臺灣博碩士論文加值系統

經銷商管理系統（Dealer Management System, DMS）普遍應用於汽車產業品牌公司經銷商客戶服務管理及財務管理，常見功能包含車輛保修、零件進銷存、新車銷售、財務管理等。車輛保修、零件進銷存功能將每位車主返廠保養、維修履歷完整紀錄儲存於系統底層資料庫，維修履歷包含完整的不良零件換件清單、客戶所陳述的故障現象（Voice of Customer, VOC）及服務廠技師對故障現象的初步判斷（Voice of Engineering, VOE）。
本研究以國內某車廠DMS保養、維修履歷資料為研究素材，運用開源程式碼軟體（Open Source Software, OSS）文字探勘模組對非結構化的維修履歷資料進行VOC特徵詞萃取，經實證運用文字探勘斷詞技術可有效在大量的維修履歷資料中快速提取VOC特徵詞，有助於對不良問題表象進行使用情境判別。運用決策分類預測技術找出適切的分類預測方法，針對未明確陳述問題VOC的車輛推判主要潛在風險不良零件類別，作為服務廠問題調查指南。依據分類結果識別具相同VOC特徵詞的零件類別及相同零件類別非常見VOC特徵詞，以豐富故障模式情境資料庫。

Dealer Management System (DMS) is commonly used in customer service management and financial management of dealers in the automotive industry. Common functions include vehicle warranty, parts purchase and inventory, sales, financial management, etc. The vehicle warranty, parts purchase and inventory function store the complete record of each car return to the dealer for maintenance and repair in the database. The records include a complete list of defective parts, replacements and complian by customer (Voice of Customer, VOC ), and the dealer technician’s preliminary judgment on the fault phenomenon (Voice of Engineering, VOE).
This study uses the DMS maintenance and repair data of a local vehicle service company as the research data and uses the Open-Source Software (OSS) text mining module to extract VOC feature words from the unstructured maintenance history data. Text miming technology can effectively quickly extract VOC feature words from a large amount of maintenance data, helping to identify the use situation of fault symptoms. In addition, this study uses decision-making classification prediction technology to find an appropriate classification prediction method and infer the main potential risk defective parts categories for vehicles that unspecified VOC, as investigation guide for technician. Based on the classification results, parts categories with the same VOC feature words and uncommon VOC feature words of the same part category are identified to enrich the failure mode scenario database.

中文摘要 .............................................................................................. i
英文摘要 .............................................................................................. ii
誌謝 .............................................................................................. iii
目錄 .............................................................................................. iv
表目錄 .............................................................................................. vi
圖目錄 .............................................................................................. vii
第一章 緒論 ...................................................................................... 1
1.1 研究背景 .............................................................................. 1
1.2 研究目的 .............................................................................. 3
1.3 研究步驟 .............................................................................. 5
第二章 文獻探討 .............................................................................. 7
2.1 資料探勘 .............................................................................. 7
2.2 文字探勘 .............................................................................. 11
2.2.1 中文斷詞 .............................................................................. 19
2.2.2 向量空間 .............................................................................. 22
2.3 分類與預測 .......................................................................... 24
2.3.1 Naïve Bayes ......................................................................... 25
2.3.2 Decision Tree ....................................................................... 25
2.3.3 Random Forest ..................................................................... 27
2.3.4 Gradient Boosting ................................................................ 27
2.3.5 Logistic Regression .............................................................. 30
