臺灣博碩士論文加值系統

在這高度競爭的商業環境中，企業利用專利保護智慧資產並以專利進行相關手段以獲取競爭優勢，而其中專利前案檢索對專利有效性以及新穎性的搜尋都是極為重要並富有價值的。本研究旨在發展一套混合式方法，試圖結合申請專利範圍結構與專利說明來加強專利前案檢索的效率及效能。我們選擇美國專利分類編號438的類別作為我們的資料來源，我們總共蒐集了從1976年至2005年間的52111篇專利，並且從2005年的專利中隨機抽取300篇作為我們的測試資料。為了驗證我們的混合方法，我們設計了一系列的實驗：第一我們透過實驗找出我們的申請專利範圍結構方法中最佳的參數配置；第二我們透過實驗找到從專利描述說明中取出相關句子的最佳比例；最後我們從專利描述說明中取出70%的相關句子，並搭配我們的申請專利範圍結構方法，混合後進行最佳化，成功獲得了良好的結果。我們成功的驗證了混合方法的有效性，同時也能夠驗證了申請專利範圍結構的方法在專利前案檢索的應用中具有其特殊功效，也因此本研究所提出的方法能夠有效的幫助企業或專利相關人員找出專利的相關前案，同時也驗證了本方法在專利前案檢索中的有用性。

In the highly competitive business environment, companies use patents as the intellectual asset to gain strategic competiveness. Patent prior art retrieval is a nontrivial task for invalidity and patentability search. This study adopts a hybrid approach to include claim structure and patent description to enhance prior art retrieval performance in terms of recall rate. We used USPC class 438 as the data set, which contains 52,311 patents from 1976 to 2005, and we randomly selected 300 patents in 2005 as the testing data. To evaluate the proposed hybrid approach, we designed a series of experiments; first, we identified the best parameter settings in claim structure; second, we decide the best ratios of sentences in description as relevant contents; finally, we obtain the best result by combining the information of claim structure and top 70% sentences in description. We successfully achieve the competitive result in terms of raising the recall rate with the proposed hybrid approach, which also demonstrates the usefulness of including claim structure into prior art retrieval system.

Chapter 1 1
1.1 Research background 1
1.2 Research motivation 3
1.3 Research objective 4
Chapter 2 5
2.1 Claim tree structure 5
2.2 Patent prior art research 9
Chapter 3 12
3.1. Claim structure approach 13
3.2. Claim-related sentence extraction 19
3.3. Hybrid approach 20
Chapter 4 24
4.1. Data source 25
4.2. Evaluation criterion 25
4.3. Baseline experiment 26
4.4. Parameter arrangements in claim structure comparison 29
4.5. Sentences retrieval in description 32
4.6. Hybrid approach 33
5.1. Conclusion 38
5.2. Research limitations 38
5.3. Future work 39
References 40

Chen, R.-C. (2008). The Study of Searching Relevant Patents of Multi-disciplinary Products Based on Patent Claim Structure. Unpublished thesis, National Tsing-Hua University.
Fujii, A. (2007). Enhancing Patent Retrieval by Citation Analysis. The 30th Annual International ACM SIGIR Conference (pp. 793-794). Amsterdam: ACM.
FujiiAtsushi, IwayamaMakoto, & KandoNoriko. (2004). Invalidity Patent Search System of NTT DATA. Proceedings of the Fourth NII Test Collection for IR Systems (NTCIR-4)Workshop. Tokyo, Japan.
Graf, E., & Azzopardi, L. (2008). A methodology for building a patent test collection for prior art search. The Second International Workshop on Evaluating Information Access (EVIA). Tokyo, Japan.
Huang, F.-m. (2007). The study of patent prior art retrieval using claim structure and link analysis. Unpublished thesis, National Tsing-Hua University.
Kang, I.-S., Na, S.-H., Kim, J., & Lee, J.-H. (2007). Cluster-based patent retrieval. Information Processing and Management , 43, pp. 1173–1182.
Kazenske, E. R. (2003). The future of prior art searching at the United States patent and trademark office. World Patent Information , 25, pp. 283–287.
Lai, K.-K., & Wu, S.-J. (2005). Using the patent co-citation approach to establish a new patent classification system. Information Processing & Management , 41, pp. 313-330.
Lemley, M. A. (2001). Rational Ignorance at the Patent Office. Northwestern University Law Review , 95.
Mase, H., Matsubayashi, T., Ogawa, Y., & Iwayama, M. (2005). Proposal of Two-Stage Patent Retrieval Method Considering the Claim Structure. ACM Transactions on Asian Language Information Processing, 4, pp. 186-202.
OpenNLP. (n.d.). Retrieved from http://opennlp.sourceforge.net/
Ratnaparkhi, A. (1999). Learning to Parse Natural Language with Maximum Entropy Models. Machine Learning , 34, pp. 151-175.
Sheremetyeva, S. (2008). An Efficient Patent Keyword Extractor As Translation Resource.
Szarvas, G., Herbert, B., & Gurevych, I. (2009). Prior Art Search using International Patent Classication Codes and All Claims Queries. The CLEF 2009 Workshop.
Tseng, Y.-H., Lin, C.-J., & Lin, Y.-I. (2007). Text mining techniques for patent analysis. Information Processing and Management , 43, pp. 1216-1247.
United States Patent and Trademark Office. (n.d.). Retrieved from http://www.uspto.gov/
Verberne, S., & D'hondt, E. (2009). Prior art retrieval using the claims section as a bag of words. The CLEF 2009 Workshop.
Yoon, B., & Park, Y. (2004). A text-mining-based patent network: Analytical tool for high-technology trend. Journal of High Technology Management Research , 15, pp. 37-50.
Yu, C.-C. (2008). Use of Text Summarization Technique for Supporting Patent Prior Art Retrieval. Unpublished thesis, National Tsing-Hua University.