Multi-party win-win contract parking space sharing system

Abstract

The invention discloses a multi-party win-win contract parking space sharing system, which comprises the steps of firstly, preprocessing and screening data, specifically, collecting parking records of each community and section, collecting environment and holiday and festival data, processing phenomena such as missing values and abnormities, and screening proper contract parking spaces meeting requirements according to information entropy and relative entropy indexes; secondly, conducting model prediction by adopting a neural network mode, and predicting the parking time; and finally, maximizing the total utilization time of the parking space through an approximate dynamic programming algorithm based on hierarchical processing by adopting a comprehensive balance strategy. The system has the beneficial effects that the total utilization time of the parking spaces is maximized, and different from a traditional scheduling algorithm, the system enables the utilization rate of the contract parking spaces to be improved by 50% or above. On the one hand, the original vacant parking space can be utilized, and the original vacant parking space brings a certain profit to a parking space owner; and on the other hand, the problem that parking around a parking lot is difficult can be solved.

Description

technical field [0001] The invention relates to a multi-party win-win sharing contract parking space system. Background technique [0002] With the rapid development of China's economy, the number of private cars in my country has reached 260 million. According to statistics, due to the sudden increase in the number of vehicles, the construction of parking facilities has not kept up with it. Nearly 30% of traffic congestion during peak hours is caused by vehicles not finding parking spaces in time. With the maturity of the Internet of Things technology, most parking lots can now record fine-grained parking data through sensor devices. Using these data, the free time of parking spaces can be predicted in advance, so as to make more reasonable scheduling arrangements. The sharing system provides the conditions. [0003] Some studies have also proposed solutions to the problem of "difficult parking": For example, some researchers have used recurrent neural networks (RNN) in e...

AI Technical Summary

Problems solved by technology

[0005] Purpose of the invention: Inspired by the existing parking behavior modeling research, aiming at the obvious periodicity of parking behavior and the characteristics of being easily affected by various factors, a multi-party win-win shared contract parking space system is designed. The parking space can be utilized, so that the original vacant parking space can generate certain profits for the owner of the parking space. On the other hand, it can also alleviate the problem of difficult parking around the parking lot.

Images