跳到主要內容

臺灣博碩士論文加值系統

(44.210.149.205) 您好!臺灣時間:2024/04/12 21:47
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:楊詠筑
研究生(外文):YANG, YONG-ZHU
論文名稱:應用文字探勘技術於客戶中心
論文名稱(外文):The application of text mining technologies in a call center
指導教授:吳沛儒吳沛儒引用關係
指導教授(外文):WU, PEI-JU
口試委員:鄭家年陳志騰
口試委員(外文):ZHENG, JIAN-IANCHEN, CHIHTENG
口試日期:2022-06-29
學位類別:碩士
校院名稱:逢甲大學
系所名稱:運輸與物流學系
學門:運輸服務學門
學類:運輸管理學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:英文
論文頁數:83
中文關鍵詞:文字探勘客戶服務中心客戶服務大數據科技
外文關鍵詞:Text MiningCall CenterCustomer ServiceBig Data
相關次數:
  • 被引用被引用:0
  • 點閱點閱:183
  • 評分評分:
  • 下載下載:33
  • 收藏至我的研究室書目清單書目收藏:0
顧客關係管理被目前的企業所重視。然而,本研究中的探討對象為台灣的軟體業者開發之發票管理系統。其發票管理系統的客服紀錄為該客服中心人員於接觸用戶時以文字的方式進行記錄。由於每一個人員的紀錄習慣不同,累積數據庫後仍難以進行人工判讀的方式歸納用戶常見問題。且發票管理系統提供經銷存管理服務,不同於實體貨品交易,用戶提出的問題更為多元複雜。
目前大數據科技應用於提供顧客滿意度有相當卓越的表現。因此本研究採文字探勘技術解決大量、繁複及高度重複性之資料分析作業。本研究首先手動刪除了質量較差的數據,包含原始數據的內容並不詳盡,原始數據僅記錄案例時間或案件編號,以及其他無法按原始含義和情況閱讀的數據。本研究使用文本挖掘軟件SAS Enterprise Miner進行分析。在數據預處理階段中,過濾掉多餘字段,添加供應商名稱掩碼,並建立黑名單,去除不必要的分詞、介詞等。接著依據文字探勘的實證結果,回溯原文分析不同集群各自的意義,將用戶需求、客服服務過程個別整理為八個集群。再將八個用戶需求集群的資料依據服務時間效率拆分為獨立數據集,個別進行分析以了解各議題下不同客服服務的效率程度。最後,本研究以pzb量表之理論為基礎,探討個別客戶服務符合之理論。並將用戶需求的性質分為一次性需求和非一次性需求,根據服務效率將服務分為四個像限。期望本研究結果能提供軟體業者者,進行客戶服務中心策略擬定之參考,以及對學術界在服務品質研究領域有所貢獻。
Customer relationship management was valued by enterprises currently. The research object of this study is an invoice management system developed by a software company in Taiwan. The customer service records of its invoice management system were recorded by the call center personnel in the form of text when they contact to users. Due to the different recording habits of each personnel, the raw data is difficult to summarize the common problems of users by manual interpretation. In addition, the invoice management system provides distribution and storage management services. Unlike physical goods transactions, the questions raised by users are more diverse and complex.At present, the application of big data technology provides substantial help to the field of customer satisfaction. Therefore, this study adopts text mining technology to solve a big data of complex and highly repetitive data analysis operations. Before textmining,this study remove the poor quality data which were not exhaustive. This study uses analysis the data by SAS Enterprise Miner 15.1. In the data preprocessing stage of SAS Enterprise Miner 15.1, this study list a blacklist to remove unnecessary words sucj like segmentations and prepositions, etc. Based on the empirical results of text mining, this study backtracking to the original data to analysis the meanings of different clusters. After text mining, this study organize 8 clusters each of customer demands and call center service processes. And then, the data of the eight user demand clusters are divided into independent data sets according to the service time efficiency, individual analysis of each cluster to understand the efficiency of different customer service based on each issue. Finally, this study explores the theory of individual customer service compliance of the theory in pzb scale. The nature of user demands were divided into one-time needs and non-one-time needs, and divide the services into four quadrants according to service efficiency. It is hoped that the results of this study can provide software industry operators with a reference for customer service strategy formulation and contribute to academia in the field of service quality research.
誌  謝
摘  要
ABSTRACT
CONTENTS
LIST OF FIGURES
LIST OF TABLES
1 INTRODUCTION
1.1 BACKGROUND AND MOTIVATION
1.2 PROPOSE AND SCOPE
1.3 RESEARCH PROCEDURES
2 LITERATURE REVIEW
2.1 CUSTOMER SERVICE IMPACT ON BUSINESS DEVELOPMENT
2.2 THE IMPACT OF BIG DATA IN CUSTOMER SERVICE IMPROVEMENT
2.3 SUMMARY
2.4 SUMMARY
3 METHODOLOGY
3.1 PROBLEM STATEMENT
3.2 DATA PREPROCESSING
3.3 TEXT MINING
4 RESULT AND DISCUSSION
4.1 CUSTOMER DEMANDS CLUSTERING
4.2 CUSTOMER SERVICE PROCESS CLUSTERING
4.3 CLUSTER OF METHODS FOR HANDLING INDIVIDUAL CUSTOMER NEEDS
4.3.1 Cluster of processing methods for “New user profile request” requirements Basic Scenario Analysis
4.3.2 Cluster of processing methods for “Application progress confirmation and inquiry”requirements
4.3.3 Cluster of processing methods for “accounting issues” requirements
4.3.4 Cluster of processing methods for “account/system exceptions” requirements
4.3.5 Cluster of processing methods for “system function guide” requirements
4.3.6 Cluster of processing methods for “confirming the acceptance amount of the debit note” requirements
4.3.7 Cluster of processing methods for “invoice issuance” requirements
4.3.8 Cluster of processing methods for “signature process issuance” requirements
5 IMPLICATIONS
5.1 THEORETICAL IMPLICATIONS
5.1.1 Introduction to SERVQUAL Model
5.1.2 Theoretical implications of “request for new user file” requirements 62
5.1.3 Theoretical implications of “application progress confirmation and inquiry”requirements
5.1.4 Theoretical implications of “accounting issues” requirements
5.1.5 Theoretical implications of “account/system exceptions” requirements
5.1.6 Theoretical implications of “system function guide” requirements 66
5.1.7 Theoretical implications of “confirming the acceptance amount of the debit note” requirements
5.1.8 Theoretical implications of “invoice issuance” requirements
5.1.9 Theoretical implications of “signature process issuance” requirements
5.1.10 Theoretical implications of issues that cannot be addressed immediately
5.2 MANAGEMENT IMPLICATIONS
5.2.1 Design one-station service process
5.2.2 Design FAQ with technology
5.2.3 Service Mode Classification
6 CONCLUSION
REFERENCE
Bruhn, M., and Grund, M.A. (2000). "Theory, Development and Implementation of National”.
