Human machine collaboration in ideological education supports students with disabilities through AI-assisted communication tools

Abstract The incorporation of artificial intelligence (AI) into ideological and political education (IPE) has tremendous potential to improve accessibility and engagement, particularly among students with impairments. Traditional IPE methods frequently fail to adequately accommodate children with various communication needs, restricting participation, comprehension, and learning outcomes. The purpose of this research is to develop a human–machine collaborative (HMC) framework that uses AI-assisted communication tools to promote inclusive online IPE. The proposed framework begins with the collection of multimodal learning data, including audio, video, and interaction logs, from students during online sessions. The proposed framework used graph memory neural networks (GMNN) method that combines long short-term memory (LSTM) networks to extract and analyse learning features while also capturing temporal trends in student engagement and comprehension. actual monitoring uses graph neural networks (GNNs) to model correlations between body joints and student interactions, detecting attention levels and potential learning issues. Students with hearing or speech impairments benefit from an AI-assisted communication interface that uses google speech-to-text and text-to-speech APIs to provide actual translation, voice synthesis, and sign language support. This integrated approach enables teachers to gain actionable insights and dynamically alter their training. Experimental evaluations on students with disabilities showed better effectiveness, with an average recognition accuracy. The technology outperformed behavior recognition techniques. The findings show that HMC greatly increases engagement, comprehension, and communication in online IPE.