Entity discovery method for non-intelligent sensors by integrating knowledge graph and large models

doi:10.11772/j.issn.1001-9081.2025020238

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (2): 354-360.DOI: 10.11772/j.issn.1001-9081.2025020238

• Artificial intelligence • Previous Articles

Entity discovery method for non-intelligent sensors by integrating knowledge graph and large models

Jindong HE¹^,², Yuxuan JI¹, Tianci CHEN¹, Hengming XU³, Ji GENG¹, Mingsheng CAO¹(), Yuanning LIANG⁴

^1.Key Laboratory of Network and Data Security of Sichuan Province （University of Electronic Science and Technology of China），Chengdu Sichuan 610054，China
^2.Digital Institute，Electric Power Research Institute，State Grid Fujian Electric Power Company Limited，Fuzhou Fujian 350007，China
^3.School of Law，Humanities and Sociology，Wuhan University of Technology，Wuhan Hubei 430070，China
^4.Unit 31680 of the People’s Liberation Army，Chengdu Sichuan 610000，China

Received:2025-03-20 Revised:2025-04-22 Accepted:2025-04-28 Online:2025-05-16 Published:2026-02-10
Contact: Mingsheng CAO
About author:HE Jindong， born in 1982， Ph. D. candidate， senior engineer. His research interests include network security.
JI Yuxuan， born in 2000， M. S. candidate. His research interests include reinforcement learning， network resource scheduling.
CHEN Tianci， born in 2003. His research interests include network security， artificial intelligence.
XU Hengming， born in 2006. His research interests include network security， artificial intelligence.
GENG Ji， born in 1963， Ph. D.， professor. His research interests include system software， information security.
CAO Mingsheng， born in 1986， Ph. D.， associate research fellow. His research interests include network security， artificial intelligence. Emai:cms@uestc.edu.cn
LIANG Yuanning， born in 1986， M.S.， engineer. His research interests include network security， artificial intelligence.
Supported by:
National Natural Science Foundation of China(62372083);Project of Lianyungang Science and Technology Bureau(CG2322)

基于知识图谱和大模型的非智能传感器的实体发现方法

何金栋¹^,², 及宇轩¹, 陈天赐¹, 许恒铭³, 耿技¹, 曹明生¹(), 梁员宁⁴

^1.网络与数据安全四川省重点实验室（电子科技大学），成都 610054
^2.国网福建省电力有限公司电力科学研究院数字研究所，福州 350007
^3.武汉理工大学法学与人文社会学院，武汉 430070
^4.中国人民解放军31680部队，成都 610000

通讯作者: 曹明生
作者简介:何金栋（1982—），男，福建福州人，正高级工程师，博士研究生，主要研究方向：网络安全
及宇轩（2000—），男，内蒙古呼和浩特人，硕士研究生，主要研究方向：强化学习、网络资源调度
陈天赐（2003—），男，四川达州人，主要研究方向：网络安全、人工智能
许恒铭（2006—），男，四川成都人，主要研究方向：网络安全、人工智能
耿技（1963—），男，安徽合肥人，教授，博士，主要研究方向：系统软件、信息安全
曹明生（1986—），男，江苏盐城人，副研究员，博士，CCF会员，主要研究方向：网络安全、人工智能 Emai:cms@uestc.edu.cn
梁员宁（1986—），男，广西贵港人，工程师，硕士，CCF会员，主要研究方向：网络安全、人工智能。
基金资助:
国家自然科学基金资助项目(62372083);连云港市科学技术局项目(CG2322)

Abstract

Abstract:

In the field of industrial Internet of Things （IoT）， device entity discovery constitutes a critical component of device management. Compared to intelligent sensors， the discovery process of non-intelligent sensors is particularly complex due to their lack of inherent communication protocols， making efficient and accurate recognition of non-intelligent devices a technical challenge urgent to be solved. Therefore， a knowledge graph and Large Language Model （LLM）-based efficient recognition method for non-intelligent sensors was proposed. Firstly， a three-layer knowledge graph was constructed by extracting attribute values from non-intelligent sensors. Secondly， the feature vectors of sensors were extracted from the knowledge graph. Finally， the feature vector information was fed into LLM for fine-tuning， and the optimal fine-tuning parameters for the model were obtained through optimization via a series of experiments. Experimental results demonstrate that the proposed method achieves a recognition accuracy of 96.2% on the public IoT sensor dataset SensorData， enhancing recognition efficiency significantly.