Chen, M. S., J. Han and P. S. Yu (1996) Data mining: An overview from database perspective. IEEE Transactions on Knowledge and Data Engineering, 8(6), 866-883.
Customer Satisfaction Indices: The Swiss Index of Customer Satisfaction." Total Quality Management and Business Excellence Vol.11, No.7: pp.1017-1028.
Deepak Sirdeshmukh, Jagdip Singh & Barry Sabol(2002), “Consumer Trust, Value, and Loyalty in Relational Exchanges,” Journal of Marketing, 66 (January),pp.15-37
Gronholdt, L., Martensen, A., and Kristensen, K. (2000). "The relationship between customer satisfaction and loyalty: Cross-industry differences." Total Quality Management Vol.11:pp.509-516.
Hashimi, Hussein, Alaaeldin Hafez,Hassan Mathkour. 「Selection Criteria for Text Mining Approaches」. Computers in Human Behavior, Computing for Human Learning, Behaviour and Collaboration in the Social and Mobile Networks Era, 51 (2015): 729–33. https://doi.org/10.1016/j.chb.2014.10.062.
Jason Brownlee (2020). “A Gentle Introduction to Expectation-Maximization (EM Algorithm)
https://machinelearningmastery.com/expectation-maximization-em-algorithm/
Li-Cin (2021) “Applying Data Mining Methods for Customer Relationship Management in Online Food Industry.”
Li, L. and J. Ma(2008). “A BYY Scale-incremental EM Algorithm for Gaussian Mixture Learning,” Applied Mathematics and Computation, 205, pp. 832-840
Losiewicz, P,. Oard, D. W., & Kostoff, R. N. (2000). Textual data mining to support science and technology management. Journal of Intelligent Information Systems, 15(2), 99-119.
Mohan, A. and Deshmukh, A.K. (2013), “Conceptualization and development of a supply chaincustomer relationship management (SC2R-M) synergy mode”, Journal of Supply Chain Management Systems, Vol. 2 No. 3, pp. 9-25, available at: http://adezproxy.adu.ac.ae/docview/ 1490542754?accountid=26149
Mougayar, W. (1997), Opening digital markets: battle plans and business strategies for Internet Commerce, McGraw-Hill, New York, USA, pp. 83-84
Naeem, Tehreem. 「Understanding Structured, Semi-Structured, and Unstructured Data」. Astera (blog), 2020/11/01. https://www.astera.com/type/blog/structured-semi-structured-and-unstructured-data/.
SAS Institute Inc., 2013. Text Mining and Analysis: Practical Methods, Examples, and Case Studies Using SAS. 34.
SAS Institute Inc., 2016. SAS® Enterprise MinerTM 15.2: Reference Help. 1806.
Taleb, N.; Salahat, M.; Ali, L. Impacts of Big-Data Technologies in Enhancing CRM Performance. In 2020 6th International Conference on Information Management (ICIM); 2020; pp 257–263. https://doi.org/10.1109/ICIM49319.2020.244708.
Parasuraman,A., Zeithaml, V.A. & Berry, L. L., Berry., 1993,The Neture and Determinants of Customer Expectations of Service, Journal of the Academy of Marketing Science,Vol.21, No.1,Winter, pp.1-12.
Parasuraman A, Zeithaml VA, Berry LL. A Conceptual Model of Service Quality and Its Implications for Future Research. J Mark. 1985;49: 41-50
Parasuraman, Anantharanthan, Valarie A Zeithaml, and Leonard L Berry 1985 A conceptual model of service quality and its implications for future research. Journal of marketing 49(4):41-50.
Petar Ristoski, H. Paulheim (2016)” Semantic Web in data mining and knowledge discovery: A comprehensive survey.”
Xiangna Li; Zhongping Xu; Xuedong Li; Tao Zhang; Rongrong Zheng; Xiao Han; Chenhui Wang; Bing Tian(2020)"Research and Development of ICT Call Center Data Auxiliary Analysis System Based on Knowledge Discovery"
Zeithaml, V. A., Bitner, M.J., and Gremler, D.D. (2009). Services Marketing -Integrating Customer Focus Across the firm New York, McGraw Hill.
Zheng, H. Customer Purchase Behavior Prediction and Analysis Based on CRM Data Analysis Technology. In 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE); 2020; pp 1374–1378. https://doi.org/10.1109/ICMCCE51767.2020.00301.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