D-R) value. This causal diagram between (D+R) value and (D-R) value can help judge the mutual influence among various technical categories of LED bicycle light. The study proposes an innovative modified fuzzy DEMATEL method for application to the carrier of LED bicycle light, collects the related patents, and uses term and word segmentation system to calculate the normalized numerical values of key technical words, part/component words and functional words in the related patents. The study analyzes and categorizes the technical words and part/component word clusters in each first-layer technical category, defines the second-layer technical category and functional category of the first-layer technical category, and further establishes a technical/functional matrix. Subsequently, calculation is made according to the abovementioned fuzzy DEMATEL method. Finally, based on the acquired causal diagram of various technical categories, the study judges the mutual influence among various technical categories of LED bicycle light. The study also analyzes the life span and life cycle of LED bicycle light patents, and makes a consolidated analysis of DEMATEL causal diagram, activity trend chart of techiques, life span of patents and technological life cycle of patents.
After that, with LED projection light as the carrier, the paper calculates the ratio of normalized numerical values of the patent technical words having repeated definitions or the same definition between a technical category and another technical category in the related technical category of LED projection light. The paper also applies the fuzzy theoretical equation of triangular membership function, and employs the modified DEMATEL method and the modified fuzzy DEMATEL method to achieve the evaluated the value od extent mutual influence 0~4 among various technical categories. Furthermore, after calculation, the paper obtains the general relational influence matrix, the direct/indirect relationship diagram, and the causal diagram between (D+R) value and (D-R) value, so as to judge the mutual influence among various technical categories of LED projection light. Besides, the paper also analyzes the life span and technological life cycle of LED projection light patents. What’s more, applying combination of improved cosine similarity and probability method, the study carries out judgment of patent categorization of the newly added LED projection light patents. First of all, improved cosine similarity is adopted for screening. Then, probability method is used to calculate the technical or functional category that a patent may belong to. Finally, it is proposed that through consolidated analysis of DEMATEL causal diagram, activity trend chart of techniques, life span of patents and technological life cycle of patents, the space for development of the patents relating to technical categories of LED projection light can be explored. The study also conducts analysis of International Patent Classification (IPC), analysis of inventors, and analysis of the core competitiveness and activity trend chart of techniques of different companies. The above analytic results can be provided as a reference for enterprises and engineers in development of new patents. In addition, enterprises are also able to know the core competitiveness of their competitors.

【1】 「國際專利分類表第七版使用指南」，經濟部智慧財產局，民國九十年。
【2】 「國際專利分類之研究」，經濟部中央標準局。
【3】 Overview of the Classification System, http://www.uspto.gov/main/patents.htm
美國專利商標(USPTO)。
【4】 The EPO Guide to Patent Information on the Internet,
http://epart.epo.org/dwl/espacenet_manual.pdf
歐洲專利組織(EPO)。
【5】 Trappey, C.V., Trappey, A.J.C., and Wu, C.Y., “Clustering Patents Using Non.exhaustive Overlaps”, Journal of Systems Science and Systems Engineering, Vol.19, No.2, pp.162-181 (2010).
【6】 Trappey, C.V., Trappey, A.J.C., and Wu, C.Y., “Automatic Patent Document Summarization for Collaborative Knowledge Systems and Services”, Journal of Systems Science and Systems Engineering, Vol.18, No.1, pp.71-94 (2009).
【7】 Singhal, A. and Salton, G., “Automatic Text Browsing Using Vector Space Model”, Technical Report, Department of Computer Science, Cornell University (1993).
【8】 Lawrence, S. and Giles, C.L., “Searching the Web: General and Scientific Information Access”, IEEE Communication, Vol.37, pp.116-122 (1999).
【9】 陳哲宏、陳逸南、謝銘洋、徐宏昇，「專利法解讀」，月旦出版公司，第14.15頁，民國八十三年。
【10】 Gruber, T., “A Translation Approach to Portable Ontology Specifications”, Knowledge Acquisition, Vol.5, pp.199-200 (1993).
【11】 O’Leary, D.E., “Enterprise Knowledge Management”, IEEE Computer, Vol.31, pp.54-61 (1998).
