檢索專利先前技術在專利審查中扮演非常重要的角色。如果專利審查官能快速且正確無誤地檢索出專利的先前技術，他就能有效率地判斷專利的新穎與否，而不會因為專利的氾濫導致技術發展的障礙。對公司而言，在研發之初進行專利先前技術的檢索可以避免因為侵權訴訟而導致的無形和有形資產損失。但是由於專利不但在數量上快速地成長，也越來越複雜。所以這此研究中我們提供另一種以專利申請範圍的結構為主的方式來協助更精準地檢索龐大的專利資料庫。
目前大部分專利檢索是單純利用關鍵字去搜尋和比對專利，但是這種方式往往會忽略專利發明本身的結構。故此研究利用專利申請範圍的敘述找出發明元件的架構，並用發明元件連線的關係來比對專利的相似程度。我們用發明元件的樹狀結構來解析專利申請範圍的內容，再從專利說明書中找出跟專利發明的元件有相關的文字作為文字的擴充。在最後作專利檢索比對時，我們用專利的發明元件結構相似程度作為篩選專利先前技術的門檻。在此研究中，我們希望透過專利結構相似度的比對來提升專利前案技術的檢索，大大降低專利檢索後人工篩選的負擔。

Prior art retrieval plays an important role in patent examination. If a patent examiner can retrieve prior art for an application patent quickly and accurately, he or she will be able to efficiently and effectively judge the novelty of an application patent, and in turn, avoid hampering the technology development of the application domain. Moreover, in order to avoid losing tangible and intangible assets caused by patent infringement, companies need to search patent prior art before doing development. However, the increasing number of patents is not seen only in quantity but also in complexity. Bewaring the emerging need of prior art retrieval form large patent database, the main objective of this project is to develop a methodology which can build the claim hierarchy automatically in order to facilitate the identification of relevant patent prior art.
Most existing patent retrieval tools use keywords to find relevant patents; however, they ignore the structure of the invention, which mentions in the claim of patent. Thus, this study parses the sentences of patent claim and finds the structure of the invention. Then, we compare the similarity of structure of invention and find the relevant patent. We first convert the claim sentence into the claim hierarchy to represent the structure of invention, and use specification of patent to expand the words in claim hierarchy. Finally, we calculate the similarity of invention structure and use the threshold to find the relevant patents. This claim hierarchy based search will reduce the cognitive load of prior art judgment by comparing similar invention structure between patents.

Barrish, D. and Smith, M. (2004). The challenge of searching prior art. Townsend and Townsend and Crew LLP.
Basu,A., and Blanning, R. W. (1994). Model integration using metagraphs. Information Systems Research 5(3) 195–218.
Basu,A., Blanning, R. W. (1996). A metagraph-based DSS analysis workbench. proceedings of the 29th annual Hawaii International Conference on System Sciences.
Berger, A. L., Della Pietra, Stephen A., and Della Pietra, Vincent J. (1996). A Maximum Entropy Approach to Natural Language Processing. Computational Linguistics 22: 39–71.
East, W.R.T. (1995). Patent claims- how to keep track of them. IEEE AES System Magazine. Volume: 10, Issue: 8.
Harhoff, D, Narin, F., Scherer, M.,Vopel, K. (1999). Citation frequency and the value of patented inventions. The Review of Economics and Statistics.
Hall,B.H., Jaffe, A., Trajtenberg, M. (1999). Market Value and Patent Citations: a first look, Collection Cahiers de l'Innovation, 99004, CNRS.
Inoue, N., Matsumoto, K., Hoashi, K., Hashimoto, K. (2000). Patent Retrieval System Using Document Filtering Techniques. Proceedings of the Workshop on Patent Retrieval, ACM SIGIR.
Kando, N. (2000). What Shall We Evaluate? -- Preliminary Discussion for the NTCIR
Patent IR Challenge (PIC) Based on the Brainstorming with the Specialized Intermediaries in Patent Searching and Patent Attorneys. NTCIR workshop.
Kazenske, R. (2003). The future of prior art searching at the United States patent and trademark office. WORLD PATENT INFORMATION
Larkey, L.S. (1999). A patent search and classification system. Proceedings of the fourth ACM conference on Digital libraries. pp. 179 – 187.
Lim, S.-S., Jung, S.-W., Kwon H.-C. (2004). Improving patent retrieval system using ontology. Industrial Electronics Society, 2004. IECON 2004. 30th Annual Conference of IEEE.
Loerch, U. An Introduction to Graph Algorithms. Retrieved January 8, 2007, from http://www.cs.auckland.ac.nz/~ute/220ft/graphalg/graphalg.html
Marcu, D. (1997). The rhetorical parsing, summarization, and generation of Natural language texts. Ph.D. thesis, Department of Computer Science, University of Toronto, December.
Mase, H., Matsubayashi, T., Ogawa, Y., Iwayama, M., Oshio, T. (2005). Proposal of two-stage patent retrieval method considering the claim structure. ACM Transactions on Asian Language Information Processing (TALIP), Volume 4 Issue 2.
Radev, D.R., Jing ,H., Styś, M., Tam, D.l. (2004). Centroid-based summarization of multiple documents. Information Processing and Management.
Santorini, B. Part-of speech Tagging Guidelines for Penn Treebank Project. Retrieved January 8, 2007, http://www.cis.upenn.edu/~treebank/.
Salton, G. & Buckley, C. (1998). Term-weighting approaches in automatic text retrieval. Information Processing & Management, 24 (5):513-523.
Scheu, E., Veefkind, V., Verbandt Y., Molina Galan, E., Absalom, R., Förster, W. (2006). Mapping nanotechnology patents: The EPO approach. World Patent Information.
Sheremetyeva, S., Nirenburg, S., Nirenburg, I. (1996). Generating patent claims from interactive input. Proceedings of the 8th international workshop on natural language generation. Hersmonceux, Sussex, UK.
Sheremetyeva, S..(2003). Natural language analysis of patent claims. Proceeding of the ACL-2003 workshop on patent corpus processing, pp. 66-73.
Silverman, B., Stacey, K. (1996). Understanding "Patentese"—A Patent Glossary. Retrieved January 8, 2007, from
http://www.tms.org/pubs/journals/JOM/matters/matters-9609.html
Shinmori, A., Okumura, M., Marukawa, Y. and Iwayama, M. (2003). Patent claim processing for readability – structure analysis and term explanation. In Proceedings of the Workshop on Patent Corpus Processing. (ACL 2003 Post-Conference Workshop), pages 56-65.
Toutanova, K., Manning, C. D. (2000). Enriching the Knowledge Sources Used in a Maximum Entropy Part-of-Speech Tagger. Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC-2000), pp. 63-70. Hong Kong.
Toutanova, K., Klein, D., Manning, D., and Yoram, S. (2003). Feature-Rich Part-of-Speech Tagging with a Cyclic Dependency Network. HLT-NAACL 2003.
USPTO Prior Art General Search Guidelines. Retrieved January 8, 2007, from http://www.uspto.gov/web/offices/pac/mpep/documents/0900_904_02.htm#sect904.02
USPTO PATENT RULES. Retrieved January 8, 2007, from
http://www.uspto.gov/web/offices/pac/mpep/documents/appxr.htm