專利對於企業或個人來說，都是一項相當重要的智慧資產，它不但可以作為保護發明與想法的手段，甚至可以帶來相關的經濟收益，因此，該如何去偵測專利侵權以避免造成相關法律訴訟，也變成企業的一項重要工作。專利前案搜尋其主要之目的是找尋與目標專利申請相關之前案，進而能夠避免去侵犯他人專利宣告降低專利侵權的可能性，而專利前案搜尋系統即是透過系統的處理，能夠得到快速且準確的得到與該目標專利最為相關之前案，這部分已有許多文獻已證實其可能性，而基於利用專利宣告結構來進行前案搜尋之相關研究的成果，此論文透過利用雲端運算及關鍵字語意擴充搜尋的方式，成功達成了對於時間效率及準確度的改進。
除此之外，研究的主要貢獻不僅是對於專利前案搜尋系統的效率及準確度的改善，更重要的是在實際應用方面，提升讓專利分析師能夠利用此系統對於新專利的搜尋，能夠快速過濾掉不相關的大筆專利資料，以提升其在實務界應用的可能性。

Patent is one of the most valuable intelligent properties. It not only protects inventions and ideas but also is an economic source of enterprises. Since that, it is important for enterprises to detect patent infringement to avoid any legal and economic risks. Patent prior art search task is mainly to identify prior patents that are relevant to a patent application. Thus, a system for retrieving patent prior art is expected to obtain the set of patents which are the most relevant to a target patent. Beyond the existing achievements including patent claim structure in prior retrieval, this research enhances the time efficiency and accuracy of the patient prior retrieval task by using cloud computing and semantic term expansion.
The major contribute of this research is to enhance the prior art retrieval system in terms of time efficiency and accuracy, by which enterprises or patent analyzers are operationally viable to identify the most relevant prior patents in filing or approving a new patent

Chapter 1 Introduction 1
1.1 Research Background 1
1.2 Research Motivation 1
1.3 Research Objective 3
Chapter 2 Literature Review 4
2.1 Claim Tree Stricture 4
2.1.1 Claim Tree Format and Similarity Comparison 4
2.1.2 Hybrid Approach Using Claim Structure and Claim-Related Description 5
2.2 Keyword Expansion 6
2.3 Screening Threshold 7
Chapter 3 System Architecture 8
3.1 Pre-processing 9
3.1.1 Text Segmentation 9
3.1.2 Stop Words Removal 9
3.1.3 Word Stemming 9
3.2 Tree Structure Formation 10
3.2.1 Preamble and Components Extracted 10
3.2.2 Dependent Claims Noun Phrase Extracted 10
3.2.3 Tree Structure Formation 11
3.3 Candidate Patent Selection 11
3.3.1 Pure Text Comparison 11
3.4 Prior Art Identification 11
3.4.1 Tree Structure Comparison 11
3.4.2 Claim Related Description 13
3.4.3 Keyword Expansion 13
3.4.4 Claim Related Description with Keyword Expansion 14
Chapter 4 System Implementation and Experimental Design 15
4.1 Data Source 15
4.2 Cloud Computing 15
4.3 Experimental Design 16
4.3.1 Experiment A - Screening Threshold Experiment 17
4.3.2 Experiment B - Claim Tree Structure with Claim Related Description 18
4.3.3 Experiment C - Claim Tree Structure with Keyword Expansion 18
4.3.4 Experiment D - Claim Tree Structure with Claim Related Description and Keyword Expansion 18
Chapter 5 Experimental Results and Discussion 19
5.1 Experiment A - Screening Threshold Analysis 20
5.2 Experiment B - Claim Tree Structure with Claim Related Description 22
5.3 Experiment C - Claim Tree Structure with Keyword Expansion 25
5.4 Experiment D - Claim Tree Structure with Claim Related Description and Keyword Expansion 28
Chapter 6 Conclusion and Limitation 35
References 37
Appendix 40

