請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97807完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 項潔 | zh_TW |
| dc.contributor.advisor | Jieh Hsiang | en |
| dc.contributor.author | 朱蓉美 | zh_TW |
| dc.contributor.author | Jung-Mei Chu | en |
| dc.date.accessioned | 2025-07-17T16:05:27Z | - |
| dc.date.available | 2025-07-18 | - |
| dc.date.copyright | 2025-07-17 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-07-03 | - |
| dc.identifier.citation | Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S., ..., and Anadkat, S. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774.
Aher, G. V., Arriaga, R. I., and Kalai, A. T. (2023). Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pages 337–371. PMLR. Alcantar, K. and Gillespie, K. S. (2019). Customer-centric legal tech. GPSolo, 36(1):48– 51. Access to Justice. Bessen, J. and Maskin, E. (2009). Sequential innovation, patents, and imitation. The RAND Journal of Economics, 40(4):611–635. Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet allocation. Journal of machine Learning research, 3(Jan):993–1022. Bollacker, K., Evans, C., Paritosh, P., Sturge, T., and Taylor, J. (2008). Freebase: a collaboratively created graph database for structuring human knowledge. In Proceedings of the 2008 ACM SIGMOD international conference on Management of data, pages 1247–1250. Brown, B. B. (1968). Delphi process: a methodology used for the elicitation of opinions of experts. Bues, M.-M. and Matthaei, E. (2017). Legaltech on the rise: technology changes legal work behaviours, but does not replace its profession. Liquid LegaL: transforming Legal into a Business savvy, information enabled and performance driven industry, pages 89– 109. Burke, R. (2002). Hybrid recommender systems: Survey and experiments. User modeling and user-adapted interaction, 12:331–370. Chen, D., Fisch, A., Weston, J., and Bordes, A. (2017). Reading Wikipedia to answer open-domain questions. In Barzilay, R. and Kan, M.-Y., editors, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1870–1879, Vancouver, Canada. Association for Computational Linguistics. Chen, H. and Deng, W. (2023). Interpretable patent recommendation with knowledge graph and deep learning. Scientific Reports, 13(1):2586–2586. Cheng, Y., Zhang, C., Zhang, Z., Meng, X., Hong, S., Li, W., Wang, Z., Wang, Z., Yin, F., Zhao, J., et al. (2024). Exploring large language model based intelligent agents: Definitions, methods, and prospects. arXiv preprint arXiv:2401.03428. Christensen, C. M., Baumann, H., Ruggles, R., and Sadtler, T. M. (2006). Disruptive innovation for social change. Harvard business review, 84(12):94–101. Christofidellis, D., Torres, A. B., Dave, A., Roveri, M., Schmidt, K., Swaminathan, S., Vandierendonck, H., Zubarev, D., and Manica, M. (2022). Pgt: a prompt based generative transformer for the patent domain. In ICML 2022 Workshop on Knowledge Retrieval and Language Models. Chu, J.-M. (2020). A study on u.s. patent examination practice. Thesis Graduate Institute of Interdisciplinary Legal Studies National Taiwan University, 2020:1–179. Chu, J.-M., Lo, H.-C., Hsiang, J., and Cho, C.-C. (2024). Patent response system optimised for faithfulness: Procedural knowledge embodiment with knowledge graph and retrieval augmented generation. In Proceedings of the 1st Workshop on Towards Knowledgeable Language Models (KnowLLM 2024), pages 146–155. Ding, Y., Fan, W., Ning, L., Wang, S., Li, H., Yin, D., Chua, T.