研究生: |
鐘珮倫 Pei-Lun Chung |
---|---|
論文名稱: |
基於自然語言處理之深度學習模型建立行動疏濬風險聊天機器人 Natural language processing-based deep learning model to build mobile dredging engineering project risk chatbot |
指導教授: |
周瑞生
Jui-Sheng Chou |
口試委員: |
周瑞生
Jui-Sheng Chou 楊亦東 I-Tung Yang 郭景明 Jing-Ming Guo 曾惠斌 Hui-Ping Tserng |
學位類別: |
碩士 Master |
系所名稱: |
工程學院 - 營建工程系 Department of Civil and Construction Engineering |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 242 |
中文關鍵詞: | 疏濬工程 、風險管理 、知識管理 、文本匹配 、自然語言學習模型 |
外文關鍵詞: | dredging engineering, risk management, knowledge management, text matching, natural language processing model |
相關次數: | 點閱:368 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
疏濬工程為台灣防洪治水之重要水利工程,於執行時常遇自然、人為風險事件,同時相關單位常因資深疏濬人員退休、離職造成知識斷層,加上各河川局所遇風險屬性不同且缺乏經歷分享平台,使得各河局風險實務辦理方法無法相互交流。因此先前研究建立疏濬風險知識庫,即時提供風險預防綜合評估建議及風險事件實務辦理方法,協助全台疏濬人員遇風險進行疏濬決策;然舊有之系統具有實務辦理方法不完全、僅能以專家系統查詢、僅能於電腦前使用,且對於未知風險事件無法給予回應等缺點。爰此,本研究採訪十處河川局疏濬人員,蒐集相關經驗及知識,將原知識庫缺漏之風險事件實務辦理方法蒐集齊全;建立疏濬工程風險知識聊天機器人,其中包含「智慧風險預防決策分析」及「智慧風險檢索」系統。「智慧風險預防決策分析」使用於風險防阻階段,如使用者輸入之風險描述未收錄於風險知識庫內,則以自然語言學習技術建立之轉譯器雙向編碼表述風險分類模型,預測該描述風險子分類與風險影響程度/發生頻率分類;反之,則採用本研究建立之關鍵字搜尋法,輸入問題敘述即可進行風險事件搜索,取得對應之風險預防措施、風險影響程度/發生頻率分類、專案管理知識體系之知識領域範疇,提醒使用者風險發生頻率及影響程度高低、涉及範圍及可能因應對策,並以視覺化方式呈現,提供使用者直觀的綜合評估結果。「智慧風險檢索」則使用於風險事件發生後,運用本研究建立之關鍵字搜索及專家系統進行搜索,連結至全台相關疏濬風險事件實務辦理方法,協助進行該項疏濬風險因應決策。本研究為使疏濬工程人員面臨風險時能有一套即時評判及辦理依據進行疏濬風險回應。該風險管理系統建構於LINE通訊軟體平台上,以友善之聊天機器人介面呈現「智慧風險預防決策分析」及「智慧風險檢索」功能,研究成果預期作為疏濬工程單位經驗知識傳承及分享的決策輔助工具。
The dredging project is a significant water conservancy project for flood control in Taiwan. However, the implementation of dredging projects has three main difficulties. These are diverse natural and man-made risk events; the knowledge gaps caused by the retirement or resignation of senior dredgers, and the lack of experience sharing platforms preventing effective problem resolution. To solve these problems, the previous research established a dredging project risk knowledge base. This knowledge base not only provides comprehensive risk prevention assessment recommendations and the practical solutions for risk events, but also assists dredging personnel in Taiwan to make dredging decisions when encountering risks. However, the existing system has several shortcomings, including incomplete solution management methods, querying by expert system only, operation by computer only, and lack of response to unknown risk events.
Therefore, this study adopts the following methods to overcome the shortcomings of the previous system. First, this work collects the experience and knowledge of the dredging engineering personnel by interviewing ten River Management Offices, and collects practical solutions for risk events that are missing from the original knowledge base. This investigation also establishes a smart risk search system that includes a text matching method. The user can search related dredging risk prevention proposals in Taiwan by typing keywords. Second, this study establishes a smart risk prevention decision analysis system for unknown risk events. This system generates risk impact–frequency analysis maps and risk responses from keywords typed into a natural language processing risk classification model to assist the dredging personnel in the preliminary risk analysis of the unknown risks.
