臺灣博碩士論文加值系統

隨著工業4.0時代的來臨，全球製造業正面臨前所未有的挑戰和機遇。在這個快速變化的市場環境中，符合智慧製造的技術成為世界各國發展的核心，其中全面工廠控制扮演著至關重要的角色。全面工廠控制的核心在於集中控制所有層面的設備、機器、數據，將工業生產過程中的重要因素以集中式控制系統整合，運用該系統不僅能提高生產效率和質量，還能降低成本，是連接各種製造設備和數據的關鍵。然而，過去的研究鮮少深入探討集中式控制系統之創新技術及專利技術成份分析。因此，本論文旨在運用機會探索及文字探勘KeyGraph 演算法挖掘工業用集中式控制系統相關專利技術成分之關聯性分析與專利探勘，挖掘出主要的核心技術及具有潛力的關鍵技術。本論文提出一個基於機會探索的專利探勘方法，利用美國專利商標局（USPTO）在CPC分類號G09B 19/418「全面工廠控制；集中控制多台機器的技術」與其底下十九個子類別之相關專利技術。蒐集上述二十個類別中專利分類屬性組成之CPC分類號作為研究資料標的物，從2014年至2023年總計7608筆專利資料做分類分析。本論文的研究過程發現在專利資料量不夠多的時候將無法發覺專利之間的關聯性，因此挑選出其中九項專利資料大於300筆之類別進行專技技術成份分析並生成KeyGraph知識圖。本論文在探索全面工廠控制之集中式控制系統專利技術之研究結果顯示，根據KeyGraph演算法所挖掘出最具有價值且重要之關鍵技術共有十四項機會技術。其機會技術涵蓋四個領域，分別為神經網路與機器學習技術、控制系統與監控技術、專用網路與系統技術、物流管理技術。這些機會技術都對工業在發展集中式控制系統有相關聯性，並有助於企業在部署投資策略時能更加理解全面工廠控制的演進及策略方向。本論文也證實運用機會探索理論進行專利探勘以挖掘創新機會專利技術是可行的。

The advent of Industry 4.0 has ushered in unprecedented challenges and opportunities for the global manufacturing sector. In this dynamic market landscape, technologies aligned with smart manufacturing have assumed pivotal roles in the development agenda of nations worldwide, prominently featuring Total Factory Control. At its core, Total Factory Control entails centralized oversight over equipment, machinery, and data, harmonizing critical elements of industrial production through integrated control systems. This system not only enhances production efficiency and quality but also reduces costs, serving as a critical link between various manufacturing equipment and data. However, existing literature has provided limited exploration into the innovative technologies and patent composition within centralized control systems. Hence, this study employs chance discovery and the KeyGraph text mining algorithm to explore the patent landscape associated with industrial centralized control systems, aiming to identify core and potential key technologies. Employing a patent mining approach grounded in chance discovery, the study focuses on the U.S. Patent Office’s CPC Classification G09B 19/418 "Total factory control; centrally controlling a plurality of machines" and its associated patented technologies spanning nineteen sub-categories. Collecting CPC classification code from these twenty categories as research data, a total of 7608 patent records from 2014 to 2023 were analyzed. The research process found that when the amount of patent data is insufficient, it is impossible to discern the relationships between patents. Therefore, nine categories with more than 300 patent records each were selected for detailed analysis of technical components, generating a KeyGraph knowledge map. The study results on the centralized control systems patents for Total Factory Control indicate that the KeyGraph algorithm identified fourteen valuable and significant key technologies. These technologies encompass neural network and machine learning, control systems and monitoring, dedicated network and system infrastructures and logistics management. They also collectively inform industry stakeholders on the evolutionary trajectory and strategic imperatives of Total Factory Control, thereby guiding investment decisions and operational strategies. This paper also validates the feasibility of using chance discovery theory for patent mining to uncover innovative opportunity patents.

第一章、緒論1
第一節、研究背景與動機 1
第二節、研究目的4
第二章、文獻探討 5
第一節、機會探索理論 7
第二節、KeyGraph文字探勘演算法 10
第三章、研究方法 16
第一節、研究流程 16
第二節、資料收集與處理 18
第三節、使用KeyGraph進行專利資料之機會探索 23
第四章、研究結果與分析 26
第一節、蒐集G05B 19/418下工業用集中式控制系統技術相關之專利資料 26
第二節、KeyGraph文字探勘 41
第五章、研究結論 52
第一節、研究回顧 52
第二節、研究限制 55
第三節、研究貢獻 56
參考文獻 57

[1] A. J. C. Trappey, C. V. Trappey, U. H. Govindarajan, J. J. Sun and A. C. Chuang, “A Review of Technology Standards and Patent Portfolios for Enabling Cyber-Physical Systems in Advanced Manufacturing,” IEEE Access, vol. 4, pp. 7356-7382, 2016.
