# 利用專利分類-專利文件矩陣提升專利潛在語意分析效率

## 前言

### 2. 潛在語義分析

H 借用了統計力學的亂度 (entropy) 概念；意義上，一個字詞在字詞-文件矩陣每篇文章中出現的次數越相近，亂度越大。局部加權 lij

## 三、 結果與討論

 矩陣形式 降維前維度 餘弦值≧0.8成對數 餘弦值≧0.8人工認定準確度 CPC-專利文件 4832 93 44.1% 字詞-專利文件 14267 114 24.6%

 CPC 1階 2階 3階 4階 5階 降維前維度 餘弦值≧0.8成對數 餘弦值≧0.8人工認定準確度 例 H H05 H05K H05K72 H05K72/0336 ✓ 4832 93 44.1% ✓ ✓ 6057 78 74.4% ✓ ✓ ✓ 6316 31 61.3% ✓ ✓ ✓ ✓ 6414 29 41.4% ✓ ✓ ✓ ✓ ✓ 6423 41 39.0%

## 參考文獻

1. Dumais, S. T. (1991). Improving the retrieval of information from external sources. Behavior Research Methods, Instruments, & Computers, 23(2), 229–236. doi:10.3758/bf03203370
2. Lai, Y.-H., & Che, H.-C. (2009). Evaluating patents using damage awards of infringement lawsuits: A case study. Journal of Engineering and Technology Management, 26(3), 167–180. doi:10.1016/j.jengtecman.2009.06.005
3. Mitchell, T. M. (1997). Machine learning (7th ed.). New York: McGraw Hill Higher Education.
4. Mogee, M. E., & Kolar, R. G. (1994). International patent analysis as a tool for corporate technology analysis and planning. Technology Analysis & Strategic Management, 6(4), 485–504. doi:10.1080/09537329408524188
5. Montecchi, T., Russo, D., & Liu, Y. (2013). Searching in cooperative patent classification: Comparison between keyword and concept-based search. Advanced Engineering Informatics, 27(3), 335–345. doi:10.1016/j.aei.2013.02.002 ThemeScape – Quick Reference Guide. (n.d.). Retrieved from http://info.thomsoninnovation.com/sites/default/files/assets/ti_themescape_qrg.pdf
6. Trappey, A. J. C., & Trappey, C. V. (2008). An R&D knowledge management method for patent document summarization. Industrial Management & Data Systems, 108(2), 245–257. doi:10.1108/02635570810847608
7. Trappey, A. J. C., Trappey, C. V., Wu, C.-Y., & Lin, C.-W. (2012). A patent quality analysis for innovative technology and product development. Advanced Engineering Informatics, 26(1), 26–34. doi:10.1016/j.aei.2011.06.005
8. Trappey, C. V., Trappey, A. J. C., & Wu, C.-Y. (2010). Clustering patents using non-exhaustive overlaps. Journal of Systems Science and Systems Engineering, 19(2), 162–181. doi:10.1007/s11518-010-5134-x
9. Yang, C. H., Park, H. W., & Heo, J. (2010). A network analysis of interdisciplinary research relationships: The Korean government’s R&D grant program. Scientometrics, 83(1), 77–92. doi:10.1007/s11192-010-0157-0
10. Zhu, M., & Ghodsi, A. (2006). Automatic dimensionality selection from the scree plot via the use of profile likelihood. Computational Statistics & Data Analysis, 51(2), 918-930. doi:10.1016/j.csda.2005.09.010