Intelligent evaluation model for educational management quality based on fuzzy logic and deep neural network data analysis

With the acceleration of educational informatization, the scientific evaluation of educational management quality has become a key link in optimizing the allocation of educational resources and improving teaching efficiency. Traditional evaluation methods rely heavily on subjective experience and static indicators, making it difficult to adapt to the complexity and dynamics of modern educational systems. This study proposes an intelligent evaluation model combining fuzzy logic and deep neural network (DNN), aiming to solve the core problems of uncertain data processing and nonlinear feature mining in educational management quality evaluation. The model quantifies the fuzziness and dynamic correlation of evaluation indicators through a fuzzy logic system, and constructs a dynamic weight allocation mechanism combined with the deep feature learning ability of DNN, to realize the intelligent and adaptive optimization of the evaluation process. Experiments are conducted based on educational management data from 236 primary and secondary schools in 12 provinces of China, covering six core indicators including teacher allocation, student development, and informatization level. The results show that the evaluation accuracy of the proposed model on the test set reaches 93.7%, which is 21.5% and 8.3% higher than that of the traditional analytic hierarchy process (AHP) and single DNN model, respectively, and its robustness to data noise is significantly better than that of all comparison models. In addition, the model reveals the nonlinear threshold effect between teacher turnover rate and student satisfaction through interpretability analysis, which provides a quantitative basis for data-driven educational management decision-making.