| 168 | 0 | 91 |
| 下载次数 | 被引频次 | 阅读次数 |
通信与智能融合(Communication and Artificial Intelligence, ComAI)作为通信与智能深度融合的新范式，正成为突破传统通信瓶颈、重构网络生态的核心引擎。系统探讨了ComAI的战略定位、理论框架与关键技术，提出以语义信息论为基础的新型通信范式，通过语义熵、语义互信息等理论创新突破香农极限，构建了语义基(Semantic base, Seb)物理模型、语义知识库(Semantic Knowledge Base, SKB)、模分多址(Model Division Multiple Access, MDMA)等技术体系。ComAI通过内生智能、语义驱动和多维融合特征，赋能6G典型场景，实现通信效率、网络智能化和多智能体协同的飞跃。尽管面临理论度量、产业协同、信息安全等挑战，ComAI仍将推动通信系统从“连接万物”迈向“赋能万物”,为未来通信系统的发展提供关键路径。
Abstract：The convergence of Communication and Artificial Intelligence(ComAI) is emerging as a core engine to break through traditional communication bottlenecks and reshape the network ecosystem. This study systematically explores the strategic positioning, theoretical framework, and key technologies of ComAI, proposing a novel communication paradigm based on semantic information theory. Through theoretical innovations such as semantic entropy and semantic mutual information, ComAI transcends Shannon's limit and establishes a technical architecture encompassing Semantic base(Seb)physical models, Semantic Knowledge Base(SKB), and Model Division Multiple Access(MDMA). With its features of endogenous intelligence, semantic-driven optimization, and multi-dimensional convergence, ComAI empowers typical 6G scenarios, achieving breakthroughs in communication efficiency, network intelligence, and multi-agent collaboration. Despite challenges in theoretical metrics, industrial coordination, and information security, ComAI will drive communication systems from ‘connecting everything' to ‘empowering everything' providing a critical pathway for the development of future communication systems.
[1] 张平，牛凯，姚圣时，等.面向未来的语义通信：基本原理与实现方法[J].通信学报，2023,44(5):1-14.
[2] ZHANG P,XU W J,GAO H,et al.Toward Wisdom-evolutionary and Primitive-concise 6G:A New Paradigm of Semantic Communication Networks[J].Engineering,2022,8(1):60-73.
[3] RASHID H V,JEONG S H.AI Empowered 6G Technologies and Network Layers:Recent Trends,Opportunities,and Challenges[J].Expert Systems with Applications,2025,267:125985.
[4] LETAIEF K B,CHEN W,SHI Y M,et al.The Roadmap to 6G:AI Empowered Wireless Networks[J].IEEE Communications Magazine,2019,57(8):84-90.
[5] YANG Y,MA M L,WU H Q,et al.6G Network AI Architecture for Everyone-centric Customized Services[J].IEEE Network,2023,37(5):71-80.
[6] 牛凯，张平.语义通信的数学理论[J].通信学报，2024,45(6):7-59.
[7] PAPADOPOULOS H,WANG C W,BURSALIOGLU O,et al.Massive MIMO Technologies and Challenges Towards 5G[J].IEICE Transactions on Communications,2016(3):602-621.
[8] FARHANG-BOROUJENY B,MORADI H.OFDM Inspired Waveforms for 5G[J].IEEE Communications Surveys & Tutorials,2016,18(4):2474-2492.
[9] SHANNON C E.A Mathematical Theory of Communication[J].The Bell System Technical Journal,1948,27(3):379-423.
[10] KHAN N A,SCHMID S.AI-RAN in 6G Networks:State-of-the-art and Challenges[J].IEEE Open Journal of the Communications Society,2024,5:294-311.
[11] KUNDU L,LIN X Q,GADIYAR R,et al.AI-RAN:Transforming RAN with AI-driven Computing Infrastructure[EB/OL].(2025-01-15)[2025-04-10].https://arxiv.org/abs/2501.09007.
[12] GUO Q Y,LIANG H T,BAO Z C,et al.Intellicise Router Promotes Endogenous Intelligence in Communication Network[J].IEEE Transactions on Machine Learning in Communications and Networking,2024,2:1509-1526.
[13] ZHANG P,XU X D,DONG C,et al.Intellicise Wireless Networks from Semantic Communications:A Survey,Research Issues,and Challenges[J/OL].IEEE Communications Surveys & Tutorials,1-1[2025-02-10].https://ieeexplore.ieee.org/document/10634888.
[14] 孙亚萍，崔曙光，张平.面向语义通信的语义知识库综述[J].中兴通讯技术，2023,29(2):19-23.
[15] ZHANG P,XU X D,DONG C,et al.Model Division Multiple Access for Semantic Communications[J].Frontiers of Information Technology & Electronic Engineering,2023,24(6):801-812.
[16] DAI J C,WANG S X,TAN K L,et al.Nonlinear Transform Source-channel Coding for Semantic Communications[J].IEEE Journal on Selected Areas in Communications,2022,40(8):2300-2316.
[17] NIU K,LIANG Z J,DONG C,et al.Semantics-division Duplexing:A Novel Full-Duplex Paradigm[J].IEEE Wireless Communications,2024,31(4):307-314.
[18] DORRIA,KANHERE S S,JURDAK R.Multi-agent Systems:A Survey[J].IEEE Access,2018,6:28573-28593.
[19] XIAO Y,SHI G M,ZHANG P.Towards Agentic AI Networking in 6G:A Generative Foundation Model-as-agent Approach[EB/OL].(2025-03-20)[2025-04-10].https://arxiv.org/abs/2503.15764.
[20] 张浩严，吕文涛，余润泽，等.大语言模型研究现状[J].无线电工程，2025,55(1):163-174.
[21] LIU X H,LIU H,YANG G X,et al.A Generalist Medical Language Model for Disease Diagnosis Assistance[J].Nature Medicine,2025,31(3):932-942.
基本信息:
DOI：
中图分类号:TN929.5
引用信息:
[1]张平,马楠,许晓东等.ComAI:通信与智能深度融合新范式[J].无线电工程,2025,55(07):1367-1375.
基金信息:
国家自然科学基金(62293480,62293481)~~