基于知识图谱的6G网络场景认知研究

doi:10.11959/j.issn.2096-6652.202339

智能科学与技术学报 ›› 2023, Vol. 5 ›› Issue (4): 494-504.doi: 10.11959/j.issn.2096-6652.202339

基于知识图谱的6G网络场景认知研究

赵茁乔¹, 承楠¹(), 陈劼², 陈芳炯³, 李长乐¹

^1.西安电子科技大学通信工程学院，陕西西安 710071
^2.电子科技大学通信抗干扰技术国家级重点实验室，四川成都 610054
^3.华南理工大学电子与信息学院，广东广州 510640

收稿日期:2023-02-23 修回日期:2023-05-02 出版日期:2023-12-15 发布日期:2023-12-15
通讯作者: 承楠 E-mail:dr.nan.cheng@ieee.org
作者简介:赵茁乔（1998- ），男，西安电子科技大学通信工程学院硕士生，主要研究方向为知识图谱在通信领域的应用。
承楠（1987- ），男，博士，西安电子科技大学通信工程学院教授、博士生导师。主要研究方向为智能网联汽车与先进交通系统、无人驾驶、空天地一体化网络技术，人工智能与大数据在网络中的应用，5G、B5G、6G先进网络技术研究与探索。
陈劼（1973- ），女，博士，电子科技大学通信抗干扰技术国家级重点实验室副研究员，主要研究方向为认知无线电关键技术与应用及宽带多媒体集群。
陈芳炯（1975- ），男，博士，华南理工大学电子与信息学院教授、博士生导师。主要研究方向为无线通信及组网技术，覆盖陆地及水下网络，具体包括信道估计与均衡、新型调制技术、声电协同组网等。
陈芳炯（1975- ），男，博士，华南理工大学电子与信息学院教授、博士生导师。主要研究方向为无线通信及组网技术，覆盖陆地及水下网络，具体包括信道估计与均衡、新型调制技术、声电协同组网等。
李长乐（1976- ），男，博士，西安电子科技大学通信工程学院教授、副院长、博士生导师。主要研究方向为网联网控无人驾驶、智能网联汽车超视距感知、交通大数据分析及应用、大规模网络技术、高动态网络技术等。
基金资助:
国家重点研发计划(2020YFB1807700)

Research on 6G network scenario cognition based on knowledge graph

Zhuoqiao ZHAO¹, Nan CHENG¹(), Jie CHEN², Fangjiong CHEN³, Changle LI¹

^1.College of Communication Engineering, Xidian University, Xi'an 710071, China
^2.National Key Laboratory of Communication, University of Electronic Science and Technology of China, Chengdu 610054, China
^3.School of Electronics and Information Engineering, South China University of Technology, Guangzhou 510640, China

Received:2023-02-23 Revised:2023-05-02 Online:2023-12-15 Published:2023-12-15
Contact: Nan CHENG E-mail:dr.nan.cheng@ieee.org
Supported by:
National Key Research and Development Program of China(2020YFB1807700)

摘要/Abstract

摘要：

6G网络覆盖空天地海全域，对于多样化、个性化的场景，6G网络需要提供定制化的服务，即按需服务。为实现全域全场景的按需服务，对场景特性进行精准、实时、智能的认知是一个重要前提。如何使网络自主智能地认知不同的场景及服务并将认知结果转换成场景特定的网络关键性能指标，并进一步对网络资源进行高效调度是亟待解决的关键问题。为此，将知识图谱应用于网络场景的认知识别，形成对6G网络场景的规范化描述，并构建了基于6G场景本体的知识图谱。同时，提出一种基于知识图谱嵌入的场景认知推理方法，实现了对图谱节点和关系的嵌入学习，并对场景特征节点进行了预测推理，取得了较高的准确度。该方法有助于实现6G全场景网络中场景感知、认知、按需服务的服务全生命周期自主管控，对于提高下一代网络的自主性和智能性有重要的指导意义。

关键词: 6G全场景, 场景认知, 知识图谱, 图嵌入, 节点预测

Abstract:

