基于等级参数划分的系统智能水平评测等效映射方法研究

doi:10.12305/j.issn.1001-506X.2026.05.16

摘要/Abstract

摘要：

针对现有智能水平评测中定量评分与定性等级相互独立、缺乏统一映射机制，从而使同一系统在不同方法下难以横向比较的问题，提出一种基于等级参数划分的系统智能水平评测等效映射方法。首先构建评测指标评分分级模型，对各一级指标的评分区间进行细化。随后建立智能水平等级划分参数集合，并引入可自适应的动态等级划分模型，在统一归一化区间内刻画各等级门槛，实现定量评分向定性等级的可解释映射。将该方法应用于地外无人系统的真实评测场景后，结果表明所提方法可以可靠地将系统的定量评分映射至定性框架。所提方法为跨场景、跨方法的统一评测提供了可行路径，具有较强的适用性与可推广性。

关键词: 智能水平评测, 动态等级划分, 映射方法

Abstract:

To address the fact that current intelligence level assessment frameworks often treat quantitative scoring and qualitative hierarchical as independent schemes, without a unified mapping mechanism and therefore makes it difficult to compare the same system horizontally with different methods, an equivalence mapping method for system intelligence level assessment based on hierarchical parameter partitioning is proposed. The method first constructs an indicator scoring and grading model that refines the score intervals of each top-level indicator. It then defines an intelligence hierarchical partitioning parameter set and introduces an adaptive dynamic hierarchical partitioning model, which represents each threshold hierarchical within a unified normalized range to realize interpretable mapping from quantitative scoring to qualitative hierarchical. Applied to a realistic off-Earth unmanned system assessment scenario, results indicate that the proposed method reliably mapps the system’s quantitative scoring into a qualitative framework. The proposed method provides a feasible path toward unified assessment across different scenarios and methods, and has strong applicability and generalizability.

Key words: intelligence level assessment, dynamic hierarchical partition, mapping method

中图分类号:

V 419+.9

戴宝科, 王东, 冯李航, 胡勇, 谢进进. 基于等级参数划分的系统智能水平评测等效映射方法研究[J]. 系统工程与电子技术, 2026, 48(5): 1599-1606.

Baoke DAI, Dong WANG, Lihang FENG, Yong HU, Jinjin XIE. Reaearch on equivalent mapping method for system intelligent level assessment based on hierarchical parameter partition[J]. Systems Engineering and Electronics, 2026, 48(5): 1599-1606.

