Design of an AI-Driven Personalized Learning Roadmap Generation System for Elementary Students Based on the 2022 Revised National Curriculum

This study aims to design an AI-driven system that automatically generates personalized learning roadmaps for elementary students based on the achievement standards of the 2022 Revised National Curriculum. To address the limitations of traditional learning materials that fail to accommodate diverse learner characteristics, the proposed system integrates learner-profile analysis, achievement-standard structuring, learning-plan generation, problem and inquiry-activity construction, and personalized feedback into a unified workflow. The system interprets learner attributes—such as confidence level, learning style, and problem-solving tendencies—to adjust task difficulty and sequencing. It also extracts core concepts embedded in achievement standards to construct structured learning–review–reinforcement cycles. The generated problems and inquiry activities reflect both target proficiency levels and the learner’s inquiry disposition, while the personalized feedback component supports sustained engagement. This study demonstrates the potential of achievement-standard-driven individualized learning environments supported by AI-based automation.