CN116628435A - Road network traffic flow data restoration method, device, equipment and medium - Google Patents
Road network traffic flow data restoration method, device, equipment and medium Download PDFInfo
- Publication number
- CN116628435A CN116628435A CN202310896112.9A CN202310896112A CN116628435A CN 116628435 A CN116628435 A CN 116628435A CN 202310896112 A CN202310896112 A CN 202310896112A CN 116628435 A CN116628435 A CN 116628435A
- Authority
- CN
- China
- Prior art keywords
- missing
- data
- flow data
- matrix
- road network
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 239000011159 matrix material Substances 0.000 claims abstract description 142
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000005516 engineering process Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 230000006870 function Effects 0.000 claims description 26
- 238000003860 storage Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 11
- 238000013210 evaluation model Methods 0.000 claims description 6
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 3
- 230000037430 deletion Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011835 investigation Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000002123 temporal effect Effects 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
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to the field of data processing systems or methods for supervision or prediction purposes, and discloses a road network traffic flow data restoration method, a device, equipment and a medium, wherein the method comprises the following steps: obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network traffic data into first traffic data and second traffic data; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining values of missing elements; filling missing elements in the missing matrix to obtain missing national provincial channel flow data. The spatial neighbor correlation is described by using local measurement projection, and meanwhile, sparsity constraint is added to the measurement projection matrix to fit local characteristics of the spatial proximity, so that the fitting accuracy is improved.
Description
Technical Field
The application relates to the field of data processing systems or methods for supervision or prediction, in particular to a road network traffic flow data restoration method, device, equipment and medium.
Background
There is a correlation between traffic flow of an expressway and flow of a common national province (hereinafter referred to as "adjacent national province") adjacent to the expressway. The heterogeneous comprehensive road network (simply referred to as a whole road network) formed by the expressway network and the adjacent national province road is researched aiming at traffic flow characteristics of the expressway network, and has great theoretical significance for improving traffic control capacity and operation service level of the expressway.
At present, a large number of traffic acquisition devices, such as highway ETC portal devices and acquisition devices in national provincial road traffic investigation stations, are uniformly distributed along the lines of the highway and adjacent national provincial roads. The layout and the use of the devices effectively support the large-scale acquisition and analysis of the traffic flow data of the whole road network.
However, due to the limitation of the layout place of the collecting equipment, the ageing of the collecting equipment, the influence of rain and fog and other factors, the stability of the data collected by the traffic collecting equipment is insufficient, so that the traffic data is lost and abnormal in time or space. One typical case is: the flow data of the ETC portal of the expressway is relatively stable, and the flow data of the traffic investigation station adjacent to the national provincial road has a large quantity of defects. These problems adversely affect the prediction of traffic flow through the road network, traffic state analysis, and road network traffic capacity assessment.
Disclosure of Invention
In order to solve the above problems, the present application provides a road network traffic flow data restoration method, device and medium, wherein the method comprises:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element; filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
In one example, the dividing the road network traffic data into the first traffic data and the second traffic data specifically includes: determining the data missing moment of the national provincial road flow data in the road network flow data; taking the road network flow data before the data missing moment as first flow data; and taking the road network flow data after the data missing moment as second flow data.
In one example, the generating the deletion matrix according to the first traffic data and the second traffic data specifically includes: determining national provincial road flow data corresponding to the expressway flow data at each moment in the first flow data and the second flow data; and splicing according to the national provincial road flow data respectively corresponding to the expressway flow data at each moment to generate a missing matrix, wherein if the national provincial road flow data is missing, the corresponding position of the missing matrix is a missing element.
In one example, the processing the missing matrix by using a sparse missing matrix filling technology and a sparse correlation condition specifically includes: filling the missing matrix by a sparse missing matrix filling technology to obtain a filling matrix; and replacing the rank of the filling matrix by using the nuclear norm of the filling matrix to obtain a convex optimization model corresponding to the filling matrix.