-S., and Li, Q. (2024). A survey on rag meets llms: Towards retrieval-augmented large language models. arXiv preprint arXiv:2405.06211. DocuSign, I. (2020). Docusign announces second quarter fiscal 2021 financial results. https://investor.docusign.com. Accessed from DocuSign official financial reports. Domingues, M. A., de Moura, E. S., Marinho, L. B., and da Silva, A. (2023). A large scale benchmark for session-based recommendations on the legal domain. Artificial Intelligence and Law, pages 1–36. Edge, D., Trinh, H., Cheng, N., Bradley, J., Chao, A., Mody, A., Truitt, S., and Larson, J. (2024). From local to global: A graph rag approach to query-focused summarization. arXiv preprint arXiv:2404.16130. Falk, N. and Train, K. (2017). Patent valuation with forecasts of forward citations. Journal of Business Valuation and Economic Loss Analysis, 12(1):101–121. Fromer, J. C. (2008). Patent disclosure. Iowa L. Rev., 94:539. Gallini, N. and Scotchmer, S. (2002). Intellectual property: when is it the best incentive system? Innovation policy and the economy, 2:51–77. Gao, Y., Xiong, Y., Gao, X., Jia, K., Pan, J., Bi, Y., Dai, Y., Sun, J., Wang, M., and Wang, H. (2023). Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997. Geetha, G., Safa, M., Fancy, C., and Saranya, D. (2018). A hybrid approach using collaborative filtering and content based filtering for recommender system. In Journal of Physics: Conference Series, volume 1000, page 012101. IOP Publishing. Greene, R., Sanders, T., Weng, L., and Neelakantan, A. (2022). New and improved embedding model. https://openai.com/blog/new-and-improved-embedding-model. Accessed: 2022-12-15. Hall, B. H. and Ziedonis, R. H. (2001). The patent paradox revisited: an empirical study of patenting in the us semiconductor industry, 1979-1995. rand Journal of Economics, pages 101–128. Hartung, M., Bues, M.-M., and Halbleib, G. (2017). Legal tech. CH Beck Munich. Hatzius, J. (2023). The potentially large effects of artificial intelligence on economic growth (briggs/kodnani). Goldman Sachs. Helmers, L., Horn, F., Biegler, F., Oppermann, T., and Müller, K.-R. (2019). Automating the search for a patent＇s prior art with a full text similarity search. PloS one, 14(3):e0212103. Hsu, C.-C. and Sandford, B. A. (2019). The delphi technique: making sense of consensus. Practical assessment, research, and evaluation, 12(1). Huang, X., Zhang, J., Li, D., and Li, P. (2019). Knowledge graph embedding based question answering. In Proceedings of the twelfth ACM international conference on web search and data mining, pages 105–113. Karpukhin, V., Oğuz, B., Min, S., Lewis, P., Wu, L., Edunov, S., Chen, D., and Yih, W.-t. (2020). Dense passage retrieval for open-domain question answering. arXiv preprint arXiv:2004.04906. Kim, J.-h. (2023). Fine-tuning the llama2 large language model using books on the diagnosis and treatment of musculoskeletal system in physical therapy. medRxiv, pages 2023–11. Kim, K., Lee, S., Huang, K.-H., Chan, H. P., Li, M., and Ji, H. (2024). Can llms produce faithful explanations for fact-checking? towards faithful explainable fact-checking via multi-agent debate. arXiv preprint arXiv:2402.07401. Koren, Y., Bell, R., and Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer, 42(8):30–37. Kunaver, M. and Požrl, T. (2017). Diversity in recommender systems–a survey. Knowledge-based systems, 123:154–162. Lan, Y., He, G., Jiang, J., Jiang, J., Zhao, W. X., and Wen, J.-R. (2021). A survey on complex knowledge base question answering: Methods, challenges and solutions. arXiv preprint arXiv:2105.11644. Larroyed, A. (2023). Redefining patent translation: The influence of chatgpt and the urgency to align patent language regimes in europe with progress in translation technology. GRUR International, 72(11):1009–1017. Lauritsen, M. and Soudakoff, A. (1998). Power tools for document preparation. See http://www. capstonepractice. com/amlaw6. pdf. LawGeex (2018). Comparing the performance of artificial intelligence to human lawyers for nda review. https://www.lawgeex.com. Accessed from LawGeex website. Lee, J.-S. (2023). Evaluating generative patent language models. World Patent Information, 72:102173. Lee, J.-S. and Hsiang, J. (2020a). Patent claim generation by fine-tuning openai gpt-2. World Patent Information, 62:101983. Lee, J.