CN117523848B - Traffic jam information prediction method, device, computer equipment and medium - Google Patents
Traffic jam information prediction method, device, computer equipment and medium Download PDFInfo
- Publication number
- CN117523848B CN117523848B CN202410010051.6A CN202410010051A CN117523848B CN 117523848 B CN117523848 B CN 117523848B CN 202410010051 A CN202410010051 A CN 202410010051A CN 117523848 B CN117523848 B CN 117523848B
- Authority
- CN
- China
- Prior art keywords
- road
- matrix
- traffic
- saturation
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000011159 matrix material Substances 0.000 claims abstract description 153
- 230000004927 fusion Effects 0.000 claims abstract description 81
- 230000008846 dynamic interplay Effects 0.000 claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 14
- 238000012546 transfer Methods 0.000 claims description 11
- 230000003993 interaction Effects 0.000 claims description 10
- 230000003190 augmentative effect Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000003416 augmentation Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 241001061225 Arcos Species 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000002123 temporal effect Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a device, computer equipment and a medium for predicting traffic jam information, which comprise the following steps: receiving traffic feedback data of each terminal device; carrying out data processing on traffic feedback data by adopting edge equipment to obtain road saturation and region saturation, constructing a fusion feature matrix of the road and the region as external features, and constructing a similar feature matrix based on the external features; respectively extracting space-time characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix by adopting a space-time characteristic extraction mode; and constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics. The prediction accuracy is improved by combining the prediction of both macroscopic and microscopic, and simultaneously, the prediction efficiency can be improved and the storage redundancy can be reduced by combining an edge computing technology.
Description
Technical Field
The present invention relates to the field of data processing, and in particular, to a method, an apparatus, a computer device, and a medium for predicting traffic congestion information.
Background
With the acceleration of the progress of urban and industrialized production, the accumulation of urban residents and the maintenance of motor vehicles continuously rise, and the problem of sporadic or frequent traffic jam of urban traffic is increasingly serious. The road saturation index is one of important indexes reflecting the road service level, and also is an important index reflecting whether the road is congested, and the size of the road saturation index depends on the traffic flow and traffic capacity of the road and is influenced by factors such as weather characteristics, living habits and the like.
In order to avoid resource waste caused by traffic jam, a plurality of scholars propose various ideas for solving the problem: at present, the method for predicting the traffic jam at home and abroad mainly comprises neural network prediction, support vector machine prediction, deep learning prediction and the like, and integrated algorithms such as random forests, gradient lifting regression trees and the like are also widely applied.
The inventor realizes that at least the following technical problems exist in the prior art in the process of realizing the invention: at present, prediction research is carried out only through a macroscopic or microscopic single view angle, and road saturation indexes are ignored, so that a prediction result is not accurate enough.
Disclosure of Invention
The embodiment of the invention provides a method, a device, computer equipment and a storage medium for predicting traffic jam information, so as to improve the accuracy of traffic information prediction.
In order to solve the technical problem, an embodiment of the present application provides a method for predicting traffic congestion information, which is applied to a system for predicting traffic congestion information, where the system includes a terminal device, an edge device, and a central cloud layer, and the method for predicting traffic congestion information includes:
receiving traffic feedback data of each terminal device;
adopting the edge equipment to perform data processing on the traffic feedback data to obtain road saturation rs n,i and regional saturation Wherein rs n,i represents road saturation of road n at i time,/>The region saturation of the region m at the moment i;
Constructing a fusion characteristic matrix F n,i of a road and a region, As external features and based on the external features, constructing a similar feature matrix/>
Respectively extracting space-time characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix by adopting a space-time characteristic extraction mode;
and constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics.
Optionally, the edge device is used for performing data processing on the traffic feedback data to obtain road saturation rs n,i and region saturationComprising the following steps:
Determining road saturation based on the traffic flow and road traffic capacity;
dividing the regions by adopting a clustering mode based on density, and calculating the region saturation of each region
Optionally, the road traffic capacity includes an ideal traffic capacity RC I and a design traffic capacity RC D, and determining the road saturation based on the traffic flow and the road traffic capacity includes:
The road saturation RS is calculated using the following formula:
RCD＝λ·μ·γ·RCI
wherein λ, μ, γ are correction coefficients of the lane width, intersection, and number of lanes, respectively, and RF is the traffic flow.
Optionally, the clustering method based on density is adopted for area division, and the area saturation of each area is calculatedComprising the following steps:
the distance from the core point of the area to the road acquisition point road is calculated by using the longitude and latitude values of GPS positioning:
dcore,road＝REarth*arcos[cos(Ycore)*cos(Yroad)*cos(Xcore-Xroad)+sin(Ycore)*sin(Yroad)]
Wherein R Earth is the radius of the earth, Y core、Yroad is the latitude of the node core and the node head, and X core、Xroad is the longitude of the node core and the node head;
The area saturation is calculated using the following formula
Wherein,The region saturation of the region m at the moment i; q is the number of roads in the area; rs q,i represents the road saturation of the road q at the moment i, q being the road code number in this area.
