臺灣博碩士論文加值系統

近年來，商標侵權問題已經引起了公眾的關注。商標在商業中有著重要的作用，不但代表公司的品牌形象，也展示其產品的商業價值。然而，關於商標侵權的爭議層出不窮，不道德的商人仿造並使用類似的著名商標，吸引消費者的關注以獲取不當利潤。因此，越來越多商標所有權者提起訴訟來捍衛自己的權益。面對繁雜的訴訟準備過程，蒐集訴訟相關的前案是最耗費時間也難以省略的步驟之一。為了提高搜索和閱讀商標判決的時間和效率，本研究提出以知識本體為基之商標侵權判例電腦輔助推薦系統，將判決文件知識結構化，推薦並提供使用者作為前案蒐集之參考依據。本研究首先以法律上案件摘要(Case Brief)的觀點建構商標侵權知識本體，將本體知識分為五個類別，包含基本資料、案件背景、爭點、法條、裁決，並以美國地方法院及聯邦法院之商標侵權判例為分析文本，針對非結構化的文字資料定義相應的規則，利用自然語言處理提取判例的關鍵特徵，構建商標侵權判決領域的知識本體資料庫。最後透過主題模型(Topic Model)分析判例文本，分群並定義判例的內容主題，對應法律爭點和分類主題之集群，比對判例之間的相似性，提供最符合法律閱讀角度的前案推薦結果。

A registered trademark (TM) distinctively represents a company and the products or services the company sells. TM is a form of intellectual property (IP) legally protected by the IP laws in the country where it is officially registered. Thus, TM related legal cases have grown rapidly due to the exponential growth of globally registered TMs. In this paper, an intelligent decision support system automatically discovers similar TM related legal judgments for any given seed case, is developed to support legal research. This study constructs the semantic network (i.e., an ontology schema) representing TM legal scope and terminologies. In the research, 3580 US trademark infringement cases litigated in the US district and federal court are collected as our experimental corpus. The system extracts critical features of each legal document, in compliance with the TM legal semantic ontology schema. The system can identify matching precedents according to the critical features (representing these legal briefs), e.g., case facts, TM-related issues under disputes, judgment holdings, and applicable laws. Text mining and topic modeling techniques (LDA, DTM) are deployed to discover relevant precedents. The objective is to assist users in searching the most relevant cases in terms of different corresponding rules and laws in those litigation documents. Through the analysis of the similarity between the issues and the topics, the system can provide relevant precedents based on the reasonable legal opinion.

摘要 I
Abstract II
Table of Contents III
List of Figures V
List of Tables VI
1. Introduction 1
1.1 Research Background 1
1.2 Research Purpose 4
1.3 Research Framework and Procedure 5
2. Literature Review 7
2.1 Trademark 7
2.1.1 US Trademark Protection 8
2.1.2 US Trademark Litigation 9
2.1.3 US Statutory Trademark Law 11
2.2 E-Discovery 12
2.3 Ontology 14
2.3.1 Frame-based Ontology Knowledge Representation 15
2.3.2 The Application of Ontology 16
2.4 Information Retrieval and Recommender Systems 17
2.4.1 Information Retrieval 18
2.4.2 Recommender System 18
2.5 Text Mining 18
2.5.1 Topic Modeling 24
2.5.2 Word Embeddings 28
3. Methodology 30
3.1 Knowledge Ontology Construction 31
3.1.1 Trademark Litigation Judgment Ontology 31
3.1.2 Frame-Based Ontology Construction 36
3.1.3 “Case Brief” Feature Extraction 38
3.2 Issue Identification 40
3.2.1 System Programming Implementation 42
3.3 Similarity Calculation 42
4. Case Study 45
4.1 Seed judgments 45
4.2 Identify Precedents in Matching Issues and Their Key Terms 46
4.3 Topic modeling of seed judgments and precedent judgments 48
4.4 Matching precedents 55
4.5 Trademark case examples 56
4.6 Verification 63
5. Conclusion 67
References 69

[1] Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E. D., Gutierrez, J. B., & Kochut, K., “A brief survey of text mining: Classification, clustering and extraction techniques”, arXiv preprint arXiv:1707.02919, 2017.