[2] L. Huang, Y. Guo, Y. Zhao, Y. Wang and A. L. Porter, “The role of text mining of patent in Mergers and Acquisitions,” 2013 Proceedings of PICMET '13: Technology Management in the IT-Driven Services (PICMET), pp. 2271-2282, 2013.
[3] L. Ardito, D. D'Adda, A. M. Petruzzelli, “Mapping innovation dynamics in the Internet of Things domain: Evidence from patent analysis,” Technological Forecasting and Social Change, vol. 136, pp. 317-330, 2018.
[4] D. Lucke, C. Constantinescu, E. Westkämper, “Smart Factory - A Step towards the Next Generation of Manufacturing,” Manufacturing Systems and Technologies for the New Frontier, Springer, London, pp. 115-118, 2008.
[5] S. Wang, J. Wan, D. Li and C. Zhang, “Implementing Smart Factory of Industrie 4.0: An Outlook,” International Journal of Distributed Sensor Networks, vol. 12(1), 2016.
[6] T. Stock, G. Seliger, “Opportunities of Sustainable Manufacturing in Industry 4.0,” Procedia CIRP, vol. 40, pp. 536-541, 2016.
[7] J. Qin, Y. Liu, R. Grosvenor, “A categorical framework of manufacturing for industry 4.0 and beyond,” Procedia CIRP, vol. 52, pp. 173-178, 2016.
[8] D. Zuehlke, “SmartFactory - from vision to reality in factory technologies,” IFAC Proceedings, vol. 41(2), pp. 14101-14108.
[9] P. Osterrieder, L. Budde and T. Friedli, “The smart factory as a key construct of industry 4.0: A systematic literature review,” International Journal of Production Economics, vol. 221, pp. 1-16, 2020.
[10] H. Cañas, J. Mula, M. Díaz-Madroñero and F. Campuzano-Bolarín, “Implementing Industry 4.0 principles,” Computers & Industrial Engineering, vol. 158, Art no. 107379, 2021.
[11] P. Paritala, S. Manchikatla, P. Yarlagadda, “Digital Manufacturing- Applications Past, Current, and Future Trends,” Procedia Engineering, vol. 174, pp. 982-991, 2017.
[12] S. Vaidya, P. Ambad, S. Bhosle, “Industry 4.0 - A Glimpse,” Procedia Manufacturing, vol. 20, pp. 233-238, 2018.
[13] P.N. Stearns, The Industrial Revolution in World History, 5th Edition, Routledge, pp. 1-340, 2020.
[14] H. Lasi, P. Fettke, HG. Kemper, T. Feld and M. Hoffmann, “Industry 4.0.,” Business & Information Systems Engineering, vol. 6, pp. 239-242, 2014.
[15] L. D. Xu, E. L. Xu and L. Li, “Industry 4.0: state of the art and future trends,” International Journal of Production Research, vol. 56(8), pp. 2941-2962, 2018.
[16] A. Frank, L. Dalenogare and N. Ayala, “Industry 4.0 technologies: Implementation patterns in manufacturing companies,” International Journal of Production Economics, vol. 210, pp. 15-26, 2019.
[17] Assad Abbas, Limin Zhang, Samee U. Khan, “A literature review on the state-of-the-art in patent analysis,” World Patent Information, vol. 37, pp. 3-13, 2014.
[18] D. Bonino, A. Ciaramella and F. Corno, “Review of the state-of-the-art in patent information and forthcoming evolutions in intelligent patent informatics,” World Patent Information, vol. 32(1), pp. 30-38, 2010.
[19] D. Hunt, L. Nguyen and M. Rodgers, Patent searching: tools and techniques, John Wiley and Sons, 2007.
[20] Bernard Gress, “Properties of the USPTO patent citation network: 1963–2002,” World Patent Information, vol. 32, Issue 1, pp. 3-21, 2010.
[21] H. You, M. Li, J. Jiang, B. Ge and X. Zhang, “Evolution monitoring for innovation sources using patent cluster analysis.” Scientometrics, vol. 111, pp. 693-715, 2017.
[22] M. Shibata, Y. Ohtsuka, M. Takahashi and K. Okamoto, “Advanced FPGA technology trend based on patent analysis with link mining,” 2018 International Conference on Electronics Packaging and iMAPS All Asia Conference (ICEP-IAAC), Mie, Japan, pp. 147-151, 2018.
[23] R. Krestel, R. Chikkamath, C. Hewel and J. Risch, “A survey on deep learning for patent analysis,” World Patent Information, vol. 65, art. 102035, 2021.