-S. and Hsiang, J. (2020b). Patent classification by fine-tuning bert language model. World Patent Information, 61:101965. Lee, J.-S. and Hsiang, J. (2020c). Patenttransformer-2: Controlling patent text generation by structural metadata. arXiv preprint arXiv:2001.03708. Lemley, M. A. (2004). Property, intellectual property, and free riding. Tex L. Rev., 83:1031. Lewis, M. (2019). Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461. Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., Küttler, H., Lewis, M., Yih, W.-t., Rocktäschel, T., et al. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474. LexisNexis (2024). The disconnect between law firms and legal departments on impact of gen ai. https://www.lexisnexis.com/community/insights/legal/b/thou ght-leadership/posts/the-disconnect-between-law-firms-and-legal-d epartments-on-impact-of-gen-ai?access=1-8389565461&treatcd=social_all&utm_campAIgn=How+will+generative+AI+im&utm_content=1709337604 &utm_source=linkedin. Accessed: 2024-2-9. Liao, S.-H. (2005). Expert system methodologies and applications—a decade review from 1995 to 2004. Expert systems with applications, 28(1):93–103. Liu, N. F., Lin, K., Hewitt, J., Paranjape, A., Bevilacqua, M., Petroni, F., and Liang, P. (2024). Lost in the middle: How language models use long contexts. Transactions of the Association for Computational Linguistics, 12:157–173. Lo, H.-C. and Chu, J.-M. (2021). Pre-trained transformer-based classification for automated patentability examination. In 2021 IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE), pages 1–5. IEEE. Lo, H.-C., Chu, J.-M., Hsiang, J., and Cho, C.-C. (2024). Large language model informed patent image retrieval. arXiv preprint arXiv:2404.19360. Luo, Y., Yang, Z., Meng, F., Li, Y., Zhou, J., and Zhang, Y. (2023). An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747. Løwendahl, B. R. (2009). Strategic Management of Professional Service Firms. Copenhagen Business School Press, Copenhagen, 3rd edition. Mandal, A., Ghosh, K., Ghosh, S., and Mandal, S. (2021). Unsupervised approaches for measuring textual similarity between legal court case reports. Artificial Intelligence and Law, pages 1–35. Marković, M. and Gostojić, S. (2023). Legal document assembly system for introducing law students with legal drafting. Artificial Intelligence and Law, 31(4):829–863. Matsumoto, N., Moran, J., Choi, H., Hernandez, M. E., Venkatesan, M., Wang, P., and Moore, J. H. (2024). Kragen: a knowledge graph-enhanced rag framework for biomedical problem solving using large language models. Bioinformatics, 40(6). Mazzoleni, R. and Nelson, R. R. (1998). The benefits and costs of strong patent protection: a contribution to the current debate. Research policy, 27(3):273–284. Mills, R. (2016). Ai in law: State of play 2016. https://britishlegalitforum.com/ wp-content/uploads/2016/12/Keynote-Mills-AI-in-Law-State-of-Play-2 016.pdf. Accessed: 2024-10-22. Mishra, S. (2021). Determining patent filing targets based on patent cost retrieval from patent examination data system. World Patent Information, 65:102024. Noy, N., Gao, Y., Jain, A., Narayanan, A., Patterson, A., and Taylor, J. (2019). Industryscale knowledge graphs: Lessons and challenges: Five diverse technology companies show how it＇s done. Queue, 17(2):48–75. Osenga, K. (2011). Shape of things to come: What we can learn from patent claim length. Santa Clara Computer & High Tech. LJ, 28:617. Park, J. S., O’Brien, J., Cai, C. J., Morris, M. R., Liang, P., and Bernstein, M. S. (2023). Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. Petroni, F., Rocktäschel, T., Lewis, P., Bakhtin, A., Wu, Y., Miller, A. H., and Riedel, S. (2019). Language models as knowledge bases? arXiv preprint arXiv:1909.01066. Ram, O., Levine, Y., Dalmedigos, I., Muhlgay, D., Shashua, A., Leyton-Brown, K., and Shoham, Y. (2023). In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11:1316–1331. Rehurek, R. and Sojka, P. (2011). Gensim—statistical semantics in python. Retrieved from genism. org. Reimers, N. and Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084. Rendle, S., Freudenthaler, C., Gantner, Z., and Schmidt-Thieme, L. (2012). Bpr: Bayesian personalized ranking from implicit feedback. arXiv preprint arXiv:1205.2618. Reuters, T. (2021). Ai-powered contract analysis. https://legalsolutions.thomsonreuters.co.uk/content/dam/ewp-m/documents/legal-uk/en/pdf/reports /ai-powered-contract-analysis.pdf. Accessed: 2024-10-22. Roberts, A., Raffel, C., and Shazeer, N. (2020). How much knowledge can you pack into the parameters of a language model? arXiv preprint arXiv:2002.08910. Ruan, J., Chen, Y., Zhang, B., Xu, Z., Bao, T., Mao, H., Li, Z., Zeng, X., Zhao, R., et al. (2023). Tptu: Task planning and tool usage of large language model-based ai agents. In NeurIPS 2023 Foundation Models for Decision Making Workshop. Salmerón-Manzano, E. (2021). Legaltech and lawtech: global perspectives, challenges, and opportunities. Laws, 10(2):24. Sanmartin, D. (2024). Kg-rag: Bridging the gap between knowledge and creativity. arXiv preprint arXiv:2405.12035. Shieh, M.-Y. (2013). Introduction to IPR laws. Intellectual Property Office, Ministry of Economic Affairs, 4 edition. Soman, K., Rose, P. W., Morris, J. H., E Akbas, R., Smith, B., Peetoom, B., VilloutaReyes, C., Cerono, G., Shi, Y., Rizk-Jackson, A., et al. (2023). Biomedical knowledge graph-enhanced prompt generation for large language models. arXiv e-prints, pages arXiv–2311. Sreedhar, K. and Chilton, L. (2024). Simulating human strategic behavior: Comparing single and multi-agent llms. arXiv preprint arXiv:2402.08189. Stokman, F. N. and de Vries, P. H. (1988). Structuring knowledge in a graph. In Human-Computer Interaction: Psychonomic Aspects, pages 186–206. Springer. Su, X. and Khoshgoftaar, T. M. (2009). A survey of collaborative filtering techniques. Advances in artificial intelligence, 2009. Suarez, C. A. (2020). Disruptive legal technology, covid-19, and resilience in the profession. SCL Rev., 72:393. The White House (2023). Executive order on the safe, secure, and trustworthy development and use of artificial intelligence. https://www.whitehouse.gov/briefing-room/presidential-actions/2023/10/30/executive-order-on-the-safe-s ecure-and-trustworthy-development-and-use-of-artificial-intellige nce/. Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., ..., and Liu, Q. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288. Truong, Q.-T., Salah, A., and Lauw, H. W. (2021). Bilateral variational autoencoder for collaborative filtering. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pages 292–300. Tu, S. S. (2020). Patenting fast and slow: Examiner and applicant use of prior art. Cardozo Arts & Ent. LJ, 38:391. United States Patent and Trademark Office (2024a). The applicability of existing regulations as to party and practitioner misconduct related to the use of ai. https://www.uspto.gov/sites/default/files/documents/director_guidance_ai_use_legal_proceedings.pdf. United States Patent and Trademark Office (2024b). Guidance on use of artificial intelligence-based tools in practice before the united states patent and trademark office. https://www.federalregister.gov/documents/2024/04/11/2024-076 29/guidance-on-use-of-artificial-intelligence-based-tools-in-pract ice-before-the-united-states-patent. Federal Register, Vol. 89, No. 71, April 11, 2024. United States Patent and Trademark Office (2024c). Inventorship guidance for ai-assisted inventions. https://www.federalregister.gov/documents/2024/02/13/202 4-02623/inventorship-guidance-for-ai-assisted-inventions. United States Patent and Trademark Office (2025). Uspto announces new artificial intelligence strategy to empower