傳統萃智以邏輯定性推理的方式解題，並且依賴人為主觀來判斷哪些效應可以解題，往往因為所建議效應動輒數十或數百個，須一一檢驗非常耗時。本研究基於「類似問題，類似答案」的概念，以計量方法來判斷那些科學效應最適合解決當前問題，並客觀地提供其優先序。這個量化的方式可以讓使用者快速且客觀地從現有的效應與使用效應解決問題的案例中找到具有優先序的效應。這些效應與案例有別於個人的知識，是累積許多專家知識與經驗的結果。
本研究從科技網站與知識庫中整理210個已被解決的案例與70個常見的效應，作為測試與訓練案例。使用3-疊交叉驗證法，測試此方法的有效性。結果證明本研究方法所推薦相似性最高的前十名效應解中，有87.6%命中案例原本解答，遠超過隨機挑選十個效應解的23.8%命中率，及相似性最低的十個效應的0%命中率。證明本研究所建立的相似性指標為一有效決定解題效應優先序的計量方法。
本研究提出一個對萃智有典範轉移的解題方式，貢獻包含：1) 使用問題特徵陣列和科技效應的解答特徵陣列，使其能運用計量方式，提供具有優先序的效應觸發解，取代傳統質化的邏輯推演與沒有優先序建議的眾多效應解答。 2) 提供一個方法能藉由產生更多解決過的案例，持續累積專家的知識與經驗，提供使用者快速、客觀且有效率的問題解決系統。3) 從原先的39個通稱屬性增加到78個，通稱功能也從原本的36個增加到61個。

This research proposed a mathematical method to identify TRIZ solution models to given problems based on similarity measures. Quantitative methods were used to allow the users quickly and objectively obtaining solution models to a problem with priority based on existing effects and solved effect case base which is the accumulation of many expert knowledge and experiences instead of individual expert’s knowledge. Similarity concept was used to determine the relevant effects and related solved cases as solution models. A total of 210 known cases and 70 effects from scientific website/knowledge database are verified with the author’s research team for solution generation. By conducting a 3-fold verification of the 210 cases, the ten highest similarity solution models provided a hit rate exceeding 87.6% coverage of original solutions. This substantially exceeded the 23.8% hit rate of ten randomly selected solutions covering original solutions. The ten worst similarity solution only provided 0% hit rate.
This provides a paradigm shift in research direction for TRIZ-based research from logical reasoning to quantitative calculations contributing to TRIZ recognition in scientific fields. The contributions of this study include: 1) Using the problem characteristics array and solution characteristics array based on technical effects to enable mathematical computations for prioritized effect solutions instead of traditional qualitative reasoning and non-prioritized excessively large number of suggestions. 2) Providing a means to continually accumulate expert knowledge and experience by integrating more expert-solved cases to provide users a rapid, objective, and effective problem-solving system. This implies a continuous learning system which uses cumulative knowledge from many experts objectively instead of otherwise knowledge from individual experts. 3) Enhancing existing 39 parameters to 78 parameters and increasing existing 36 functions to 61 functions to cover more problem solving situations.

英文文獻
1. Aamodt, Agnar, and E. Plaza, (1994), “Case-based reasoning foundational issues, methodological variations and system approaches”, AI Communication, 7.1, pp. 39-59.
2. Alain Mille (2006), “From case-based reasoning to traces-based reasoning”, Annual Reviews in Control vol 30, pp. 223-232.
3. Altshuller, G. (1984), “Creativity as an Exact Science: The Theory of the Solution of Inventive Problems”, New York, NY: Gordon & Breach.
4. Altshuller, G. (1997), “40 Principles: TRIZ keys to technical innovation,” Worcester, MA: Technical Innovation Center.
5. Becattini, Niccolò, Y. Borgianni, G. Cascini, and F. Rotini, (2012), “Model and algorithm for computer-aided inventive problem analysis”, Computer-Aided Design vol.44, pp. 961–986.
6. Cao, Guozhong, H. Guo, J. Yu, and R. Tan, (2009), “Computer Aided Product Innovation Software Based on Extended-Effect and Its Application”, World Congress on Software Engineering IEEE, VOL 2, PROCEEDINGS, pp. 63-67.
7. Cao, Guozhong, H. Guo, and R. Tan, (2006), in Intemational Federation For Information Processing (IFIP), Volume 207, Knowledge Enterprise: Intelligent Strategies In Product Design, Manufacturing, and Management, eds. (Boston: Springer), pp. 412-420.
8. Cascini, G., and D. Russo, (2007), “Computer-aided analysis of patents and search for TRIZ contradictions”, Int. J. of Product Development, vol.4, no.1-2, pp. 52-67.
