| 105 | 0 | 10 |
| 下载次数 | 被引频次 | 阅读次数 |
随着通信迈入6G时代，传统依赖物理资源扩展的通信模式难以满足智能化、泛在化的发展需求。提出一种意图驱动的智简通信系统，融合认知心理学、信息论与人工智能方法，以语义token为基本单元，构建面向信息效用的通信范式。该系统集成智能体的感知、认知与反馈能力，实现异构数据的上下文感知语义建模与压缩传输，重点突破语义编码、意图解析、鲁棒传输与可信解码等关键技术。所提架构适配人—人感知、人—机控制与多机协同等差异化需求，支持在带宽受限与信道动态条件下的高效稳健传输。系统梳理了智简通信的研究脉络与核心机制，为构建高效、泛用、可持续的智能通信体系提供理论支撑与技术参考。
Abstract：As communication evolves into the 6G era, traditional paradigms relying on physical resource expansion are increasingly struggling to meet the burgeoning demand for intelligent and ubiquitous connectivity. An intent-driven intelligent and concise communications system is proposed, which seamlessly integrates insights from cognitive psychology, information theory, and artificial intelligence. Using semantic tokens as the basic representation units, the system establishes a communication framework centered on information utility. It incorporates intelligent agents with perception, cognition, and feedback capabilities to achieve context-aware semantic modeling and compressed transmission of heterogeneous data. The system's key enabling technologies comprehensively include semantic encoding, intent parsing, robust transmission, and reliable decoding. The proposed architecture supports differentiated communication needs, including high-fidelity human-human interaction, efficient human-machine control, and collaborative multi-agent systems. It is particularly effective and robust under bandwidth-limited and dynamically varying channel conditions. This study reviews the development trajectory and technical foundations of intelligent and concise communication, providing theoretical and practical guidance for building efficient, general-purpose, and sustainable communication systems.
[1] 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, 8:60-73.DOI:10.1016/j.eng.2021.11.003
[2] CHACCOUR C, SAAD W, DEBBAH M, et al.Less data, more knowledge:building next-generation semantic communication networks[J].IEEE communications surveys&tutorials, 2024, 27(1):37-76.DOI:10.1109/comst.2024.3412852
[3] XIA L, SUN Y, LIANG C S, et al.Generative AI for semantic communication:architecture, challenges, and outlook[J].IEEE wireless communications, 2025, 32(1):132-140.DOI:10.1109/mwc.003.2300351
[4] WEAVER W.Recent contributions to the mathematical theory of communication[EB/OL].[2025-05-06].https://courses.ischool.berkeley.edu/i218/s15/Weaver_Recent-Contributions.pdf
[5]路甬祥.学科交叉与交叉科学的意义[J].中国科学院院刊, 2005, 20(1):58-60.DOI:10.16418/j.issn.1000-3045.2005.01.014
[6] GRATTAN-GUINNESS I.From the calculus to set theory 1630-1910:an introductory history[M].New Jersey, USA:Princeton University Press, 2020
[7] NISHIMORI H.Statistical physics of spin glasses and information processing:an introduction[M].Oxford, UK:Clarendon Press, 2001
[8] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[EB/OL].(2023-08-02)[2025-05-22].https://arxiv.org/abs/1706.03762
[9] BARSALOU L W.Perceptual symbol systems[J].Behavioral and brain sciences, 1999, 22(4):577-609; discussion 610-660.DOI:10.1017/s0140525x99002149
[10] BENGIO Y.Learning deep architectures for AI[J].Foundations and trends in machine learning, 2009, 2(1):1-127.DOI:10.1561/2200000006
[11] BOURTSOULATZE E, BURTH KURKA D, GUNDUZ D.Deep joint source-channel coding for wireless image transmission[J].IEEE transactions on cognitive communications and networking,2019, 5(3):567-579.DOI:10.1109/tccn.2019.2919300
[12] GUNDUZ D, QIN Z J, AGUERRI I E, et al.Beyond transmitting bits:context, semantics, and task-oriented communications[J].IEEE journal on selected areas in communications, 2022, 41(1):5-41.DOI:10.1109/jsac.2022.3223408
[13]张平.语义通信:未来通信系统的智简之道[J].中兴通讯技术,2024, 30(1):1-2.DOI:10.12142/ZTETJ.202401001
[14]吕守晔,戴金晟,张平.信源信道联合的新范式:语义通信[J].中兴通讯技术, 2023, 29(2):2-8.DOI:10.12142/ZTETJ.202302002
[15] LUO X W, CHEN H H, GUO Q.Semantic communications:overview, open issues, and future research directions[J].IEEE wireless communications, 2022, 29(1):210-219.DOI:10.1109/mwc.101.2100269
[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.DOI:10.1109/jsac.2022.3180802