[2] Balabanović, M., “An adaptive web page recommendation service”, In: Proceedings of the first international conference on Autonomous agents, 1997.
[3] Beebe, B., “Trademark Law: An Open-Source Casebook”, Available at: http://tmcasebook.org/wp-content/uploads/2019/07/BeebeTMLaw-6.0-Full-Book.pdf, 2019.
[4] Bellogín, A., & Said, A., “Information Retrieval and Recommender Systems”, In: Data Science in Practice, Springer, pp. 79-96, 2018.
[5] Belt, W. W., Kiker, D. R., & Shetterly, D. E., “Technology-Assisted Document Review: Is It Defensible?”, 18 Rich. J.L. & TECH. 10, 2012.
[6] Bengio, Y., Ducharme, R., Vincent, P., & Jauvin, C., “A neural probabilistic language model”, Journal of machine learning research, pp. 1137-1155, 2003.
[7] Blei, D. M., & Lafferty, J. D., “Dynamic topic models”, In: Proceedings of the 23rd international conference on Machine learning, pp. 113-120, 2006.
[8] Blei, D. M., Ng, A. Y., & Jordan, M. I., “Latent dirichlet allocation”, Journal of machine Learning research, 3, pp. 993-1022, 2003.
[9] Bouchoux, D. E., “Intellectual Property: The Law of Trademarks, Copyrights, Patents, and Trade Secrets”, Cengage Learning, 2012.
[10] Burk, D. L., “Algorithmic Fair Use”, 86 U. Chi. L. Rev. 283, 2019.
[11] Calo, R., “Robots as Legal Metaphors”, Harvard Journal of Law and Technology, 30, pp. 209-237, 2016.
[12] Chandrasekaran, B., Josephson, J. R., & Benjamins, V. R., “What Are Ontologies, and Why Do We Need Them,” IEEE Intelligent Systems, 14 (1), pp. 20-26, 1999.
[13] Chen, C. H., “Improved TFIDF in big news retrieval: An empirical study”, Pattern Recognition Letters, 93, pp. 113-122, 2017.
[14] Chen, Y. L., Liu, Y. H., & Ho, W. L., “A Text Mining Approach to Assist the General Public in the Retrieval of Legal Documents”, Journal of the American Society for Information Science and Technology, 64(2), pp. 280–290, 2013.
[15] Chughtai, G. R., Lee, J., Shahzadi, M., Kabir, A., & Hassan, M. A. S., “An efficient ontology-based topic-specific article recommendation model for best-fit reviewers”, Scientometrics, 122, pp. 249–265, 2020.
[16] CompuMark, “The trademark ecosystem”, Available at: https://clarivate.com/compumark/wp-content/uploads/sites/6/dlm_uploads/2020/01/2020-trademark-ecosystem.pdf, 2020.
[17] Conrad, J. G., “E-Discovery revisited: the need for artificial intelligence beyond information retrieval”, Artificial Intelligence and Law, 18, pp. 321-345, 2010.
[18] Cruz, C. M., Porcel, C., Moreno, J. B., & Viedma, E. H., “A model to represent users trust in recommender systems using ontologies and fuzzy linguistic modeling”, Information Sciences, 311, pp.102-118, 2015.
[19] Dabass, J., & Dabass, B. S., “Scope of Artificial Intelligence in Law”, arXiv preprint arXiv: 201806.0474.v1, 2018.
[20] Dai, A. M., Olah, C., & Le, Q. V., “Document Embedding with Paragraph Vectors”, arXiv preprint arXiv:1507.07998, 2015.
[21] Deerwester, S., Dumais, S. T., Furnas, G. W., Landauer, T. K., & Harshman, R., “Indexing by latent semantic analysis”, Journal of the American society for information science, 41(6), pp. 391-407, 1990.
