Research on the Mechanism of Learning Intervention and Path Optimization Based on Competency Map-Driven Student Digital Twins

Abstract

Against the background of the deepening transformation of digital education and the prominent structural contradictions between talent supply and demand, the traditional higher education model can no longer meet the diverse learning needs of students nor the market's expectations for interdisciplinary talents. Based on the construction of students' competence map, this study takes the digital intelligence-driven Digital Twin of Students (DTS) as the core element of the learning architecture in institutions of higher education, and systematically explores its conceptual framework, operational mechanism, platform deployment, as well as its functions in students' learning intervention and path optimization. The research indicates that the Digital Twin of Students integrates multi-dimensional dynamic data of students; relying on AI evaluation and decision-making controllers, it achieves the transformation of learning intervention from "extensive coverage" to "precision drip irrigation", constructs a learning path optimization system featuring "goal anchoring-dynamic adaptation-continuous iteration", and ensures practical efficiency through modular deployment and standardized technologies. This system effectively resolves the structural contradictions between the supply of talent training and market demand, promotes the construction of a personalized learning ecosystem, and provides theoretical support and practical approaches for the digital transformation of talent training in colleges and universities, the improvement of students' core literacy, and the accurate alignment between talent supply and demand.