Optionally, the construction of the fusion feature matrix F n,i of the road and the region,As external features, there are:
the augmented characteristics of road n at time i are determined as follows:
etn,i＝Concat(ecn,i,tcn,i)
Where et n,i represents the augmented characteristic of road n at time i, ec n,i represents the external environmental characteristic of road n at time i, and tc n,i represents the time characteristic of road n at time i;
the fusion is performed using the following formula:
Wherein f n,i is used to fuse saturation information with the augmentation characteristic, W represents a learnable parameter of the convolution kernel, Representing a convolution operation;
And taking the fusion result as a fusion characteristic matrix F n,i of the road.
Optionally, the method for extracting the space-time features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by adopting a space-time feature extraction method includes:
extracting time features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix by adopting an expansion gate convolution algorithm;
Taking the obtained time characteristics as input, and extracting the spatial characteristics of the region fusion characteristic matrix, the road fusion characteristic matrix and the similar characteristic matrix by adopting a graph convolution neural network algorithm;
and taking the time features and the space features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix as the space-time features.
In order to solve the above technical problem, an embodiment of the present application further provides a device for predicting traffic congestion information, including:
The data receiving module is used for receiving traffic feedback data of each terminal device;
The data processing module is used for performing data processing on the traffic feedback data by adopting the edge equipment to obtain road saturation rs n,i and regional saturation Wherein rs n,i represents road saturation of road n at i time,/>The region saturation of the region m at the moment i;
The matrix construction module is used for constructing a fusion characteristic matrix F n,i of the road and the region, As external features and based on the external features, constructing a similar feature matrix/>
The feature extraction module is used for respectively extracting the space-time features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by adopting a space-time feature extraction mode;
And the result prediction module is used for constructing a dynamic interaction relation between the area and the road and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics.
Optionally, the data processing module includes:
The road saturation determining unit is used for determining road saturation based on the traffic flow and the road traffic capacity;
And the region saturation determination subunit is used for dividing the regions by adopting a density-based clustering mode and calculating the region saturation of each region.
Optionally, the road saturation determining unit includes:
a first calculating subunit, configured to calculate the road saturation RS according to the following formula:
RCD＝λ·μ·γ·RCI
wherein λ, μ, γ are correction coefficients of the lane width, intersection, and number of lanes, respectively, and RF is the traffic flow.
Optionally, the region saturation determination subunit includes:
The second calculating subunit is configured to calculate, using the longitude and latitude values of the GPS positioning, a distance from the core point of the area to the road acquisition point road, where the distance is:
dcore,road＝REarth*arcos[cos(Ycore)*cos(Yroad)*cos(Xcore-Xroad)+sin(Ycore)*sin(Yroad)]
Wherein R Earth is the radius of the earth, Y core、Yroad is the latitude of the node core and the node head, and X core、Xroad is the longitude of the node core and the node head;
a third calculation subunit for calculating the saturation of the region by using the following formula
Wherein,The region saturation of the region m at the moment i; q is the number of roads in the area; rs q,i represents the road saturation of the road q at the moment i, q being the road code number in this area.
Optionally, the matrix construction module includes:
a fourth calculation subunit, configured to determine an augmentation characteristic of the road n at the i moment in the following manner:
etn,i＝Concat(ecn,i,tcn,i)
Where et n,i represents the augmented characteristic of road n at time i, ec n,i represents the external environmental characteristic of road n at time i, and tc n,i represents the time characteristic of road n at time i;
a fifth calculation subunit, configured to perform fusion according to the following formula:
Wherein f n,i is used to fuse saturation information with the augmentation characteristic, W represents a learnable parameter of the convolution kernel, Representing a convolution operation;
and the matrix determining subunit is used for taking the fusion result as a fusion characteristic matrix F n,i of the road.
Optionally, the feature extraction module includes:
the time matrix extraction unit is used for extracting the time features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix by adopting an expansion gate convolution algorithm;
The space matrix extraction unit is used for extracting the space features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix by using the obtained time features as input and adopting a graph convolution neural network algorithm;
and the space-time feature determining unit is used for taking the time features and the space features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix as the space-time features.
In order to solve the above technical problem, an embodiment of the present application further provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the steps of the method for predicting traffic congestion information when executing the computer program.
To solve the above technical problem, an embodiment of the present application further provides a computer readable storage medium storing a computer program, where the computer program when executed by a processor implements the steps of the method for predicting traffic congestion information described above.
The method, the device, the computer equipment and the storage medium for predicting the traffic jam information provided by the embodiment of the invention receive the traffic feedback data of each terminal equipment; carrying out data processing on traffic feedback data by adopting edge equipment to obtain road saturation and region saturation, constructing a fusion feature matrix of the road and the region as external features, and constructing a similar feature matrix based on the external features; respectively extracting space-time characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix by adopting a space-time characteristic extraction mode; and constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics. The prediction accuracy is improved by combining the prediction of both macroscopic and microscopic, and simultaneously, the prediction efficiency can be improved and the storage redundancy can be reduced by combining an edge computing technology.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 is a flow chart of one embodiment of a method of predicting traffic congestion information of the present application;
FIG. 3 is a diagram showing an exemplary configuration of a feature extraction process according to the present application;
Fig. 4 is a schematic structural view of an embodiment of a prediction apparatus of traffic congestion information according to the present application;
FIG. 5 is a schematic structural diagram of one embodiment of a computer device in accordance with the present application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, as shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to vehicle smart systems, smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the method for predicting traffic congestion information provided by the embodiment of the present application is executed by a server, and accordingly, the device for predicting traffic congestion information is set in the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. Any number of terminal devices, networks and servers may be provided according to implementation requirements, and the terminal devices 101, 102, 103 in the embodiment of the present application may specifically correspond to application systems in actual production.