Finally, this study applies the proposed system to establish a dredging project risk knowledge map with LINE, the most popular communication software in Taiwan. Dredging project risk knowledge map enables relevant personnel to consult information on dredging project risk prevention programs and risk response measures at any time and place. This research will hopefully simplify the implementation of dredging projects, and reduce the possibility of risk.
[1] S. Durst, C. Hinteregger, and M. Zieba, "The linkage between knowledge risk management and organizational performance," Journal of Business Research, vol. 105, pp. 1-10, 2019/12/01/ 2019.
[2] 邱瀅蓁, "河川疏濬工程風險辨識暨知識管理系統設計與開發," 營建工程系, 225, 2019.
[3] A. E. L. Hadi, Y. Madani, R. E. L. Ayachi, and M. Erritali, "A new semantic similarity approach for improving the results of an Arabic search engine," Procedia Computer Science, vol. 151, pp. 1170-1175, 2019/01/01/ 2019.
[4] W. Cavnar and J. Trenkle, "N-Gram-Based Text Categorization," Proceedings of the Third Annual Symposium on Document Analysis and Information Retrieval, 05/02 2001.
[5] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. 2018.
[6] Y. Sun et al., ERNIE: Enhanced Representation through Knowledge Integration. 2019.
[7] C. Sun, L. Huang, and X. J. a. p. a. Qiu, "Utilizing bert for aspect-based sentiment analysis via constructing auxiliary sentence," 2019.
[8] Y. Song, J. Wang, T. Jiang, Z. Liu, and Y. J. a. p. a. Rao, "Attentional encoder network for targeted sentiment classification," 2019.
[9] I. Mahamid, "Risk matrix for factors affecting time delay in road construction projects: owners' perspective," Engineering, Construction and Architectural Management, vol. 18, no. 6, pp. 609-617, 2011.
[10] E. Ikonomakis, S. Kotsiantis, and V. Tampakas, "Text Classification Using Machine Learning Techniques," WSEAS transactions on computers, vol. 4, pp. 966-974, 08/01 2005.
[11] C. Liu and X. Wang, "Quality-related English Text Classification Based on Recurrent Neural Network," Journal of Visual Communication and Image Representation, p. 102724, 2019/11/25/ 2019.
[12] A. J. P. Tixier, M. R. Hallowell, B. Rajagopalan, and D. Bowman, "Automated content analysis for construction safety: A natural language processing system to extract precursors and outcomes from unstructured injury reports," Automation in Construction, vol. 62, pp. 45-56, 2016/02/01/ 2016.
[13] A. J. P. Tixier, M. R. Hallowell, B. Rajagopalan, and D. Bowman, "Application of machine learning to construction injury prediction," Automation in Construction, vol. 69, pp. 102-114, 2016/09/01/ 2016.
[14] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[15] K. Cho et al., "Learning phrase representations using RNN encoder-decoder for statistical machine translation," 2014.
[16] S. Roca, J. Sancho, J. García, and Á. Alesanco, "Microservice chatbot architecture for chronic patient support," Journal of Biomedical Informatics, vol. 102, p. 103305, 2020/02/01/ 2020.
[17] J. Beaudry, A. Consigli, C. Clark, and K. J. Robinson, "Getting Ready for Adult Healthcare: Designing a Chatbot to Coach Adolescents with Special Health Needs Through the Transitions of Care," Journal of Pediatric Nursing, vol. 49, pp. 85-91, 2019/11/01/ 2019.
[18] A. Piau, R. Crissey, D. Brechemier, L. Balardy, and F. Nourhashemi, "A smartphone Chatbot application to optimize monitoring of older patients with cancer," International Journal of Medical Informatics, vol. 128, pp. 18-23, 2019/08/01/ 2019.
[19] B. Kidwai and N. Rk, "Design and Development of Diagnostic Chabot for supporting Primary Health Care Systems," Procedia Computer Science, vol. 167, pp. 75-84, 2020/01/01/ 2020.