In one example, after the obtaining the convex optimization model corresponding to the filling matrix, the method further includes: determining a first linear correlation between the expressway traffic data vector and the adjacent national provincial traffic data vector at the same moment; determining a second linear correlation between the expressway traffic data matrix and the adjacent national provincial traffic data matrix according to the first linear correlation; and establishing an objective function of a road network flow sparse correlation evaluation model based on the second linear correlation.
In one example, after establishing the objective function of the road network traffic sparse correlation evaluation model based on the second linear correlation, the method further includes: based on the objective function and the convex optimization model, establishing an overall objective function of a missing element filling model; values of the missing elements are determined based on the overall objective function.
In one example, the method further comprises: acquiring an adjacency relation between a highway and a national province road, and initializing the overall objective function based on the adjacency relation; fixing a measurement projection matrix in the overall objective function, and updating a national provincial road flow data matrix by using a singular value threshold algorithm; and fixing the national provincial road flow data matrix, and updating the measurement projection matrix by using a minimum gradient descent method.
The application also provides a road network traffic flow data restoration device, which comprises:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module acquires road network flow data, and the road network flow data comprises expressway flow data and national provincial road flow data; the data dividing module divides the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; the matrix generation module is used for generating a missing matrix according to the first flow data and the second flow data and determining missing elements in the missing matrix; the missing element module is used for processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions to determine the value of the missing element; and the filling module is used for filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
The application also provides road network traffic flow data restoration equipment, which comprises: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform: obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element; filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
The present application also provides a non-volatile computer storage medium storing computer-executable instructions configured to:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element; filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
The method provided by the application has the following beneficial effects: the spatial neighbor correlation is described by using local measurement projection, and meanwhile, sparsity constraint is added to the measurement projection matrix to fit local characteristics of the spatial proximity, so that the fitting accuracy is improved. Meanwhile, the low rank property of the matrix is used for capturing the flow reachable correlation of the traffic flow of the whole road network, so that the repair accuracy of the missing data is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of a road network traffic flow data restoration method according to an embodiment of the application;
FIG. 2 is a schematic diagram of a method for constructing a deletion matrix according to an embodiment of the present application;
FIG. 3 is a schematic block diagram of a road network traffic flow data restoration device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a road network traffic flow data repairing device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Currently, for data loss repair, there are mainly several types of methods:
(1) The statistical analysis method comprises the following steps: and establishing a distribution model of the original data based on the observed value of the original data, thereby repairing the missing data. However, the distribution of the original data is difficult to obtain and complicated, and may not satisfy the set assumption condition. (2) sequence interpolation method: based on local temporal and spatial correlations, repair is performed using near historical data. But is less effective against high miss rates and is unable to fluctuate traffic flow caused by weather or emergencies. (3) tensor-based method: traffic flows have a certain spatiotemporal correlation, so that a matrix of traffic flow data also has a low rank structure. The method utilizes macroscopic correlation of the whole road network, but discards road network structure information.
The following describes in detail the technical solutions provided by the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flow chart of a road network traffic flow data restoration method according to one or more embodiments of the present disclosure. The process may be performed by computing devices in the respective areas, with some input parameters or intermediate results in the process allowing manual intervention adjustments to help improve accuracy.
The implementation of the analysis method according to the embodiment of the present application may be a terminal device or a server, which is not particularly limited in the present application. For ease of understanding and description, the following embodiments are described in detail with reference to a server.
It should be noted that the server may be a single device, or may be a system formed by a plurality of devices, that is, a distributed server, which is not particularly limited in the present application.
As shown in fig. 1, an embodiment of the present application provides a road network traffic flow data repairing method, including:
s101: and obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data.
Assume that the number of highway flow collection devices isThe number of national provincial road flow collection devices adjacent to the expressway is +.>. At->Time->The highway flow collection device generates a flow data vector setThe national provincial road flow collection device generates a flow data vector set +.>。
S102: dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing, but the national provincial road traffic data is missing.
In one embodiment, when dividing road network traffic data, determining a data missing time of national provincial road traffic data in the road network traffic data, and then taking the road network traffic data before the data missing time as first traffic data; and taking the road network flow data after the data missing moment as second flow data. Specifically, it is assumed thatIn the moment, the highway traffic data and the national provincial traffic data are all complete, and the +.>In the moment, the expressway flow data is complete, and the national provincial road flow data has data loss due to the failure of acquisition equipment and the like. I.e. < ->And->The data is complete, ++>The data in (a) is that there is a miss, i.e., a partial value of 0.