[22] Deng, N., Chen, X., & Li, D., “Intelligent recommendation of Chinese traditional medicine patents supporting new medicine’s R&D”, Journal of Computational and Theoretical Nanoscience, 13(9), pp. 5907-5913, 2016.
[23] Endo, S. K., “Technological Opacity & Procedural Injustice”, 59 B.C. L. Rev. 821, 2018.
[24] Fikes, R., & Kehler, T., “The role of frame-based representation in reasoning”, In Communications of the ACM, 28(9), pp. 904-920, 1985.
[25] Friedl, J. E., Mastering regular expressions, O'Reilly Media, 2006.
[26] Govindarajan, U. H., Trappey, A. J., & Trappey, C. V., “Intelligent collaborative patent mining using excessive topic generation”, Advanced Engineering Informatics, 42, pp.100955, 2019.
[27] Grimmelmann, J., “Regulation by software”, 114 Yale LJ, pp. 1719-1758, 2005.
[28] Gruber, T. R., “A translation approach to portable ontology specifications”, Knowledge acquisition, 5(2), pp.199-220, 1993.
[29] Haggerty, J., “LexisNexis versus Westlaw revisited”, Available at: https://lac-group.com/blog/lexisnexis-versus-westlaw-revisited/, 2018.
[30] Hildebrandt, M., “The meaning and the mining of legal texts”, Understanding Digital Humanities, Palgrave Macmillan, pp. 145-160, 2012.
[31] Hofmann, T., “Probabilistic latent semantic analysis”, In: Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence, pp. 289-296, 1999.
[32] Kant, G., Singh, V. K., Darbari, M., Yagyasen, D., & Shukla, P., “Legal Semantic Web-A Recommendation System”, International Journal of Applied Information Systems (IJAIS), 7, pp. 21-27, 2014.
[33] Kerikmäe, T., Hoffmann, T., & Chochia, A., “Legal technology for law firms: determining roadmaps for innovation”, Croatian International Relations Review, 24 (81), pp. 91-112, 2018.
[34] Lin, K., “Knowledge Representation and Intelligent Recommender System for Trademark Protection and Litigation Analysis”, Master's thesis, National Tsing Hua University, Hsinchu, Taiwan, 2018.
[35] Kuo, M. H., Chen, L. C., & Liang, C. W., “Building and evaluating a location-based service recommendation system with a preference adjustment mechanism”, Expert Systems with Applications, 36(2), pp. 3543-3554, 2009.
[36] Lai, S., Liu, K., He, S., & Zhao, J., ”How to generate a good word embedding”, IEEE Intelligent Systems, 31(6), pp. 5-14, 2016.
[37] Lau, J. H., & Baldwin, T., “An empirical evaluation of doc2vec with practical insights into document embedding generation”, arXiv preprint arXiv:1607.05368, 2016.
[38] Lin, J., “Divergence measures based on the Shannon entropy”, IEEE Transactions on Information theory, 37(1), pp. 145-151, 1991.
[39] Le, Q., & Mikolov, T., “Distributed representations of sentences and documents”, In: Proceedings of the 31th International Conference on Machine Learning, ICML 2014.
[40] Liddy, E. D., “Natural language processing”, 2001.
[41] Li, A. A. S., Trappey, A. J., & Trappey, C. V., “Intelligent Identification of Trademark Case Precedents Using Semantic Ontology”, In:　TE 2020 Conference, 2020 (Accepted).
[42] Li, A. A. S., Trappey, A. J., Trappey, C. V., & Fan, C. Y., “E-discover State-of-the-art Research Trends of Deep Learning for Computer Vision”, In: 2019 IEEE International Conference on Systems, Man, and Cybernetics, Bari, 2019.
[43] Liu, H., Kong, X., & Bai, X., “Context-based collaborative filtering for citation recommendation”, IEEE Access, 3, pp. 1695-1703, 2015.
[44] Lu, Q., & Conrad, J. G., “Bringing Order to Legal Documents: An Issue-based Recommendation System via Cluster Association”, In: International Conference on Knowledge Engineering and Ontology Development, 2012.