Referring to fig. 2, fig. 2 shows a method for predicting traffic congestion information according to an embodiment of the present invention, and the method is applied to the server in fig. 1 for illustration, and is described in detail as follows:
S201: and receiving traffic feedback data of each terminal device.
S202: adopting edge equipment to process traffic feedback data to obtain road saturation rs n,i and regional saturationWherein rs n,i represents road saturation of road n at i time,/>The region saturation of the region m at the time i is indicated.
In a specific optional embodiment, the edge device is used to process the traffic feedback data to obtain the road saturation rs n,i and the regional saturationComprising the following steps:
Determining road saturation based on traffic flow and road traffic capacity;
dividing the regions by adopting a clustering mode based on density, and calculating the region saturation of each region
Rs n,i represents the road saturation of road n at time i. The vehicle speed acquisition interval is set to be a fixed value, the traffic flow is an average value of all vehicle speeds on the road within the acquisition time interval, the vehicle speed information is transmitted to the road sensor by the sensor of the vehicle, and the road sensor is used as cloud edge equipment for subsequent data processing.
Road Saturation (RS) is the ratio of the traffic flow (RF) to the Road traffic capacity (RC), and is an important index reflecting the analysis of the Road traffic condition, and the higher the Road saturation, the greater the traffic load.
In a specific alternative embodiment, the road traffic capacity includes an ideal traffic capacity RC 1 and a design traffic capacity RC D, and determining the road saturation based on the traffic flow and the road traffic capacity includes:
The road saturation RS is calculated using the following formula:
RCD＝λ·μ·γ·RCI
wherein λ, μ, γ are correction coefficients of the lane width, intersection, and number of lanes, respectively, and RF is traffic flow.
The road traffic capacity RC may be divided into an ideal traffic capacity RC I and a design traffic capacity RC D,RCI, which refer to the maximum traffic volume that a certain lane or section passes per unit time under ideal conditions, and RC D refers to the maximum traffic volume under expected conditions of roads, regulations, and the like.
In a specific optional implementation manner, performing region division by adopting a clustering mode based on density, and calculating the region saturation RC D of each region includes:
the distance from the core point of the area to the road acquisition point road is calculated by using the longitude and latitude values of GPS positioning:
dcore,road＝REarth*arcos[cos(Ycore)*cos(Yroad)*cos(Xcore-Xroad)+sin(Ycore)*sin(Yroad)]
Wherein: r Earth is the radius of the earth. Y core、Yroad is the latitude of the node core and the node head, and X core、Xroad is the longitude of the node core and the node head;
The area saturation is calculated using the following formula
Wherein,The region saturation of the region m at the moment i; q is the number of roads in the area; rs q,i represents the road saturation of the road q at the moment i, q being the road code number in this area.
Specifically, a traffic map g= (V, E, a) is defined. Wherein V, E respectively represent nodes and edges of the diagram, namely an intersection and a road; the adjacency matrix A is constructed according to connectivity among nodes, if connectivity assignment 1 exists between two nodes, otherwise, the adjacency matrix A is 0 and is used for describing objectively existing space correlation; the degree matrix D refers to the number of nodes connected to the node. When calculating the distance and judging whether the road belongs to a certain area, the geographic center position of the road is adopted for representing. The DBSCAN is a clustering algorithm based on a density space, and finally, the effects that the density of each cluster is higher than the density around the cluster and the density of noise is lower than the density of any cluster are achieved. The areas are divided based on the node distance and the congestion degree. Setting the area distance of each area to be less than or equal to epsilon, wherein each area contains MinPts sample points at least, and finally obtaining M areas.
S203: constructing a fusion characteristic matrix F n,i of a road and a region,As external features and based on the external features, constructing a similar feature matrix/>
In a specific alternative embodiment, in step S203, a road and region fusion feature matrix F n,i is constructed,As external features, there are:
the augmented characteristics of road n at time i are determined as follows:
etn,i＝Concat(ecn,i,tcn,i)
Where et n,i represents the augmented characteristic of road n at time i, ec n,i represents the external environmental characteristic of road n at time i, and tc n,i represents the time characteristic of road n at time i;
the fusion is performed using the following formula:
Wherein f n,i is used to fuse saturation information with the augmentation characteristic, W represents a learnable parameter of the convolution kernel, Representing a convolution operation;
And taking the fusion result as a fusion characteristic matrix F n,i of the road.
The road saturation is affected by external environmental characteristics, and the present embodiment adopts external environmental characteristics and time characteristics as the augmented information of the road saturation. Wherein the external environmental characteristics comprise 4 types of weather, temperature, humidity and wind speed; the time characteristics include season, day of work, day of week.
Further, F n,i represents a road saturation feature matrix of the road n at the i time. In the same way, the processing method comprises the steps of,The road saturation feature matrix of the region m at the time i is represented.
