Abstract The global prevalence of non-suicidal self-harm (NSSI) among adolescents is becoming increasingly severe. Traditional mental health services are struggling to meet the growing social demand due to limited resource allocation and service accessibility. The rapid development of artificial intelligence (AI) technology provides a new technological path. The article systematically reviews the research progress of AI technology in adolescent NSSI, demonstrating key technologies such as machine learning, natural language processing, and deep learning in predicting NSSI risk prediction, emotion recognition and online intervention for adolescents. However, challenges remain, including algorithm bias, data privacy protection, model interpretability and ethical decision making. Future research should focus on multi disciplinary collaborative cooperation based on artificial intelligence to build a safe, effective and sustainable digital psychological intervention system, so as to provide innovative strategies and technical support for the early warning and intervention of NSSI behavior in adolescents.