responsible implementation of innovation. https://www.uspto.gov/subscription-center/2025/uspto-announces-new-artificial-intelligence-strategy-empower-responsible. Press Release 25-02. U.S. Copyright Office (2025). Copyright and artificial intelligence, part 2: Copyrightability. Technical report, U.S. Copyright Office. A Report of the Register of Copyrights. Van Zeebroeck, N. (2011). The puzzle of patent value indicators. Economics of innovation and new technology, 20(1):33–62. Vayansky, I. and Kumar, S. A. (2020). A review of topic modeling methods. Information Systems, 94:101582. Von Nordenflycht, A. (2010). What is a professional service firm? toward a theory and taxonomy of knowledge-intensive firms. Academy of management Review, 35(1):155– 174. Wang, S., Huang, C., Li, J., Yuan, Y., and Wang, F.-Y. (2019). Decentralized construction of knowledge graphs for deep recommender systems based on blockchain-powered smart contracts. IEEE Access, 7:136951–136961. Wernikoff, D. (2020). Create documents easily with free templates, drafted by attorneys. https://www.legalzoom.com/templates. Accessed: 01-17-2024. Wu, J., Zhu, J., and Qi, Y. (2024). Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation. arXiv preprint arXiv:2408.04187. Wu, L., He, X., Wang, X., Zhang, K., and Wang, M. (2021). A survey on neural recommendation: From collaborative filtering to content and context enriched recommendation. arXiv preprint arXiv:2104.13030. Xu, S., Pang, L., Yu, M., Meng, F., Shen, H., Cheng, X., and Zhou, J. (2024). Unsupervised information refinement training of large language models for retrieval-augmented generation. arXiv preprint arXiv:2402.18150. Yao, L., Peng, J., Mao, C., and Luo, Y. (2023). Exploring large language models for knowledge graph completion. arXiv preprint arXiv:2308.13916. Zamini, M., Reza, H., and Rabiei, M. (2022). A review of knowledge graph completion. Information, 13(8):396. Zhao, P., Jin, Z., and Cheng, N. (2023). An in-depth survey of large language model-based artificial intelligence agents. arXiv preprint arXiv:2309.14365. 項潔 (2017). 檔案與數位人文：數位人文視野下的檔案系統. 國史研究通訊, 13:161. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97807 | - |
| dc.description.abstract | 在美國專利申請過程（U.S. Patent Prosecution）中，對於審查階段所收到的官方審查意見通知書（Office Action, OA）進行及時且有效的答辯（OA-Response）是成功取得專利的關鍵。然而，由於答辯資料取得不易，使得過去在自動化和 AI 領域難以進行深入研究。為了補足該差距，我們引入了審查意見通知書答辯智能系統（Patent Office Action Response Intelligence System, PARIS）及其進階版本——利用大型語言模型強化的 PARIS 系統（Large Language Model （LLM）Enhanced PARIS, LE-PARIS）和 PARIS 與代理式檢索增強生成（PARIS with Agentic RAG Optimization, PARIS-PRO），以提高 OA 答辯的效率。系統的關鍵功能包括建立 OA 主題資料庫（OA Topics Database）、開發答辯模板（Response Templates）和推薦系統（Recommender Systems）以及基於 LLM 的答辯生成（LLM-based Response Generation）。為了證明系統的有效性，我們對 OA 資料和基於過去使用者與系統互動的縱向數據進行研究分析。透過七項分析，我們檢驗了 OA 主題的分類（分析 1 和 2）；為 OA 答辯所設計的推薦系統有效性（分析 3）；生成答辯的質量（分析 4）；以及透過使用者研究探討系統在現實世界場景中的實際價值（分析 5）；PRO 及其結果比較（分析 6）；三個系統質性研究（分析 7）。結果表明，系統在關鍵性能指標上對提升使用者的效率，產生了正面影響。本研究所提出的系統架構，亦可作為醫療、法律等其他高度專業領域應用 AI 與人機協作時的參考。 | zh_TW |
| dc.description.abstract | In U.S.patent prosecution, a timely and effective response to Office Actions (OAs) is essential for securing patent rights. Despite the critical nature of this process, previous research on automation and artificial intelligence (AI) has largely overlooked this domain. To bridge this gap, we introduce the Patent Office Action Response Intelligence System (PARIS) and its advanced iterations: the Large Language Model (LLM) Enhanced PARIS (LE-PARIS) and PARIS with Agentic RAG Optimization (PARIS-PRO). These systems are designed to augment the efficiency of patent attorneys by leveraging AI-assisted collaboration. Key components include the development of an OA Topics Database, the creation of response templates, the integration of recommender systems with LLM-based response generation, and the utilization of Agentic AI framework.
