Artificial intelligence-based creative thinking skill analysis model using human–computer interaction in art design teaching

Abstract

Due to the rapid growth of network technology, its openness and sharing capabilities and interaction have helped change the art education model for the better. Increased science has been presented to students who spend a lot of time utilizing technology. They similarly did greater mathematical abilities. IT has a good effect on student learning must be included in classroom education. Art education must shift from a teacher-centred to a student-centred approach, and students' passive reception of knowledge must be altered. Students' academic enthusiasm and awareness must be fostered, and their ability to locate knowledge resources must be enhanced. Using pedagogical content knowledge (PCK) in visual art education as a benchmark and this study examines art teachers' PCK proficiency in this area. Social learning theory is applied in the art education curriculum through observational learning based on the Artificial Intelligence-based Creative Thinking Skills Analysis Model (AI-CTSAM). An analytical hierarchy process (AHP) and a grey clustering-based performance analysis model are established to enhance AI's effectiveness in art instruction. Most of the methods to assess clustering performance exist in two types in which one is irrelevant actions requiring labels of foundation truth. Examples are Adjusted Rand, Fowlkes-Mallows, Mutual information scores, Homogeneity, Completeness, and V measurements. Model-based cluster analysis is a new classification approach for investigating population heterogeneity utilizing a limited multivariate mixture. Students can describe, analyze, interpret, and evaluate artwork through the visual art education curriculum.