Foodborne pathogenic microorganisms are the primary causative agents of food safety incidents and public health risks. Traditional detection methods exhibit limitations in detection cycle, sensitivity, and adaptability to complex matrices, failing to meet the modern food supply chain’s demands for rapid, high-throughput, and intelligent monitoring. The rapid advancement of artificial intelligence (AI) technology has opened new technical pathways for the transformation and upgrading of microbial detection systems. This article systematically reviewed the application progress of AI in the detection of foodborne pathogenic microorganisms, focused on 3 major directions: Molecular biology detection, spectral analysis techniques and mass spectrometry detection. It highlighted the functional mechanisms and technical effects of machine learning and deep learning algorithms in amplification signal analysis,spectral feature extraction, mass spectrometry data mining and multi-source information fusion. The analysis indicated that the introduction of AI had effectively enhanced the sensitivity, specificity and automation level of detection systems, accelerating the transition from laboratory analysis to on-site rapid screening and intelligent early warning. Meanwhile, this article identified the current deficiencies in standardized dataset construction, model generalization capability verification, algorithm interpretability and cross-platform data fusion standards, and proposed future development recommendations from the perspectives of data governance, regulatory adaptation and industrial collaboration. This article aims to provide systematic literature reference and theoretical support for the integration and optimization of intelligent detection systems in the field of food safety.