Unlock instant, AI-driven research and patent intelligence for your innovation.

An online-offline-related urban passenger flow forecasting method

A prediction method, online and offline technology, applied in prediction, neural learning method, data processing application, etc., can solve the problem of low prediction accuracy, achieve the effect of good sequence modeling ability and improve the accuracy rate

Active Publication Date: 2022-07-19
WUHAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention proposes a method for predicting urban passenger flow associated with online and offline, which is used to solve or at least partially solve the technical problem that the prior art method relies on historical data for prediction, so the prediction accuracy is not high

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An online-offline-related urban passenger flow forecasting method
  • An online-offline-related urban passenger flow forecasting method
  • An online-offline-related urban passenger flow forecasting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The embodiment of the present invention provides a method for predicting urban passenger flow associated with online and offline. On the one hand, dilated causal convolution (DCNN) is used to capture short-term, periodic, and long-term dependencies in time, and combined with external factors such as weather and holidays, On the other hand, it captures the correlation between online and offline behaviors, fully considers the impact of emergencies and their resulting online behaviors on the movement of offline user groups, and more accurately predicts the distribution of passenger traffic at the next moment. .

[0048] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides a method for predicting urban passenger flow associated with online and offline. On the one hand, it fully captures the time dependence of historical passenger flow data, and combines the characteristics of external factors such as weather, holidays, and major events. The online access content of users in different states in each region builds the correlation between online and offline behaviors. After combining the features of the two parts through a trained single-hidden-layer fully-connected network, it can more accurately predict the inflow and outflow of passenger flow in all areas, and fully consider the impact of emergencies on passenger flow changes.

Description

technical field [0001] The invention relates to a passenger flow prediction technology related to smart city applications, and the technical fields of big data analysis and deep neural network, in particular to a city passenger flow prediction method associated with online and offline. Background technique [0002] With the rapid development of Internet of Things technology, the Internet of Things technology makes cities develop in a smarter direction. IoT-based smart cities involve technologies such as densely distributed sensors, heterogeneous network infrastructure, intelligent information processing, and urban computing in a large number of cities. Urban passenger flow forecasting is one of the important components for smart city applications. [0003] At present, a wide range of smart IoT devices and services provide us with more convenience to obtain urban crowd flow data. We can obtain a variety of security data for urban crowd detection from the interconnected data...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/04G06Q50/26G06Q50/30G06N3/08G06N3/04G06F17/16
CPCG06Q10/04G06F17/16G06Q50/26G06N3/08G06N3/045G06Q50/40
Inventor 周蜀杰曾园园江昊
Owner WUHAN UNIV