Here, extracting feature similarity matrixThe linear transformation is then input into TSGCN module to extract the space-time characteristic information, and the extracted space-time characteristic information is used as one input information of DIB2 module.
The external characteristic et N',T' can be obtained from the condition information (T 'time, specified road N') to be predicted. And under the condition of extracting the saturation of the traffic road similar to the external characteristic to be predicted, comparing et N,T with et n,i in the historical data by adopting a cosine similarity method.
The similarity Sim is ranked from high to low within the range considered acceptable by the interval 0.5, 1. If the number meeting the similarity requirement is greater than M, randomly selecting M to form a similarity matrix; if the number is smaller than M, selecting M from high to low according to the similarity. Corresponding rs n,i and et n,i form a feature similarity matrix together
S204: and respectively extracting the space-time characteristics of the road fusion characteristic matrix, the region fusion characteristic matrix and the similar characteristic matrix by adopting a space-time characteristic extraction mode.
In a specific optional embodiment, in step S204, the extracting the spatio-temporal features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by adopting the spatio-temporal feature extraction method includes:
extracting time features of a road fusion feature matrix, a region fusion feature matrix and a similar feature matrix by adopting an expansion gate convolution algorithm;
Taking the obtained time characteristics as input, and adopting a graph convolution neural network algorithm to extract the spatial characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix;
And taking the time features and the space features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix as space-time features.
Specifically, F n,i,The input is subjected to linearization coding to obtain coding characteristics respectively as followsAnd then carrying out time feature extraction and space feature extraction on the coding features.
The time feature extraction adopts an expansion gate convolution algorithm, and the specific formula is as follows:
Short-term temporal correlations of data are extracted using gated temporal convolution, or GLU. Wherein the method comprises the steps of The time convolution operator is represented, the convolution kernel size is H, dil is an expansion coefficient, split represents an equal division operator, and tan H () and sigmoid () are activation functions. Wherein/>Passing through a temporal feature extraction operation, its outputT 1 = T-dil (H-1), the output flows to the spatial feature extraction module.
The spatial feature extraction adopts a graph convolution neural network algorithm, and a result of the temporal feature extraction is used as input. Knowing the adjacency matrix A and the degree matrix D of adjacency matrix A of the traffic map G, the corresponding Laplace matrix of the map structure is calculated.
Wherein the above formula is a layer feature propagation formula, whereinIs a Laplace matrix, where/> I is the identity matrix,/>Is/>Is a degree matrix of (2).
S205: and constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics.
In this embodiment, in order to implement interaction between the region and the road map convolution, a dynamic interaction module is used to fuse the region features and the road features, and a module for completing dynamic interaction between the macro region and the road is referred to as a dynamic interaction module 1.
Judging the relation between the road node and the area, if the road node a belongs to the area b, copying the characteristics of the area b and connecting the characteristics of the area b with the characteristics of the road section a, wherein the transformation matrix is defined as follows:
due to the dynamic change characteristic of the traffic data, the road saturation changes with time according to the change condition of the regional division, and the road saturation value of the region also changes with time or is influenced by the parameters of the regional division. . Therefore, a dynamic transfer matrix is constructed, and the attention thought is combined, if the road belongs to the region, the region weight is enhanced, and the mean function output matrix is a row, namely, the average of each row is calculated. The form is as follows:
Wherein U 1、U2、U3、be is obtained through deep learning. And finally, the dynamic region characteristic information can be obtained and spliced with the road characteristic information.
Thus, the final dynamic feature transfer function can be expressed as:
Meanwhile, in order to enhance the influence of the information of the road saturation consistent with the external feature to be predicted on the overall prediction, the road saturation information F n,i with the same road saturation information as the external feature to be predicted The dynamic interaction of the whole and the part is constructed by combining, and the prediction accuracy is improved. The module that completes the overall and partial dynamic interactions is referred to as dynamic interaction module 2. The operation logic is similar to that of the dynamic interaction module 1.
The dynamic interaction module 2 is similar to but different from the Tran matrix judgment rule of the dynamic interaction module 1. If the external characteristics of the road feature matrix are the same as the external characteristics to be predicted, assigning 1, otherwise, assigning 0 to obtain a Tran S matrix; wherein the method comprises the steps ofAll are obtained through deep learning, and the dynamic characteristic transfer function is learned to obtain the final/>
This section will macroscopic and microscopic interaction resultsResults of interactions of whole and part/>And (5) processing. First, skip-Connection is adopted for integration, and the integration is input into a prediction block for predicting a result. The prediction block is formed by overlapping two layers of Relu which are subjected to linear transformation, and a final prediction result is obtained.
Skip-Connection is a way of residual Connection, the main idea of which is to express the output as a linear superposition of inputs and a nonlinear transformation of the inputs, to avoid gradient explosion or gradient extinction by deep learning.
Wherein S 1、S2 and W are parameter matrixes, and are obtained through deep learning.
And according to the predicted result, the road service level evaluation and the congestion condition prediction result are given by comparing with the execution standard of China.
