Event-driven-based remaining parking berth number real-time prediction method and event-driven-based remaining parking berth number real-time prediction system

Abstract

The invention discloses an event-driven-based remaining parking berth number real-time prediction method and an event-driven-based remaining parking berth number real-time prediction system. The event-driven-based remaining parking berth number real-time prediction method comprises the following steps: acquiring historical parking information and performing continuous repairing and smoothing process on the historical parking information, wherein the historical parking information comprises historical vehicle arriving time, historical vehicle leaving time, driving event occurrence time and historical remaining parking berth number; and obtaining arriving probability and leaving probability of parking vehicles from the current time to the next time based on the driving event occurrence time and according to the historical vehicle parking information, supposing that the parking vehicle arriving probability is subjected to normal distribution; obtaining a remaining parking berth number prediction model according to a difference value between the remaining parking berth number acquired actually at the present time and the sum of the arriving probability and the leaving probability of the parking vehicles from the current time point to the next time point; and inputting both the current time point and the next time point into the remaining parking berth number prediction model, and outputting a remaining parking berth number prediction value in real time.

Description

Technical field [0001] The invention belongs to the field of traffic information systems, and in particular relates to an event-driven method and system for real-time prediction of the number of vacant parking spaces. Background technique [0002] With the proliferation of vehicles in Chinese cities, the imbalance between parking demand and supply has caused various traffic problems. The uneven distribution of parking demand and supply during peak hours makes parking spaces unable to be used efficiently, thereby increasing the traffic pressure on urban roads. The Parking Guidance Information System collects parking space information, estimates and predicts the number and location of vacant parking spaces, provides users with real-time and accurate information, assists users in planning travel routes, and facilitates parking lot managers to effectively manage free parking spaces. [0003] Domestic and foreign researches on the prediction of the number of vacant parking spaces mainl...

AI Technical Summary

Problems solved by technology

Although the methods mentioned above have been verified in actual measurements, these empirical methods have poor universality and cannot characterize the dynamic behavior of parking

Images