S103: generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix.
In one embodiment, when the missing matrix is generated, firstly, in the first traffic data and the second traffic data, determining the national provincial road traffic data corresponding to the expressway traffic data at each moment, and then splicing the national provincial road traffic data corresponding to the expressway traffic data at each moment to generate the missing matrix, wherein if the national provincial road traffic data is missing, the corresponding position of the missing matrix is a missing element. In particular, as shown in FIG. 2, willHigh-speed traffic data of time of day->Traffic data of national province>Splicing to obtain data->. According to the same way ∈ ->Moment to about->The high-speed flow data and the national provincial flow data at the moment are spliced to obtain +.>. Combination->Obtaining the deletion matrix->。
S104: and processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element.
In one embodiment, when a sparse missing matrix filling technology is used for processing the missing matrix, the missing matrix is filled by the sparse missing matrix filling technology to obtain a filled matrix; and then using the nuclear norm of the filling matrix to replace the rank of the filling matrix so as to obtain a convex optimization model corresponding to the filling matrix. Specifically, according to the flow reachable correlation assumption, the expressway flow and the national provincial flow are arranged into a matrix according to the method as shown in fig. 2, and the matrix has a low rank property because the matrix has a linear independent row number far smaller than the actual row number of the matrix due to the correlation relationship between the rows of the upper and lower parts. Therefore, the matrix filling technology can be utilized to reconstruct the missing national provincial road traffic flow data. Let it be assumed that the matrixThe matrix obtained after filling is +.>. Then there are:
wherein,,is a matrix->Middle->Line, th->Column element->Is a matrix->Middle->Line, th->Column element->Is a matrix->A set of element coordinates is known. The above optimization problem is a non-deterministic problem of polynomial complexity, using the matrix +.>Nuclear norms instead of ++>It is possible to obtain:
wherein,,for matrix->The above problem is a convex optimization problem, and a globally optimal solution can be obtained.
Further, when the missing matrix is processed according to the sparse correlation condition, a first linear correlation relationship between the expressway traffic data vector and the adjacent national provincial traffic data vector at the same moment needs to be determined; determining a second linear correlation between the expressway traffic data matrix and the adjacent national provincial traffic data matrix according to the first linear correlation; and establishing an objective function of the road network flow sparse correlation evaluation model based on the second linear correlation. Specifically, the traffic of the neighboring provincial road has a strong correlation with only the traffic of the expressway section spatially adjacent thereto, but has a weak correlation with the traffic of the expressway section spatially distant therefrom, and therefore, the correlation between the traffic of the neighboring provincial road and the traffic of the expressway network is sparse from the whole road network level. The method integrates the relevance and the sparsity, and establishes a whole road network flow sparse relevance evaluation model based on measurement learning.
For the purpose ofHighway traffic data vector at time +.>And adjacent country provincial way traffic data vector +.>. The patent weakens the correlation between the two into approximate linear correlation, namely
Wherein,,to measure the projection matrix.
Similarly, based on the first linear correlation, forAnd->There is the following approximate linear relationship:
then the following objective function can be obtained:
wherein,,the L0 norm of the matrix, i.e. the number of non-0 elements in the matrix, is represented. The locality or sparsity of the correlation between the high-speed traffic and the national provincial traffic is embodied.
Further, after the missing matrix is processed through a sparse missing matrix filling technology and sparse correlation conditions, an overall objective function of a missing element filling model is established based on the objective function and the convex optimization model, and missing elements are determined based on the overall objective function. Specifically, the overall objective function is as follows:
in the formulaAnd representing the rank after the missing matrix is filled, and representing the flow reachable correlation of the whole road network. In the formulaAnd (3) representing the spatial neighbor correlation of the high-speed traffic data and the national provincial road traffic data. Wherein, parameter->For balancing the importance of traffic reachability correlation and spatial neighbor correlation. />The L1 norm representing the matrix is an approximation to the L0 norm.
