Research and application of intelligent operation and maintenance human-computer interaction system based on large language models for communication networks

Han Sai; Fan Fengxia; Ma Jiafu; Wang Zelin; Xu Bohua; Wang Guangquan; Tang Xiongyan

doi:10.11959/j.issn.1000-0801.2026020

您当前的位置：

首页 >

文章列表页 >

Research and application of intelligent operation and maintenance human-computer interaction system based on large language models for communication networks

Engineering and Application | 更新时间：2026-03-02

- Research and application of intelligent operation and maintenance human-computer interaction system based on large language models for communication networks
- Telecommunications Science Vol. 42, Issue 1, Pages: 199-210(2026)
- 作者机构：
  
  中国联合网络通信有限公司研究院，北京 100044
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2026020
  CLC： TP393;TN915.07
- Received：01 July 2025，
  
  Revised：2025-08-25，
  
  Accepted：19 September 2025，
  
  Published：20 January 2026
- 稿件说明：
移动端阅览
韩赛,范凤霞,马家福等.基于通信网络大模型的智能运维人机交互系统研究与应用[J].电信科学,2026,42(01):199-210.

Han Sai,Fan Fengxia,Ma Jiafu,et al.Research and application of intelligent operation and maintenance human-computer interaction system based on large language models for communication networks[J].Telecommunications Science,2026,42(01):199-210.
韩赛,范凤霞,马家福等.基于通信网络大模型的智能运维人机交互系统研究与应用[J].电信科学,2026,42(01):199-210. DOI： 10.11959/j.issn.1000-0801.2026020.

Han Sai,Fan Fengxia,Ma Jiafu,et al.Research and application of intelligent operation and maintenance human-computer interaction system based on large language models for communication networks[J].Telecommunications Science,2026,42(01):199-210. DOI： 10.11959/j.issn.1000-0801.2026020.

摘要

随着网络规模的扩大和5G应用的爆发式增长，网络管理运营面临新的需求和挑战。运营效率直接影响网络使用效能和服务质量，亟须通过智能化手段提升网络管理运营水平，减少传统低效、重复性工作。随着AI技术和通信网络的深度融合，引入通信网络大模型成为提升网络管理运营效率的关键路径。对此，研发了一套基于大语言模型的智能运维人机交互系统。该系统通过大小模型协同机制，集成了知识问答、人机交互、数据分析与方案生成等功能。该系统在现网的部署应用表明，其不仅能够显著提升运维效率，降低运维成本，还能通过预测性维护减少网络故障的发生，提升用户体验，增强企业竞争力。该系统具备高度可复制性与推广适应性，具有广泛的应用前景与实用价值。

Abstract

With the continuous expansion of network scale and the explosive growth of 5G applications

new demands and challenges are encountered in network management and operations. Since operational efficiency directly influences network utilization and service quality

it becomes imperative to enhance the level of network management through intelligent means and reduce traditional inefficient and repetitive tasks. As AI technology becomes deeply integrated with communication networks

the introduction of large-scale communication network models is recognized as a key pathway to promote network management and operations. In response

an intelligent operational human-computer interaction system based on large language models (LLMs) was developed. This system integrated capabilities such as knowledge-based question answering

human-computer interaction

data analysis

and solution generation through a collaboration mechanism between large and small models. Deployment and application of the system in live networks demonstrated that it not only significantly improved operational efficiency and reduced maintenance costs

but also minimized network failures through predictive maintenance

thereby enhancing user experience and strengthening corporate competitiveness. The system was designed with high replicability and adaptability

indicating broad application prospects and practical value.

关键词

Keywords

references

王泽林 , 韩赛 , 张洁 , 等 . 中国联通自智网络研究与实践 [J ] . 通信世界 , 2022 ( 21 ): 42 - 45 .

Wang Z L , Han S , Zhang J , et al . Research and practice of China Unicom’s intelligent network [J ] . Communications World , 2022 ( 21 ): 42 - 45 .

Han S , Ma H B , Chen D , et al . Streaming video optimization in mobile communications [C ] // Proceedings of the 2018 IEEE/CIC International Conference on Communications in China (ICCC) . Piscataway : IEEE Press , 2019 : 495 - 499 .

裴培 , 王爽 , 刘一平 , 等 . 数字化转型时代下运营商IT架构进阶之路 [J ] . 信息通信技术 , 2021 , 15 ( 6 ): 66 - 71 .

Pei P , Wang S , Liu Y P , et al . The advanced path of telecom operators' IT architecture in the era of digital transformation [J ] . Information and Communications Technologies , 2021 , 15 ( 6 ): 66 - 71 .

Han S , Ma H B , Zhang P , et al . Improved MPEG-4 high-efficiency AAC with variable-length soft-decision decoding of the quantized spectral coefficients [J ] . China Communications , 2019 , 16 ( 10 ): 65 - 82 .

周晶 , 王德政 , 洪科 . 5G网络智能运维AI应用研究 [J ] . 邮电设计技术 , 2021 ( 11 ): 83 - 87 .