The 6G network covers the entire space, air, ground, and sea. For diversified and personalized scenarios, the 6G network needs to provide customized services, that is, on-demand services. In order to realize on-demand services in all domains and scenarios, accurate, real-time, and intelligent cognition of the characteristics of the scenarios is an important prerequisite. How to enable the network to autonomously and intelligently recognize different scenarios and services, convert them into scenario-specific network key performance indicator (KPI), and further efficiently schedule network resources is a key problem that urgently needs to be solved. This paper applies the knowledge graph to the cognitive recognition of network scenarios, forms a standardized description of 6G network scenarios, and builds a knowledge graph based on the 6G scenario ontology. At the same time, a scene cognition reasoning method based on knowledge graph embedding is proposed, which realizes the embedding learning of graph nodes and relationships and reasons about scene feature nodes, achieving high accuracy. The method proposed in this paper helps to realize the autonomous control of the service life cycle of scene awareness, cognition, and on-demand services in the 6G full-scenario network, and has important innovation and guiding significance for improving the autonomy and intelligence of the next-generation network.

Key words: 6G full scenario, scenario cognition, knowledge graph, graph embedding, node prediction

中图分类号:

TP391.1

赵茁乔, 承楠, 陈劼, 等. 基于知识图谱的6G网络场景认知研究[J]. 智能科学与技术学报, 2023, 5(4): 494-504.

Zhuoqiao ZHAO, Nan CHENG, Jie CHEN, et al. Research on 6G network scenario cognition based on knowledge graph[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(4): 494-504.

图/表 13

图1

表1

表2

图2

图3

表3

图4

图5

图6

图7

图8

表4

图9

参考文献 19

1	赵亚军,郁光辉,徐汉青.6G移动通信网络:愿景、挑战与关键技术[J].中国科学:信息科学, 2019, 49(8): 963-987.
	ZHAO Y J, YU G H, XU H Q. 6G mobile communication networks: vision, challenges, and key technologies[J]. Scientia Sinica(Informationis), 2019, 49(8): 963-987.
2	IMT-2030推进组. IMT-2030(6G)推进组正式发布《6G总体愿景与潜在关键技术》白皮书[J]. 互联网天地, 2021(6): 8-9.
	IMT-2030 Promotion Group. IMT-2030 (6G) Promotion Group officially released the white paper, "6G Overall Vision and Potential Key Technologies"[J]. China Internet, 2021(6): 8-9.
3	CHENG K X, ZHU L, YAO C H, et al. Squeeze-excitation based communication behavior recognition approach for spectrum sensing data[C]//Proceedings of 2021 7th International Conference on Computer and Communications (ICCC). Piscataway: IEEE Press, 2021: 682-686.
4	ZHOU T, WANG Y J, WANG C X, et al. Multi-feature fusion based recognition and relevance analysis of propagation scenes for high-speed railway channels[J]. IEEE Transactions on Vehicular Technology, 2020, 69(8): 8107-8118.
5	WANG Y, WANG X, SHEN B, et al. Clustering optimization and HOG feature extraction based primary user activity scene recognition scheme[C]//Proceedings of 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring). Piscataway: IEEE Press, 2022: 1-5.
6	李建东, 杨晶晶, 黄铭. 基于知识图谱的Wi-Fi室内定位技术研究[J]. 物联网学报, 2022, 6(2): 19-25.
	LI J D, YANG J J, HUANG M. Research on Wi-Fi indoor positioning technology based on knowledge graph[J]. Chinese Journal on Internet of Things, 2022, 6(2):19-25.
7	BAI Y L, WANG D, SONG B. A knowledge graph-based cooperative caching scheme in MEC-enabled heterogeneous networks[C]//Proceedings of GLOBECOM 2022 - 2022 IEEE Global Communications Conference. Piscataway: IEEE Press, 2022: 5959-5964.
8	SONG G X, ZHENG M Z, XU H K, et al. Construction of 5G protocol knowledge graph based on multi-relation and sequential chain[C]//Proceedings of 2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA). Piscataway: IEEE Press, 2022: 1374-1377.
9	徐增林, 盛泳潘, 贺丽荣, 等.知识图谱技术综述[J]. 电子科技大学学报, 2016, 45(4): 589-606.
	XU Z L, SHENG Y P, HE L R, et al. Review on knowledge graph techniques[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(4): 589-606.
10	STUDER R. Knowledge engineering: principles and methods[J].Data & Knowledge Engineering, 2008, 25(1-2) :161-197.
11	牟天昊,李少远. 流程工业控制系统的知识图谱构建[J]. 智能科学与技术学报, 2022, 4(1): 129-141.
	MOU T H, LI S Y. Knowledge graph construction for control systems in process industry[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(1): 129-141.
12	HUANG Z, XU W, YU K. Bidirectional LSTM-CRF models for sequence tagging[EB]. arXiv preprint, 2015, arXiv:1508.01991.
13	LIU X Y, TAN H B, CHEN Q H, et al. RAGAT: relation aware graph attention network for knowledge graph completion[J]. IEEE Access, 2021, 9: 20840-20849.
14	陈名杨, 张文, 陈湘楠, 等. 群体知识图谱:分布式知识迁移与联邦式图谱推理[J]. 智能科学与技术学报, 2022, 4(1): 55-64.
	CHEN M Y, ZHANG W, CHEN X N, et al. Collective knowledge graph: meta knowledge transfer and federated graph reasoning[J]. Chinese Journal of Intelligent Science and Technology, 2022, 4(1): 55-64.
15	WANG Q, MAO Z, WANG B, et al. Knowledge graph embedding: a survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724-2743.
16	BORDES A, USUNIER N, GARCIA-DURáN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2. New York: ACM, 2013: 2787-2795.
17	WANG Z, ZHANG J W, FENG J L, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence. New York: ACM, 2014: 1112-1119.
18	LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence. New York: ACM, 2015: 2181-2187.
19	DEVLIN J, CHANG M W, LEE K, et al. Bert: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). [S.l.:s.n.], 2019: 4171-4186.

