Public bicycle peak time demand prediction method considering user reservation data

Abstract

The invention discloses a public bicycle peak time demand prediction method considering user reservation data. The public bicycle peak time demand prediction method is characterized in that 1) user peak time reservation data can be acquired and extracted; 2) the use data of the public bicycle historical peak time can be acquired; 3) the reservation data can be processed, and the reservation demand quantities of different rental stations at different times in the next day can be acquired; 4) the historical data can be processed, and the demand prediction values of different rental stations at different times in the next day can be acquired; 5) the prediction values can be integrated according to the reservation data and the historical data, and the final borrowing and returning demand quantities of different rental stations at different times can be determined; 6) the scheduling demand table having the time window can be drawn. The public bicycle peak time demand prediction method is advantageous in that the accuracy of predicting the bicycle and locking pile demands of different public bicycle rental stations at peak times can be effectively improved, and the data having the actual reference value can be provided for the peak time scheduling.

Description

technical field [0001] The invention relates to the technical field of domestic urban public bicycle system construction and operation management, in particular to a public bicycle peak demand forecasting method considering user reservation data. Background technique [0002] At present, demand forecasting plays a very important role in the construction and operation management of domestic urban public bicycle systems. In the network planning link of system construction, it is generally necessary to comprehensively consider factors such as regional function types, regional land use properties, service population size, and bicycle use intensity, and use different forecasting methods such as Logit model and transfer volume estimation to estimate the demand for regional public bicycles. Make predictions to determine the layout and scale of public bicycles in the region. Although the results predicted by these methods cannot be said to be very accurate, they can basically meet ...

AI Technical Summary

Problems solved by technology

It can be found that these dispatches are not based on demand forecasting, and there is a serious lag, resulting in the difficulty of borrowing and returning cars during peak hours.

Images