Zhou J , Wang D Z , Hong K . Research on AI application in 5G network intelligent operation and maintenance [J ] . Designing Techniques of Posts and Telecommunications , 2021 ( 11 ): 83 - 87 .

Menaria V K , Jain S C , Raju N , et al . NLFFT: a novel fault tolerance model using artificial intelligence to improve performance in wireless sensor networks [J ] . IEEE Access , 2020 , 8 : 149231 - 149254 .

Mohammed S . Artificial intelligence in computer networks: delay estimation, fault detection, and network automation [D ] . Ottawa : University of Ottawa , 2021 .

Cao Y , Wang R , Chen M , et al . AI agent in software-defined network: agent-based network service prediction and wireless resource scheduling optimization [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 7 ): 5816 - 5826 .

Aron R , Abraham A . Resource scheduling methods for cloud computing environment: the role of meta-heuristics and artificial intelligence [J ] . Engineering Applications of Artificial Intelligence , 2022 , 116 : 105345 .

Ribeiro H , Barbosa B , Moreira A C , et al . Customer experience, loyalty, and churn in bundled telecommunications services [J ] . Sage Open , 2024 , 14 ( 2 ): 21582440241245191 .

Banjanin M K , Stojčić M , Danilović D , et al . Classification and prediction of sustainable quality of experience of telecommunication service users using machine learning models [J ] . Sustainability , 2022 , 14 ( 24 ): 17053 .

韩赛 , 张冬月 , 王泽林 , 等 . 跨专业承载网络智能运维研究与应用 [J ] . 电信科学 , 2022 , 38 ( 11 ): 113 - 122 .

Han S , Zhang D Y , Wang Z L , et al . Research and applications on intelligent operations of cross-professional carrying network [J ] . Telecommunications Science , 2022 , 38 ( 11 ): 113 - 122 .

Zhou H , Hu C M , Yuan Y , et al . Large language model (LLM) for telecommunications: a comprehensive survey on principles, key techniques, and opportunities [J ] . IEEE Communications Surveys & Tutorials , 2025 , 27 ( 3 ): 1955 - 2005 .

Ma J F , Han S , Wang G Q , et al . An LLM-based cross-domain fault localization in carrier networks [C ] // Proceedings of the 2024 4th International Conference on Artificial Intelligence, Robotics, and Communication (ICAIRC) . Piscataway : IEEE Press , 2025 : 731 - 736 .

Abdelaziz I , Basu K , Agarwal M , et al . Granite-function calling model: introducing function calling abilities via multi-task learning of granular tasks [J ] . arXiv preprint , 2024 , arXiv: 2407.00121 .

韩赛 , 范凤霞 , 叶晓斌 , 等 . 面向优质用户体验的自智网络研究与应用 [J ] . 信息通信技术 , 2023 , 17 ( 3 ): 34 - 41 .

Han S , Fan F X , Ye X B , et al . Research and application of autonomous networks for high quality user experience [J ] . Information and Communications Technologies , 2023 , 17 ( 3 ): 34 - 41 .

Bariah L , Zhao Q Y , Zou H , et al . Large generative AI models for telecom: the next big thing? [J ] . arXiv preprint , 2023 , arXiv: 2306.10249 .

Vaswani A , Shazeer N , Parmar N , et al . Attention is all you need [C ] // Proceedings of the 31st International Conference on Neural Information Processing System . New York : Curran Associates , 2017 : 6000 - 6010 .

Kan K B , Mun H , Cao G H , et al . Mobile-LLaMA: instruction fine-tuning open-source LLM for network analysis in 5G networks [J ] . IEEE Network , 2024 , 38 ( 5 ): 76 - 83 .

Marvin G , Hellen N , Jjingo D , et al . Prompt engineering in large language models [M ] // Data Intelligence and Cognitive Informatics: Proceedings of ICDICI 2023 . Singapore : Springer , 2024 : 387 - 402 .

Han S , Wang Z , Wang G , et al . Automatic association of cross-domain network topology [C ] // IEEE International Conference on Trust, Security and Privacy in Computing and Communications . Piscataway : IEEE Press , 2022 : 1173 - 1178 .

Han S , Li A , Zhang D Y , et al . Early warning of core network capacity in space-terrestrial integrated networks [J ] . Journal of Systems Engineering and Electronics , 2024 , 35 ( 4 ): 855 - 864 .

Views

144

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on customer escalated complaints prediction based on LLM-RFE-XGBoost approach

Automated extraction and evaluation of business process entities and relations via pre-trained models

Large language model for cloud-network configuration audit and its application in IP network

Multi-hop question answering by integrating large language models and knowledge graphs

Related Author

HAN Sai

FAN Fengxia

MA Jiafu

WANG Zelin

XU Bohua

WANG Guangquan

TANG Xiongyan

Qiao Yaqian

Related Institution

China Mobile Online Service Co., Ltd., AI Capability Center

China Mobile Online Service Co., Ltd., Shandong Branch

Electric Power Science Research Institute, State Grid Liaoning Electric Power Co., Ltd.

State Grid Information and Communication Industry Group Corporation

Aostar Information Technologies Co., Ltd.

⁰