【12】 杜家宏，「整合繁體和簡體中文及英文斷詞斷字系統之發光二極體檯燈專利分析研究」，碩士論文，國立台灣科技大學機械工程學系，台北，民國一百年。
【13】 吳俞灃，「LED水族燈之相關專利分析研究」，碩士論文，國立台灣科技大學機械工程學系，台北，民國一百零一年。
【14】 Salton, G. and McGill, M., “Introduction to Modern Information Retrieval”, McGraw.Hill, New York (1983).
【15】 Vallet, D., Fernández, M. and Castells, P., “An Adaptation of the Vector.Space Model for Ontology.Based Information Retrieval”, IEEE Knowledge and Data Engineering, Vol.19, No.2, pp.261-272 (2005).
【16】 Wang, S., Sun, J., Gao, B.J. and Ma, J., “Adapting Vector Space Model to Ranking.based Collaborative Filtering”, CIKM 12 Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp.1487-1491, New York, USA (2012).
【17】 Gan, J. and Chen, L.C., “Research of Improved IF.IDF Weighting Algorithm”, International Conference on Information Science and Engineering (ICISE), pp.2304-2307, Hangzhou, China (2010).
【18】 Zhang, G.H. and Odbal, “Sentence Alignment For Web Page Text Based on Vector Space Model”, International Conference on Computer Science and Information Processing (CSIP), pp.167-170, Shaanxi, China (2012).
【19】 Trappey, C.V., Wang, T.M., Hoang, S. and Trappey, A.J.C., “Constructing a Dental Implant Ontology for Domain Specific Clustering and Life Span Analysis,” Advanced Engineering Informatics, Vol.27, pp.346-357 (2013).
【20】 Bermudez.Edo, M., Noguera, M., Hurtado.Torres, N., Hurtado, M.V. and Garrido, J.L., “Analyzing a Firm’s International Portfolio of Technological Knowledge: A Declarative Ontology-based OWL Approach for Patent Documents”, Advanced Engineering Informatics , Vol.27, pp.358-365 (2013).
【21】 Trappey, C.V., Trappey, A.J.C., Peng, H.Y., Lin, L.D. and Wang, T.M., “A Knowledge Centric Methodology for Dental Implant Technology Assessment Using Ontology Based Patent Analysis and Clinical Meta-analysis,” Advanced Engineering Informatics, Vol.28, pp.153-165 (2014).
【22】 Tzeng, G. H., Chiang, C. H., and Li, C. W., “Evaluating Intertwined Effects Ine-learning Programs: A Novel Hybrid MCDM Model Based on FactorAnalysis and DEMATEL,” Expert Systems with Applications, Vol.32, No4, pp.1028-1044 (2007).
【23】 Lin, Chi-Jen and Wu, Wei-Wen, “A Fuzzy Extension of the DEMATEL Method for Group Decision Making”, 第一屆作業研究學會學術研討會論文集，台北科技大學，台灣 (2004).
【24】 Snezˇana Tadic´, Slobodan Zecˇevic´, and Mladen Krstic´“A Novel Hybrid MCDM Model Based on Fuzzy DEMATEL, Fuzzy ANP”, Expert Systems with Applications, Vol.41, pp.8112-8128 (2014).
【25】 LED Inside of TRENDFORCE Corp., http://www.ledinside.com.tw/knowledge/20120801.22324.html
【26】 林武憲，「LED整合中英文斷詞斷字系統之專利分析」，碩士論文，國立台灣科技大學機械工程學系，台北，民國九十九年。
【27】 McGlen, R.J., Jachuck, R., and Lin, S., “Integrated Thermal Management Techniques for High Power Electronic Devices”, Applied Thermal Engineering, Vol.24, Issue 8-9, pp.1143-1156 (2004).
【28】 洪國恩，「結合修正式DEMATEL與改良式餘弦相似度及專利類別歸屬之機率方法進行LED自行車車燈相關專利分析研究」，碩士論文，國立台灣科技大學機械工程學系，台北，民國一百零四年。
【29】 Ernst, H., “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).
【30】 Meyer, Perrin S., Yung, Jason W., and Ausubel, Jesse H., “A Primer on Logistic Growth and Substitution: The Mathematics of the Loglet Lab Software“, Technological Forecasting and Social Change, Vol.61, pp.247-271 (1999).
【31】 Trappey, C.V., Wu, H.Y., Taghaboni-Dutta, Fataneh, and Trappey, A.J.C, “Using Patent Data for Technology Forecasting: China RFID Patent Analysis.”, Advanced Engineering Informatics, Vol.25, pp.53-64 (2011).