Key words: Internet of Things (IoT), knowledge graph, large model, fine-tuning, non-intelligent sensor, entity discovery

摘要：

在工业物联网（IoT）领域，设备实体发现构成了设备管理的关键组成部分。相较于智能传感器，非智能传感器由于缺少内在的通信协议，它们的发现过程尤为复杂，这让高效且准确地识别非智能设备成为亟待解决的技术难题。因此，提出一种基于知识图谱和大模型的非智能传感器识别方法。首先，通过提取非智能传感器的属性值，构建三层知识图谱；其次，从知识图谱中提取传感器的特征向量；最后，将特征向量信息输入大模型中进行微调，并通过系列实验优化，得到最佳模型微调参数。实验结果表明，在公开的IoT传感器数据集SensorData上，所提方法的识别准确率高达96.2%，显著提升了识别效率。

关键词: 物联网, 知识图谱, 大模型, 微调, 非智能传感器, 实体发现

CLC Number:

TP181

Jindong HE, Yuxuan JI, Tianci CHEN, Hengming XU, Ji GENG, Mingsheng CAO, Yuanning LIANG. Entity discovery method for non-intelligent sensors by integrating knowledge graph and large models[J]. Journal of Computer Applications, 2026, 46(2): 354-360.

何金栋, 及宇轩, 陈天赐, 许恒铭, 耿技, 曹明生, 梁员宁. 基于知识图谱和大模型的非智能传感器的实体发现方法[J]. 《计算机应用》唯一官方网站, 2026, 46(2): 354-360.

Figures/Tables 10

Fig. 1 Overall architecture of proposed method

Fig. 2 Knowledge graph of non-intelligent sensors

Fig. 3 Sensor data feature representation process

Fig. 4 LoRA fine-tuning principle

Tab. 1 Performance comparison of experimental methods

方法	F1分数	精确率	召回率	准确率
SVM	0.758	0.818	0.718	0.718
KNN	0.445	0.824	0.312	0.343
DT	0.765	0.812	0.719	0.735
RF	0.788	0.852	0.733	0.742
HGAT	0.868	0.873	0.852	0.876
fastGTN	0.860	0.876	0.845	0.862
MAGNN	0.858	0.869	0.848	0.872
本文方法	0.947	0.961	0.934	0.962

Tab. 2 Parameter setting

参数	值
epoch	13
cutoff_len	2 048
learning_rate	5E-5
batch_size	1
gradient_accumulation	4/8

