Short-time passenger flow prediction method and system based on multi-source data fusion input

Abstract

The invention discloses a short-time passenger flow prediction method based on multi-source data fusion input. The short-time passenger flow prediction method comprises the following steps: acquiring sample data; preprocessing the sample data; extracting multi-source data features from the sample data; adjusting the dimensions of the obtained external factor features and video features through two full-connection layers, and enabling the dimensions of the features to be unified; performing multi-source data feature fusion on the sample data, and establishing a passenger flow prediction model; and predicting the passenger flow data according to the passenger flow prediction model, and automatically adjusting the working states of various facilities according to the prediction condition. The invention discloses a short-time passenger flow prediction system based on multi-source data fusion input. According to the method, unified data features are extracted from intricate passenger flow influence factors through a multi-source data fusion method, so that the accuracy of short-time passenger flow prediction is improved, precise passenger flow prediction and warning in different specific scenes are realized, the working states of various facilities are automatically adjusted according to prediction conditions, and safe operation is ensured.

Description

technical field [0001] The invention relates to the technical field of rail transit, in particular to a short-term passenger flow prediction method and system based on multi-source data fusion input. Background technique [0002] The passenger flow of rail transit has obvious time-space and periodicity, and is easily affected by factors such as weather, emergencies, holidays, large-scale events, etc. In order to more accurately predict the short-term passenger flow of rail transit, it is very necessary to analyze the multi-source data that affects passenger flow Conduct analytical research. Multi-source data has very strong spatio-temporal attributes, often accompanied by the problem of multi-source and heterogeneous data. Among them, multi-source means that the source channels of data are diverse, and heterogeneous means that data includes structured data and unstructured data. According to the type of data structure, multi-source data fusion can be divided into homogeneou...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the technical problems existing in the background technology, the present invention proposes a short-term passenger flow prediction method and system based on multi-source data fusion input to solve the problems of poor efficiency of multi-source data fusion and low accuracy of rail transit passenger flow prediction

Images