The invention relates to an artificial intelligence convolutional neural network face recognition system. The system comprises a shooting terminal (100), a network (200), a server (300), a convolutional neural network module (400), an artificial intelligence early warning operation system (500), a cloud computing unit (600), a comparison analysis with a cloud database face blacklist unit (700), atarget person identity determination unit (800) and a local database module (900). The method comprises the following steps: acquiring an image or video stream containing a face by using a shooting terminal through an artificial intelligence convolutional neural network face recognition system, automatically detecting and tracking the face in the image, and further performing a series of technicalprocessing related to the face on the detected face, including face detection, face key frame extraction and face verification; all-weather 24-hour uninterrupted monitoring on the periphery of the shooting terminal is realized, a user can realize information sharing, the utilization rate of information resources is improved, and the safety guarantee is increased for maintaining the stability of social security.