系统仿真学报 ›› 2026, Vol. 38 ›› Issue (4): 1030-1045.doi: 10.16182/j.issn1004731x.joss.25-0674

• 论文 • 上一篇    下一篇

基于作战实验的虚拟兵力智能水平测试与评估方法研究

刘大勇1,2, 董志明1, 张伟东2, 张文军3, 高建成1   

  1. 1.陆军兵种大学,北京 100072
    2.中国人民解放军32302部队
    3.国防大学 联合勤务学院,北京 100858
  • 收稿日期:2025-07-14 修回日期:2025-11-17 出版日期:2026-04-20 发布日期:2026-04-22
  • 通讯作者: 董志明
  • 第一作者简介:刘大勇(1984-),男,工程师,博士生,研究方向为装备试验与仿真。

Method for Testing and Evaluating Intelligence Level of Virtual Forces Based on Operational Experiments

Liu Dayong1,2, Dong Zhiming1, Zhang Weidong2, Zhang Wenjun3, Gao Jiancheng1   

  1. 1.Army Arms University of PLA, Beijing 100072, China
    2.PLA 32302 Troops
    3.Joint Logistics College, National Defense University, Beijing 100858, China
  • Received:2025-07-14 Revised:2025-11-17 Online:2026-04-20 Published:2026-04-22
  • Contact: Dong Zhiming

摘要:

虚拟兵力的智能水平是影响战术对抗仿真可信度与有效性的关键因素。针对当前其测试评估体系基本缺失的问题,提出了一种基于作战实验的虚拟兵力智能水平测试与评估 方法 。以作战实验理论为指导,通过构设动态对抗环境激发虚拟兵力的智能行为,并按照一套系统流程对其智能表现数据进行采集、计算、分析与评估。设计了该方法的总体架构、逻辑功能模块与基本测评流程;构建了涵盖任务完成效能、认知效能、认知适应性及认知效率的“4M”基线评估指标体系,以及九级智能分级模型;论证对比了3种典型评估实验实施模式的适用性,并示范了该方法的具体应用。

关键词: 虚拟兵力, 智能水平, 作战实验, 测试与评估, 基线评估指标体系, 智能分级模型

Abstract:

The intelligence level of virtual forces is a key factor affecting the credibility and effectiveness of tactical confrontation simulations. To address the current lack of a testing and evaluation system, a method for testing and evaluating the intelligence level of virtual forces based on operational experiments is proposed. Guided by operational experiment theory, the method stimulates the intelligent behavior of virtual forces by constructing dynamic confrontation environments, and collects, calculates, analyzes, and evaluates their intelligence performance data according to a systematic process. The overall architecture, logical functional modules, and basic evaluation process of the method are designed. A "4M" baseline evaluation index system is conducted, covering task completion effectiveness, cognitive effectiveness, cognitive adaptability, and cognitive efficiency, along with a nine-level intelligence level model. The applicability of three typical evaluation experiment implementation modes is analyzed and compared. A case study demonstrates the method's application.

Key words: virtual forces, intelligence level, operational experiment, testing and evaluation, baseline evaluation index system, intelligence level model

中图分类号: