A WeChat-Delivered Offline AI Toolchain for Hardware Simulation Teaching in Rural High Schools: An Exploratory Feasibility Pilot

Abstract

Rural high schools in low-resource environments face substantial barriers to AI-enhanced hardware simulation, including limited network bandwidth (e.g., 2G), low-specification devices (memory below 4 GB), and a lack of localized offline tools. This exploratory feasibility pilot study proposes and preliminarily evaluates a low-resource open-source AI simulation toolchain. The toolchain incorporates a MobileViT behaviour detection module and integrates it with open-source tools such as QEMU, Logisim-evolution, Tinkercad AR, MagicSchool.ai, and Blender to create a WeChat-delivered, offline AI-supported composite toolchain. The toolchain was delivered via WeChat to 25 students at a rural high school in central China over an 8-week A/B testing intervention. It was optimized for offline compatibility, localization training based on rural agricultural scenarios, and privacy protection through anonymous IDs. The study employed exploratory descriptive statistical methods. In this n = 25 exploratory feasibility pilot, descriptive statistics revealed positive descriptive trends in the experimental group for learning efficiency, test accuracy, and participation rate (task completion time reduced by approximately 30%, accuracy rate approximately +25%, participation rate approximately +28%). All statistical results are exploratory findings and require further validation with larger samples. Preliminary observations of the composite toolchain are directionally consistent with certain assumptions of Cognitive Load Theory (CLT) and Self-Determination Theory (SDT). This study provides an exploratory feasibility description of a WeChat-delivered, offline AI-supported toolchain for hardware simulation teaching in rural high schools. Rather than offering evidence of effectiveness, it identifies practical design considerations, implementation challenges, and preliminary descriptive trends that may inform future large-scale research in resource-constrained educational settings.