1.中移在线服务有限公司山东分公司,山东 济南 250022
2.中移在线服务有限公司AI能力中心,河南 郑州 450001
[ "乔雅倩(1996- ),女,现就职于中移在线服务有限公司山东分公司,主要研究方向为人工智能与数据挖掘。" ]
[ "王倩(1987- ),女,现就职于中移在线服务有限公司山东分公司,主要研究方向为自然语言处理与数据挖掘。" ]
[ "刘芳(1982- ),女,现就职于中移在线服务有限公司山东分公司,主要研究方向为智能客服解决方案、数据挖掘。" ]
[ "徐宇(1974- ),男,中移在线服务有限公司山东分公司副总经理、高级工程师,主要研究方向为服务数智化、线上化运营。" ]
[ "江君(1984− ),男,就职于中移在线服务有限公司AI 能力中心,主要研究方向为智能客服、智能策略和智能体系统。" ]
收稿:2025-11-12,
修回:2025-10-31,
录用:2025-10-31,
网络出版:2026-01-05,
移动端阅览
乔雅倩,王倩,刘芳等.基于LLM-RFE-XGBoost方法的客户升级投诉预警研究[J].电信科学,
Qiao Yaqian,Wang Qian,Liu Fang,et al.Customer escalated complaints prediction based on LLM-RFE-XGBoost approach[J].Telecommunications Science,
乔雅倩,王倩,刘芳等.基于LLM-RFE-XGBoost方法的客户升级投诉预警研究[J].电信科学, DOI:10.11959/j.issn.1000−0801.2025263.
Qiao Yaqian,Wang Qian,Liu Fang,et al.Customer escalated complaints prediction based on LLM-RFE-XGBoost approach[J].Telecommunications Science, DOI:10.11959/j.issn.1000−0801.2025263.
客户升级投诉作为衡量服务质量的关键指标,其精准预测对服务质量改善与客户问题解决具有重要意义。基于此提出了一种基于大语言模型(LLM)、递归特征消除(RFE)以及XGBoost的混合学习方法对潜在升级投诉客户进行预警,首先利用大语言模型从客户通话文本中提取语义特征,再融合结构化数据后利用RFE进行最优特征选择,最后基于有效特征选采用XGBoost进行预警。为了检验该模型的有效性,以某省运营商生产数据为研究对象进行了预测,实证结果表明提出的LLM-RFE-XGBoost混合方法具有最优的预测性能。实际上线应用后,升级投诉量下降了6.7%,成效显著,对提高服务质量及客户满意度具有重要意义。
Customer escalated complaints serve as a critical indicator for measuring service quality and are vital for improving service quality and resolving customer issues. A hybrid learning approach LLM-RFE-XGBoost was proposed for early warning of potential escalated complaints. Firstly
the paper utilized Large Language Models (LLM) to extract semantic features from customer call text. Then these features were integrated with original structured data
after which Recursive Feature Elimination (RFE) was applied to select the optimal feature set. Finally
XGBoost was employed for prediction using all selected features. To validate the effectiveness of the model
predictive analysis was conducted using production data from a provincial telecom operator as the research subject. Empirical results demonstrate that the proposed LLM-RFE-XGBoost hybrid approach delivers optimal predictive performance. After practical application in a provincial telecom operator
escalated complaints decreased by 6.7%
which is of great significance for improvement of the service quality and customer satisfaction.
景奕昕 . 基于机器学习的电商平台客户投诉精准定位研究 [J ] . 数字通信世界 , 2025 ( 1 ): 22 - 24, 27 .
JING Y X . Research on precise positioning of customer complaints on e-commerce platforms based on machine learning [J ] . Digital Communication World , 2025 ( 1 ): 22 - 24, 27 .
王金政 , 杨颖 , 余本功 . 基于多头协同注意力机制的客户投诉文本分类模型 [J ] . 数据分析与知识发现 , 2023 , 7 ( 1 ): 128 - 137
WANG J Z , YANG Y , YU B G . Classifying customer complaints based on multi-head co-attention mechanism [J ] . Data Analysis and Knowledge Discovery , 2023 , 7 ( 1 ): 128 - 137 .
祝好 , 齐磊 , 顾慧琼 . 基于人工神经网络算法的运营商客户投诉智能分类问题研究 [J ] . 电信工程技术与标准化 , 2021 , 34 ( 3 ): 31 - 35 .
ZHU H , QI L , GU H Q . Research on intelligent classification of operator customer complaints based on artificial neural network algorithm [J ] . Telecom Engineering Technics and Standardization , 2021 , 34 ( 3 ): 31 - 35 .
李青 , 杨春霞 , 蒋春辉 , 等 . 基于聚类分析和决策树的客户投诉预警体系 [J ] . 长江信息通信 , 2022 , 35 ( 7 ): 180 - 183 .