2.3.6 Support Vector Machine ...................................................... 31
2.4 應用領域案例 ...................................................................... 32
2.5 小結 ...................................................................................... 35
第三章 市場品情管理 ...................................................................... 36
3.1 經銷商管理系統 .................................................................. 36
3.2 保固檢提 .............................................................................. 39
第四章 研究方法 .............................................................................. 43
4.1 研究工具 .............................................................................. 43
4.1.1 Python .................................................................................. 43
4.1.2 Orange .................................................................................. 44
4.2 個案資料分析 ...................................................................... 48
4.2.1 資料前處理 .......................................................................... 48
4.2.2 VOC 特徵詞 ........................................................................ 49
4.3 文字探勘操作應用 .............................................................. 51
4.3.1 向量空間與相似度 .............................................................. 51
4.3.2 分類與預測結果 .................................................................. 57
第五章 結論與建議 .......................................................................... 62
參考文獻 .............................................................................................. 64
附錄 .............................................................................................. 68
英文論文大綱 .............................................................................................. 78

1.日本經濟新聞（2023），豐田換帥始末，https://zh.cn.nikkei.com/industry/icar/51201-2023-01-27-12-01-25.html?start=0， 擷取日期：2023/2/15。
2.李素杏（2023)，運用文字探勘進行議員提案分案之研究−以新北市議會為例，致理科技大學企業管理系碩士論文。
3.涂敏怡（2022），「開源創新對台灣資訊產業影響初探」，資訊社會研究，42，13-50。
4.國家發展委員會（2021），六大核心戰略產業堆動方案（核定本），國家發展委員會。
5.張瑋倫（2000），應用資料挖掘學習方法探討顧客關係管理問題，輔仁大學資訊管理學系研究所碩士論文。
6.張鈺鴻（2021），應用文字探勘技術建構預測客訴問題類別機器學習模型，國立中央大學資訊管理學系硏究所碩士論文。
7.張維元（2021），身為資料科學家，R、Python 與 Julia 該怎麼選?，https://edge.aif.tw/which-programming-language-is-good/， 擷取日期：2023/3/1。
8.張簡宇傑（2020），基於文字探勘之智慧工程文件摘要系統，國立清華大學工業工程研究所碩士論文。
9.許哲維（2019），運用資料探勘方法探討畢業生流向狀況−以國立虎尾科技大學學生為例，國立虎尾科技大學工業管理系工業工程與管理碩士班碩士論文。
10.郭泰竹（2019)，集成式學習應用於電子零件供應鏈需求預測，國立政治大學資訊管理學系研究所碩士論文。
11.陳彥龍（2020），中文斷詞方法之研究與實作，國立暨南國際大學資訊工程學系碩士論文。
12.陳群凱（2023)，以文字探勘方法預測假新聞−以烏俄戰爭為例，國立成功大學工程科學系碩士論文。
13.黃允亭（2022)，應用實價登錄建立以聚類方法之堆疊泛化房價預測模型−以桃園市區分建物房價資料為例，國立政治大學經濟學系碩士論文。
14.楊渝婷（2022），運用文字探勘技術建構使用鈉−葡萄糖共同轉運蛋白-2抑制劑之糖尿病腎病變患者腎功能改善預測模型，國立中正大學醫療資訊管理硏究所碩士論文
15.潘怡秀（2018），資料探勘應用於醫藥物流中心藥品消耗預測，國立虎尾科技大學工業管理系工業工程與管理碩士班碩士論文。
16.賴明助（2010），運用文字探勘技術於顧客問題分類之研究−以某ERP軟體公司為例，靜宜大學資訊碩士在職專班碩士論文。
17.Allahyari, M., Pouriyeh, S., Assefi, M., Safaei, S., Trippe, E. D., Gutierrez, J. B., & Kochut, K. (2017). A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques, KDD Bigdas, Halifax, Canada.
18.Berry, M. J. A., & Linoff, G. S. (1997). Data Mining Techniques: For Marketing, Sales, and Customer Support, Wiley Publishing, Inc., New York.
19.Berson, A., Smith, S., & Thearling, K. (2000). Building Data Mining Applications for CRM, McGraw-Hill, New York.
20.Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., & Zanasi, A. (1997). Discovering Data Mining: From Concept to Implementation, Prentice Hall, New York.
21.Coronado, M. B., Mori, U., Mendiburu, A., & Alonso, M. J. (2020). “Survey of Network Intrusion Detection Methods from the Perspective of the Knowledge Discovery in Databases Process”, https://doi.org/10.48550/arXiv.2001.09697.
22. Fayyad, U., Piatetsky, S. G., & Smyth, P. (1996). “From Data Mining to Knowledge Discovery in Databases” , AI Magazine, 17(3), pp. 37-54.
23.Friedman, J. H. (2001). “Greedy Function Approximation: A Gradient Boosting Machine”, The Annals of Statistics, 29(5), pp. 1189-1232.
24.GitHub jieba (2022), https://github.com/fxsjy/jieba, retrived date: 2022/10/18.
