日趨增多之網路訊息使得使用者很難快速的從搜尋引擎回傳的大量頁面中找到真正所需內容。具有自然語言處理與理解能力的聊天機器人(chatbot)提供了一個自動問答之媒介，與搜尋引擎不同，它能夠直接回答使用者所需的答案而不是相關的網頁，具有快速高效的優勢。本研究提出了一個以虛擬實境(VR)為基之工程諮詢機器人之系統架構與設計方法，此檢索式聊天機器人(retrieval-based chatbot)蒐集了約1262筆國內外大型機電工程製造商之顧客常問問題(FAQs)與約20個國際標準文件來建構聊天機器人之知識庫，並以維基百科語料庫、相關文獻與工程文件訓練詞向量模型，計算使用者與問答庫問句之相似度來進行資訊檢索以提供適當且完整的回答。此外本研究進一步將聊天機器人與虛擬實境(VR)進行系統整合，結合了自動問答系統與沉浸式科技之高度即時互動性優勢，使得使用者能夠在與系統進行工程諮詢時獲得文字答覆的同時也能與相關產品之三維(3D)模型進行互動。基於提出之系統架構與設計方法本研究建構一電力變壓器製造商提供給顧客之工程諮詢機器人作為系統功能示範，此外也進行問答準確性測試以驗證系統成效與知識庫完整度其結果顯示問答準確度達85 %並與現今常見之語音助理進行比較探討此系統在變壓器工程知識領域之優勢。此系統目的為在虛擬實境環境中提供顧客(例如大型電廠或需大型變壓器之廠商)進行電力變壓器採購作業之相關工程問答諮詢、產出相關的物料清單(BOM)並提供暫定成本資訊，主要虛擬實境系統功能介面著重在呈現電力變壓器及其零組件設計、組合、拆解、客製化等沉浸式互動環境。

Increasing amount of data and information online make it difficult for users to quickly find what they really need from a large number of web pages returned by search engines. A chatbot with natural language processing and understanding capabilities can provide an interface for automatic question answering. Unlike search engines, it can directly provide answer for user instead of related web pages. This research proposes system framework and design of Virtual Reality (VR) enabled engineering consultation chatbot. The proposed retrieval-based chatbot collects about 1,262 FAQs from transformer manufacturers and about 20 international standard files to build a chatbot knowledge base, and Wikipedia corpus and engineering documents are used to train a word embedding model used in information retrieval to calculate the similarity between the user’s question and the questions in the database to provide appropriate answers. The research integrates chatbot with Virtual Reality (VR), combining advantages of them to enable users conduct engineering consultation and interact with 3D models in real time. Based on the proposed system framework and design, the research constructs a consultation chatbot for power transformer manufacturers as an example and conduct test of question answering accuracy to verify the effectiveness of system. The result shows the answering accuracy is about 85% and is compared with other voice assistants to discuss the advantages of the proposed system in the field of transformer engineering knowledge. The system aims to provide real-time engineering consultation, bill of materials (BOM) for cost estimation, and the main system functions focuses on presenting the immersive interactive environment of power transformers and the components design, disassembly / assembly, customization, etc.

中文摘要 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 scope and purpose 2
1.3 Research framework and process 4
2. Literature review 6
2.1 Chatbot 6
2.1.1 The development of chatbots 7
2.1.2 Classification of chatbots based on design techniques 8
2.1.3 Dialogue generation models 11
2.1.4 Patent analysis of chatbot patents 13
2.1.5 User experience 15
2.2 Natural language processing 16
2.3 Virtual Reality 21
2.3.1 VR applications for engineering and manufacturing sectors 24
2.3.2 VR human-machine interface applications 27
3. Methodology 29
3.1 Question answering system 30
3.1.1 Chatbot knowledge base construction 32
3.1.2 Data preprocessing 35
3.1.3 Information retrieval 36
3.2 Cost estimation system 44
3.2.1 Knowledge base 44
3.2.2 Cost estimation process 46
3.3 Virtual Reality environment design 48
3.3.1 3D objects modeling 48
3.3.2 Unity development environment 50
3.3.3 Unity execution environment 54
3.4 Systems integration 56
4. Case study 58
4.1 Power transformers 58
4.1.1 Types of power transformers 60
4.1.2 Main components of power transformers 60
4.1.3 Request for quotation 64
4.1.4 International standards 65
4.2 Question answering system development and verification 66
4.3 VR-enabled consultation system demonstrations 73
4.3.1 Output of cost estimation system 74
4.3.2 Design of 3D models, scenes and interface 75
4.3.3 User interactions 78
5. Conclusions 83
References 84

1. Abdul-Kader, S. A., & Woods, J., “Survey on Chatbot Design Techniques in Speech Conversation Systems,” International Journal of Advanced Computer Science & Applications, 6 (7), pp. 72-80, 2015.
2. Adly, A. A., “Computation of Inrush Current Forces on Transformer Windings,” IEEE Transactions on Magnetics, 37 (4), pp. 2855-2857, 2001.
3. Alvarez, J. E., “A Review of Word Embedding & Document Similarity Algorithms Applied to Academic Text,” University of Freiburg,” 2017.
4. Atoum, I., “Scaled Pearson’s Correlation Coefficient for Evaluating Text Similarity Measures, Modern Applied Science, 13 (10), pp.26-38, 2019.
5. Bamodu, O., & Ye, X., “Virtual Reality & Virtual Reality System Components,” Proceedings of the 2nd International Conference On Systems Engineering & Modeling (ICSEM-13), pp. 1169-1172, 2013.
6. Bengio, Y., Ducharme, R., & Vincent, P., “A Neural Probabilistic Language Model,” Journal of Machine Learning Research, 3, pp. 1137–1155, 2003.
7. Berg, L. P., & Vance, J. M., “Industry Use of Virtual Reality in Product Design & Manufacturing: A Survey,” Virtual Reality, 22 (1), pp. 1-17, 2017.
8. Blume, L. F., Camilli, G., Farnham, S. B., & Peterson, H. A., “Transformer Magnetizing Inrush Currents and Influence on System Operation,” Transactions of the American Institute of Electrical Engineers, 63(6), pp. 366-375, 1944.
9. Bojanowski, P., Grave, E., Joulin, A., & Mikolov, T., “Enriching Word Vectors with Subword Information,” arXiv preprint arXiv:1607.04606, 2016.
10. Bouzianea, A., Bouchihaa, D., Doumib, N., & Malki, M., “Question Answering Systems: Survey & Trends,” Procedia Computer Science, 73, pp. 366-375, 2015.
11. Burdea, G. C., & Coiffet, P., “Virtual Reality Technology 2nd ed,” John Wiley & Sons, New York, 2003.
12. Chang, S. H., Lee, W. L., & Li, R. K., “Manufacturing Bill-of-Material Planning,” Production Planning & Control, 5, pp.437-450, 1997.
13. Chen, H., Liu, X. Yin, D., & Tang, J., “A Survey on Dialogue Systems: Recent Advances & New Frontiers,” ACM SIGKDD Explorations Newsletter, 19 (2), pp. 25-35, 2017.
14. Chowdhury, G., “Natural Language Processing,” Annual Review of Information Science & Technology, 37. pp. 51-89, 2003.
15. Colace, F., De Santo, M., Lombardi, M., Pascale, F., Pietrosanto, A., & Lemma, S., “Chatbot for E-Learning: A Case of Study,” International Journal of Mechanical Engineering & Robotics Research, 7 (5), pp. 528-533, 2018.
16. Colledani, M., & Tolio, T., “A Decomposition Method to Support the Configuration / Reconfiguration of Production Systems,” CIRP Annals, 54(1), pp. 441–444, 2005.
17. Choi, S., Jung, K., & Noh, S. D., “Virtual Reality Applications in Manufacturing Industries: Past Research, Present Findings, & Future Directions,” Concurrent Engineering, 23 (1), pp.1-24, 2015.
18. Coomans, M. K. D., & Timmermans, H. J. P., “A VR-User Interface for Design by Features,” In Proceedings of 4-rd Design & Decision Support Systems in Architecture & Urban Planning Conference, pp. 1-13, 1998.
19. Cui, L., Huang, S., Wei, F., Tan, C., Duan, C., & Zhou, M., “SuperAgent: A Customer Service Chatbot for E-commerce Websites,” Proceedings of ACL System Demonstrations, pp. 97-102, 2017.
20. Dersingh, A., Srisakulpinyo, P., Rakkarn, S., & Boonkanit, P., “Chatbot and Visual Management in Production Process,” ICEIC 2017 International Conference on Electronics, Information, and Communication, pp. 274-277, 2017.
21. Deshpande, A., Shahane, A., Gadre, D., Deshpande, M., & Joshi, P. M., “A Survey of Various Chatbot Implementation Techniques,” International Journal of Computer Engineering & Applications, 11, 2017.
