Vehicle operation parameter prediction method and system containing space-time characteristics, electronic equipment and readable storage medium

A technology of vehicle operation and spatiotemporal characteristics, applied in the field of intelligent transportation, can solve the problems of lack of semantic information in the area, destroy the integrity of urban areas, and difficult to capture spatial correlation, and achieve the effect of improving the prediction results.

Pending Publication Date: 2021-03-12
HUNAN UNIV
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of tensor modeling method based on grid division is limited by the ideal Euclidean space modeling, the urban area is an irregular shape, and the relationship between each area also exists in a non-Euclidean space.
Through the regular grid division, not only the integrity of the urban area itself is destroyed, but also the divided area lacks clear semantic information
At the same time, sequence models such as long-term and short-term memory networks only regard traffic data as sequence data, which can only capture temporal correlation, but it is difficult to capture spatial correlation; convolutional neural network methods can only deal with the tensor structure of Euclidean space

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
  • Vehicle operation parameter prediction method and system containing space-time characteristics, electronic equipment and readable storage medium
  • Vehicle operation parameter prediction method and system containing space-time characteristics, electronic equipment and readable storage medium
  • Vehicle operation parameter prediction method and system containing space-time characteristics, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] Urban private car travel flows consist of the total number of vehicles entering, staying and leaving urban areas. Its travel is affected by regional functions and the dynamic interaction of travel flows between regions. For example, the travel flow of office areas during the day is usually more than that of residential areas; There is a lot of traffic. The dynamic interaction of private car travel flow between regions also reflects the travel rules of private cars and the relationship between regions. How to extract the spatio-temporal characteristics of private car travel is the first challenge. Furthermore, in this embodiment, the travel flow forecast for private cars includes the following steps:

[0061] Step 1: Construct a multi-view space-time map of the study area

[0062] Among them, the dynamic association between private car travel and urban areas is modeled as a multi-view space-time graph, which specifically includes distance graph, similarity graph, func...

Embodiment 2

[0106] Considering that the residence time of private cars reflects the attractiveness of the area to users, for example, the longer the user stays, the more attractive the area is to the user. How to make full use of the dwell time characteristics of private car users is the second challenge. For this reason, on the basis of Example 1, the dwell time is used to weight the spatio-temporal features, for any vertex v in the spatio-temporal graph i , the output sequence H of the multi-graph convolutional gate recurrent network 1 [i],...,H t [i]...,H T [i], T is the total number of time periods, the formula is as follows:

[0107]

[0108]

[0109]

[0110] Among them, W i,st Indicates the average residence time of vehicles in the i-th AOI area in the previous τ research period, τ is the number of research periods before the current research period t, u is the weight vector, e i is the attention vector of vertex i, a i is the weight vector of the attention network c...

Embodiment 3

[0113] In real life, other external factors such as weather, holidays and events will also affect the distribution of private car travel flow, and these factors make the prediction problem more difficult. Therefore, on the basis of Embodiment 1 or Embodiment 2, this Embodiment 3 also considers adding external features corresponding to external factors, and merging external features with spatiotemporal features as the input of joint prediction, and then transforming to obtain prediction results, that is, research The vehicle operating parameters of each AOI area in the time period.

[0114] In this embodiment, the conversion formula of the following fully connected network is selected:

[0115]

[0116] Among them, E t is the external feature, W is the learned weight, σ is the activation function, such as the Sigmoid function, and b is the bias item.

[0117] It should be understood that before the actual application, the model needs to be trained. After the present invent...

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 invention discloses a vehicle operation parameter prediction method and system containing space-time characteristics, electronic equipment and a readable storage medium, and the method comprises the steps: S1, constructing a multi-view space-time diagram of a research region, taking an AOI region in the research region as a vertex, and taking the region feature quantities of two AOI regions assides; S2, inputting the information of the multi-view space-time diagram and historical data of a research period into a constructed MGCAN network to extract space-time features; wherein the historical data is historical vehicle operation parameters of each AOI area in the research time period; and S3, converting a vehicle operation parameter prediction result of each AOI area in the research time period by utilizing the space-time features. According to the method, the multi-view space-time diagram is constructed through the diagram structure, the multi-view space-time diagram and the space-time characteristics in the historical data are extracted through the MGCAN, vehicle operation parameter prediction is achieved through a brand-new means, and the method can be particularly applied to private car travel flow prediction.

Description

technical field [0001] The invention belongs to the technical field of intelligent transportation, and in particular relates to a method for predicting vehicle operating parameters including spatiotemporal characteristics, a system, electronic equipment and a readable storage medium. Background technique [0002] With the rapid advancement of the world's urbanization process, more and more people live in cities. According to the latest report of the United Nations, about 55% of the world's people live in cities at present, and this proportion will reach 68% in 2050. As the main means of transportation for people to travel, private cars (private small and miniature passenger cars) in cities have also increased sharply. Taking China as an example, as of the end of 2019, the number of private cars reached 207 million, accounting for 81.4% of the total number of cars. The average annual increase of private cars in the past five years is 19.66 million. The contradiction between...

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
IPC IPC(8): G06K9/62G06N3/04G08G1/017G08G1/065
CPCG08G1/017G08G1/065G06N3/045G06F18/22G06F18/253
Inventor 刘晨曦肖竹王东刘代波蒋洪波
Owner HUNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap