Article Details

Abstract

At present, there are some pain points in customer service operation, such as insufficient digital and intelligent empowerment and inability to efficiently predict customer perception and implement satisfactory service operation. Based on the Big Data base, this paper focuses on the full-dimensional perception portrait of all customers, and uses the algorithm technology such as entropy weight method and emotion analysis to create the customer word-of-mouth index prediction model of telecom operators. Intelligent prediction of total customer perception lays the foundation for deepening satisfactory service operation. It realizes the transformation from the passive service mode focusing on complaint problem solving to the active service mode driven by digital intelligent satisfactory service operation, effectively improving customer satisfaction, and striving to forge a high-quality service “gold business card”.

Keywords

customer word-of-mouth index; entropy weight method; satisfactory service; customer perception; satisfaction

References

1. [1] Deng Yunzhi. A Brief Analysis of the Challenges and Business Model Innovation Faced by Telecom Operators in the 5G Era [J]. Modern Economic Information, 2018 (9): 361+363
2. [2] Southern Sword Flying, Hou Jianrong Customer Satisfaction Study [M]. Shanghai: Shanghai Jiao Tong University Press, 2019
3. [3] Liu Jinlan, Zhu Xiaoyang Principal Component Analysis and Multiple Regression Method for Measuring the Importance of Customer Satisfaction Indicators [J]. Journal of Tianjin University: Social Sciences Edition, 2004 (2): 159-163
4. [4] Dong Xiaomeng Analysis of Factors Influencing Statistical Professional Satisfaction Based on Multiple Linear Regression [J]. Value Engineering, 2019, 38 (36): 276-277
5. [5] Gou Lei Perceived satisfaction prediction of mobile Internet users based on LTE signaling S1-MME interface data [D]. Chengdu: Southwest Jiaotong University, 2018
6. [6] Yan Xuejuan, Zhu Daiwu Safety performance evaluation of airline maintenance departments based on entropy weight method [J]. Science and Industry, 2021, 21 (12): 53-60
7. [7] Zhu Haiyan, Ma Houqiang Satisfaction evaluation of bus lanes based on entropy weight method [J]. Qinghai Transportation Science and Technology, 2021, 33 (6): 25-32
8. [8] Yan Ying Risk assessment of closed-loop management of cold chain logistics based on entropy weight method and grey correlation analysis [J]. Logistics Technology, 2021, 40 (11): 48-53
9. [9] Deng Xu, Lin Liang, Li Liqin A 5G Value Station Building Method Based on Entropy Weight Method [J]. Telecommunication Engineering Technology and Standardization, 2021, 34 (10): 69-72
10. [10] Li Jingwei, Kang Manling, Li Qiyu Measurement and Evaluation of Regional Financial Risks in China Based on Entropy Weight Method [J]. Economic Forum, 2024 (2): 98-109
11. [11] Fu Yan, Zhou Tao, Xu Qingqing, etc Optimization of Fresh Cutting Method for Tianma Based on Entropy Weight Method and Analytic Hierarchy Process [J]. Chinese Herbal Medicine, 2024, 55 (5): 1493-1501
12. [12] Cheng Qiyue Structural Entropy Weight Method for Determining Evaluation Index Weights [J]. Systems Engineering Theory and Practice, 2010, 30 (7): 1225-1228

About the authors

Fan Chenxi (1988-), female, Han ethnicity, from Wuxi, Jiangsu, engineer, PhD, research direction: data governance, big data analysis; Wang Lihua (1974-), male, Han ethnicity, from Changzhou, Jiangsu, Vice General Manager of Customer Service Department, bachelor's degree, research direction: high-quality service, AI+perception operation; Zhou Menghan (1999-), female, Han ethnicity, from Anqing, Anhui, engineer, bachelor's degree, research direction: big data analysis; Wang Yunqiang (1994-), male, Han ethnicity, from Xinyang, Henan, engineer, master's degree, research direction: machine vision and natural language processing; Zhao Jing (1979-), female, Han nationality, from Lishui, Zhejiang, engineer, undergraduate, research direction: customer service.