摘要
语义通信是一种超越比特传输的通信范式,可使无线网络更智能和可持续。首先,本文简述了语义通信的基本构成以及常用的性能度量;然后,依据接收端任务是否可为发射端已知,将语义通信分为面向特定任务和面向广义任务两类,现有语义通信工作以面向特定任务为主;接着,通过仿真表明现有语义通信工作无法有效处理广义任务;最后,探讨了语义通信的潜在问题和未来工作方向。
Semantic communication is a communication paradigm that goes beyond bit transmission to make wireless networks more intelligent and sustainable.Firstly,this paper briefly introduces the basic structure and common performance metrics of semantic communications.Secondly,based on whether the task of the receiver can be known to the transmitter,semantic communications are divided into two categories:oriented to specific tasks and oriented to generalized tasks,and the existing semantic communication works mainly focus on specific tasks.Then,simulations demonstrate that the existing semantic communication works cannot effectively cope with generalized tasks.Finally,potential issues and future directions for semantic communication are discussed.
作者
王衍虎
郭帅帅
WANG Yanhu;GUO Shuaishuai(Shandong University,Jinan 250061,China)
出处
《移动通信》
2023年第4期14-17,24,共5页
Mobile Communications
基金
国家自然科学基金(62171262)
山东省重大科技创新工程(2020CXGC010109)
山东省自然科学基金(ZR2021YQ47)
山东省泰山人才工程(tsqn201909043)。
关键词
语义通信
6G
面向任务
深度学习
semantic communication
6G
task-oriented
deep learning