The invention provides a method and a
system for accurately inducing passenger flow in multiple scenes of
urban rail transit, and belongs to the technical field of
urban rail transit
train operation control. The method comprises the following steps: establishing a passenger path selection behavior model taking
utility maximization as a target under multi-scene induction information; calculating the time when the passenger passes through each section and each
transfer station on the effective path, quantitatively evaluating the overall congestion level of the path based on the congestion condition of each section and each
transfer station at the corresponding time, and reflecting the congestion degree; sorting the feasible paths based on the passenger path selection behavior model; and forthe sorted feasible paths, optimizing path selection behavior
model parameters in combination with a Q-learning learning
algorithm to obtain an optimal induction path. According to the method, the feasible paths are sorted in combination with
related factors such as congestion degree, time and transfer times, and are recommended to passengers as induction information; and finally, parameters of the path selection behavior model are optimized in combination with a
reinforcement learning method, so that the
informatization level and the
service quality of
urban rail transit are effectively improved.