Based on saturation, china divides service level into the following four grades:
First level service level: road saturation is between 0 and 0.6, road traffic conditions are smooth, and service level is high; secondary service level: road saturation is between 0.6 and 0.8, road traffic is slightly congested, but traffic delay is low, and service level is relatively high; three levels of service: the saturation of the road section is between 0.8 and 1.0, at the moment, the traffic load of the road section is close to the saturation state, the traffic condition starts to have short-time congestion, the traffic delay is higher, and the service level is poorer; four levels of service: the road section saturation is above 1.0, and at this time, the traffic running state is in a supersaturation state, and the road is congested for a long time, so that the service level is extremely poor.
In this embodiment, traffic feedback data of each terminal device is received; carrying out data processing on traffic feedback data by adopting edge equipment to obtain road saturation and region saturation, constructing a fusion feature matrix of the road and the region as external features, and constructing a similar feature matrix based on the external features; respectively extracting space-time characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix by adopting a space-time characteristic extraction mode; and constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics. The prediction accuracy is improved by combining the prediction of both macroscopic and microscopic, and simultaneously, the prediction efficiency can be improved and the storage redundancy can be reduced by combining an edge computing technology.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
Fig. 4 shows a schematic block diagram of a traffic congestion information prediction apparatus in one-to-one correspondence with the traffic congestion information prediction method of the above embodiment. As shown in fig. 4, the traffic congestion information prediction apparatus includes a data receiving module 31, a data processing module 32, a matrix constructing module 33, a feature extracting module 34, and a result prediction module 35. The functional modules are described in detail as follows:
a data receiving module 31, configured to receive traffic feedback data of each terminal device;
The data processing module 32 is configured to perform data processing on the traffic feedback data by using an edge device to obtain a road saturation rs n,i and a region saturation Wherein rs n,i represents road saturation of road n at i time,/>The region saturation of the region m at the moment i;
A matrix construction module 33 for constructing a fusion feature matrix F n,i of the road and the region, As external features and based on the external features, constructing a similar feature matrix/>
The feature extraction module 34 is configured to extract the space-time features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix respectively by adopting a space-time feature extraction manner;
The result prediction module 35 is configured to construct a dynamic interaction relationship between the area and the road, and determine a traffic information prediction result based on the dynamic interaction relationship and the space-time feature.
Optionally, the data processing module 32 includes:
The road saturation determining unit is used for determining road saturation based on traffic flow and road traffic capacity;
And the region saturation determination subunit is used for dividing the regions by adopting a density-based clustering mode and calculating the region saturation of each region.
Optionally, the road saturation determining unit includes:
a first calculating subunit, configured to calculate the road saturation RS according to the following formula:
RCD＝λ·μ·γ·RCI
/>
wherein λ, μ, γ are correction coefficients of the lane width, intersection, and number of lanes, respectively, and RF is traffic flow.
Optionally, the region saturation determination subunit comprises:
The second calculating subunit is configured to calculate, using the longitude and latitude values of the GPS positioning, a distance from the core point of the area to the road acquisition point road, where the distance is:
dcore,road＝REarth*arcos[cos(Ycore)*cos(Yroad)*cos(Xcore-Xroad)+sin(Ycore)*sin(Yroad)]
wherein R Earth is the radius of the earth, Y core、Yroad is the latitude of the node core and the node head, and X core、Xroad is the longitude of the node core and the node head;
a third calculation subunit for calculating the saturation of the region by using the following formula
Wherein,The region saturation of the region m at the moment i; q is the number of roads in the area; rs q,i represents the road saturation of the road q at the moment i, q being the road code number in this area.
Optionally, the matrix construction module 33 includes:
a fourth calculation subunit, configured to determine an augmentation characteristic of the road n at the i moment in the following manner:
etn,i＝Concat(ecn,i,tcn,i)
Where et n,i represents the augmented characteristic of road n at time i, ec n,i represents the external environmental characteristic of road n at time i, and tc n,i represents the time characteristic of road n at time i;
a fifth calculation subunit, configured to perform fusion according to the following formula:
Wherein f n,i is used to fuse saturation information with the augmentation characteristic, W represents a learnable parameter of the convolution kernel, Representing a convolution operation;
and the matrix determining subunit is used for taking the fusion result as a fusion characteristic matrix F n,i of the road.
Optionally, the feature extraction module 34 includes:
The time matrix extraction unit is used for extracting the time features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by adopting an expansion gate convolution algorithm;
the space matrix extraction unit is used for extracting the space features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by taking the obtained time features as input and adopting a graph convolution neural network algorithm;
and the space-time matrix determining unit is used for taking the time features and the space features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix as space-time features.
For specific limitations on the prediction means of the traffic congestion information, reference may be made to the above limitations on the prediction method of the traffic congestion information, and no further description is given here. Each module in the above-described traffic congestion information prediction apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 5, fig. 5 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 4 comprises a memory 41, a processor 42, a network interface 43 communicatively connected to each other via a system bus. It is noted that only a computer device 4 having a component connection memory 41, a processor 42, a network interface 43 is shown in the figures, but it is understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and/or information processing according to a preset or stored instruction, and its hardware includes, but is not limited to, a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), a Programmable gate array (Field-Programmable GATE ARRAY, FPGA), a digital Processor (DIGITAL SIGNAL Processor, DSP), an embedded device, and the like.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 41 includes at least one type of readable storage medium including flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or D interface display memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 41 may be an internal storage unit of the computer device 4, such as a hard disk or a memory of the computer device 4. In other embodiments, the memory 41 may also be an external storage device of the computer device 4, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD) or the like, which are provided on the computer device 4. Of course, the memory 41 may also comprise both an internal memory unit of the computer device 4 and an external memory device. In this embodiment, the memory 41 is typically used to store an operating system and various types of application software installed on the computer device 4, such as program code for prediction of traffic congestion information. Further, the memory 41 may be used to temporarily store various types of data that have been output or are to be output.
