Research on intelligent regulation mechanisms of learner cognitive load in digital learning environments

Abstract

This research develops an intelligent cognitive load regulation framework for digital learning environments in the context of educational policy reforms. After China's Double Reduction Policy took effect, tutorial-concentrated schooling evolved into technology-facilitated learning, putting unimaginable cognitive burdens on students. In response, the research combines cognitive load theory with adaptive technologies to resolve these issues through real-time recognition of cognitive states and personalized interventions. Based on the mixed-methods design with 320 Dongcheng District students, the research uses established measures such as NASA-TLX adapted to e-learning environments to assess multidimensional patterns of cognitive load. The smart regulation system shows significant efficacy with lower socioeconomic students posting 15.3-point improvements in academic scores, task accomplishment rates enhanced by 32%, and the level of cognitive loads decreased by 23.1% on average across various types of learners. The system can recognize with 87.3% accuracy and respond in 234 milliseconds, thus facilitating timely interventions. Self-paced review activities yield 91.2% success rates, while collaborative tasks remain problematic at 68.4% success rates. The results extend cognitive load theory with dynamic adaptation capacities needed for self-managed digital learning. The present study provides evidence-based practice to maximize cognitive experiences of e-learning, facilitating education equity objectives while developing core self-regulated learning skills in post-reform education systems.