9. Cascini, G., and M. Zini, (2008), “Measuring patent similarity by comparing inventions functional trees”, Computer-Aided Innovation (CAI), vol.277, pp. 31-42.
10. Cavallucci, D. (2001), “Integrating Altshuller’s development laws for technical systems into the design process”, CIRP Annals-Manufacturing Technology, vol.50, issue.1, pp. 115-120.
11. Choi, S. C., D. W. Kang, J. Y. Lim, and K. S. Kim, (2012), “A fact-oriented ontological approach to SAO-based function modeling of patents for implementing Function-based Technology Database”, Expert Systems with Applications vol.39, pp. 9129–9140.
12. Choi, S. S., S. H. Cha, and C. Tappert, (2010), “A Survey of Binary Similarity and Distance Measures, Journal of Systemics:, Cybernetics and Informatics, vol. 8, No.1, pp. 43-48.
13. Collins, J. A., B. T. Hagan and H. M. Bratt, (1976), “The failureexperience matrix − A useful design tool”, Transactions of the ASME, Journal of Engineering in Industry, 98, pp. 1074-1079.
14. Cong, H., and L. H. Tong, (2008), “Grouping of TRIZ Inventive Principles to facilitate automatic patent classification”, Expert Systems with Applications, vol.34, issue.1, pp.788-795.
15. CREAX Function & Attributes Database (2011), at: http://function.creax.com, http://attributes.creax.com/. (2017/11)
16. Dewulf, S. (2011), “Directed variation: Variation of properties for new or improved function product DNA- a base for connect and develop”, Proceeding of the ETRIA World TRIZ Future Conference, vol.9, pp. 646-652.
17. Donald, A. J., M. S. Keith, and H. H. Harold, (1989), “Similarity coefficients: measures of co-occurrence and association or simple measures of occurrence”, The American Naturalist, vol.133, No.3, pp.436-453.
18. Dunn, G., and B. S. Everitt, (1982), “An Introduction to Mathematical Taxonomy”, Cambridge University Press.
19. Faith, D. P. (1983), “Asymmetric binary similarity measures”, Oecologia, vol.57, pp. 287-290.
20. Goldfire (2017), at: https://www.ihs.com/products/design-standards-software-goldfire.html. (2017/11)
21. Gomila, José M. Vicente, and Fernando Palop Marro (2013), “Combining tech-mining and semantic-TRIZ for a faster and better technology analysis: a case in energy storage systems”, Technology Analysis & Strategic Management, Vol. 25, No. 6, pp. 725–743.
22. Ilevbare, Imoh M., D. Probert, and R. Phaal, (2013), “A review of TRIZ, and its benefits and challenges in practice”, Technovation vol.33, pp. 30-37.
23. Jackson, D. A., K. M. Somers, and H. H. Harvey, (1989), “Similarity Coefficients: Measures of Co-occurrence and Association or Simple Measures of Occurrence”, The American Naturalist, vol.133, No.3, pp. 436-453.
24. Kirschman, C. F., and G. M. Fadel, (1998), “Classifying Functions for Mechanical Design”, Transactions of the ASME, Journal of Mechanical Design vol.120, pp. 475-482.
25. Li, Z., D. Tate, C. Lane, and C. Adams, (2012), “A framework for automatic TRIZ level of invention estimation of patents using natural language processing, knowledge-transfer and patent citation metrics”, Computer-Aided Design vol.44, pp. 987-1010.
26. Mahalanobis, P. C. (1936), “On the generalized distance in statistics”, Paper was presented in Proc. Nat. Inst. of Sciences of India, vol.12, pp. 49–55.
27. Mann, D. L. (2002), “Hands on Systematic Innovation”, CREAX press.
28. Meyer, A. S., Garcia, A. A. F. Garcia, P. D. Souza, and C. L. D. Souza Jr, (2004), “Comparison of Similarity Coefficients Used for Cluster Analysis with Dominant Markers on Maize (Zea mays L)”, Genetics and Molecular Biology, vol. 27, issue.1, pp. 83-91.
29. Myung, S. H., and S. H. Han, (2001), “Knowledge-based parametric design of mechanical products based on configuration design method”, International Journal of Expert Systems with Applications, vol.21, no. 2, pp. 99-107.
30. Oxford Creativity (2017), at: http://wbam2244.dns-systems.net//EDB_Welcome.php. (2017/11)
31. Park, Hyunseok, J. Yoon, and K. Kim, (2013), “Using function-based patent analysis to identify potential application areas of technology for technology transfer”, Expert Systems with Applications vol.40, pp. 5260-5265.
32. Pro/Solutions KB (2009), at: http://www.prosolutionskb.com/Help-New.htm. (2017/11)
33. Robles, G. C., S. Negny, and J. M. Le Lann, (2009), “Case-based reasoning and TRIZ: A coupling for innovative conception in Chemical Engineering”, Chemical Engineering and Processing vol.48, pp. 239-249.