[45] Ma, S., Zhang, C. & Liu, X., “A review of citation recommendation: from textual content to enriched context”, Scientometrics, 122, pp. 1445–1472, 2020.
[46] Mandel, R. S., & Schmidt, J. K., “Trade mark litigation in the United States: overview”, Available at: https://uk.practicallaw.thomsonreuters.com/w-009-7807?transitionType=Default&contextData=(sc.Default), 2017.
[47] Mehri, A., Jamaati, M., & Mehri, H., “Word ranking in a single document by Jensen–Shannon divergence”, In Physics Letters A, 379(28-29), pp. 1627-1632, 2015.
[48] Mikolov, T., Chen, K., Corrado, G., & Dean, J., “Efficient estimation of word representations in vector space”, arXiv preprint arXiv:1301.3781, 2013.
[49] Minsky, M., “A framework for representing knowledge”, 1974.
[50] Montaner, M., López, B., & Rosa, J. L. D. L., “A taxonomy of recommender agents on the internet”, Artificial Intelligence Review, 19, pp. 285–330, 2003.
[51] Munir, K., & Anjum, M. S., “The use of ontologies for effective knowledge modelling and information retrieval”, Applied Computing and Informatics, 14(2), pp. 116-126, 2018.
[52] Oard, D. W., & Webber, W., “Information retrieval for e-discovery”, Foundations and Trends® in Information Retrieval, 7(2-3), pp. 99-237, 2013.
[53] Park, D. H., Kim, H. K., Choi, I. Y., & Kim, J. K., “A literature review and classification of recommender systems on academic journals”, Journal of intelligence and information systems, 17(1), pp. 139-152, 2011.
[54] Park, Y., & Yoon, J., “Application technology opportunity discovery from technology portfolios: Use of patent classification and collaborative filtering”, Technological Forecasting and Social Change, 118, pp. 170-183, 2017.
[55] Poelmans, J., Ignatov, D. I., Kuznetsov, S. O., & Dedene, G., “Formal concept analysis in knowledge processing: A survey on applications”, Expert systems with applications, 40(16), pp. 6538-6560, 2013.
[56] Qaiser, S., & Ali, R., “Text mining: use of TF-IDF to examine the relevance of words to documents”, International Journal of Computer Applications, 181(1), pp. 25-29, 2018.
[57] Rashid, P. Q., “Semantic network and frame knowledge representation formalisms in artificial intelligence”, Eastern Mediterranean University (EMU)-Doğu Akdeniz Üniversitesi (DAÜ), 2015.
[58] Ritz, B. L. S., “Will This Dog Hunt?: An Attorney's Guide To Predictive Coding”, 57 S. Tex. L. Rev. 345, 2016.
[59] Robertson, S., “Understanding inverse document frequency: on theoretical arguments for IDF”, Journal of documentation, 60(5), pp. 503-520, 2004.
[60] Robertson, S., & Zaragoza, H. “The probabilistic relevance framework: BM25 and beyond”, Now Publishers Inc, 2009.
[61] Röder, M., Both A., & Hinneburg, A., “Exploring the space of topic coherence measures”, In: Proceedings of the eighth ACM international conference on Web search and data mining, pp. 399-408, 2015.
[62] Rogers, E. S., “The Lanham Act and the Social Function of Trade-Marks”, Law & Contemp. Probs., 14, pp. 173-184, 1949.
[63] Roitblat, H. L., Kershaw, A., & Oot, P., “Document categorization in legal electronic discovery: computer classification vs. manual review”, Journal of the American Society for Information Science and Technology, 61(1), pp. 70-80, 2010.
[64] Russell, S., Dewey, D., & Tegmark, M., “Research priorities for robust and beneficial artificial intelligence”, Ai Magazine, 36(4), pp. 105-114, 2015.
[65] Sanfilippo, E. M., Belkadi, F., Bernard, A., “Ontology-based knowledge representation for additive manufacturing”, Computers in Industry, 109, pp. 182-194, 2019.
