The Construction and Verification of Early childhood Personalized Education Path Based on Artificial Intelligence

Abstract

Early childhood education (ece) is foundational to lifelong learning & development, but traditional pedagogy uses a “one size fits all” method that can’t account for the different ways kids grow, like their interests and how fast they learn. This paper addresses this issue with an innovative system to build personalized learning paths with AI that has been proved valid. Main thing we’re looking at revolves around designing an AI that puts together a dynamic learner profile, a bunch of structured materials, and a good recommendation system all together. Learner profile module. Learner profile gathers an individual’s ability, and their engagement by carrying out interactive assessments and constantly tracking. The content repository comprises modular learning activities tagged with rich metadata - difficulty level and prerequisite skills are just two components of it. AI engine uses a hybrid algorithm, mixing collaborative filtering and a knowledge graph, to create an ever-changing order of those activities, thus providing a perfect, personal learning journey for every child. In order to verify the effectiveness of this model, a 12-week quasi-experiment was carried out by choosing 60 kindergarten children for the experiment, the experimental group which used the AI-based platform and the control group which used non-personalized digital curriculum. From the statistical results we can see that the learning outcome of experimental group is significantly better than that of control group, especially concerning numeracy and solving problems. Moreover, engagement metrics like task completion rates and time-on-task were notably better for kids on the personal path. These results show how powerful AI might be in making better, more fun, and fair learning places for kids in ECE, which could lead to a whole new way of teaching each student differently.