图/表 10

图1

图2

图3

表1

图4

图5

图6

表2

图7

表3

参考文献 30

1	邱日升, 潘继飞, 赵君, 等. 基于组合赋权的ELINT系统效能评估算法[J]. 现代雷达, 2020, 42 (8): 13- 18.
	QIU R S, PAN J F, ZHAO J, et al. Efficient evaluation algorithm for ELINT system based on combination weighting[J]. Modern Radar, 2020, 42 (8): 13- 18.
2	李明泽, 谢忠, 朱学森, 等. 基于改进层次分析法的无人机输电线路巡检能力量化研究[J]. 电气技术, 2022, 23 (12): 44- 51.
	LI M Z, XIE Z, ZHU X S, et al. Research on quantification of UAV transmission line inspection capability based on improved analytic hierarchy process[J]. Electrical Engineering, 2022, 23 (12): 44- 51.
3	胡杰, 陈化良, 刘亮, 等. 无人机蜂群作战效能评估研究[J]. 火力与指挥控制, 2022, 47 (4): 164- 168.
	HU J, CHEN H L, LIU L, et al. Research on operational effectiveness evaluation of UAV swarm[J]. Fire Control & Command Control, 2022, 47 (4): 164- 168.
4	沈博, 武文亮, 杨刚, 等. 基于群体OODA的无人集群系统智能评价模型及方法[J]. 航空学报, 2023, 44 (14): 328003.
	SHEN B, WU W L, YANG G, et al. Evaluation models and methods for intelligence of unmanned swarm systems based on collective OODA loop[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44 (14): 328003.
5	JAHIC J, ROITSCH R, GRZYMKOWSKI L. Knowledge-based adequacy assessment approach to support AI adoption[C]//Proc. of the IEEE 18th International Conference on Software Architecture Companion, 2021: 8−14.
6	HASSAN H A, EID M M, ELMESALAWY M M, et al. A new intelligent system for evaluating and assisting students in laboratory learning management system[C]//Proc. of the 14th International Conference on Computational Intelligence and Communication Networks, 2022: 566−571.
7	孔军, 朱海峰, 潘芸, 等. 基于实时信息的智能变电站二次设备状态综合评价[J]. 机电工程技术, 2023, 52 (4): 221- 226.
	KONG J, ZHU H F, PAN Y, et al. Comprehensive evaluation of secondary equipment in smart substation based on real-time information[J]. Mechanical & Electrical Engineering Technology, 2023, 52 (4): 221- 226.
8	HE L, YUAN D L, REN L W, et al. Evaluation model research of coal mine intelligent construction based on FDEMATEL-ANP[J]. Sustainability, 2023, 15 (3): 2238. doi: 10.3390/su15032238
9	PANAGIOTOPOULOS I E, KARATHANASOPOULOU K N, DIMITRAKOPOULOS G J. Risk assessment in the context of dynamic reconfiguration of level of driving automation in highly automated vehicles[C]//Proc. of the International Conference on Computational Science and Computational Intelligence, 2021: 1868−1873.
10	KAWAANISHI Y, NISHIHARA H, SOUMA D, et al. A study on quantitative risk assessment methods in security design for industrial control systems[C]//Proc. of the IEEE 16th Internatimal Conference on Dependable, Autonomic and Secure Computing, 2018: 62−69.
11	HAN Y M, FANG D, ZHANG H Y, et al. Evaluation of attack capability of UAV intelligent swarm based on AHP fuzzy evaluation[J]. Journal of Physics: Conference Series, 2020, 1651 (1): 012012. doi: 10.1088/1742-6596/1651/1/012012
12	LIU J Y, SUN L N, ZHAO Z M. Unmanned aerial vehicle cluster distributed combat effectiveness evaluation based on DoDAF[C]//Proc. of the International Conference on Autonomous Unmanned Systems, 2022: 2264−2272.
13	何胜杰, 郭强, 王兴虎, 等. 基于ADC分析法优化的无人机效能评估方法[J]. 无人系统技术, 2022, 5 (2): 106- 116.
	HE S J, GUO Q, WANG X H, et al. UAV effectiveness evaluation method based on optimized ADC analysis[J]. Unmanned Systems Technology, 2022, 5 (2): 106- 116.
14	WANG S, DU Y H, ZHAO S J, et al. Research on the construction of weaponry indicator system and intelligent evaluation methods[J]. Scientific Reports, 2023, 13 (1): 19370. doi: 10.1038/s41598-023-46660-5
15	JIANG T Y, ZHOU J T, LUO X, et al. A systematic multi-layer cognitive model for intelligent machine tool[J]. Journal of Intelligent Manufacturing, 2025, 36, 4915- 4939. doi: 10.1007/s10845-024-02481-5
16	WEN Z Q, WANG F, YANG N. Optimized evaluation of the quality of sensor video internet of things （VIOT） by the integration of big data and artificial intelligence[J]. Discover Computing, 2024, 27, 45. doi: 10.1007/s10791-024-09482-1
17	CHEN M Z, WEI X, XIE P Z, et al. QoE oriented intelligent online learning evaluation technology in B5G scenario[J]. Digital Communications and Networks, 2024, 10 (1): 7- 15. doi: 10.1016/j.dcan.2022.05.018
18	PAN P L, LIN X M, XU D. Application of analytic hierarchy process (AHP) in the evaluation of the intelligent teaching system (ITS) module[C]//Proc. of the IEEE International Conference on Advanced Infocomm Technology, 2023: 251−263.
19	YOUNG L, YETTER J, GUYNN M. System analysis applied to autonomy: application to high-altitude long-endurance remotely operated aircraft[EB/OL]. [2025-05-01]. https://doi.org/10.2514/6.2005-7103.
20	赵蒙, 王明宇, 殷双斌. 基于主客观组合赋权的变权TOPSIS弹道目标威胁评估模型[J]. 军事运筹与评估, 2023, 38 (1): 27- 33.
	ZHAO M, WANG M Y, YIN S B. Variable weight TOPSIS ballistic target threat assessment model based on subjective and objective combination weighting[J]. Military Operations Research and Assessment, 2023, 38 (1): 27- 33.
21	彭妮娜, 殷建丰, 王倩, 等. 多层次多维度网络化航天装备效能评估方法研究[J]. 计算机仿真, 2022, 39 (7): 91- 95.
	PENG N N, YIN J F, WANG Q, et al. Research on multi-level and multi-dimensional networked effectiveness evaluation method of aerospace equipment[J]. Computer Simulation, 2022, 39 (7): 91- 95.
22	RUSSO R, CAMANHO R. Criteria in AHP: a systematic review of literature[J]. Procedia Computer Science, 2015, 55, 1123- 1132. doi: 10.1016/j.procs.2015.07.081
23	李彦斐, 姚奕. 基于OODA环的对陆攻击巡航导弹作战效能评估[J]. 舰船电子工程, 2022, 42 (11): 128- 133.
	LI Y F, YAO Y. Operational effectiveness evaluation of submarine-launched land attacking cruise missile based on OODA loop[J]. Ship Electronic Engineering, 2022, 42 (11): 128- 133.
24	LIN Z Z, WEN F, WANG H, et al. CRITIC-based node importance evaluation in skeleton-network reconfiguration of power grids[J]. IEEE Trans. on Circuits and Systems II: Express Briefs, 2018, 65 (2): 206- 210.
25	ZHANG T Y, GAO T, XU P, et al. A review of AI and AI intelligence assessment[C]// Proc. of the IEEE 4th Conference on Energy Internet and Energy System Integration, 2020: 3039−3044.
26	王瑛, 史翔宇, 李超. 基于DoDAF的无人机协同作战效能评估[J]. 空军工程大学学报（自然科学版）, 2020, 21 (6): 66- 72.
	WANG Y, SHI X Y, LI C. Research on evaluation of UAV cooperative combat effectiveness based on DoDAF[J]. Journal of Air Force Engineering University, 2020, 21 (6): 66- 72.
27	MA S D, ZHANG H Z, YANG G Q. Target threat level assessment based on cloud model under fuzzy and uncertain conditions in air combat simulation[J]. Aerospace Science and Technology, 2017, 67, 49- 53. doi: 10.1016/j.ast.2017.03.033
28	HUANG H M. Autonomy levels for unmanned systems (ALFUS) framework: safety and application issues[C]//Proc. of the Workshop on Performance Metrics for Intelligent Systems, 2007: 48−53.
29	HUANG Y J, ZHANG Z P, TAO Y, et al. Quantitative risk assessment of railway intrusions with text mining and fuzzy rule-based bow-tie model[J]. Advanced Engineering Informatics, 2022, 54, 101726. doi: 10.1016/j.aei.2022.101726
30	WANG D, LV L, TANG J, et al. Research on establishment and method of performance evaluation index system of smart grid distribution network[C]// Proc. of the IEEE Innovative Smart Grid Technologies-Asia , 2019: 3327−3332.