Azzopardi, Leif, Vanderbauwhede, Wim, & Joho, Hideo. (2010). Search system requirements of patent analysts. Paper presented at the Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval.
Bashir, Shariq, & Rauber, Andreas. (2010). Improving retrievability of patents in prior-art search Advances in Information Retrieval (pp. 457-470): Springer.
Bergmann, Isumo, Butzke, Daniel, Walter, Lothar, Fuerste, Jens P, Moehrle, Martin G, & Erdmann, Volker A. (2008). Evaluating the risk of patent infringement by means of semantic patent analysis: the case of DNA chips. R&d Management, 38(5), 550-562.
Bizer, Christian, Lehmann, Jens, Kobilarov, Georgi, Auer, Sören, Becker, Christian, Cyganiak, Richard, & Hellmann, Sebastian. (2009). DBpedia-A crystallization point for the Web of Data. Web Semantics: Science, Services and Agents on the World Wide Web, 7(3), 154-165.
Daim, Tugrul U, Rueda, Guillermo, Martin, Hilary, & Gerdsri, Pisek. (2006). Forecasting emerging technologies: Use of bibliometrics and patent analysis. Technological Forecasting and Social Change, 73(8), 981-1012.
Fabry, Bernd, Ernst, Holger, Langholz, Jens, & Köster, Martin. (2006). Patent portfolio analysis as a useful tool for identifying R&D and business opportunities—an empirical application in the nutrition and health industry. World Patent Information, 28(3), 215-225.
Fluck, Juliane, Zimmermann, Marc, Kurapkat, Günther, & Hofmann, Martin. (2005). Information extraction technologies for the life science industry. Drug Discovery Today: Technologies, 2(3), 217-224.
Fujii, Atsushi. (2007). Enhancing patent retrieval by citation analysis. Paper presented at the Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, Amsterdam, The Netherlands.
Hufker, Tim, & Alpert, Frank. (1994). Patents: a managerial perspective. Journal of Product & Brand Management, 3(4), 44-54.
Itoh, Hideo, Mano, Hiroko, & Ogawa, Yasushi. (2003). Term distillation in patent retrieval. Paper presented at the Proceedings of the ACL-2003 workshop on Patent corpus processing-Volume 20.
Kang, I. S., Na, S. H., Kim, J., & Lee, J. H. (2007). Cluster-based patent retrieval. Information Processing & Management, 43(5), 1173-1182.
Konishi, Kazuya. (2005). Query terms extraction from patent document for invalidity search. Paper presented at the Proc. of NTCIR.
Lanjouw, Jean O, & Schankerman, Mark. (2001). Characteristics of patent litigation: A window on competition. RAND journal of economics, 129-151.
Lin, Fu-ren, Chen, Ken-ren, & Lin, Szu-Yin. A Hybrid Patent Prior Art Retrieval Approach Using Claim Structure and Description. The 8th International Knowledge Management in Organizations Conference, Kaohsiung Taiwan, September 9~13, 2013.
Lin, F., & Huang, F. (2010). The Study of Patent Prior Art Retrieval Using Claim Structure and Link Analysis. Paper presented at the Proceedings of the 14rd Pacific Asia Conference on Information Systems (PACIS), Taipei, Taiwan.
Lin, Fu-ren, Lee, An-yun, & Cheng, Ching-Pin. (2013). Exploring Business Ecological Information with Personal Attention.
Magdy, Walid, & Jones, Gareth JF. (2010). PRES: a score metric for evaluating recall-oriented information retrieval applications. Paper presented at the Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval.
Magdy, Walid, Lopez, Patrice, & Jones, Gareth JF. (2011). Simple vs. sophisticated approaches for patent prior-art search Advances in Information Retrieval (pp. 725-728): Springer.
Pitkethly, Robert. (1997). The Valuation of Patents: A review of patent valuation methods with consideration of option based methods and the potential for further research. RESEARCH PAPERS IN MANAGEMENT STUDIES-UNIVERSITY OF CAMBRIDGE JUDGE INSTITUTE OF MANAGEMENT STUDIES.
Ratnaparkhi, A. (1999). Learning to parse natural language with maximum entropy models. Machine Learning, 34(1-3), 151-175.
Szarvas, Gyorgy, Herbert, Benjamin, & Gurevych, Iryna. (2009). Prior art search using international patent classification codes and all-claims-queries. Paper presented at the Proceedings of the 10th cross-language evaluation forum conference on Multilingual information access evaluation: text retrieval experiments, Corfu, Greece.
Takaki, Kazuya Konishi Akira Kitauchi Toru. (2004). Invalidity Patent Search System of NTT DATA.
Tseng, Yuen-Hsien, Lin, Chi-Jen, & Lin, Yu-I. (2007). Text mining techniques for patent analysis. Information Processing & Management, 43(5), 1216-1247.
Verberne, S., & D'hondt, E. (2010). Prior Art Retrieval Using the Claims Section as a Bag of Words. Multilingual Information Access Evaluation I: Text Retrieval Experiments, 6241.
Yoon, Byungun, & Park, Yongtae. (2004). A text-mining-based patent network: Analytical tool for high-technology trend. Journal of High Technology Management Research, 15(1), 37.
Yoon, Byungun, & Park, Yongtae. (2005). A systematic approach for identifying technology opportunities: Keyword-based morphology analysis. Technological Forecasting and Social Change, 72(2), 145-160.