Urban traffic model construction method based on big data

The invention discloses an urban traffic model construction method based on big data. The method comprises a travel generation stage, a travel distribution stage, a mode division stage and a traffic distribution stage which are executed in sequence, in the mode division stage, a non-aggregated model is adopted; after the traffic distribution stage is executed once, the obtained motor vehicle flowof the road section is substituted into a travel distribution stage as background flow to restart calculation; and the relative error of the motor vehicle flows of the two road sections is calculated,and if the requirement of the relative error is not met, the new motor vehicle flow of the road section is substituted into the travel distribution stage again to restart calculation until the relative error meets the requirement. By adopting the non-aggregated model in the mode division stage, the model precision is improved, and meanwhile, excessive calculated amount is not increased. By meansof loop iteration of the mo