Research on the Quantitative Evaluation System for Simulation Training Effects

To enhance the objectivity and real-time nature of simulation training effect evaluation, this paper constructs a multilevel quantitative evaluation model by integrating the fuzzy theory and big data technology. The Analytic Hierarchy Process (AHP) is employed to determine the weights of evaluation indicators. The fuzzy theory is utilized to quantify the uncertainties in the evaluation process, and big data technology is introduced to optimize the data collection, storage, and analysis processes. A distributed computing framework is used to process massive training data, machine learning algorithms are combined to optimize the weight allocation, and dynamic evaluation results are generated through real-time data flow analysis. Taking the redblue formation confrontation training as an example, an evaluation system based on big data is designed to achieve multidimensional analysis and visualization of training effects.