22. Deutsch, David., “The Beginning of Infinity: Explanations That Transform the World,” Penguin Publishing Group, 2011.
23. Dorf, R. C., “Systems, Controls, Embedded Systems, Energy, & Machines,” Taylor & Francis, 2006.
24. Ganguly, D., Roy, D., Mitra, M., & Jones, G., “Word Embedding based Generalized Language Model for Information Retrieval,” The 38th International ACM SIGIR Conference, pp. 795-798, 2015.
25. García-Crespo, Á., Ruiz-Mezcua, B., López-Cuadrado, J. L., & González-Carrasco, I., “A Review of Conventional & Knowledge based Systems for Machining Price Quotation,” Journal of Intelligent Manufacturing, 22(6), pp. 823–841, 2011.
26. Ghannay, S., Favre, B., Esteve, Y., & Camelin, N., “Word Embeddings Evaluation & Combination. Language Resources & Evaluation,” Language Resources & Evaluation, pp. 300-305, 2016.
27. Glina, E. M., & Kang, B. H., “Conversation System with State Information,” Journal of Advanced Computational Intelligence & Intelligent Informatics (JACII), 14 (6), pp. 741-745, 2010.
28. Gorecky, D., Khamis, M., & Mura, K., “Introduction & Establishment of Virtual Training in the Factory of the Future,” International Journal of Computer Integrated Manufacturing, 30(1), pp. 182-190, 2017.
29. Gonzalez-Badillo, G., Medellin-Castillo, H. I., & Lim, T., “Development of a Haptic Virtual Reality System for Assembly Planning & Evaluation,” Procedia Technology, 7, pp. 265-272, 2013.
30. Gorecky, D., Schmitt, M., Loskyll, M., & Zühlke, D., “Human-Machine-Interaction in the Industry 4.0 Era,” 2014 12th IEEE International Conference on Industrial Informatics (INDIN), pp. 289-294, 2014.
31. Grznár, P., Krajčovič, M., Mozol, Š., Schickerle, M., Gabajová, G., & Bučková, M., “Cooperation between Human & Agents in Holonic Manufacturing Systems,” CBU International Conference Proceedings, 7, 2019.
32. Hamid, N. S. S., Aziz, F. A., & Azizi, A., “Virtual Reality Applications in Manufacturing System,” 2014 Science & Information Conference, pp. 1034-1037, 2014.
33. Hong, N. J., Govindarajan, U. H., Chang Chien, Y. C., & Trappey, A. J. C., “Comprehensive Technology Function Product Matrix for Intelligent Chatbot Patent Mining,” 2019 IEEE International Conference on Systems, Man, & Cybernetics (SMC), pp. 1344-1348, 2019.
34. Hong, Y. R., “Ontology Based Trademark Protection Consulting Chatbots (Master Thesis),” National Tsing Hua University, 2018.
35. Hussain, S., Sianaki, O. A., & Ababneh, N., “Survey on Conversational Agents/ Chatbots Classification & Design Techniques,” Developments in Primatology: Progress & Prospects, pp. 946–956, 2019.
36. IEEE Std C57.12.00: IEEE Standard for Standard General Requirements for Liquid-Immersed Distribution, Power, and Regulating Transformers, 2006. Retrieved from https://ieeexplore.ieee.org/document/7469278 [Sep 07, 2019].
37. IEEE Std C57.19.00: IEEE General Requirements & Test Procedure for Outdoor Power Apparatus Bushings, 2005. Retrieved from https://ieeexplore.ieee.org/document/1440990 [Sep 07, 2019].
38. IEEE Std C57.12.80: IEEE Standard Terminology for Power & Distribution Transformers, 2010. Retrieved from https://ieeexplore.ieee.org/document/1049144 [Sep 07, 2019].
39. Jamison, D. C., “Structured Query Language (SQL) Fundamentals,” Current Protocols in Bioinformatics, 00(1), 9.2.1–9.2.29, 2003.
40. Joel, O., “Parts of a Power Transformer,” In Owlcation, 2019. Retrieved from https://owlcation.com/stem/Parts-of-a-power-transformer [ Sep 24, 2019].
41. Jurafsky, D., & Martin, J. H., “Dialog Systems & Chatbots,” Speech & Language Processing, 24, pp.1-26, 2018.
42. Kostelník, P., Pisařovic, I., Muroň, M., Dařena, F., & Procházka, D., “Chatbots for Enterprises: Outlook,” Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis, 67(6), pp. 1541-1550, 2019.
43. Kumar, S., Islam, T., & Raina, K. K., "A Moisture-In-Breather Model for Transformer Health Monitoring," 2015 Annual IEEE India Conference (INDICON), pp. 1-5, 2015.