34. Shen, Victor R. L., C. Y. Yang, and J. H. Lee (2012), “Analysis of the problem description in the Algorithm for Inventive Problem Solving using Petri nets”, Knowledge-Based Systems vol.35, pp. 290–303.
35. Sheu, D. Daniel, and H. K. Lee. (2011) “A proposed process for systematic innovation.” International Journal of Production Research. Vol. 49, No. 3, 1 Febuary, pp. 847-868.
36. Sheu, D. Daniel, S. C. Chiu, and T. H. Lu. (2014) “TRIZ identification of solution models by function-attribute characteristics using mathematical measures.” The 5th international conference on systematic innovation. San Jose, California, U.S.A. July, pp. 16–18. (Best paper award).
37. Sheu, D. Daniel, and S. C. Chiu (2017) “Prioritized relevant trend identification for problem solving based on quantitative measures.” Computers & Industrial Engineering. 107, pp. 327-344.
38. Tong, L. H., H. Cong, and S. Lixiang, (2006), “Automatic classification of patent documents for TRIZ users”, World Patent Information vol.28, pp. 6–13.
39. Wang, D., Q. Sun, and J. Ning, (2012), “Research on Knowledge Base System of Coal Energy Saving Based on TRIZ Theory”, Proced Engineering vol.29, pp. 44–451.
40. Yang, C. J., and J. L. Chen, (2012), “Forecasting the design of eco-products by integrating TRIZ evolution patterns with CBR and Simple LCA methods”, Expert Systems with Applications vol.39, pp. 2884-2892.
41. Yoon, J., and K. Kim, (2012), “TrendPerceptor: A property-function based technology intelligence system for identifying technology trends from patents”, Expert Systems with Applications, vol.39, issue.3, pp. 2927-2938.
42. Zhang, X., X. Mao, and S. M. AbouRizk, (2009), “Developing a knowledge management system for improved value engineering practices in the construction industry”, Automation in Construction vol.18, pp. 777–789.
中文文獻
1. 許棟樑 (2015)，萃智創新工具精通(上冊)四版，ISBN：978-986-85795-2-1。
2. 許棟樑(譯) (2013)，Darrell Mann著，萃智系統性創新上手(再版)，ISBN：978-986-85795-0-7。
3. 蘇朝墩 (2010)，品質工程，ISBN：978-986-57740-6-6。
4. 林川煥 (2004)，「模糊集相似性測度性質與其應用之研究」，南台科技大學工業管理研究所碩士論文。
5. 郭盛揚 (2004)，「以顧客交易特徵為基礎的顧客分群方法」，朝陽科技大學資訊管理學系碩士論文。
6. 陳彥霖 (2006)，「應用潛在語意分析於試題相似度比較之可行性」，國立臺灣師範大學資訊教育學系碩士論文。
7. 陳家杰 (2007)，「集群分析於二元變數上的研究」，銘傳大學應用統計資訊學系碩士論文。
8. 陳振原 (2007)，「方法式專利步驟相似度之比對」，國立清華大學資訊系統與應用研究所碩士論文。
9. 沈穎廷 (2009)，「運用田口法、模糊理論以及TRIZ於產品之重新設計」，國立臺灣大學工學院機械工程學系碩士論文。
10. 徐建業 (2009)，「混合色彩空間以及區域紋理特徵之商標辨識系統」，國立中央大學資訊工程學系碩士論文。
11. 蔡美慧 (2010)，「以偏好導向為相似性量測的協同過濾式推薦」，朝陽科技大學資訊管理學系碩士論文。
12. 曾筱雯 (2010)，「人類心智模式衡量中不同相似係數之評估」，國立台北科技大學工業工程與管理系碩士論文。
13. 黃鈺婷 (2010)，「以功能屬性關係辨識相關技術演化趨勢」，國立清華大學工業工程與工程管理系碩士論文。
14. 陳佳宏 (2011)，「基於功能屬性之通用問題與解答模式：自動辨識解答發明原則和趨勢」，國立清華大學工業工程與工程管理系博士論文。
15. 廖坤祈 (2011)，「整合TRIZ與品質機能展開法評估產品未來演化趨勢」，國立成功大學機械工程學系碩士論文。
16. 張家瑋 (2012)，「功能-屬性-效應知識庫之研究」，國立清華大學工業工程與工程管理系碩士論文。
17. 邱聖家 (2013)，「使用相似性指標辨識萃智解答模型: 以相關趨勢辨識為例」，國立清華大學工業工程與工程管理系碩士論文。
18. 鄧乃誠 (2015)，「基於功能屬性相似性具優先序的萃智趨勢解答辨識」，國立清華大學工業工程與工程管理系碩士論文。