[24] A. Hussain, J. Jeon, M. Rehman, “Technological Convergence Assessment of the Smart Factory Using Patent Data and Network Analysis,” Sustainability, vol. 14(3), 2022.
[25] P. Sharma and R. C. Tripathi, “Patent citation: A technique for measuring the knowledge flow of information and Innovation,” World Patent Information, vol. 51, pp. 31-42, 2017.
[26] E. Marilungo, A. Papetti, M. Germani, M. Peruzzini, “From PSS to CPS Design: A Real Industrial Use Case Toward Industry 4.0,” Procedia CIRP, vol. 64, pp. 357-362, 2017.
[27] A. Al-Mulla and A. ElSherbini, “Demand management through centralized control system using power line communication for existing buildings,” Energy Conversion and Management, vol. 79, pp. 477-486, 2014.
[28] K.C.T. Vivaldini, G. Tamashiro, J. Martins Junior and M. Becker, “Communication Infrastructure in the Centralized Management System for Intelligent Warehouses,” Communications in Computer and Information Science, vol. 371, Springer, Berlin, Heidelberg, 2013.
[29] B. Chen, J. Wan, L. Shu, P. Li, M. Mukherjee and B. Yin, “Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges,” IEEE Access, vol. 6, pp. 6505-6519, 2018.
[30] D. Pliatsios, P. Sarigiannidis, T. Lagkas and A. G. Sarigiannidis, “A Survey on SCADA Systems: Secure Protocols, Incidents, Threats and Tactics,” IEEE Communications Surveys & Tutorials, vol. 22(3), pp. 1942-1976, 2020.
[31] S. D. Antón, D. Fraunholz, C. Lipps, F. Pohl, M. Zimmermann and H. D. Schotten, “Two decades of SCADA exploitation: A brief history,” 2017 IEEE Conference on Application, Information and Network Security (AINS), Miri, Malaysia, pp. 98-104, 2017.
[32] L. Cardwell, A. Shebanow, “The Efficacy and Challenges of SCADA and Smart Grid Integration,” Cyber Security and Information Systems Information Analysis Center, vol. 1(3), pp. 1-7, 2013.
[33] D. Babunski, E. Zaev, A. Tuneski and D. Bozovic, “Optimization methods for water supply SCADA system,” 2018 7th Mediterranean Conference on Embedded Computing (MECO), Budva, Montenegro, pp. 1-4, 2018.
[34] D. O. Kovaliuk, K. M. Huza, O. O. Kovaliuk, “Development Of Scada System Based On Web Technologies,” International Journal Of Information Engineering And Electronic Business, vol. 10(2), pp. 25-32, 2018.
[35] Y. Ohsawa, T. Terano, T. Nishida, A. Namatame, S. Tsumoto and T. Washio, “The Scope of Chance Discovery,’’ New Frontiers in Artificial Intelligence, vol. 2253, pp. 413, 2001.
[36] Y. Ohsawa, P. McBurney, “Modeling the Process of Chance Discovery,” Advanced Information Processing, pp.2-15, 2003
[37] Y. Ohsawa, S. Tsumoto, “Chance Discovery: The Current States of Art, Chance Discoveries in Real World Decision Making,” Studies in Computational Intelligence, vol. 30, pp.3-20, 2006.
[38] Y. Ohsawa, H. Fukuda, “Chance Discovery by Stimulated Groups of People. Application to Understanding Consumption of Rare Food,” Journal of Contingencies and Crisis Management, vol. 10(3), pp. 129-138, Dec. 2002.
[39] Edward Tsang, Sheri Markose, Hakan Er, “Chance Discovery In Stock Index Option And Futures Arbitrage,” New Mathematics and Natural Computation, World Scientific (NMNC), vol. 1(3), pp. 435-447, 2005.
[40] A. Garcia-Almanza, E. Tsang, “Forecasting stock prices using Genetic Programming and Chance Discovery,” Society for Computational Economics, Computing in Economics and Finance, no. 489, 2006.
[41] K. J. Kim, M. C. Jung, and S. B. Cho, “KeyGraph-based chance discovery for mobile contents management system,” International Journal of Knowledge-Based and Intelligent Engineering Systems, vol. 11(5), pp. 313-320, 2007.
[42] Gary K. W. Wong and Simon Y. K. Li, “Academic Performance Prediction Using Chance Discovery from Online Discussion Forums,” 2016 IEEE 40th Annual Computer Software and Applications Conference (COMPSAC), Atlanta, GA, USA, pp. 706-711, Jun. 2016.
