1.北京邮电大学 北京 100876
2.中国信息通信研究院 北京 100876
3.中国移动通信集团内蒙古有限公司 内蒙古 呼和浩特 010090
[ "张梦婷(2003-),女,北京邮电大学硕士研究生,主要研究方向为数据挖掘与商务智能。" ]
[ "张晓航(1975-),男,北京邮电大学博士,教授,主要研究方向为数据挖掘与商务智能、风险建模、因果推理。" ]
[ "李征仁(1987-),男,博士,北京邮电大学,副教授,主要研究方向为数据挖掘与商务智能。" ]
[ "王海燕(1977-),女,博士学位,中国信息通信研究院高级工程师,主要从事人工智能技术应用及电信用户服务研究。" ]
[ "陈中华(1990-),男,学士学位,中国移动通信集团内蒙古有限公司,中级工程师,系统支撑方案设计,大数据及人工智能。" ]
收稿:2025-12-11,
修回:2026-03-25,
录用:2026-05-11,
移动端阅览
张梦婷, 张晓航, 李征仁, 等. 基于大模型的电信申诉判责全流程智能化方法研究[J/OL]. 电信科学, 2026.
ZHANG Mengting, ZHANG Xiaohang, LI Zhengren, et al. A Large-Language-Model–Driven End-to-End Intelligent Framework for Responsibility Determination in Telecom Complaints[J/OL]. Telecommunications Science, 2026.
张梦婷, 张晓航, 李征仁, 等. 基于大模型的电信申诉判责全流程智能化方法研究[J/OL]. 电信科学, 2026. DOI: 10.11959/j.issn.1000-0801.DXKX250712.
ZHANG Mengting, ZHANG Xiaohang, LI Zhengren, et al. A Large-Language-Model–Driven End-to-End Intelligent Framework for Responsibility Determination in Telecom Complaints[J/OL]. Telecommunications Science, 2026. DOI: 10.11959/j.issn.1000-0801.DXKX250712.
电信申诉处理涉及多个环节,传统人工模式在效率与一致性上存在瓶颈,现有自动化研究多局限于单点任务。基于此提出一种基于大语言模型的智能化判责框架,通过提示词工程依次构建申诉无效判断、类型识别、内容拆解、人机协同证据链收集与判责报告生成五个模块。在某省级运营商约7000条真实工单上的实验表明:无效判断准确率达83.2%,较BERT等基线方法最低提升14.2%;服务顽疾分类准确率为97%;申诉内容拆解F1值为73.9%,要点覆盖率为82.1%;各环节处理效率较人工提升最高达96.7%。跨月份泛化测试显示模型性能稳定,为电信申诉判责提供了完整的智能化解决方案,对行业智能化实践具有参考价值。
Telecom complaint adjudication involves multiple stages. Traditional manual processing faces clear bottlenecks in efficiency and consistency
while existing automation studies mostly focus on isolated tasks. To address this issue
this paper proposes an intelligent adjudication framework based on large language models. Through prompt engineering
the framework comprises five modules: invalid complaint detection
complaint type identification
complaint content decomposition
human-in-the-loop evidence chain collection
and adjudication report generation. Experiments on approximately 7
000 real complaint cases from a provincial telecom operator show that the proposed method achieves 83.2% accuracy in invalid complaint detection
outperforming BERT and other baselines by at least 14.2%; 97% accuracy in service issue classification; and an F1 score of 73.9% with 82.1% key-point coverage in complaint content decomposition. Processing efficiency across stages improves by up to 96.7% compared with manual handling. Cross-month generalization tests further demonstrate stable performance. The proposed framework provides a complete intelligent solution for telecom complaint adjudication and offers practical value for digital transformation in the telecom industry.
黄堃 , 胡涵清 , 赵东明 , et al . 基于深度学习的电信运营商网络投诉工单智能分类技术研究 [J ] . 电信工程技术与标准化 , 2023 , 36 ( 10 ): 6 - 12 .
梁伟明 , 肖军 , 马晓亮 , et al . 基于改进Transformer的电信重投报告自动生成方法研究 [J ] . 电信科学 , 2025 , 41 ( 6 ): 197 - 207 .
梁昕露 , 李美娟 . 电信业投诉分类方法及其应用研究 [J ] . 中国管理科学 , 2015 , 23 ( S1 ): 188 - 192 .
赵进 , 杨小军 . 基于GRW和FastText模型的电信用户投诉文本分类应用 [J ] . 电信科学 , 2021 , 37 ( 06 ): 125 - 131 .
Yang Y , Xu D-L , Yang J-B , et al . An evidential reasoning-based decision support system for handling customer complaints in mobile telecommunications [J ] . Knowledge-Based Systems , 2018 , 162 : 202 - 210 .
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 ( 03 ): 31 - 35 .
Devlin J , Chang M-W , Lee K , et al . BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, Minneapolis, Minnesota, F June, 2019 [C ] . Association for Computational Linguistics .
张亮 , 代晓菊 , 郑荣 , et al . 多模型融合的客服工单文本分类方法的研究与实现 [J ] . 电信科学 , 2021 , 37 ( 11 ): 86 - 96 .
Zhou H , Hu C , Yuan Y , et al . Large language model (llm) for telecommunications: A comprehensive survey on principles, key techniques, and opportunities [J ] . IEEE Communications Surveys & Tutorials , 2024 .
查德飞 , 臧永顺 , 史鸿晖 . 通信企业大模型技术突破与规模化应用实践 [J ] . 数字通信世界 , 2025 , ( 08 ): 232 - 234 .
王希 , 赵灏 , 尹培 . 基于星辰语义大模型的潜在申诉用户预测应用研究 [J ] . 山东通信技术 , 2025 , 45 ( 02 ): 38 - 42 .
殷昌承 , 陆绍雯 , 冯超 , et al . 面向业务端到端的投诉智能体技术研究与应用 [J ] . 电信工程技术与标准化 , 2025 , 38 ( 08 ): 1 - 6 .
Sahoo P , Singh A K , Saha S , et al . A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications [J/OL ] 2024 , arXiv: 2402 . 07927 [https://ui.adsabs.harvard.edu/abs/2024arXiv240207927S. 10.48550/arXiv.2402.07927
Pawlik L . How the Choice of LLM and Prompt Engineering Affects Chatbot Effectiveness [J ] . Electronics , 2025 , 14 ( 5 ): 888 .
Gao M , Sun B , Wang T , et al . Domain-Aware Reinforcement Learning for Prompt Optimization [J ] . Mathematics , 2025 , 13 ( 16 ): 2552 .
Shahriar A , Hisham S J , Rahman K A , et al . 5GPT: 5G vulnerability detection by combining Zero-Shot capabilities of GPT-4 with domain aware strategies through prompt engineering [J ] . IEEE Transactions on Information Forensics and Security , 2025 .
Wang F , Zhang Z , Zhang X , et al . A comprehensive survey of small language models in the era of large language models: Techniques, enhancements, applications, collaboration with llms, and trustworthiness [J ] . ACM Transactions on Intelligent Systems and Technology , 2025 , 16 ( 6 ): 1 - 87 .
Ilchenko M . NEXT-GEN TELECOM AI: MASTERING PROMPT ENGINEERING FOR INNOVATION [J ] . Information and Telecommunication Sciences , 2025 , ( 1 ): 22 - 29 .
0
浏览量
0
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