Construction and Practical Exploration of Learner Self-Evaluation System Based on AIGC Environment

Abstract

With the large-scale application of AIGC in the education field, traditional learners' self-evaluation is difficult to adapt to digital learning needs due to fixed standards, missing data, and lagging feedback. This article is based on the Guiding Opinions of the Ministry of Education on Strengthening the Digitization of Education in the New Era in 2023, combined with AIGC's natural language processing and data mining capabilities, and using literature research and teaching practice summary as methods, to explore the logic and path of constructing a self-evaluation system in the AIGC environment. Clarify the core connotation of "data-driven+self reflection", analyze the four dilemmas of traditional evaluation standards, data, feedback, and subjectivity, propose a five in one framework, design tool selection to process implementation, and propose optimization directions based on teaching feedback. AIGC can automatically collect data throughout the entire process and generate personalized feedback in real-time, improving the objectivity and timeliness of evaluation, providing practical solutions for the digital reform of educational evaluation, and also providing reference for the practice of independent evaluation in primary and secondary schools and universities.