44. Le, Q., & Mikolov, T., “Distributed Representations of Sentences and Documents,” In International Conference on Machine Learning, pp. 1188-1196, 2014.
45. Li, H., & Womer, K., “Optimizing the Supply Chain Configuration for Make-To-Order Manufacturing,” European Journal of Operational Research, 221(1), pp. 118–128, 2011.
46. Lommatzsch, A., & Katins, J., “An Information Retrieval-based Approach for Building Intuitive Chatbots for Large Knowledge Bases,” Learning. Knowledge. Data. Analytics, 2454 (60), pp. 1-10, 2019.
47. López, G., Quesada, L., & Guerrero, L. A., “Alexa vs. Siri vs. Cortana vs. Google Assistant: A Comparison of Speech-Based Natural User Interfaces.,” Advances in Human Factors & Systems Interaction, pp. 241-250, 2018.
48. Manns, M., Fischer, K., Du, H., Slusallek, P., & Alexopoulos, K., “A New Approach to Plan Manual Assembly,” International Journal of Computer Integrated Manufacturing, 31(9), 907-920, 2018.
49. Mehta, A. K., Sharma, R. N., Chauhan, S., & Agnihotri, S. D., "Study & Diagnosis of Power Transformer Bushing Insulation System," 2011 IEEE Pulsed Power Conference, pp. 700-705, 2011.
50. Michaud, L. N., "Observations of a New Chatbot: Drawing Conclusions from Early Interactions with Users," IT Professional, 20 (5), pp. 40-47, 2018.
51. Mikolov, T., Chen, K., Corrado, G., & Dean, J., “Efficient Estimation of Word Representations in Vector Space,” In Proceedings of the International Conference on Learning Representations, pp. 1-12, 2013.
52. Mikolov, T., Sutskever, I., Chen, K., Corrado, G. & Dean, J., “Distributed Representations of Words & Phrases & their Compositionality,” In Advances in Neural Information Processing Systems, 26, pp. 3111–3119, 2013.
53. Mishra, A., & Jain, S. K., “A Survey on Question Answering Systems with Classification,” Journal of King Saud University-Computer & Information Sciences, 28(3), pp. 345-361, 2016.
54. Mohan, R., “The Chatbot Revolution & the Indian HR Professionals,” International Journal of Information & Computing Science, 6 (3), pp. 489-499, 2019.
55. Moubarak, M., “Conversational Marketing in Real Estate,” In Mediem, 2017. Retrieved from https://medium.com/roof-ai/conversational-marketing-in-real-estate-f6dc866e267a [Jun 08, 2020].
56. Mujber, T. S., Szecsi, T., & Hashmi, M. S., “Virtual Reality Applications in Manufacturing Process Simulation,” Journal of Materials Processing Technology, 155, pp.1834–1838, 2004.
57. Mumme, C., Pinkwart, N., & Loll, F., “Design & Implementation of a Virtual Salesclerk,” International Workshop on Intelligent Virtual Agents, pp. 379-385, 2009.
58. Munster, G., & Thompson, W., “Annual Smart Speaker IQ Test,” In Loup Ventures, 2018. Retrieved from https://loupventures.com/annual-smart-speaker-iq-test/ [ Jun 11, 2020].
59. Nandakumar, N., Salehi, B., & Baldwin, T., “A Comparative Study of Embedding Models in Predicting the Compositionality of Multiword Expressions.,” In Proceedings of the Australasian Language Technology Association Workshop, pp. 71-76, 2018.
60. Nee, A. Y. C., & Ong, S. K., “Virtual & Augmented Reality Applications in Manufacturing,” International Federation of Automatic Control (IFAC) Proceedings, 46(9), pp. 15–26, 2013.
61. Peng, G., Wang, G., Liu, W., & Yu, H., “A Desktop Virtual Reality-Based Interactive Modular Fixture Configuration Design System,” Computer-Aided Design, 42(5), pp. 432–444, 2010.
62. Pennington, J., Socher, R., & Manning, C. D., “Glove: Global Vectors for Word Representation,” In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1532–1543, 2014.
63. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L., “Deep Contextualized Word Representations,” arXiv preprint arXiv:1802.05365, 2018.
64. Prerapat, A., Srisakulpinyo, P., Rakkarn, S., & Boonkanit, P., “Chatbot & Visual Management in Production Process,” ICEIC 2017 International Conference on Electronics, Information, & Communication, pp. 274-277, 2017.
65. Ramesh, K., Ravishankaran, S., Joshi, A., & Chandrasekaran, K., “A Survey of Design Techniques for Conversational Agents,” In International Conference on Information, Communication & Computing Technology, pp. 336-350, 2017.