实体类型	举例
场景	URLLC, satellite network
环境	room, sea, highway
服务	education, sending a message
资源	bandwidth, IP address
主体	user, car, service provider
KPI	latency, reliability
方法	massive MIMO, tHz, digital twins
特征	temporal traffic variations
数据信息	rendering information
能力	achieve a Gbps-level

关系类型	举例
继承类关系	is_part_of, subclass_of, is_a
属性类关系	has_scenario,has_KPI
需求类关系	solution_of, require, purpose
能力类关系	cause, limit, improve, capable_of
比较类关系	higher, equal, larger

类名	类属性
主体	{id, name, UE_state, UE_type, priority, access}
环境	{id, name, network_type, service_area, density}
服务	{id, name}
KPI	{id, name, value}

模型	平均排名	Hits@10/%
TransE	19	58.3
TransH	10	71.7
TransR	18	60
BERT	11	82.86

[1]	王晓, 杨林瑶, 胡斌, 侯家琛. 平行推理：一种基于ACP方法的虚实互动的知识协同框架[J]. 智能科学与技术学报, 2023, 5(1): 69-82.
[2]	覃缘琪, 季青原, 葛俊, 戴星原, 陈圆圆, 王晓. 城市交通路网动态短时推理与精准预测研究[J]. 智能科学与技术学报, 2022, 4(3): 380-395.
[3]	牟天昊, 李少远. 流程工业控制系统的知识图谱构建[J]. 智能科学与技术学报, 2022, 4(1): 129-141.
[4]	陈名杨, 张文, 陈湘楠, 周虹廷, 陈华钧. 群体知识图谱：分布式知识迁移与联邦式图谱推理[J]. 智能科学与技术学报, 2022, 4(1): 55-64.
[5]	郭陈凤, 伍冬睿. 基于典型相关分析的多视图学习方法综述[J]. 智能科学与技术学报, 2022, 4(1): 14-26.
[6]	姚裕, 万鸣华. 鲁棒的非负监督低秩鉴别嵌入算法[J]. 智能科学与技术学报, 2021, 3(3): 342-350.
[7]	柴洪峰,王帅,涂晓军,孙权,马小峰,吴杰,才华,郑晓龙,王飞跃. 智能化金融科技创新监管工具：理念、平台框架和展望[J]. 智能科学与技术学报, 2020, 2(3): 214-226.

基于知识图谱的6G网络场景认知研究

Research on 6G network scenario cognition based on knowledge graph

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 19

相关文章 7

Metrics

推荐阅读 0