[20] H.-Y. Chan and M.-H. Tsai, "Question-answering dialogue system for emergency operations," International Journal of Disaster Risk Reduction, vol. 41, p. 101313, 2019/12/01/ 2019.
[21] Y. Sermet and I. Demir, "An intelligent system on knowledge generation and communication about flooding," Environmental Modelling & Software, vol. 108, pp. 51-60, 2018/10/01/ 2018.
[22] D. Doherty and K. Curran, "Chatbots for online banking services," in Web Intelligence, no. Preprint, pp. 1-16: IOS Press.
[23] M. Nuruzzaman and O. K. Hussain, "IntelliBot: A Dialogue-based chatbot for the insurance industry," Knowledge-Based Systems, vol. 196, p. 105810, 2020/05/21/ 2020.
[24] M. Casillo, F. Clarizia, G. D'Aniello, M. De Santo, M. Lombardi, and D. Santaniello, "CHAT-Bot: A cultural heritage aware teller-bot for supporting touristic experiences," Pattern Recognition Letters, vol. 131, pp. 234-243, 2020/03/01/ 2020.
[25] G. McLean and K. Osei-Frimpong, "Chat now… Examining the variables influencing the use of online live chat," Technological Forecasting and Social Change, vol. 146, pp. 55-67, 2019/09/01/ 2019.
[26] K. Reinecke et al., "Predicting users' first impressions of website aesthetics with a quantification of perceived visual complexity and colorfulness," in Proceedings of the SIGCHI conference on human factors in computing systems, 2013, pp. 2049-2058.
[27] J. Martin, G. Mortimer, L. J. J. o. r. Andrews, and c. services, "Re-examining online customer experience to include purchase frequency and perceived risk," vol. 25, pp. 81-95, 2015.
[28] C. Chakrabarti and G. F. Luger, "Artificial conversations for customer service chatter bots: Architecture, algorithms, and evaluation metrics," Expert Systems with Applications, vol. 42, no. 20, pp. 6878-6897, 2015/11/15/ 2015.
[29] R. Agarwal and E. J. M. q. Karahanna, "Time flies when you're having fun: Cognitive absorption and beliefs about information technology usage," pp. 665-694, 2000.
[30] M. Maybury, "Natural Language Processing: System Evaluation," in Encyclopedia of Language & Linguistics (Second Edition), K. Brown, Ed. Oxford: Elsevier, 2006, pp. 518-523.
[31] V. Chattaraman, W.-S. Kwon, and J. E. J. C. i. H. B. Gilbert, "Virtual agents in retail web sites: Benefits of simulated social interaction for older users," vol. 28, no. 6, pp. 2055-2066, 2012.
[32] G. J. J. M. I. McLean and Planning, "Investigating the online customer experience–a B2B perspective," 2017.
[33] X. Guo, K. C. Ling, and M. J. A. S. S. Liu, "Evaluating factors influencing consumer satisfaction towards online shopping in China," vol. 8, no. 13, p. 40, 2012.
[34] S. Mallios and N. Bourbakis, "A survey on human machine dialogue systems," in 2016 7th International Conference on Information, Intelligence, Systems & Applications (IISA), 2016, pp. 1-7.
[35] S. Pei et al., "Wind speed prediction method based on Empirical Wavelet Transform and New Cell Update Long Short-Term Memory network," Energy Conversion and Management, vol. 196, pp. 779-792, 2019/09/15/ 2019.
[36] T. Mikolov, I. Sutskever, K. Chen, G. s. Corrado, and J. Dean, "Distributed Representations of Words and Phrases and their Compositionality," Advances in Neural Information Processing Systems, vol. 26, 10/16 2013.
[37] T. Mikolov, K. Chen, G. s. Corrado, and J. Dean, "Efficient Estimation of Word Representations in Vector Space," Proceedings of Workshop at ICLR, vol. 2013, 01/16 2013.
[38] X. Rong, "word2vec Parameter Learning Explained," 11/11 2014.
[39] A. Vaswani et al., "Attention Is All You Need," 06/12 2017.