[66] Sharma, M., & Mann, S., “A survey of recommender systems: approaches and limitations”, International Journal of Innovations in Engineering and Technology, 2(2), pp. 8-14, 2013.
[67] Shishehchi, S., Banihashem, S. Y., Zin, N. A. M., Noah, S. A. M., & Malaysia, K., “Ontological approach in knowledge based recommender system to develop the quality of e-learning system”, Australian Journal of Basic and Applied Sciences, 6(2), pp. 115-123, 2012.
[68] Staab, S., & Studer, R., “What is an ontology?”, Handbook on ontologies, Springer Science & Business Media, pp. 1-17, 2013.
[69] Studer, R., Benjamins, V. R., & Fensel, D., “Knowledge engineering: principles and methods”, Data & knowledge engineering, 25(1-2), pp. 161-197, 1998.
[70] Surden, H., “Machine Learning and Law”, 89 Wash. L. Rev. 87, pp. 87-115, 2014.
[71] Trappey, C. V., Chang, A. C., & Trappey, A. J. C., “Building an internet based knowledge ontology for trademark protection”, Journal of Global Information Management (JGIM), 2019 (Accepted).
[72] Trappey, A. J. C., Trappey, C. V., & Hsieh, H. I., “Development of a smart patent recommendation system with natural language processing capabilities”, In: Proceedings of the 48th International Conference on Computers and Industrial Engineering (CIE 48), Auckland, New Zealand, Dec. 2-5, 2018.
[73] Trappey, A. J. C., Trappey, C. V., & Lin, B. H., “Identify trademark legal case precedents - Using machine learning to enable semantic analysis of judgments,” World Patent Information, 2020 (Accepted).
[74] Trappey, A. J. C., Trappey, C. V., Wu, C. Y., Fan, C. Y., & Lin, Y. L., “Intelligent patent recommendation system for innovative design collaboration”, Journal of Network and Computer Applications, 36(6), pp. 1441-1450, 2013.
[75] Trstenjak, B., Mikac, S., & Donko, D., “KNN with TF-IDF based framework for text categorization”, Procedia Engineering, 69, pp. 1356-1364, 2014.
[76] World Intellectual Property Organization (WIPO), “Statistical Country Profiles”, Available at: https://www.wipo.int/ipstats/en/statistics/country_profile/profile.jsp?code=US, 2020.
[77] United States Patent and Trademark Office (USPTO), “Basic Facts About Trademarks”, Available at: https://www.uspto.gov/sites/default/files/documents/BasicFacts.pdf, 2020.
[78] Vijayarani, S., Ilamathi, M. J., & Nithya, M., “Preprocessing techniques for text mining-an overview”, International Journal of Computer Science & Communication Networks, 5(1), pp. 7-16, 2015.
[79] Wang, B., Liu, S., Ding, K., Liu, Z., & Xu, J., “Identifying technological topics and institution-topic distribution probability for patent competitive intelligence analysis: a case study in LTE technology”, Scientometrics, 101, pp. 685–704, 2014.
[80] Wang, Q., Du, W., Ma, J., & Liao, X., “Recommendation Mechanism for Patent Trading Empowered by Heterogeneous Information Networks”, International Journal of Electronic Commerce, 23(2), pp. 147-178, 2019.
[81] Weiss, S. M., Indurkhya, N., & Zhang, T., “Information Retrieval and Text Mining”, In: Fundamentals of Predictive Text Mining, Springer, pp.75-90, 2010.
[82] Wheeler, L., The Art of Regular Expressions, 2016.
[83] Yang, S. Y., “Developing an ontology-supported information integration and recommendation system for scholars”, Expert Systems with Applications, 37(10), pp. 7065–7079, 2010.
[84] Zhang, D., Xu, H., Su, Z., & Xu, Y., “Chinese comments sentiment classification based on word2vec and SVMperf”, Expert Systems with Application, 42, pp. 1857-1863, 2014.