Multi-source data-based crowding degree prediction method of urban public open space

Abstract

The present invention proposes a multi-source data-based crowding degree prediction method of an urban public open space. Urban multi-source data such as WeChat user number data, POI data, comment data, area attribute data, meteorological data and time attribute data are utilized to determine the spatial-temporal features of each small region in the space; the people flow indexes of a region in different historical periods are obtained from the WeChat user number chart data through using a gridding sampling adding method; the historical people flow indexes and the spatial-temporal features are inputted into a fuzzy neural network model, so that people flow index prediction can be realized; and a predicted people flow index is converted into crowding degree through using clustering and comparison. With the method of the invention adopted, the prediction of the crowding degree is successfully achieved through using the open urban multi-source data; and the technological problems of too high prediction costs caused by over-reliance on hardware equipment, and incapability of realizing accurate prediction by using a single data source of a traditional crowding degree prediction method can be solved; and prediction economic costs are decreased, and prediction accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of urban computing. Background technique [0002] The increase in urbanization rate and population increase has led to an increase in the demand for urban public open space, and the degree of congestion in urban public open space will also increase. And this will bring hidden dangers to urban public safety and traffic order. Therefore, it is necessary to predict the crowding degree of urban public open space. However, due to the randomness and dispersion of the flow of people, it is difficult to accurately count the flow of people in the space, and it is difficult to reasonably divide and predict the degree of crowding. Japan's BAB HITACHIIND company discloses a method for evaluating the crowding degree of the flow of people through the video image analysis of the camera (JP2007180709A). However, this method cannot achieve prediction and relies heavily on expensive camera hardware, so its popularity is po...

AI Technical Summary

Problems solved by technology

Although this technical method realizes the evaluation and prediction of crowding degree independent of hardware equipment, the mobile phone signaling data it is based on is not a real-time public data, and the classification of crowding is also relatively subjective, resulting in poor versatility The problem

[0003] In summary, the above-mentioned methods all have the problems of large hardware investment or relying only on the analysis and prediction of a single data source, resulting in the problems of poor economy and versatility of technical methods

Images