通信学报 ›› 2021, Vol. 42 ›› Issue (5): 1-12.doi: 10.11959/j.issn.1000-436x.2021084

• 学术论文 •    

频谱知识图谱:面向未来频谱管理的智能引擎

孙佳琛, 王金龙, 丁国如, 陈瑾, 龚玉萍   

  1. 陆军工程大学通信工程学院,江苏 南京 210007
  • 修回日期:2020-11-09 出版日期:2021-05-01 发布日期:2021-05-01
  • 作者简介:孙佳琛(1994- ),女,江苏南通人,陆军工程大学博士生,主要研究方向为频谱数据分析、无线通信、认知无线网络
    王金龙(1963- ),男,河北沧州人,博士,中国科学院院士,陆军工程大学教授、博士生导师,主要研究方向为短波通信、数字通信、数字信号处理、移动通信、软件无线电与认知无线电等
    丁国如(1986- ),男,河南新乡人,博士,陆军工程大学教授,主要研究方向为认知无线网络、大规模MIMO、机器学习、大数据分析等
    陈瑾(1971- ),女,福建仙游人,博士,陆军工程大学教授、博士生导师,主要研究方向为认知无线网络、分布式优化、数字信号处理等
    龚玉萍(1978- ),女,安徽庐江人,陆军工程大学教授,主要研究方向为短波通信、认知无线电等
  • 基金资助:
    科技创新2030?“新一代人工智能”重大项目(2018AAA0102303);国家自然科学基金资助项目(U20B2038);国家自然科学基金资助项目(61871398);国家自然科学基金资助项目(61931011);江苏省自然科学基金杰出青年基金资助项目(BK20190030)

Spectrum knowledge graph: an intelligent engine facing future spectrum management

Jiachen SUN, Jinlong WANG, Guoru DING, Jin CHEN, Yuping GONG   

  1. College of Communications Engineering, Army Engineering University, Nanjing 210007, China
  • Revised:2020-11-09 Online:2021-05-01 Published:2021-05-01
  • Supported by:
    The Science and Technology Innovation 2030-Key Project of “New Generation Artificial Intelligence” of China(2018AAA0102303);The National Natural Science Foundation of China(U20B2038);The National Natural Science Foundation of China(61871398);The National Natural Science Foundation of China(61931011);The Natural Science Foundation for Distinguished Young Scholars of Jiangsu Province(BK20190030)

摘要:

针对当前频谱管理中表征方式较单一、管理方式对人的经验依赖性较强、管理效率和精准度较低等问题,面向未来频谱管理的自动化、智能化、精准化需求,将知识图谱理论与技术引入频谱管理中,给出了频谱知识图谱的概念和其依赖的频谱知识体系,以及三元组形式的表示方法,构建了由图谱层、设备层和场景层构成的基于频谱知识图谱的智能频谱管理框架,探讨了基于频谱知识图谱的用频推荐、频谱搜索、频谱问答等典型应用。仿真实验表明,频谱知识图谱能在用频推荐中发挥知识引导的作用。

关键词: 频谱管理, 知识图谱, 认知图谱, 认知无线电, 用频推荐, 频谱搜索, 频谱问答

Abstract:

To solve the issues of simple representations on spectrum situation, much dependence on artificial experience in manual management and low efficiency and accuracy in the current spectrum management, meeting the requirements of automation, precision and real time for future spectrum management, the theory and technology of knowledge graph were introduced into spectrum management.The definition of spectrum knowledge graph, the knowledge schema it depends on and its representation in the form of triples were proposed.The intelligent spectrum management framework based on spectrum knowledge graph, consisting of the graph layer, the equipment layer and the scenario layer, was constructed.Typical applications based on spectrum knowledge graph were discussed, including the recommendation system for spectrum usage, the search engine on spectrum management, and question answering for spectrum management.Experiments demonstrate the spectrum knowledge graph can play a role of guidance by spectrum knowledge in spectrum usage recommendation.

Key words: spectrum management, knowledge graph, cognitive graph, cognitive radio, recommendation for spectrum usage, search on spectrum management, question answering for spectrum management

中图分类号: 

No Suggested Reading articles found!