To evaluate the effectiveness of our approach, we conducted a comprehensive analysis using the USPTO Office Action database, supplemented by six years of longitudinal data from attorney interactions with our systems. Our investigation comprised seven studies: the first two assessed the constructiveness of OA topics using topic modeling and a Delphi process; the third evaluated the performance of our hybrid LLM-based recommender system specifically tailored for OA responses; the fourth examined the quality of the generated responses; the fifth explored the practical utility of the systems in real-world scenarios through user studies; the sixth examined the performance outcomes of PARIS-PRO；and the seventh qualitative research on three systems. The results demonstrate a significant positive impact on key performance indicators, underscoring the potential of AI-driven solutions in enhancing the patent prosecution process. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-17T16:05:27Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-17T16:05:27Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
致謝 iii 摘要 v Abstract vii 目次 ix 圖次 xiii 表次 xv 第一章 緒論 1 第二章 文獻回顧 7 2.1 專利申請流程與自動化技術 . . . . . . . . . . . . . . . . . . . . . . 7 2.1.1 專利申請流程概述 . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.1.2 專利答辯性質及其自動化需求 . . . . . . . . . . . . . . . . . . . 8 2.1.3 自動化技術在專利答辯中的應用機會 . . . . . . . . . . . . . . . 11 2.2 數位人文與法律自動化的融合 . . . . . . . . . . . . . . . . . . . . . 14 2.2.1 數位人文研究過程 . . . . . . . . . . . . . . . . . . . . . . . . . . 14 2.2.2 數位人文研究過程在專利答辯中的具體應用 . . . . . . . . . . . 15 2.3 法律自動化的歷史演進 . . . . . . . . . . . . . . . . . . . . . . . . . 16 2.3.1 法律自動化的背景和需求 . . . . . . . . . . . . . . . . . . . . . . 16 2.3.2 早期法律自動化技術（1980-2010） . . . . . . . . . . . . . . . . 17 2.3.3 法律科技的崛起（2010-2020） . . . . . . . . . . . . . . . . . . . 18 2.3.4 生成式 AI 時代的法律自動化（2023 至今） . . . . . . . . . . . 19 2.3.5 代理式人工智慧（Agentic AI） . . . . . . . . . . . . . . . . . . . 20 2.3.6 知識圖譜（Knowledge Graph, KG） . . . . . . . . . . . . . . . . 21 2.3.7 檢索增強生成（Retrieval-Augmented Generation, RAG） . . . . . 24 2.4 專利申請和答辯中的法律與倫理考量 . . . . . . . . . . . . . . . . . 26 第三章 三階段系統架構 33 3.1 第一階段系統架構 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 3.1.1 背景介紹 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 3.1.2 系統概覽 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37 3.2 第二階段系統架構 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 3.2.1 背景介紹 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 3.2.2 系統概覽 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 3.3 第三階段系統架構 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 3.3.1 背景介紹 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44 3.3.2 系統概覽 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 第四章 實驗與分析 57 4.1 分析 1：主題建模（Topic Modeling） . . . . . . . . . . . . . . . . . 58 4.1.1 資料來源 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58 4.1.2 資料預處理 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59 4.1.3 潛在狄利克雷分配模型（Latent Dirichlet Allocation, LDA） . . . 59 4.1.4 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60 4.2 分析 2：專家共識（Panel Consensus） . . . . . . . . . . . . . . . . 62 4.2.1 參與者和測量指標 . . . . . . . . . . . . . . . . . . . . . . . . . . 62 4.2.2 收斂式德爾菲方法（Convergent Delphi Process, CDP） . . . . . 63 4.2.3 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64 4.3 分析 3：推薦系統（Recommender System） . . . . . . . . . . . . . 