本文針對質子交換膜燃料電池台灣及中國大陸之中文專利資料進行分析，應用專利知識盤點及中文語意分析之概念，建立中文專利技術及功能分類模式。本文所建立之中文專利分析方法，其步驟為先研讀部分主要中文專利、工程知識及技術報告，以階層式架構之專利知識盤點概念，建立質子交換膜燃料電池之初步的物料料表及其技術領域。再以本文所建立之中文專利語意分析斷詞系統，萃取中文專利之技術與功能詞彙以及零組件關鍵詞，再計算各零組件關鍵詞出現之次數。本文並提出將所得各零組件關鍵詞次數常態化概念，將分析所得到之零組件關鍵詞出現次數值除以該篇的總字數，使各零組件關鍵詞之常態化後的數值不因其篇數長短，而影響字群統計結果。再配合同義字之概念，以及所萃取出的中文專利之技術及功能詞彙，進而分析歸納中文專利之第二層技術及功能，並建立立體型之技術/功能矩陣架構，透果此立體型之技術/功能矩陣的建立，建構出中文專利技術功能分類模式，並修正初步之物料料表及其技術領域架構，其結果可做為中文專利技術功能分類之重要參考資訊，可讓研究人員達到較快速取得相關技術的專利資料進而縮短研發的時間。
最後，本文針對質子交換膜燃料電池之中文專利資料，進行專利分析建置相關之技術專利地圖，其包括件數、國家別、技術發展趨勢、竸爭者核心分佈、及IPC國際專利分類碼等較詳細之專利分析，以期瞭解質子交換膜燃料電池業有關中文專利技術發展現況與未來可能研發方向。

Abstract
The paper analyzes the Chinese patent information of proton exchange membrane fuel cell (PEMFC) in Taiwan and Mainland China, and applies the concepts of patent knowledge audit and Chinese semantic analysis to establish a Chinese patent technical and functional classification model. Regarding the Chinese patent analysis method established by the paper, the first step is to read part of the reports on the main Chinese patents, engineering knowledge and techniques, and use the patent knowledge audit concept of hierarchal structure to establish a preliminary material list of PEMFC and its technical area. After that, the paper uses the work-breaking system of the Chinese patent semantic analysis developed by the paper to extract the technical and functional vocabularies of the Chinese patents as well as the keywords of the parts, and then calculates the appearance frequency of the keywords of each part. The paper also proposes the concept of normalizing the acquired appearance frequency of the keywords of each part. The numerical value of the obtained appearance frequency of the keywords of each part is divided by the total number of words of the essay. As a result, the normalized numerical value of the keywords of each part will not have its word group statistical results affected by the number and length of essays. Aligned with the concept of synonym and the extracted technical and functional vocabularies of the Chinese patents, the paper further analyzes and summarizes the techniques and functions of the Chinese patents on the second hierarchy, and establishes a three-dimensional technical/functional matrix structure. Through the establishment of such three-dimensional technical/functional matrix, the paper constructs a technical and functional classification model of the Chinese patents, and revises the preliminary material list and the structure of its technical area. The results can be the important referential information for the technical and functional classification of the Chinese patents, allowing researchers to acquire the patent information of the related techniques more rapidly, and further shorten the time of research and development (R&D).
Finally, focusing on the Chinese patent information of PEMFC, the paper performs patent analysis and establishes the related technical patent maps, which include the more detailed patent analysis, such as the number of patents and their nationalities, trend of technical development, core distribution of competitors, international patent classification (IPC) codes, and so on. It is hoped that we can know the current development of the Chinese patent techniques of PEMFC, and the possible R&D directions in future.