The processor 42 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 42 is typically used to control the overall operation of the computer device 4. In this embodiment, the processor 42 is configured to execute the program code stored in the memory 41 or process data, such as the program code for running the prediction of traffic congestion information.
The network interface 43 may comprise a wireless network interface or a wired network interface, which network interface 43 is typically used for establishing a communication connection between the computer device 4 and other electronic devices.
The present application also provides another embodiment, namely, a computer-readable storage medium storing an interface display program executable by at least one processor to cause the at least one processor to perform the steps of the traffic congestion information prediction method as described above.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (10)
1. The method for predicting the traffic congestion information is characterized by being applied to a traffic congestion information prediction system, wherein the system comprises terminal equipment, edge equipment and a central cloud layer, and the traffic congestion information prediction method comprises the following steps:
receiving traffic feedback data of each terminal device;
adopting the edge equipment to perform data processing on the traffic feedback data to obtain road saturation rs n,i and regional saturation Wherein rs n,i represents road saturation of road n at i time,/>The region saturation of the region m at the moment i;
Constructing a fusion characteristic matrix F n,i of a road and a region, As external features and based on the external features, constructing a similar feature matrix/>Wherein the similarity feature matrix/>The method comprises the steps of performing similarity calculation and determination generation on the obtained external features and the external features in the historical data by adopting a cosine similarity method;
Respectively extracting space-time characteristics of a road fusion characteristic matrix, a region fusion characteristic matrix and a similar characteristic matrix by adopting a space-time characteristic extraction mode;
constructing a dynamic interaction relation between the area and the road, and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics;
wherein, the constructing the dynamic interaction relation between the area and the road, and determining the traffic information prediction result based on the dynamic interaction relation and the space-time feature comprises:
Judging the relation between the road node and the area, if the road node a belongs to the area b, copying the characteristics of the area b and connecting the characteristics of the area b with the characteristics of the road section a, wherein the transformation matrix is defined as follows:
Based on the transformation matrix, determining regional characteristic information by adopting the following formula:
u 1、U2、U3、be is obtained through deep learning, and the mean function output matrix is the average of each column;
Splicing the regional characteristic information and the road characteristic information to obtain a final dynamic characteristic transfer function The final dynamic characteristic transfer function/>The interaction results used to characterize macroscopic and microscopic are expressed as:
if the road feature matrix is the same as the external feature to be predicted, assigning 1, otherwise, assigning 0 to obtain a Trans matrix; wherein the method comprises the steps of All are obtained through deep learning, and the dynamic characteristic transfer function is learned to obtain the interaction result/>, of the whole and partExpressed as:
residual Connection mode of Skip-Connection is adopted to transfer function to the final dynamic characteristic And the interaction results of the whole and the part/>Integrating, and inputting the integrated result into a prediction block to obtain a prediction result, wherein the prediction result is expressed as:
Wherein, S 1、S2 and W are both parameter matrixes, relu is a linear transformation prediction block, and the linear transformation prediction block is formed by superposing two layers of Relu subjected to linear transformation, so as to obtain a final prediction result.
2. The traffic congestion information prediction method according to claim 1, wherein the traffic feedback data includes traffic flow and road traffic capacity, and the edge device is adopted to perform data processing on the traffic feedback data to obtain road saturation rs n,i and regional saturationComprising the following steps:
Determining road saturation based on the traffic flow and road traffic capacity;
dividing the regions by adopting a clustering mode based on density, and calculating the region saturation of each region
3. The method of predicting traffic congestion information of claim 2, wherein the road traffic capacity comprises an ideal traffic capacity RC I and a design traffic capacity RC D, and wherein determining the road saturation based on the traffic flow and the road traffic capacity comprises:
The road saturation RS is calculated using the following formula:
RCD＝λ·μ·γ·RCI
wherein λ, μ, γ are correction coefficients of the lane width, intersection, and number of lanes, respectively, and RF is the traffic flow.
4. The traffic congestion information prediction method according to claim 2, wherein the density-based clustering method is adopted for region division, and the region saturation of each region is calculatedComprising the following steps:
the distance from the core point of the area to the road acquisition point road is calculated by using the longitude and latitude values of GPS positioning:
dcore,road＝REarth*arcos[cos(Ycore)*cos(Yroad)*cos(Xcore-Xroad)+sin(Ycore)*sin(Yroad)]
Wherein R Earth is the radius of the earth, Y core、Yroad is the latitude of the node core and the node head, and X core、Xroad is the longitude of the node core and the node head;
The area saturation is calculated using the following formula
Wherein,The region saturation Q representing the region m at the i time is the road saturation of the road Q at the i time represented by the number of roads rs q,i in the region, and Q is the road code number in the region.