65 4.3.1 混合推薦系統 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65 4.3.2 實驗設置 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 67 4.3.3 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68 4.4 分析 4：答辯生成（Response Generation） . . . . . . . . . . . . . . 70 4.4.1 方法 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 71 4.4.2 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72 4.5 分析 5：PARIS 與 LE-PARIS 使用者研究 . . . . . . . . . . . . . . . 73 4.5.1 參與者和實驗程序 . . . . . . . . . . . . . . . . . . . . . . . . . . 73 4.5.2 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74 4.6 分析 6：PARIS-PRO 效能研究 . . . . . . . . . . . . . . . . . . . . . 77 4.6.1 不忠實性錯誤 (Unfaithfulness Error) 分類 . . . . . . . . . . . . . 77 4.6.1.1 內在實體錯誤（Intrinsic Entity Error, IN） . . . . . . 78 4.6.1.2 外在實體錯誤（Extrinsic Entity Error, EN） . . . . . 79 4.6.1.3 內在事件錯誤（Intrinsic Event Error, IV） . . . . . . 79 4.6.1.4 外在事件錯誤（Extrinsic Event Error, EV） . . . . . 79 4.6.1.5 推理連貫性錯誤（Reasoning Coherence Error, RC） 79 4.6.1.6 無關證據錯誤（Irrelevant Evidence Error, IE） . . . . 80 4.6.2 實驗設置 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80 4.6.3 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81 4.7 分析 7：三系統的質性研究 . . . . . . . . . . . . . . . . . . . . . . . 81 4.7.1 參與者和實驗程序 . . . . . . . . . . . . . . . . . . . . . . . . . . 81 4.7.2 結果 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83 4.7.2.1 使用經驗與頻率 . . . . . . . . . . . . . . . . . . . . 83 4.7.2.2 效率與生產力 . . . . . . . . . . . . . . . . . . . . . . 84 4.7.2.3 使用體驗與滿意度 . . . . . . . . . . . . . . . . . . . 85 4.7.2.4 信任度與可靠性 . . . . . . . . . . . . . . . . . . . . 86 4.7.2.5 人機互動 . . . . . . . . . . . . . . . . . . . . . . . . 87 4.7.2.6 未來期望 . . . . . . . . . . . . . . . . . . . . . . . . 88 第五章 討論和未來方向 91 5.1 結果討論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 91 5.2 理論貢獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 93 5.3 實務貢獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95 5.4 研究限制與未來方向 . . . . . . . . . . . . . . . . . . . . . . . . . . 97 第六章 結論 101 參考文獻 103 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 專利答辯 | zh_TW |
| dc.subject | AI代理 | zh_TW |
| dc.subject | 使用者研究 | zh_TW |
| dc.subject | 大型語言模型 | zh_TW |
| dc.subject | 推薦系統 | zh_TW |
| dc.subject | 專利申請 | zh_TW |
| dc.subject | Large Language Model (LLM) | en |
| dc.subject | Recommender System | en |
| dc.subject | OA-Response | en |
| dc.subject | Patent Prosecution | en |
| dc.subject | Agentic AI | en |
| dc.subject | User Study | en |
| dc.title | 自動化專利答辯：大語言模型的應用 | zh_TW |
| dc.title | Automating Patent Response: An Application of Large Language Models | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 博士 | - |
| dc.contributor.oralexamcommittee | 謝銘洋;張智星;陳文進;李宏毅;王文杰;劉昭麟 | zh_TW |
| dc.contributor.oralexamcommittee | Ming-Yan Shieh;JS Jang;WC Chen;Hung-yi Lee;Wen-Chieh Wang;Chao-Lin Liu | en |
| dc.subject.keyword | 專利申請,專利答辯,推薦系統,大型語言模型,使用者研究,AI代理, | zh_TW |
| dc.subject.keyword | Patent Prosecution,OA-Response,Recommender System,Large Language Model (LLM),User Study,Agentic AI, | en |
| dc.relation.page | 115 | - |
| dc.identifier.doi | 10.6342/NTU202501160 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-07-04 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 資訊網路與多媒體研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 未授權公開取用 | 12.42 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。