Fig. 5 Relationship between training epoch and accuracy

Fig. 6 Relationship between cutoff length and average accuracy

Fig. 7 Relationship between learning rate and average accuracy

Fig. 8 Model’s LoRA fine-tuning loss

References 31

[1]	张普宁，亢旭源，刘宇哲，等. 相似度自适应估计的物联网实体高效搜索方法［J］. 电子与信息学报， 2020， 42（7）： 1702-1709.
	ZHANG P N， KANG X Y， LIU Y Z， et al. Efficient search method for IoT entities with similarity adaptive estimation［J］. Journal of Electronics and Information Technology， 2020， 42（7）：1702-1709.
[2]	蒋栋年，李炜，王君，等. 基于故障可诊断性量化评价的传感器优化配置方法研究［J］. 自动化学报， 2018， 44（6）： 1128-1137.
	JIANG D N， LI W， WANG J， et al. Research on sensor optimal placement method using quantitative evaluation of fault diagnosability［J］. Acta Automatica Sinica， 2018， 44（6）： 1128-1137.
[3]	何曙光，石枚弘. 考虑生产任务的制造设备关键部件的机会维修优化［J］. 控制与决策， 2023， 38（3）： 715-720.
	HE S G， SHI M H. Opportunistic maintenance optimization for key components of manufacturing equipment considering production tasks［J］. Control and Decision， 2023， 38（3）： 715-720.
[4]	伊德尔昆，孙锴，王滨，等. 无线传感器网络时钟同步中节点之间的延时分布［J］. 计算机应用， 2020， 40（S2）： 85-89.
	YI D E K， SUN K， WANG B， et al. Delay distribution between nodes in clock synchronization of wireless sensor networks［J］. Journal of Computer Applications， 2020， 40（S2）： 85-89.
[5]	CHEN D， ZHAO Z， QIN X， et al. MAGLeak： a learning-based side-channel attack for password recognition with multiple sensors in IIoT environment［J］. IEEE Transactions on Industrial Informatics， 2022， 18（1）： 467-476.
[6]	袁牧，张兰，姚云昊，等. 面向智能物联网的资源高效模型推理综述［J］. 计算机学报， 2024， 47（10）： 2247-2273.
	YUAN M， ZHANG L， YAO Y H， et al. Resource-efficient model inference for AIoT： a survey［J］. Chinese Journal of Computers， 2024， 47（10）： 2247-2273.
[7]	DENG H， HUANG J， LIU Q， et al. BGSD： a SBERT and GAT-based service discovery framework for heterogeneous distributed IoT［J］. Computer Networks， 2023， 220： No.109488.
[8]	李鸣，许善智，尹雨晴，等. WiFi与ZigBee双向移动跨网通信方法研究［J］. 电子学报， 2024， 52（11）： 3858-3864.
	LI M， XU S Z， YIN Y Q， et al. Research on bidirectional mobile cross-technology communication method between WiFi and ZigBee［J］. Acta Electronica Sinica， 2024， 52（11）： 3858-3864.
[9]	何蓉，方旭明. 蓝牙Ad hoc网络形成算法的性能评价［J］. 计算机应用， 2005， 25（5）： 1173-1176.
	HE R， FANG X M. Performance evaluation of Bluetooth Ad hoc network formation algorithms［J］. Journal of Computer Applications， 2005， 25（5）： 1173-1176.
[10]	GÖRGÜ L， KROON B， O’GRADY M J， et al. Sensor discovery in ambient IoT ecosystems［J］. Journal of Ambient Intelligence and Humanized Computing， 2018， 9（2）： 447-458.
[11]	韩蓓，盛戈皞，江秀臣，等. 基于ZigBee无线传感网络的导线接头在线测温系统［J］. 电力系统自动化， 2008， 32（16）： 72-77.
	HAN B， SHENG G H， JIANG X C， et al. An online thermal condition monitoring system with wireless sensor network based on ZigBee technology for transmission line joints［J］. Automation of Electric Power Systems， 2008， 32（16）： 72-77.
[12]	AMIN S I， KHALED Y Y， AHMED H， et al. Adaptive aggregation based IoT traffic patterns for optimizing smart city network performance［J］. Alexandria Engineering Journal， 2022， 61（12）： 9553-9568.
[13]	SAGAR S， MAHMOOD A， WANG K， et al. Trust⁃SIoT： toward trustworthy object classification in the social internet of things［J］. IEEE Transactions on Network and Service Management， 2023， 20（2）： 1210-1223.
[14]	RODRIGUEZ-MIER P， PEDRINACI C， LAMA M， et al. An integrated semantic web service discovery and composition framework［J］. IEEE Transactions on Services Computing， 2016， 9（4）： 537-550.
[15]	WAN Y， XU K， WANG F， et al. IoTAthena： unveiling IoT device activities from network traffic［J］. IEEE Transactions on Wireless Communications， 2022， 21（1）： 651-664.
[16]	秦臻，庄添铭，朱国淞，等. 面向人工智能模型的安全攻击和防御策略综述［J］. 计算机研究与发展， 2024， 61（10）： 2627-2648.
	QIN Z， ZHUANG T M， ZHU G S， et al. Survey of security attack and defense strategies for artificial intelligence model［J］. Journal of Computer Research and Development， 2024， 61（10）： 2627-2648.
[17]	田玲，张谨川，张晋豪，等. 知识图谱综述：表示、构建、推理与知识超图理论［J］. 计算机应用， 2021， 41（8）： 2161-2186.
	TIAN L， ZHANG J C， ZHANG J H， et al. Knowledge graph survey： representation， construction， reasoning and knowledge hypergraph theory［J］. Journal of Computer Applications， 2021， 41（8）： 2161-2186.
[18]	焦守龙，段友祥，孙歧峰，等. 融合实体描述信息和邻居节点特征的知识表示学习方法［J］. 计算机应用， 2022， 42（4）： 1050-1056.
	JIAO S L， DUAN Y X， SUN Q F， et al. Knowledge representation learning method incorporating entity description information and neighbor node features［J］. Journal of Computer Applications， 2022， 42（4）： 1050-1056.
[19]	XIE C， YU B， ZENG Z， et al. Multilayer Internet-of-Things middleware based on knowledge graph［J］. IEEE Internet of Things Journal， 2021， 8（4）： 2635-2648.
[20]	ZENG Z， XIE C， TAO W， et al. Knowledge-graph-based IoTs entity discovery middleware for nonsmart sensor［J］. IEEE Transactions on Industrial Informatics， 2024， 20（2）： 2551-2563.
[21]	KHOKHLOV I， REZNIK L. Knowledge graph in data quality evaluation for IoT applications［C］// Proceedings of the 2020 IEEE 6th World Forum on Internet of Things （WF-IoT）. Piscataway： IEEE， 2020： 1-6.
[22]	YIM H J， SON Y H， LEE K C. A data distribution service quality of services policy configuration for data/events/services in the internet of things［J］. Advanced Science Letters， 2016， 22（11）： 3612-3617.
[23]	ZHANG N， SHANG F， LI X. Knowledge graph construction method for mobile IOT management platform device anomaly［C］// Proceedings of the 2023 12th International Conference of Information and Communication Technology （ICTech）. Piscataway： IEEE， 2023： 376-382.
[24]	HUANG Y， XUE X， JIANG C. Semantic integration of sensor knowledge on artificial Internet of things［J］. Wireless Communications and Mobile Computing， 2020， 25： 1-8.
[25]	LU Y， WANG H， XU X. ManuService ontology： a product data model for service-oriented business interactions in a cloud manufacturing environment［J］. Journal of Intelligent Manufacturing， 2019， 30（1）： 317-334.
[26]	LIU J， LI T， JI S， et al. Urban flow pattern mining based on multi-source heterogeneous data fusion and knowledge graph embedding［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（2）： 2133-2146.
[27]	VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph attention networks［EB/OL］. ［2024-12-15］..
[28]	justZZY. Model data sensor of knowledge graph based adaptive IoTs middleware［EB/OL］. ［2024-12-15］..
[29]	YANG T， HU L， SHI C， et al. HGAT： heterogeneous graph attention networks for semi-supervised short text classification［J］. ACM Transactions on Information Systems， 2021， 39（3）： No.32.
[30]	YUN S， JEONG M， YOO S， et al. Graph Transformer networks： learning meta-path graphs to improve GNNs［J］. Neural Networks， 2022， 153： 104-119.
[31]	CHEN J， SHI L， CHEN B. RSEA-MVGNN： multi-view graph neural network with reliable structural enhancement and aggregation［J］. Information Fusion， 2025， 121： No.103143.