级别	ALFUS 定性描述
1级	远程控制
2级	远程控制/车辆状态识别
3级	预先任务规划或后序遍历
4级	传感图像联机处理
5级	简单障碍物检测与躲避
6级	复杂障碍物检测与躲避、地形分析
7级	移动目标检测道路或越野环境自主驾驶
8级	协同操作﹑护航、通过十字路口、运输跟随
9级	协同操作、交通标识和信号、接近人工驾驶
10级	达到或超过人类水平的完全自主能力

智能水平级别	感知理解	规划决策	行为执行
0级	0.89	0	0
1级	22.67	20	18.67
2级	44.44	40	37.78
3级	64.5	60	57.75
4级	80.5	75	72.25
5级	94.22	90	88.89

智能水平等级	定量评测				定性评测
智能水平等级	感知理解	规划决策	行为执行	指标总分	定性评测
0级	≥0.89	≥0	≥0	≥0.89	—
1级	≥0.89	≥0	≥0	≥38.67	远程控制
2级	≥22.67	≥20	≥18.67	≥61.34	远程控制/车辆状态识别
3级	≥22.67	≥20	≥18.67	≥96.45	预先任务规划或后序遍历
4级	≥44.44	≥40	≥37.78	≥122.22	传感图像联机处理
5级	≥44.44	≥40	≥37.78	≥155.53	简单障碍物检测与躲避
6级	≥64.50	≥60	≥57.75	≥182.25	复杂障碍物检测与躲避、地形分析
7级	≥64.50	≥60	≥57.75	≥205.00	移动目标检测道路或越野环境自主驾驶
8级	≥80.50	≥75	≥72.25	≥227.75	协同操作、护航、通过十字路口、运输跟随
9级	≥80.50	≥75	≥72.25	≥251.14	协同操作、交通标识和信号、接近人工驾驶水平
10级	≥94.22	≥90	≥88.89	≥273.11	达到或超过人类水平的完全自主能力