Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method, device and server for intelligent traffic traffic prediction

A technology of intelligent transportation and prediction method, which is applied in the direction of traffic flow detection, neural learning method, biological neural network model, etc., can solve the problem of low accuracy rate of vehicle passing time prediction, and achieve the effect of improving the prediction accuracy rate

Active Publication Date: 2020-09-18
ZDST COMM TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention aims to provide a smart traffic traffic prediction method, device and server, which solves the current technical problem of low prediction accuracy of vehicle transit time, and improves the accuracy of vehicle traffic through the combination of convolutional neural network and LSTM network. time prediction accuracy

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
  • Method, device and server for intelligent traffic traffic prediction
  • Method, device and server for intelligent traffic traffic prediction
  • Method, device and server for intelligent traffic traffic prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] see figure 1 , figure 1 It is a schematic diagram of a ConvLSTM neural network provided by an embodiment of the present invention;

[0060] Such as figure 1 As shown, the ConvLSTM neural network is a convolution-long short-term memory network, and the embodiment of the present invention establishes a transit time prediction algorithm through the ConvLSTM neural network, specifically, as figure 1 As shown, C1, C2 and D form a convolutional neural network, and S1 and S2 form a two-layer LSTM network. By combining the convolutional neural network and the LSTM network, both the ability of the convolutional neural network to extract spatial features and the ability of the LSTM network to process time series can be used to better train the transit time prediction algorithm. Wherein, the ConvLSTM neural network includes: a convolutional neural network and an LSTM network.

[0061] Such as figure 1 As shown, C1 and C2 represent the convolutional layer, and D represents the...

Embodiment 2

[0155] see Figure 8 , Figure 8 It is a schematic structural diagram of a smart traffic prediction device provided by an embodiment of the present invention; the smart traffic prediction device 100 can be applied to a server, such as Figure 8 As shown, the intelligent traffic prediction device 100 includes:

[0156] Historical traffic information unit 10, used to obtain historical traffic information;

[0157] The traffic feature unit 20 is used to extract a plurality of traffic features based on the convolutional neural network according to the historical traffic information;

[0158] The passing time prediction algorithm unit 30 is used to establish a passing time prediction algorithm based on the long short-term memory network according to the traffic characteristics;

[0159] The vehicle transit time prediction unit 40 is configured to predict the vehicle transit time of a specific road segment in a specific time period based on the transit time prediction algorithm. ...

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

Embodiments of the invention relate to the technical field of intelligent traffic, and disclose an intelligent traffic passage prediction method and apparatus as well as a server. The intelligent traffic passage prediction method comprises the following steps: acquiring historical traffic information; extracting a plurality of traffic characteristics according to the historical traffic informationand based on a convolutional neural network; according to the traffic characteristics and based on a long-term / short-term memory network, establishing a passage time prediction algorithm; and based on the passage time prediction algorithm, predicting a vehicle passing time of a specific road section in a specific time period. By virtue of the intelligent traffic passage prediction method, the technical problems of low prediction accuracy of the existing vehicle passing time can be solved, and the prediction accuracy of the vehicle passing time can be improved by combining the convolutional neural network and the LSTM network.

Description

technical field [0001] The present invention relates to the technical field of intelligent traffic, in particular to a method, device and server for predicting intelligent traffic traffic. Background technique [0002] At present, with the improvement of people's living standards, the number of vehicles held is increasing, and urban road congestion has become an unspeakable secret for every traveler, which has a great impact on urban management and residents' lives. Therefore, how to accurately predict the passage of road sections Time has become an urgent problem that needs to be solved. With the advent of the mobile Internet era, every traveler has become a contributor to urban traffic information, making the cloud anonymously collect a large number of users' geographical location and other data, which can be processed Then generate traffic information that covers the whole time of the city and has no blind spots. At present, most of the predictions of passing time are ba...

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): G08G1/01G06N3/04G06N3/08
Inventor 李晓刚
Owner ZDST COMM TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com