LI Q , YANG C X , JIANG C H , et al . Customer complaint early warning system based on cluster analysis and decision tree [J ] . Changjiang Information &Communications , 2022 , 35 ( 7 ): 180 - 183 .
张艳莉 . 基于Logistic回归算法的企业顾客抱怨管理机制的构建 [J ] . 科技通报 , 2014 , 30 ( 5 ): 156 - 159 .
ZHANG Y L . Enterprise management mechanism for build customer complaints based on logistic regression algorithm [J ] . Bulletin of Science and Technology , 2014 , 30 ( 5 ): 156 - 159 .
张蕊 , 张丽红 , 吴登群 . 客户投诉处理精准分析与定位研究 [J ] . 数字通信世界 , 2024 ( 6 ): 58 - 60 .
ZHANG R , ZHANG L H , WU D Q . Research on accurate analysis and positioning of customer complaint handling [J ] . Digital Communication World , 2024 ( 6 ): 58 - 60 .
张爱华 , 孙嘉鸿 . 基于TF-IDF算法的运营商客户投诉原因研究 [J ] . 北京邮电大学学报(社会科学版) , 2024 , 26 ( 2 ): 39 - 49 .
ZHANG A H , SUN J H . Reasons for customer complaints in operators based on TF-IDF algorithm [J ] . Journal of Beijing University of Posts and Telecommunications (Social Sciences Edition) , 2024 , 26 ( 2 ): 39 - 49 .
郑杰明 , 梁伟明 , 陈震原 , 等 . 快速发现和定位投诉问题 运用多元分析方法提升客户满意度 [J ] . 通信企业管理 , 2023 ( 11 ): 78 - 80 .
ZHENG J M , LIANG W M , CHEN Z Y , et al . Quickly find and locate complaints and improve customer satisfaction by multivariate analysis [J ] . C-Enterprise Management , 2023 ( 11 ): 78 - 80 .
周文杰 , 严建峰 , 杨璐 . 基于深度学习的用户投诉预测模型研究 [J ] . 计算机应用研究 , 2017 , 34 ( 5 ): 1428 - 1432 .
ZHOU W J , YAN J F , YANG L . Research on prediction model of complaint based on deep learning [J ] . Application Research of Computers , 2017 , 34 ( 5 ): 1428 - 1432
BRITO J B G , BUCCO G B , HELDT R , et al . A framework to improve churn prediction performance in retail banking [J ] . Financial Innovation , 2024 , 10 ( 1 ): 17 .
马晓亮 , 刘英 , 高洁 . 基于联合神经网络的投诉预测模型研究 [J ] . 电信科学 , 2024 ( 1 ): 48 - 58 .
MA X L , LIU Y , GAO J . Research on a complaint prediction model utilizing joint neural networks [J ] . Telecommunications Science , 2024 ( 1 ): 48 - 58
李龙戈 , 郑铿城 . 基于集成森林元学习网络的客户流失预测 [J ] . 电信科学 , 2024 , 40 ( 10 ): 163 - 172 .
LI L G , ZHENG K C . Customer churn prediction based on the integration of meta-learning network of the forest [J ] . Telecommunications Science , 2024 , 40 ( 10 ): 163 - 172 .
张爱华 , 于涵 , 陈超雨 . 基于文本分析的运营商潜在升级投诉客户挖掘 [J ] . 北京邮电大学学报(社会科学版) , 2022 , 24 ( 5 ): 32 - 38, 57 .
ZHANG A H , YU H , CHEN C Y . Mining of operators’ potential customers with further complaints based on text analysis [J ] . Journal of Beijing University of Posts and Telecommunications (Social Sciences Edition) , 2022 , 24 ( 5 ): 32 - 38, 57 .
穆晓玛 . 主流客户投诉预测模型的对比与研究 [J ] . 智能计算机与应用 , 2018 , 8 ( 5 ): 100 - 102, 105 .
MU X M . Comparison and research of several mainstream customer complaint prediction models [J ] . Intelligent Computer and Applications , 2018 , 8 ( 5 ): 100 - 102, 105 .
WU D N , ZHOU Z K , SU Z . Consumer negative opinions on stock returns: evidence from E-commerce reviews in China [J ] . Financial Innovation , 2025 , 11 ( 1 ): 71 .
周志华 . 机器学习 [M ] . 北京 : 清华大学出版社 , 2016 .
Zhou Z H . Machine learning [M ] . Beijing : Tsinghua University Press , 2016 .
CHEN T , GUESTRIN C . XGBoost: a scalable tree boosting system [C ] // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . New York : ACM Press , 2016 .
0
浏览量
1
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621