The invention relates to an urban intelligent traffic signal control system and method. According to the present invention, the real-time hierarchical control over the area is achieved on the basis ofa hierarchical reinforcement learning method, the adaptive flow control and the data feedback of the intersection are achieved on the basis of the deep reinforcement learning method, the abnormal flow monitoring is achieved, the calculation efficiency is greatly improved, and the intelligent control, adaptive flow and emergency situations of the intersection in the area are achieved. By dependingon the data to generate a reliable scheme, a closed loop of the traffic signal control key three-factor data, the scheme and the signal equipment is formed, so that the requirements of the travelersfor the traffic control that the traffic flow change can be responded real-timely and the red light waiting time is shortened, can be realized.