A Method of Target Group Type Identification Oriented System Combat

doi:10.3969/j.issn.1009-086x.2025.02.008

Abstract

Abstract:

In order to assist commanders in making decisions efficiently， this paper makes researches on the grouping of operational targets in situation awareness. Aiming at the characteristics of numerous targets， different functions and complex interrelationships in the operational system of systems， the graph matching idea is used to solve the target group type identification problem. A graph-based target group representation method is proposed， where the target is abstracted as a node and the interrelation is abstracted as an edge， which depicts the targets and their mutual relationship. A graph matching network model is designed to identify the type of target group. The model can jointly learn the vector representation of the group to be identified and the group of known types. The type of target group can be identified by calculating the similarity between the two groups. Experimental results show that the proposed method can efficiently identify the type of target groups.

Key words: situation awareness, target group, graph matching networks, similarity computation, graph neural network, attention mechanism

摘要：

为辅助指挥人员高效地进行决策，研究了态势感知中的目标群体类型判识问题。针对体系作战中目标数量众多、类型功能各异、相互关系复杂的特点，运用图匹配思想对目标群体类型判识问题进行求解。提出了基于图的目标群体表示方法，将目标抽象为节点，关系抽象为边，刻画了目标及其之间的相互关系；设计了一种用于判识目标群体类型的图匹配网络模型，该模型能够联合学习待判识目标群体和已知类型群体的向量表示，通过计算二者的相似性来判识群体的类型。实验表明，所提方法可以有效地判识出目标群体的类型。

关键词: 态势感知, 目标群体, 图匹配网络, 相似性计算, 图神经网络, 注意力机制

CLC Number:

TP181

Wendong ZHAO, Mingzhi ZHANG, Shengming GUO. A Method of Target Group Type Identification Oriented System Combat[J]. Modern Defense Technology, 2025, 53(2): 74-81.

赵文栋, 张明智, 郭圣明. 一种面向体系作战的目标群体类型判识方法[J]. 现代防御技术, 2025, 53(2): 74-81.

Figures/Tables 6

Fig. 1 General architecture of GMNOTGTR

Fig. 2 Examples of two matching methods

Table 1 Dataset statistics

数据集	图数	平均节点数	平均边数
AIDS700	700	8.90	8.80
兵棋数据集	668	14.70	24.30

Fig. 3 Error rate of wargame data training and test sets

Table 2 Experimental results of different models in dataset

数据集	模型	MSE（10^-3）	P@10	P@20	$ρ$	$τ$
AIDS700	HierarchicalMean	3.046	0.245	0.340	0.682	0.627
	SimGNN	1.451	0.425	0.511	0.839	0.685
	GMNOTGTR	1.391	0.454	0.531	0.901	0.744
兵棋数据集	HierarchicalMean	2.506	0.631	0.751	0.832	0.745
	SimGNN	1.970	0.798	0.818	0.887	0.779
	GMNOTGTR	1.928	0.811	0.819	0.890	0.763

Table 2 Experimental results of different models in dataset

数据集	模型	MSE（10^-3）	P@10	P@20	$ρ$	$τ$
AIDS700	HierarchicalMean	3.046	0.245	0.340	0.682	0.627
	SimGNN	1.451	0.425	0.511	0.839	0.685
	GMNOTGTR	1.391	0.454	0.531	0.901	0.744
兵棋数据集	HierarchicalMean	2.506	0.631	0.751	0.832	0.745
	SimGNN	1.970	0.798	0.818	0.887	0.779
	GMNOTGTR	1.928	0.811	0.819	0.890	0.763

Table 3 Experimental results comparison of GMNOTGTR variant models

数据集	模型	MSE（10^-3）	P@10	P@20	$ρ$	$τ$
AIDS700	GMNOTGTR	1.391	0.454	0.531	0.901	0.704
	GMNOTGTR （GraphSAGE）	1.486	0.343	0.485	0.895	0.722
	GMNOTGTR （GCN）	1.547	0.321	0.493	0.892	0.735
	GMNOTGTR （GGNN）	1.951	0.299	0.468	0.872	0.710
兵棋数据集	GMNOTGTR	1.928	0.811	0.819	0.890	0.763
	GMNOTGTR （GraphSAGE）	2.739	0.759	0.770	0.823	0.735
	GMNOTGTR （GCN）	2.847	0.743	0.759	0.809	0.729
	GMNOTGTR （GGNN）	2.951	0.752	0.765	0.801	0.730

Table 3 Experimental results comparison of GMNOTGTR variant models

数据集	模型	MSE（10^-3）	P@10	P@20	$ρ$	$τ$
AIDS700	GMNOTGTR	1.391	0.454	0.531	0.901	0.704
	GMNOTGTR （GraphSAGE）	1.486	0.343	0.485	0.895	0.722
	GMNOTGTR （GCN）	1.547	0.321	0.493	0.892	0.735
	GMNOTGTR （GGNN）	1.951	0.299	0.468	0.872	0.710
兵棋数据集	GMNOTGTR	1.928	0.811	0.819	0.890	0.763
	GMNOTGTR （GraphSAGE）	2.739	0.759	0.770	0.823	0.735
	GMNOTGTR （GCN）	2.847	0.743	0.759	0.809	0.729
	GMNOTGTR （GGNN）	2.951	0.752	0.765	0.801	0.730

References 22

1	段玉先，刘昌云，魏文凤. 战场态势感知关键技术研究［J］. 火力与指挥控制， 2021， 46（11）： 1-11， 19.
	DUAN Yuxian， LIU Changyun， WEI Wenfeng. Review of Key Technologies for Battlefield Situational Awareness［J］. Fire Control & Command Control， 2021， 46（11）： 1-11， 19.
2	吕学志，胡晓峰，吴琳，等. 基于贝叶斯网络的任务共同体识别［J］. 计算机工程与应用， 2019， 55（5）： 251-257.
	Xuezhi LÜ， HU Xiaofeng， WU Lin， et al. Identification Method of Mission Community Based on Bayesian Network［J］. Computer Engineering and Applications， 2019， 55（5）： 251-257.
3	蔡益朝，张维明，刘忠，等. 态势评估中的作战群体类型识别［J］. 系统工程与电子技术， 2006， 28（12）： 1845-1849.
	CAI Yichao， ZHANG Weiming， LIU Zhong， et al. Group Classification in Situation Assessment［J］. Systems Engineering and Electronics， 2006， 28（12）： 1845-1849.
4	LOONEY C G， LIANG L R. Cognitive Situation and Threat Assessments of Ground Battlespaces［J］. Information Fusion， 2003， 4（4）： 297-308.
5	柴慧敏. 态势估计中的关键技术研究［D］. 西安：西安电子科技大学， 2009.
	CHAI Huimin. Research on Key Technology in Situation Assessment［D］. Xi'an： Xidian University， 2009.
6	吕昭，邓锦洲，梁东晨. 作战体系的结构建模与应用研究［J］. 战术导弹技术， 2021（3）： 109-118.
	Zhao LÜ， DENG Jinzhou， LIANG Dongchen. Study of Operation SoS Architecture Modeling and Application［J］. Tactical Missile Technology， 2021（3）： 109-118.
7	KIPF T N， WELLING M. Semi-Supervised Classification with Graph Convolutional Networks［EB/OL］. （2017-02-22）［2021-11-26］. .
8	LI Yujia， TARLOW D， BROCKSCHMIDT M， et al. Gated Graph Sequence Neural Networks［EB/OL］. （2017-09-22）［2021-09-17］. .
9	HAMILTON W L， YING R， LESKOVEC J. Inductive Representation Learning on Large Graphs［C］∥Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2017： 1025-1035.
10	VELIČKOVIĆ P， CUCURULL G， CASANOVA A， et al. Graph Attention Networks［EB/OL］. （2018-02-04）［2021-07-02］. .
11	LEE J， LEE I， KANG J. Self-Attention Graph Pooling［C］∥Proceedings of the 36th International Conference on Machine Learning. Chia Laguna Resort： PMLR， 2019： 3734-3743.
12	LI Yujia， GU Chenjie， DULLIEN T， et al. Graph Matching Networks for Learning the Similarity of Graph Structured Objects［C］∥Proceedings of the 36th International Conference on Machine Learning. Chia Laguna Resort： PMLR， 2019： 3835-3845.
13	SRIVASTAVA R K， GREFF K， SCHMIDHUBER J. Highway Networks［EB/OL］. （2015-11-03）［2021-10-12］. .
14	MESHRAM S， ANAND KUMAR M. Long Short-Term Memory Network for Learning Sentences Similarity Using Deep Contextual Embeddings［J］. International Journal of Information Technology， 2021， 13（4）： 1633-1641.
15	BAI Yunsheng， DING Hao， BIAN Song， et al. SimGNN： A Neural Network Approach to Fast Graph Similarity Computation［C］∥Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining. New York： ACM， 2019： 384-392.
16	邱珍，郑朝晖. 面向图相似性搜索的高效图编辑距离算法［J］. 计算机应用研究， 2023， 40（2）： 371-377.
	QIU Zhen， ZHENG Zhaohui. Efficient Graph Edit Distance Algorithm for Graph Similarity Search［J］. Application Research of Computers， 2023， 40（2）： 371-377.
17	BLUMENTHAL D B， GAMPER J. On the Exact Computation of the Graph Edit Distance［J］. Pattern Recognition Letters， 2020， 134： 46-57.
18	RIESEN K， EMMENEGGER S， BUNKE H. A Novel Software Toolkit for Graph Edit Distance Computation［C］∥Proceedings of the 2013 International Workshop on Graph-Based Representations in Pattern Recognition. Berlin： Springer Berlin Heidelberg， 2013： 142-151.
19	FISCHER A， RIESEN K， BUNKE H. Improved Quadratic Time Approximation of Graph Edit Distance by Combining Hausdorff Matching and Greedy Assignment［J］. Pattern Recognition Letters， 2017， 87： 55-62.
20	RIESEN K， BUNKE H. Approximate Graph Edit Distance Computation by Means of Bipartite Graph Matching［J］. Image and Vision Computing， 2009， 27（7）： 950-959.
21	FANKHAUSER S， RIESEN K， BUNKE H. Speeding Up Graph Edit Distance Computation through Fast Bipartite Matching［C］∥Graph-Based Representations in Pattern Recognition. Berlin： Springer Berlin Heidelberg， 2011： 102-111.
22	DEFFERRARD M， BRESSON X， VANDERGHEYNST P. Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering［C］∥Proceedings of the 30th International Conference on Neural Information Processing Systems. Red Hook： Curran Associates Inc.， 2016： 3844-3852.