Entity discovery method for non-intelligent sensors by integrating knowledge graph and large models

基于知识图谱和大模型的非智能传感器的实体发现方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 31

Related Articles 15

Recommended Articles

Metrics

[1]	Xue WANG, Liping ZHANG, Sheng YAN, Na LI, Xuefei ZHANG. Review of multi-modal knowledge graph completion methods [J]. Journal of Computer Applications, 2026, 46(2): 341-353.
[2]	Fei WANG, Ye TAO, Jiawang LIU, Wei LI, Xiugong QIN, Ning ZHANG. Bimodal fusion method for constructing spatio-temporal knowledge graph in smart home space [J]. Journal of Computer Applications, 2026, 46(1): 52-59.
[3]	Sheping ZHAI, Pengju ZHU, Rui YANG, Jiayiteng LIU. Blockchain-based identity management system for internet of things [J]. Journal of Computer Applications, 2025, 45(9): 2873-2881.
[4]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[5]	Xiaoyang ZHAO, Xinzheng XU, Zhongnian LI. Research review on explainable artificial intelligence in internet of things applications [J]. Journal of Computer Applications, 2025, 45(7): 2169-2179.
[6]	Lixiao ZHANG, Yao MA, Yuli YANG, Dan YU, Yongle CHEN. Large-scale IoT binary component identification based on named entity recognition [J]. Journal of Computer Applications, 2025, 45(7): 2288-2295.
[7]	Shuang LIU, Daqing LIU, Jiana MENG, Di ZHAO. Hyper-relational knowledge graph completion method fusing noise filtering [J]. Journal of Computer Applications, 2025, 45(6): 1817-1826.
[8]	Sheping ZHAI, Qing YANG, Yan HUANG, Rui YANG. Knowledge graph completion using hierarchical attention fusing directed relationships and relational paths [J]. Journal of Computer Applications, 2025, 45(4): 1148-1156.
[9]	Liqin WANG, Zhilei GENG, Yingshuang LI, Yongfeng DONG, Meng BIAN. Open-world knowledge reasoning model based on path and enhanced triplet text [J]. Journal of Computer Applications, 2025, 45(4): 1177-1183.
[10]	Zixin XU, Xiuwen YI, Jie BAO, Tianrui LI, Junbo ZHANG, Yu ZHENG. Construction and application of knowledge graph for epidemiological investigation [J]. Journal of Computer Applications, 2025, 45(4): 1340-1348.
[11]	Chun XU, Shuangyan JI, Huan MA, Enwei SUN, Mengmeng WANG, Mingyu SU. Consultation recommendation method based on knowledge graph and dialogue structure [J]. Journal of Computer Applications, 2025, 45(4): 1157-1168.
[12]	Yiheng SUN, Maofu LIU. Tender information extraction method based on prompt tuning of knowledge [J]. Journal of Computer Applications, 2025, 45(4): 1169-1176.
[13]	Peng CAO, Guangqi WEN, Jinzhu YANG, Gang CHEN, Xinyi LIU, Xuechun JI. Efficient fine-tuning method of large language models for test case generation [J]. Journal of Computer Applications, 2025, 45(3): 725-731.
[14]	Yan YANG, Feng YE, Dong XU, Xuejie ZHANG, Jin XU. Construction of digital twin water conservancy knowledge graph integrating large language model and prompt learning [J]. Journal of Computer Applications, 2025, 45(3): 785-793.
[15]	Chengzhe YUAN, Guohua CHEN, Dingding LI, Yuan ZHU, Ronghua LIN, Hao ZHONG, Yong TANG. ScholatGPT： a large language model for academic social networks and its intelligent applications [J]. Journal of Computer Applications, 2025, 45(3): 755-764.