25.Han, J., Kamber, M., & Pei, J. (2012). Data Mining: Concepts and Techniques, Third Edition, Morgan Kaufmann, New York.
26.Hassan, S. U., Ahamed, J., & Ahmad, K. (2022). “Analytics of Machine Learning-based Algorithms for Text Classification”, Sustainable Operations and Computers, 3, pp. 238-248.
27.Hotho, A., Nürnberger, A., & Paaß, G. (2005). “A Brief Survey of Text Mining”, Journal for Language Technology and Computational Linguistics, 20(1), pp. 19-62.
28.Kim, H., Soibelman, L., & Grobler, F. (2008). “Factor Selection for Delay Analysis Using Knowledge Discovery in Databases”, Automation in Construction, Vol. 17, pp. 550-560.
29.Kleissner, C. (1998). “Data Mining for the Enterprise”, Proceedings of the Thirty-First Hawaii International Conference, 7, pp. 295-304.
30.Kobayashi, V. B., Mol, S. T., Berkers, H. A., Kismihok, G., & Den Hartog, D. N. (2018). “Text Mining in Organizational Research”, Organizational Research Methods, 21(3), pp. 733-765.
31.Lau, K. N., Lee, K. H., & Ho, Y. (2005). “Text mining for the hotel industry”, Cornell Hotel and Restaurant Administration Quarterly, 46(3), pp. 344-362.
32.Lee, S., Nguyen, N. H., Karamanli, A., Lee, J., & Vo, T. P. (2022). “Super Learner Machine-learning Algorithms for Compressive Strength Prediction of High Performance Concrete”, Structural Concrete, 24, pp. 2208–2228.
33.Maata, R. L. R., Pineda, A. P., Epoc, F. J., & Cordova, R. (2021). “Application of Text Mining to Analyze Customer Opinions on Social Media”, Global Business and Management Research: An International Journal, 13(3), pp. 1-9.
34.Matplotlib (2022). https://matplotlib.org, retrived date: 2022/10/18.
35.Mooney, R. J., & Nahm, U. Y (2005). “Text Mining with Information Extraction”, Multilingualism and Electronic Language Management: Proceedings of the 4th International MID Colloquium, pp.141-160.
36.NumPy (2022). https://numpy.org, retrived date: 2022/10/18.
37.openpyxl (2022). https://openpyxl.readthedocs.io, retrived date: 2022/10/18.
38.orange (2022). https://orangedatamining.com, retrived date: 2022/10/18.
39.Otten, N. V. (2023). How To Implement Logistic Regression Text Classification in Python with Scikit-learn and PyTorch, https://spotintelligence.com/2023/02/22/logistic-regression-text-classification-python.
40.pandas (2022). https://pandas.pydata.org, retrived date: 2022/10/18.
41.Python Package Index (2022). https://pypi.org, retrived date: 2022/10/18.
42.Python (2022). https://www.python.org, retrived date: 2022/10/18.
43.Qorib, M., Oladunni, T., Denis, M., Ososanya, E., & Paul, C. (2023). “Covid-19 Vaccine Hesitancy: Text Mining, Sentiment Analysis and Machine Learning on COVID-19 Vaccination Twitter Dataset”, Expert Systems with Applications, 212, 118715.
44.Salloum, S. A., Al-Emran, M., Monem, A. A., & Shaalan, K. (2017). “A Survey of Text Mining in Social Media: Facebook and Twitter Perspectives”, Advances in Science, Technology and Engineering Systems Journal, 2(1), pp. 127-133.
45.seaborn (2022). https://seaborn.pydata.org/#, retrived date: 2022/10/18.
46.Sun, C., & Luo, B. (2022). “Analysis of English Writing Text Features Based on Random Forest and Logistic Regression Classification Algorithm”, Mobile Information Systems, Volume 2022, Article ID 6306025, https://doi.org/10.1155/2022/6306025.
47.Tan, A. H. (2000). Text Mining: The State of the Art and the Challenges, https://www.researchgate.net/publication/2471634_Text_Mining_The_state_of_the_art_and_the_challenges.
48.Thuraisingham, B. (2000). “A Primer for Understanding and Applying Data Mining”, IT Professional, 2(1), pp. 28-31.