[1]	Jiakuan LI, Bo FENG, Lunhao SHEN, Chunmao YE, Jizhou YU. Aerodynamic Target Recognition Method Based on Incidence Angle-Guided Radar Image Feature Fusion [J]. Modern Defense Technology, 2025, 53(2): 129-140.
[2]	Wendong ZHAO, Mingzhi ZHANG, Shengming GUO. Operational Action Identification Method from Knowledge Association Perspective [J]. Modern Defense Technology, 2024, 52(3): 64-72.
[3]	Zhe LI, Yiqi TONG, Wenbo XIA, Yuxin YING. A Multi-source Centralized Air Target Classification Method [J]. Modern Defense Technology, 2023, 51(4): 53-62.
[4]	Ming HE, Zihan ZHU, Xulong ZHAI, Zheng ZHAI, Chengpeng HAO. Air-to-Ground Target Detection Algorithm Based on Multi-branch Context Fusion [J]. Modern Defense Technology, 2023, 51(3): 91-98.
[5]	Lei YUE, Jianhu YUAN, Liu YANG, Tingting LÜ. Research on a Patrol Duty Object Detection Algorithm [J]. Modern Defense Technology, 2023, 51(1): 67-74.
[6]	WANG Wen-qing, PANG Ying, LIU Yang, YANG Dong-fang, ZHANG Meng. Air-to-Ground Target Intelligent Detection Algorithm Based on Dual Attention Mechanism [J]. Modern Defense Technology, 2020, 48(6): 81-88.