5. The traffic congestion information prediction method according to claim 1, wherein the fusion feature matrix F n,i of the constructed road and region,As external features, there are:
the augmented characteristics of road n at time i are determined as follows:
etn,i＝Concat(ecn,i,tcn,i)
Where et n,i represents the augmented characteristic of road n at time i, ec n,i represents the external environmental characteristic of road n at time i, and tc n,i represents the time characteristic of road n at time i;
the fusion is performed using the following formula:
Wherein f n,i is used to fuse saturation information with the augmentation characteristic, W represents a learnable parameter of the convolution kernel, Representing a convolution operation;
And taking the fusion result as a fusion characteristic matrix F n,i of the road.
6. The traffic congestion information prediction method according to claim 1, wherein the method for extracting the spatio-temporal features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by using the spatio-temporal feature extraction method comprises:
extracting time features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix by adopting an expansion gate convolution algorithm;
Taking the obtained time characteristics as input, and extracting the spatial characteristics of the region fusion characteristic matrix, the road fusion characteristic matrix and the similar characteristic matrix by adopting a graph convolution neural network algorithm;
and taking the time features and the space features of the region fusion feature matrix, the road fusion feature matrix and the similar feature matrix as the space-time features.
7. A traffic congestion information prediction apparatus, characterized in that the traffic congestion information prediction apparatus includes:
The data receiving module is used for receiving traffic feedback data of each terminal device;
The data processing module is used for carrying out data processing on the traffic feedback data by adopting edge equipment to obtain road saturation and regional saturation;
The matrix construction module is used for constructing a fusion feature matrix of the road and the region as an external feature and constructing a similar feature matrix based on the external feature, wherein the similarity feature matrix The method comprises the steps of performing similarity calculation and determination generation on the obtained external features and the external features in the historical data by adopting a cosine similarity method;
the feature extraction module is used for respectively extracting the space-time features of the road fusion feature matrix, the region fusion feature matrix and the similar feature matrix by adopting a space-time feature extraction mode;
the result prediction module is used for constructing a dynamic interaction relation between the area and the road and determining a traffic information prediction result based on the dynamic interaction relation and the space-time characteristics;
Wherein, the result prediction module includes:
Judging the relation between the road node and the area, if the road node a belongs to the area b, copying the characteristics of the area b and connecting the characteristics of the area b with the characteristics of the road section a, wherein the transformation matrix is defined as follows:
Based on the transformation matrix, determining regional characteristic information by adopting the following formula:
u 1、U2、U3、be is obtained through deep learning, and the mean function output matrix is the average of each column;
Splicing the regional characteristic information and the road characteristic information to obtain a final dynamic characteristic transfer function The final dynamic characteristic transfer function/>The interaction results used to characterize macroscopic and microscopic are expressed as:
if the road feature matrix is the same as the external feature to be predicted, assigning 1, otherwise, assigning 0 to obtain a Trans matrix; wherein the method comprises the steps of All are obtained through deep learning, and the dynamic characteristic transfer function is learned to obtain the interaction result/>, of the whole and partExpressed as:
residual Connection mode of Skip-Connection is adopted to transfer function to the final dynamic characteristic And the interaction results of the whole and the part/>Integrating, and inputting the integrated result into a prediction block to obtain a prediction result, wherein the prediction result is expressed as:
Wherein, S 1、S2 and W are both parameter matrixes, relu is a linear transformation prediction block, and the linear transformation prediction block is formed by superposing two layers of Relu subjected to linear transformation, so as to obtain a final prediction result.
8. The traffic congestion information prediction apparatus according to claim 7, wherein the traffic feedback data includes traffic flow and road traffic capacity, and the data processing module includes:
The road saturation determining unit is used for determining road saturation based on the traffic flow and the road traffic capacity;
And the region saturation determination subunit is used for dividing the regions by adopting a density-based clustering mode and calculating the region saturation of each region.
9. Computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method for predicting traffic congestion information according to any one of claims 1 to 6 when executing the computer program.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the traffic congestion information prediction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410010051.6A CN117523848B (en) | 2024-01-04 | 2024-01-04 | Traffic jam information prediction method, device, computer equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410010051.6A CN117523848B (en) | 2024-01-04 | 2024-01-04 | Traffic jam information prediction method, device, computer equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117523848A CN117523848A (en) | 2024-02-06 |
| CN117523848B true CN117523848B (en) | 2024-04-19 |
Family
ID=89744238
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410010051.6A Active CN117523848B (en) | 2024-01-04 | 2024-01-04 | Traffic jam information prediction method, device, computer equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117523848B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399742A (en) * | 2018-01-30 | 2018-08-14 | 昆明理工大学 | A kind of traffic situation thermal map method for visualizing based on traffic saturation degree |
| CN110288165A (en) * | 2019-07-02 | 2019-09-27 | 南京信息工程大学 | The unmanned monitoring and tracking method of multiple target based on quick clustering and optimization distribution |
| CN111785024A (en) * | 2020-07-17 | 2020-10-16 | 陕西工业职业技术学院 | Urban vehicle working condition construction method based on regions and time domains |
| WO2021109318A1 (en) * | 2019-12-03 | 2021-06-10 | 东南大学 | Method for estimating and predicting short-term traffic circulation state of urban road network |
| CN113643532A (en) * | 2021-07-22 | 2021-11-12 | 深圳先进技术研究院 | Regional traffic prediction method and device |
| CN114360254A (en) * | 2022-03-17 | 2022-04-15 | 湖南工商大学 | Space-time-based traffic flow prediction method and related equipment |
| CN114519932A (en) * | 2022-01-10 | 2022-05-20 | 中国科学院深圳先进技术研究院 | Regional traffic condition integrated prediction method based on space-time relation extraction |
| WO2022247677A1 (en) * | 2021-05-28 | 2022-12-01 | 南京师范大学 | Urban-region road network vehicle-passage flow prediction method and system based on hybrid deep learning model |
| CN117275215A (en) * | 2023-05-04 | 2023-12-22 | 长江空间信息技术工程有限公司(武汉) | Urban road congestion space-time prediction method based on graph process neural network |
-
2024
- 2024-01-04 CN CN202410010051.6A patent/CN117523848B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399742A (en) * | 2018-01-30 | 2018-08-14 | 昆明理工大学 | A kind of traffic situation thermal map method for visualizing based on traffic saturation degree |
| CN110288165A (en) * | 2019-07-02 | 2019-09-27 | 南京信息工程大学 | The unmanned monitoring and tracking method of multiple target based on quick clustering and optimization distribution |
| WO2021109318A1 (en) * | 2019-12-03 | 2021-06-10 | 东南大学 | Method for estimating and predicting short-term traffic circulation state of urban road network |
| CN111785024A (en) * | 2020-07-17 | 2020-10-16 | 陕西工业职业技术学院 | Urban vehicle working condition construction method based on regions and time domains |
| WO2022247677A1 (en) * | 2021-05-28 | 2022-12-01 | 南京师范大学 | Urban-region road network vehicle-passage flow prediction method and system based on hybrid deep learning model |
| CN113643532A (en) * | 2021-07-22 | 2021-11-12 | 深圳先进技术研究院 | Regional traffic prediction method and device |
| CN114519932A (en) * | 2022-01-10 | 2022-05-20 | 中国科学院深圳先进技术研究院 | Regional traffic condition integrated prediction method based on space-time relation extraction |
| CN114360254A (en) * | 2022-03-17 | 2022-04-15 | 湖南工商大学 | Space-time-based traffic flow prediction method and related equipment |
| CN117275215A (en) * | 2023-05-04 | 2023-12-22 | 长江空间信息技术工程有限公司(武汉) | Urban road congestion space-time prediction method based on graph process neural network |
Non-Patent Citations (3)
| Title |
|---|
| Congestion Prediction Based on Dissipative Structure Theory:A Case Study of Chengdu, China;xiaoke sun 等;《Hindawi》;20211231;第1-13页 * |
| 基于动态交通信息的电动汽车充电需求预测模型及其对配网的影响分析;李磊 等;《电网与清洁能源》;20200331;第36卷(第3期);第107-118页 * |
| 考虑拥堵区域的多车型绿色车辆路径问题优化;赵志学 等;《计算机应用》;20200310;第40卷(第3期);第883-890页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117523848A (en) | 2024-02-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210377355A1 (en) | Message pushing method, storage medium, and server | |
| CN112382099B (en) | Traffic road condition prediction method and device, electronic equipment and storage medium | |
| Liu et al. | A spatio‐temporal ensemble method for large‐scale traffic state prediction | |
| CN111522838B (en) | Address similarity calculation method and device | |
| CN113570867B (en) | Urban traffic state prediction method, device, equipment and readable storage medium | |
| CN113282692A (en) | Big data sharing method and device for smart city | |
| CN113643532B (en) | Regional traffic prediction method and device | |
| CN113822460A (en) | Traffic flow prediction method and device, electronic equipment and storage medium | |
| CN112069635B (en) | Method and device for deploying battery changing cabinet, medium and electronic equipment | |
| CN113159403A (en) | Method and device for predicting pedestrian track at intersection | |
| CN116828515A (en) | Edge server load prediction method based on space-time diagram convolution under Internet of vehicles | |
| CN116346863A (en) | Vehicle-mounted network data processing method, device, equipment and medium based on federal learning | |
| Huang et al. | A time-dependent attention convolutional LSTM method for traffic flow prediction | |
| CN117079148B (en) | Urban functional area identification method, device, equipment and medium | |
| CN117523848B (en) | Traffic jam information prediction method, device, computer equipment and medium | |
| CN108770014B (en) | Calculation evaluation method, system and device of network server and readable storage medium | |
| CN114915940B (en) | Vehicle-road communication link matching method, system, equipment and medium | |
| CN111210513A (en) | Information processing method, device, equipment and storage medium | |
| CN115775366A (en) | Road target detection method, detection device, electronic equipment and storage medium | |
| CN115563522A (en) | Traffic data clustering method, device, equipment and medium | |
| CN112183824A (en) | Online and offline associated urban passenger flow prediction method | |
| CN112016503A (en) | Sidewalk detection method and device, computer equipment and storage medium | |
| CN116150699B (en) | Traffic flow prediction method, device, equipment and medium based on deep learning | |
| EP3857404A1 (en) | Dynamic generation and suggestion of tiles based on user context | |
| CN112329119B (en) | Virtual scene simulation processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |