A regional people number prediction method and system based on variable components and minimum structure risks

Abstract

The invention provides a regional people number prediction method and system based on variable components and minimum structure risks. The method comprises the steps of obtaining multiple sets of sample data of the number of people in a target region, wherein the sample data comprises a historical real user number and a historical login user variable component of the target area, and the historical login user variable component is obtained according to the historical base station login user number and the stable period user number of the target area; inputting all the sample data into a prediction model containing structural risk factors for training, and taking the prediction model with the minimum structural risk as a target prediction model; obtaining a base station login user number ofthe target area, and obtaining a login user variable component according to the base station login user number and the stable period user number; and inputting the variable component of the login user into the target prediction model to obtain a corresponding predicted value of the number of people in the target area. According to the method, the prediction efficiency and the generalization degree of the model are obviously improved while the accurate prediction of the passenger flow volume is realized.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method and system for predicting the number of people in an area based on variable components and minimum structural risk. Background technique [0002] With the take-off of my country's economy, large-scale events have gradually become the main carrier to promote cultural exchanges and economic prosperity and development. In large-scale cities such as Shanghai and Beijing, the scale and number of various large-scale activities (such as holiday celebrations, sports events, etc.) are increasing day by day, which leads to various group security problems emerging in an endless stream. According to the "Social Blue Book" data released by the Chinese Academy of Social Sciences, the number of mass incidents in my country has increased by about 10 times from 1993 to 2005, and there is still an upward trend in recent years. [0003] After analyzing the mass incidents th...

AI Technical Summary

Problems solved by technology

The operator's telecom network has the following characteristics. First, the network coverage cannot completely match the physical location of the actual area. In some key areas, there are multiple base stations covering at the same time. Second, there are factors such as signal drift and interference. The number of mobile phones logged in at the base station cannot truly reflect the number of people in the area; in addition, there are certain differences in the rate and number of mobile phones owned by the population, and dual-card and single-card mobile phones coexist, so it is impossible to accurately count the number of logged-in mobile phones in the area; At the same time, regular or irregular adjustments by operators to the location, number, and network of base stations lead to sudden changes in the number of users in fixed areas; therefore, using common linear and nonlinear deep learning models to directly construct the relationship between the number of mobile phone users and the number of real passengers The effect is often not good, and problems such as cross-regional use of the model cannot be realized

Images