66. Rong, X., “Word2Vec Parameter Learning Explained,” arXiv preprint arXiv:1411.2738, 2014.
67. Rouse, T. O., “Mineral Insulating Oil in Transformers,” IEEE Electrical Insulation Magazine, 14(3), pp. 6-16, 1998.
68. Scott, C., Lundgren, H., & Thompson, P., “Guide to Outsourcing in Supply Chain Management,” Guide to Supply Chain Management, pp. 169–182, 2011.
69. Serban, I. V., Lowe, R., Henderson, P., Charlin, L., & Pineau, J., “A Survey of Available Corpora for Building Data-Driven Dialogue Systems,” arXiv preprint arXiv:1512.05742, 2015.
70. Seth, A., Vance, J. M., & Oliver, J. H., “Virtual Reality for Assembly Methods Prototyping: A Review,” Virtual Reality, 15(1), pp. 5–20, 2010.
71. Sheikh, S., Tiwari, V., & Bansal, S., “Generative Model Chatbot for Human Resource using Deep Learning,” International Conference on Data Science & Engineering (ICDSE), pp. 126-132, 2019.
72. Sheth, A., Yip, H. Y., & Shekarpour, S., "Extending Patient-Chatbot Experience with Internet-of-Things & Background Knowledge: Case Studies with Healthcare Applications," IEEE Intelligent Systems, 34 (4), pp. 24-30, 2019.
73. Shewan, D., “10 of the Most Innovative Chatbots on the Web”, In WordStream, 2020. Retrieved from wordstream.com/blog/ws/2017/10/04/chatbots [ Jun 09, 2020].
74. Skjuve, M., Haugstveit, I. M., Folstad, A., & Br&tzaeg, P. B., “Help! Is My Chatbot Falling into the Uncanny Valley? An Empirical Study of User Experience in Human–Chatbot Interaction,” Human Technology, 15 (1), pp. 30-54, 2019.
75. Stănică, I. C., Dascălu, M. I., Moldoveanu, A., & Moldoveanu, F., “Virtual Reality Training System for Improving Interview Performance,” eLearning & Software for Education, 2, pp. 262-267, 2018.
76. Trappey, A. J. C., Trappey, C. V., & Govindarajan, U. H., “Knowledge Extraction of RfQ Engineering Documents for Smart Manufacturing,” International Conference on Advances in Materials & Processing Technologies, 2019.
77. Turian, J., Ratinov, L. A., & Bengio, Y., “Word Representations: A Simple & General Method for Semi-Supervised Learning,” In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pp. 384-394, 2010.
78. Vinyals, O., & Le, Q., “A Neural Conversational Model,” arXiv preprint arXiv:1506.05869, 2015.
79. Winders, J., “Power Transformers Principles & Applications,” Marcel Dekker, New York, 2002.
80. Wongvasu, N., “Methodologies for Providing Rapid & Effective Response to Request for Quotation (RFQ) of mass customization products,” Northeastern University, Boston, Massachusetts, 2001.
81. Woo, J. H., & Oh, D., “Development of Simulation Framework for Shipbuilding,” International Journal of Computer Integrated Manufacturing, 31(2), pp. 210-227, 2018.
82. Wu, W., Shao, X., & Liu, H., “Automatic Visibility Evaluation Method for Application in Virtual Prototyping Environment,” International Journal of Computer Integrated Manufacturing, 32(10), pp. 960-978, 2019.
83. Wu, Y., Wu, W., Xing, C., Li, Z., & Zhou, M., “Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots,” Computational Linguistics, 45 (1), pp. 163-197, 2016.
84. Li, X., Liao, Q., Yin, X., & Xie, J., “A New On-Load Tap Changing System with Power Electronic Elements for Power Transformers,” In Proceedings. International Conference on Power System Technology, 1, pp. 556-559, 2002.
85. Yang, X., Malak, R. C., Lauer, C., Weidig, C., Hagen, H., Hamann, B., & Kreylos, O., “Manufacturing System Design with Virtual Factory Tools,” International Journal of Computer Integrated Manufacturing, 28(1), pp. 25–40, 2015.
86. Young, S., Schatzmann, J., Weilhammer, K., & Ye, H., “The Hidden Information State Approach to Dialog Management,” Acoustics, Speech, & Signal Processing, 4, pp. 149-152, 2007.
87. Ye, Z., Jia, Z., Yang, Y., Huang, J., & Yin, H., “Research on open domain question answering system,” In Natural Language Processing and Chinese Computing, pp. 527-540, 2015.