[43] N. Ko, B. Jeong, S. Choi, and J. Yoon, “Identifying product opportunities using social media mining: Application of Topic Modeling and Chance Discovery Theory,” IEEE Access, vol. 6, pp. 1680-1693, 2018.
[44] Y. Ohsawa, N. E. Benson and M. Yachida, “KeyGraph: automatic indexing by co-occurrence graph based on building construction metaphor,” Proceedings IEEE International Forum on Research and Technology Advances in Digital Libraries -ADL'98, pp. 12-18, 1998.
[45] R. Pan, C. Hong, C. Huang, F. Hsu, L.H. Wang, and T. Chi, “One-Scan KeyGraph Implementation,” 2005.
[46] Y. Nezu and T. Miura, “Extracting Keywords on SNS by Successive KeyGraph,” 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI), Baltimore, MD, USA, pp. 997-1003, 2020.
[47] L. Zahrotun, “Comparison Jaccard similarity, cosine similarity and combined both of the data clustering with shared nearest neighbor method,” Computer Engineering and Applications Journal, vol. 5(1), pp.11, 2016.
[48] R. Thawonmas, K. Hata, “Aggregation of Action Symbol Sub-sequences for Discovery of Online-Game Player Characteristics Using KeyGraph,” ICEC 2005. Lecture Notes in Computer Science, vol. 3711, pp. 126-135, 2005.
[49] Y. Geum and M. Kim, “How to identify promising chances for technological innovation: Keygraph-based patent analysis,” Advanced Engineering Informatics, vol. 46, 2020.
[50] Y. Seo, Y. Iwase and Y. Takama, “KeyGraph-based BBS for Online Chance Discovery,” 2006 IEEE International Conference on Systems, Man and Cybernetics, Taipei, Taiwan, pp. 1754-1758, 2006.
[51] Tzu-Fu Chiu, “Applying KeyGraph and Data Crystallization to technology monitoring on solar cell,” Journal of Intelligent & Fuzzy Systems, vol. 21(3), pp. 209-219, 2010.
[52] H. Sayyadi, L. Raschid, “A graph analytical approach for topic detection,” ACM Trans. Internet Technol (TOIT), vol. 13(2), pp. 1-23, 2013.
[53] F. Kobayashi and Y. Nara, “A Study on the View of Oral Health and Oral Risk Management in Japan: Narrative Analysis in Combination with Text-mining and KJ Method”, Intelligent Decision Technologies, vol. 10(3), pp. 249-261, 2016.
[54] M. Kushima, K. Araki, T. Yamazaki, S. Araki, T. Ogawa and N. Sonehara, “Text Data Mining of Care Life Log by the Level of Care Required Using KeyGraph,” 2017 Proceedings of the International MultiConference of Engineers and Computer Scientists (IMECS), vol. I, pp. 1-5, 2017.
[55] J. Wang, J. Y. Lai and Y. H. Lin, “Social media analytics for mining customer complaints to explore product opportunities,” Computers & Industrial Engineering, vol. 178, 2023.
[56] United States Patent and Trademark Office (USPTO), “CPC scheme- G05B 19/418,” https://www.uspto.gov/web/patents/classification/cpc/html/cpc-G05B.html#G05B19/418, (accessed Jun. 12, 2024).
[57] L.C. Chen, T.J. Yu, and C.J. Hsieh, “KeyGraph-based chance discovery for exploring the development of e-commerce topics,” Scientometrics, vol. 95, pp.257-275, 2013.
[58] United States Patent and Trademark Office (USPTO), “Patent essentials,” https://www.uspto.gov/patents/basics/essentials, (accessed Jun. 12, 2024).
[59] Cooperative Patent Classification “Guide to the CPC,” https://www.cpcinfo.org, (accessed Jun. 7, 2024).
[60] Y. Ohsawa, “KeyGraph: A basic tool since 1998”, https://www.panda.sys.t.u-tokyo.ac.jp/KeyGraph/, (accessed Jun. 7, 2024).
[61] Y. Ohsawa, “Polaris, a data visualization software of KeyGraph,” A free basic manual (version E-0) of Polaris, that is a piece of KeyGraph software, https://www.panda.sys.t.u-tokyo.ac.jp/KeyGraph/manualKG.pdf, (accessed Jun. 7, 2024).
[62] C. Replogle, “A new way to search the US Patent Database,” ScienceDocs Inc, https://www.sciencedocs.com/patent-writing-us-patent-database/, (accessed May 29, 2024).
[63] United States Patent and Trademark Office (USPTO), “USPTO launches new Patent Public Search tool and webpage”, https://www.uspto.gov/about-us/news-updates/uspto-launches-new-patent-public-search-tool-and-webpage, (accessed Jun. 7, 2024).