研究生: |
高紫瑄 Tzu-Hsuan Kao |
---|---|
論文名稱: |
生成式聊天機器人於古物交易客服系統之應用 The usage of generative model chatbot in antiquities trading customer service system |
指導教授: |
陳正綱
Cheng-Kang Chen |
口試委員: |
賴源正
Yuan-Cheng Lai 查士朝 Shi-cho Cha |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 中文 |
論文頁數: | 61 |
中文關鍵詞: | 聊天機器人 、自然語言處理 、樣板式模型 、檢索式模型 、生成式模型 、對話式商務 |
外文關鍵詞: | Chatbot, Natural Language Processing, Rule-based model, Retrieval-based model, Generative model, Conversational Commerce |
相關次數: | 點閱:525 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 |
有鑒於近年來行動裝置的發展,使通訊軟體的使用率逐漸提升。聊天機器人也帶動了對話式商務的熱潮。過去有不少以任務導向的聊天機器人為顧客服務,而這些聊天機器人大多是屬於樣板式模型的架構,使用者只能詢問特定的問題,系統從資料庫抓取答案回覆給使用者,使用者得到的回應都是制式化的回答,且因架構缺少靈活度,使用者常會有得不到聊天機器人回應的結果。檢索式模型雖能在資料庫找到較適合答案輸出給使用者,但因答案也需事先存於資料庫中,透過相似度計算來尋找關鍵字進行配對,無法針對上下文進行分析,因此結果也可能導致答案配對不理想。
本研究將對聊天機器人的技術進行探討,以古物領域聊天機器人為主,建置以基於生成式模型的聊天機器人,使聊天機器人能針對整句話的上下文進行分析自動生成回覆解決此問題,解決聊天機器人無法滿足特定族群需求的問題。運用第三方對話資料集與本文所建立的古物領域資料集,將這些資料進行自然語言處理,文本轉換成向量進行模型訓練,透過模型評估指標證明生成式模型分數較檢索式模型高。本研究設計之聊天機器人流程能確保使用者在詢問古物領域專業問題時,得到最相關的回覆。
In recent years, the development of mobile devices has gradually increased the use of communication software. Chatbots have also driven the development of conversational commerce. In the past, there were a lot of task-oriented chatbots doing customer service. Most of these chatbots belong to the rule-based model. Users can only ask some specific questions, so the system will match the answer which were already created in databased, and then reply to the user. The response that the user received is all standardized answer. Also, because of the system architecture lacks flexibility, users often fail to get their response from the chatbot. Although the retrieval model can find a more suitable answer in the database, but the answer also needs to be stored in the database in advance, through similarity calculation to find keywords to match, it is impossible to analyze the context, so the answer matching is not ideal.
This thesis will discuss the technology of chatbots, mainly in the field of antiquities. Build a chatbot based on a generative model, so that the chatbot can analyze the context of the whole sentence and automatically generate a reply to solve this problem. Using the third-party dialogue dataset and the antiquities field dataset created in this article. These data are processed in natural language, and the text is converted into vectors for model training. The model evaluation proves that the score of generative model is higher than retrieval model. The chatbot process designed in this paper can ensure that users get the most relevant answers when they ask professional questions in the field of antiquities.
英文文獻
1. Bhriguraj Borah, Dhrubajyoti Pathak, Priyankoo Sarmah, Bidisha Som, and Sukumar Nandi. (2019). Survey of Textbased Chatbot in Perspective of Recent Technologies. Communications in Computer and Information Science book series. 1031, 84-96.
2. Bingquan Liu, Zhen Xu, Chengjie Sun, Baoxun Wang, Xiaolong Wang, Derek F. Wong, and Min Zhang. (2017). Content-Oriented User Modeling for Personalized Response Ranking in Chatbots. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 26, 122-133.
3. Chris Camps. (2017). How six retailers are using chatbots to boost customer engagement. Retrieved from https://www.clickz.com
4. Dijana R. Vukovic and Igor M. Dujlovic. (2016). Facebook messenger bots and their application for business. 24th Telecommunications Forum (TELFOR).
5. Hiroshi Honda and Masafumi Hagiwara. (2019). Question Answering Systems With Deep Learning-Based Symbolic Processing. IEEE Access. 7, 152368-152378.
6. J. L. Elman, "Distributed representations, simple recurrent networks, and grammatical structure," Machine learning. vol. 7, no. 2-3, pp. 195-225, 1991.
7. JenniferHill, W.Randolph Ford, and Ingrid G.Farreras. (2015). Real conversations with artificial intelligence: A comparison between human–human online conversations and human–chatbot conversations. Computers in Human Behavior. 49, 245-250.
8. Jia-Chen Gu, Zhen-Hua Ling, and Quan Liu. (2019). Utterance-to-Utterance Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots. IEEE/ACM Transactions on Audio, Speech, and Language Processing. 28, 369-379.
