Research on cultivating students’ creative thinking ability in art design teaching based on machine learning

Abstract Background As technology advances, the emergence of digital media art has transformed how businesses interact with their customers. The traditional approach to digital media design often relies on manual labor and subjective decision-making, which can be time-consuming and limited by human bias. Methodology To overcome this issue, we propose a framework that combines artificial intelligence (AI) algorithms and graphic elements to design digital media interfaces in painting, focusing on enhancing user experiences. By analyzing system requirements and employing AI visual elements, the three models: the user, the window, and the display, are utilized to create a robust system hierarchy. Media libraries are used to develop Windows with general control, ensuring the effectiveness of system functions. The proposed algorithm shows a good chance of obtaining the ideal answer in real design scenarios. Result Fine-tuning the best image restoration quality &amp; PSNR value are obtained when parameters and are set to $$\alpha = 0.6 and \beta =0.4$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mrow> <mml:mi>α</mml:mi> <mml:mo>=</mml:mo> <mml:mn>0.6</mml:mn> <mml:mi>a</mml:mi> <mml:mi>n</mml:mi> <mml:mi>d</mml:mi> <mml:mi>β</mml:mi> <mml:mo>=</mml:mo> <mml:mn>0.4</mml:mn> </mml:mrow> </mml:math> , respectively. System testing displays a 96% accuracy rate in detecting targets and significantly reduces working time. User satisfaction with the design interface is reported to have improved by 82%, making it an ideal fit for the demands of digital media art crossing point design.