[1].Nic, J. Y. and M. Briscobois, “On Chinese Text Retrieval”, Proceeding of SIGIR, pp.225-233 (1996)
[2].黃大一，中文詞碼，長松文化事業有限公司，民 79年。
[3].王良志、貝子勝、黎偉權、黃麗卿，「以剖析為導向的中文斷詞法」，電子發展月刊，163期，第40-45頁，民80年。
[4].范長康、蔡文祥，「以鬆弛法作中文斷詞」，全國計算機會議論，第 423-431頁，淡江大學 民 76年。
[5].陳克建、陳正佳、林隆基，「中文語句分析的研究-斷詞與構詞」，中央研究院資訊所技術報告，TR86-004，民75年。
[6].Chen, K. J. And S. H. Liu, “Word Identification for Mandarin Chinese Sentences” , Proceeding of COLING-92, 14th Int. Conf. On Computational Linguistics, pp.101-107 (1992)
[7].Fan, C. K. and W. H. Tsai, “Automatic Word Identification in Chinese Sentences by the Relaxation Technique” , Computer Processing of Chinese and Oriental Languages, Vol.2, No.4, pp.33-56 (1988)
[8].Gan, K. W., M. Palmer and K. T. Lua, “A Statistically Emergent approachfor language Processing : Application to Modeling ContextEffectsinAmbiguousChinese Word Boundary Perception” , Computational Linguistics, pp.531-553 (1996)
[9].Leung, C. H. and W. K. Kan, “A Statistical Learning Approach to Improving the Accuracy of Chinese Word Segmentation” , Literary and Linguistic Computing, pp.87-92, (1996)
[10].Nie, J. Y., M. L. Hannan and W. Jin, “Combining Dictionary, Rules and Statistical Information in Segmentation of Chinese” , Computer Processing of Chinese and Oriental Languages , Vol.9, pp.125-143, (1995)
[11].Sporat, R. and C. Shih, “A Statistical Method for Finding Word Boundaries in ChineseText” , Computer Processing of Chinese and Oriental Languages , Vol.4, No.4, pp.336-351 (1990)
[12].Sporat, R. and N.Chang, “A Stochastic Finite-State Word- Segmentation AlgorithmforChines” , Computational Linguistics , Vol.22, pp.377-404 (1996)
[13].Wu,Z. and G.Tseng, “ACTS: An Automatic Chinese Text Segmentation System for Full Text Retrieval” , Journal of the American Society for Information Science , Vol.46, pp.83-96 (1995)
[14].Yeh, C. L.and H. J. Lee, “Rule-Based Word Identification for MandarinChineseSentences-AUnificationApproach” , Computer Processing of Chinese and Oriental Languages ,Vol.5, No.2, pp.97-118 (1991)
[15].中央研究院斷詞表http://rocling.iis.sinica.edu.tw/CKIP/onlinesystem.htm#t2
[16].中央研究院線上展示系統http://ckipsvr.iis.sinica.edu.tw/
[17].Gruber, T., “Ontolingua: A translation approach to portable ontology specifications” , Knowledge Acquisition, pp.199-200,(1993)
[18].Oleary, D. E, “Enterprise knowledge management” ,Computer IEEE, Vol.31, pp.54-61 (1998)
[19].Singhal, A. and G. Salton, “Automatic Text Browsing Using Vector Space Model ” , Technical Report, Department of Computer Science , Cornell University, (1993)
[20].Lawrence, S. and C. L.Giles, “Searching the World Wilde Web: General and Scientific InformationAccess ” , IEEE Communication, Vol.37, pp.116-122 (1999)
[21].Singhal, A. and G. Salton, “Automatic Text Browsing Using VectorSpace Model ” ,TechnicalReport,Departmentof Computer Science, Cornell University, (1993)
[22].Han, E. H, D. Boley, M. Gini, R. Gross, K. Hastings, G. Karypis, V. Kumar, B. Mobasher and J. Moore, “WebACE: A Web Agent forDocument Categorization and Exploration ” , In Proceedings of International Conference on Autonomous Agent, pp.408-415, (1998)
[23].Belkin, N. J. and W. B. Croft, “Information Filtering and Information Retrieval : Two sides of the Same Coin” ,Communication of the ACM , 35(12), pp.29-38 (1992)
[24].Grossman, D.A.and O. Frieder, “Information Retrieval: AlgorithmsandHeuristics ”, Kluwer Academic Publishers, (1998)
[25].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83年。
[26].林聖富，「專利資訊和專利檢索」，智慧財產權管理季刊，民75年。
[27].陳瑞田，創新性之專利迴避設計，機械工業雜誌，民87年，2月號。
[28].許耀華，「專利分類系統及其應用」，智慧財產局，民93年，11月。
[29].「國際專利分類表第七版使用指南」，經濟部智慧財產局，民90年，7月。
[30].「國際專利分類之研究」，經濟部中央標準局。
[31].Overview of the Classification System, http://www.uspto.gov/main/patents.htm
[32].International patent Classification Eight Edition Guide, http://www.wipo.int/classifications/ipc/en/other/guide/guide_ipc8.pdf
[33].The EPO guide to patent information on the internet, http://epart.epo.org/dwl/espacenet_manual.pdf
[34].Guide Book for Practical Use of Patent Map for Each Technology Field, Japan Patent Office Asia-Pacific Industrial Property Center, JIII(2000)
[35].車慧中，「IP管理關鍵考量-電子機械案例解析與全程輔導」，冠亞智財股份有限公司(2005)。
[36].陳振源，「未來的綠色能源－燃料電池」，科學發展，第391期，第62-65頁(2005)。
[37].林彥均，奈米複合觸媒於質子交換型燃料電池之應用，國立中央大學，化學研究所，第01-05頁，民95年。
[38].衣寶蓮，「燃料電池－原理與應用」，五南出版(2007)。
[39].石井弘毅，「圖解燃料電池」，世茂出版有限公司(2008)。
[40].衣寶廉，「燃料電池-高效、環保的發電方式」，五南出版(2003)。
[41].楊志忠、林頌恩、韋文誠，「燃料電池的發展現況」，科學發展，第367期，第30-33頁(2003)。
[42].台灣燃料電池資訊網http://www.tfci.org.tw/Fc/index.asp
[43].陳建安、莊文瑞，「燃料電池裝置」，中華民國新型專利，M304119(2005)。
[44].楊源生、楊德洲，「燃料電池組之氣體通道防漏結構」，中華民國新型專利，00553497(2003)。
[45].徐耀昇，「燃料電池加濕模組之瞬間啟動及調溫裝置」，中華民國發明專利，I234309(2005)。