9. Kai Yu, Zijian Zhao, Xueyang Wu, Hongtao Lin, and Xuan Liu, "Rich Short Text Conversation Using Semantic-Key-Controlled Sequence Generation. (2018). IEEE/ACM Transactions on Audio, Speech, and Language Processing. 26, 1359-1368.
10. Kulothunkan Palasundram, Nurfadhlina Mohd Sharef, Khairul Azhar Kasmiran, and Azreen Azman. (2020). Enhancements to the Sequence-to-Sequence-Based Natural Answer Generation Models. IEEE Access. 8, 45738 – 45752.
11. Md. Shahriare Satu, Md. Hasnat Parvez, and Shamim-Al-Mamun. (2015). Review of integrated applications with AIML based chatbot. International Conference on Computer and Information Engineering (ICCIE).
12. Ming-Hsiang Su, Chung-Hsien Wu, Kun-Yi Huang, Qian-Bei Hong, and Hsin-Min Wang. (2018). A chatbot using LSTM-based multi-layer embedding for elderly care. International Conference on Orange Technologies (ICOT).
13. Mohammad Nuruzzaman, and Omar Khadeer Hussain. (2018). A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks. IEEE 15th International Conference on e-Business Engineering (ICEBE).
14. Muhammad Yusril Helmi Setyawan, Rolly Maulana Awangga, and Safif Rafi Efendi. (2018). Comparison Of Multinomial Naive Bayes Algorithm And Logistic Regression For Intent Classification In Chatbot, " in International Conference on Applied Engineering (ICAE) .
15. Organik Digital (2019). The Most Important Social Media Marketing Graph For 2020 from https://organikdigital.com.au
16. Panitan Muangkammuen, Narong Intiruk, and Kanda Runapongsa Saikaew. (2018). Automated Thai-FAQ Chatbot using RNN-LSTM. 22nd International Computer Science and Engineering Conference (ICSEC).
17. Rupesh Singh, Manmath Paste, Nirmala Shinde, Harshkumar Patel, and Nitin Mishra,. (2018). Chatbot using TensorFlow for small Businesses. Second International Conference on Inventive Communication and Computational Technologies (ICICCT).
18. Ross Simmonds. (2016). Seven Business Models That Bot Makers Will Have The Opportunity To Leverage & Redefine. Retrieved from chatbotsmagazine.
19. Sathit Prasomphan. (2019). Improvement of Chatbot in Trading System for SMEs by Using Deep Neural Network. IEEE 4th International Conference on Cloud Computing and Big Data Analysis (ICCCBDA).
20. Stefan Kojouharov. (2018). How Businesses are Winning with Chatbots & Ai. Retrieved from https://chatbotslife.com
21. Shafquat Hussain, Omid Ameri Sianaki, and Nedal Ababneh. (2019). A Survey on Conversational Agents/Chatbots Classification and Design Techniques. Intelligent Systems and Computing book series (AISC). 927.
22. Uroš Arsenijevic and Marija Jovic. (2019). Artificial Intelligence Marketing: Chatbots. International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI).
23. Vinod Kumar Shukla and Amit Verma. (2019). Enhancing LMS Experience through AIML Base and Retrieval Base Chatbot using R Language. International Conference on Automation, Computational and Technology Management (ICACTM).
24. Weizenbaum, J. (1966). ELIZA---a computer program for the study of natural language communication between man and machine. Communications of the ACM. 9(1), 36-45.
25. Yoichi Kurachi, Shinji Narukawa, and Hideki Hara. (2018). AI chatbot to realize sophistication of customer contact points," Fujitsu scientific & technical journal. 54(3), 2-8.
中文文獻
1. Amir Shevat(2018)。設計聊天機器人:建立對話式體驗(黃朝秋, 賴薇如,譯)。臺北市:碁峰。
2. Kai Chou Yang(2017)。從零開始的Sequence to Sequence。http://zake7749.github.io/。
3. 王昊奮, 邵浩(2019)。中文自然語言處理實戰:聊天機器人與深度學習整合應用。新北市:博碩。
4. 王浩暢、李斌(2018)。聊天機器人系統研究進展。Computer applications and software,vol.35,no.12。
5. 王雅柔(2019)。聊天機器人結合關懷行為之實踐探討。國立臺灣科技大學資訊管理系碩士論文。台北市。
6. 徐慧雯(2016)。聊天機器人使用意願影響因素之研究。國立臺灣科技大學資訊管理系碩士論文。台北市。
7. 張智淵(2019)。台灣郵票網路拍賣收藏價格影響因素之探討。高苑科技大學經營管理研究所碩士論文。高雄市。
8. 陳彥妤(2018)。探討聊天機器人的信任轉移及對使用者網路再購意圖之影響。國立中山大學資訊管理學系碩士論文。高雄市。
9. 董大偉(2019)。LINE Bot與人工智慧辨識開發實戰。臺北市:碁峰。