[17]WANG S X,DAI J C,LIANG Z J,et al.Wireless deep video semantic transmission[J].IEEE journal on selected areas in communications,2022,41(1):214-229.DOI:10.1109/jsac.2022.3221977
[18]ERDEMIR E,TUNG T Y,DRAGOTTI P L,et al.Generative joint source-channel coding for semantic image transmission[J].IEEE journal on selected areas in communications,2023,41(8):2645-2657.DOI:10.1109/jsac.2023.3288243
[19]TAN K L,DAI J C,LIU Z Y,et al.Rate-distortion-perception controllable joint source-channel coding for high-fidelity generative semantic communications[J].IEEE transactions on cognitive communications and networking,2024,11(2):672-686.DOI:10.1109/tccn.2024.3511960
[20]WANG S X,DAI J C,TAN K L,et al.DiffCom:channel received signal is a natural condition to guide diffusion posterior sampling[J].IEEE journal on selected areas in communications,2025,43(7):2651-2666.DOI:10.1109/jsac.2025.3559158
[21]BLAU Y,MICHAELI T.Rethinking lossy compression:the ratedistortion-perception tradeoff[EB/OL].(2019-07-30)[2025-05-20].https://arxiv.org/abs/1901.07821
[22]WASSILIWIZKY E,MENNINGHAUS W.Why and how should cognitive science care about aesthetics?[J].Trends in cognitive sciences,2021,25(6):437-449.DOI:10.1016/j.tics.2021.03.008
[23]MIN X K,GU K,ZHAI G T,et al.Screen content quality assessment:overview,benchmark,and beyond[J].ACMcomputing surveys,2022,54(9):1-36.DOI:10.1145/3470970
[24]YU Q,WEBER M,DENG X,et al.An image is worth 32 tokens for reconstruction and generation[EB/OL].(2024-06-11)[2025-05-21].https://arxiv.org/abs/2406.07550
[25]YAO J,YANG B,WANG X.Reconstruction vs.generation:taming optimization dilemma in latent diffusion models[EB/OL].[2025-05-21].https://cvpr.thecvf.com/virtual/2025/poster/33084
[26]QIN H L,DAI J,WANG S,et al.Neural coding is not always semantic:towards the standardized coding workflow in semantic communications[EB/OL].(2025-05-24)[2025-05-25].https://arxiv.org/abs/2505.18637
[27]LAN Q,WEN D Z,ZHANG Z Z,et al.What is semantic communication?a view on conveying meaning in the era of machine intelligence[J].Journal of communications and information networks,2021,6(4):336-371.DOI:10.23919/jcin.2021.9663101
[28]YANG W T,LIEW Z Q,LIM W Y B,et al.Semantic communication meets edge intelligence[J].IEEE wireless communications,2022,29(5):28-35.DOI:10.1109/mwc.004.2200050
[29]YANG W T,XIONG Z H,YUAN Y L,et al.Agent-driven generative semantic communication with cross-modality and prediction[J].IEEE transactions on wireless communications,2024,24(3):2233-2248.DOI:10.1109/twc.2024.3519325
[30]TSENG W C,WANG T H J,LIN Y C,et al.Offline multi-agent reinforcement learning with knowledge distillation[EB/OL].(2022-11-28)[2025-05-25].https://dl.acm.org/doi/10.5555/3600270.3600287
[31]SYKORA Q,REN M,URTASUN R.Multi-agent routing value iteration network[EB/OL].(2020-07-09)[2025-05-28].https://arxiv.org/abs/2007.05096
[32]LIU Y,WANG W X,HU Y J,et al.Multi-agent game abstraction via graph attention neural network[J].Proceedings of the AAAIconference on artificial intelligence,2020,34(5):7211-7218.DOI:10.1609/aaai.v34i05.6211
[33]CHEN S K,DONG J Q,HA P Y J,et al.Graph neural network and reinforcement learning for multi-agent cooperative control of connected autonomous vehicles[J].Computer-aided civil and infrastructure engineering,2021,36(7):838-857.DOI:10.1111/mice.12702
[34]MAO H Y,LIU W L,HAO J Y,et al.Neighborhood cognition consistent multi-agent reinforcement learning[J].Proceedings of the AAAI conference on artificial intelligence,2020,34(5):7219-7226.DOI:10.1609/aaai.v34i05.6212
[35]CHEN F,REN W.On the control of multi-agent systems:a survey[J].Foundations and trends in systems and control,2019,6(4):339-499.DOI:10.1561/2600000019
[36]YANG D,YANG K,WANG Y,et al.How2comm:communicationefficient and collaboration-pragmatic multi-agent perception[J].Advances in neural information processing systems,2023,36:25151-25164
基本信息:
DOI：
中图分类号:TN929.5
引用信息:
[1]戴金晟,秦晓琦,秦海龙等.意图驱动的智简通信[J].中兴通讯技术,2025,31(04):3-12.
基金信息:
国家重点研发计划项目（2024YFF0509700）; 国家自然科学基金项目（62371063）; 北京市自然科学基金项目（L232047）; 北京市科技新星计划