In one embodiment, when optimizing the overall objective function, the objective function is optimized in a step-by-step sequential optimization manner, first, when initializing, a high-speed algorithm is usedInitializing adjacencies of roads and national provincesSpecifically, if the highway ETC portal +.>Road section and national provincial road traffic investigation station>The road sections are connected, i.e. with the same toll station, then +.>Otherwise, let(s)>. Then fix metric projection matrix +.>Updating +.Using singular value thresholding algorithm>. Then, G is fixed and the metric projection matrix W is updated using the minimum gradient descent method.
S105: filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
And recovering unknown elements in the 'missing matrix' by using a sparse missing matrix filling technology and sparse correlation conditions. And the recovery result is the missing national provincial channel flow data.
The road network flow data can be stored in a storage device of the computer equipment in advance, and when the traffic flow data needs to be repaired, the computer equipment can select the road network flow data from the storage device. Of course, the computer device may also obtain the road network traffic data from other external devices. For example, the road network traffic data is stored in the cloud, and when the traffic data needs to be repaired, the computer device can obtain the road network traffic data from the cloud, and the obtaining mode of the road network traffic data is not limited in this embodiment.
As shown in fig. 3, the embodiment of the present application further provides a road network traffic flow data repairing device, including:
the data acquisition module 301 acquires road network traffic data, wherein the road network traffic data comprises expressway traffic data and national provincial road traffic data;
the data dividing module 302 divides the road network traffic data into first traffic data and second traffic data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing;
a matrix generation module 303, configured to generate a missing matrix according to the first traffic data and the second traffic data, and determine missing elements in the missing matrix;
the missing element module 304 is used for processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions to determine the value of the missing element;
and a filling module 305, for filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
As shown in fig. 4, the embodiment of the present application further provides a road network traffic flow data repairing device, including:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element; filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
The embodiment of the application also provides a nonvolatile computer storage medium, which stores computer executable instructions, wherein the computer executable instructions are configured to:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data; dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing; generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix; processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element; filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus and medium embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the section of the method embodiments being relevant.
The devices and media provided in the embodiments of the present application are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not repeated here.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. The road network traffic flow data repairing method is characterized by comprising the following steps of:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data;
dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing;
generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix;
processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element;
filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
2. The method according to claim 1, wherein the dividing the road network traffic data into first traffic data and second traffic data specifically comprises:
determining the data missing moment of the national provincial road flow data in the road network flow data;
taking the road network flow data before the data missing moment as first flow data;
and taking the road network flow data after the data missing moment as second flow data.
3. The method according to claim 1, wherein generating the missing matrix according to the first traffic data and the second traffic data specifically comprises:
determining national provincial road flow data corresponding to the expressway flow data at each moment in the first flow data and the second flow data;
and splicing according to the national provincial road flow data respectively corresponding to the expressway flow data at each moment to generate a missing matrix, wherein if the national provincial road flow data is missing, the corresponding position of the missing matrix is a missing element.
4. The method according to claim 1, wherein the processing of the missing matrix by a sparse missing matrix filling technique and sparse correlation conditions specifically comprises:
filling the missing matrix by a sparse missing matrix filling technology to obtain a filling matrix;
and replacing the rank of the filling matrix by using the nuclear norm of the filling matrix to obtain a convex optimization model corresponding to the filling matrix.
5. The method of claim 4, wherein after the obtaining the convex optimization model corresponding to the filling matrix, the method further comprises:
determining a first linear correlation between the expressway traffic data vector and the adjacent national provincial traffic data vector at the same moment;
determining a second linear correlation between the expressway traffic data matrix and the adjacent national provincial traffic data matrix according to the first linear correlation;
and establishing an objective function of a road network flow sparse correlation evaluation model based on the second linear correlation.
6. The method of claim 5, wherein after establishing the objective function of the road network traffic sparse correlation evaluation model based on the second linear correlation, the method further comprises:
based on the objective function and the convex optimization model, establishing an overall objective function of a missing element filling model;
values of the missing elements are determined based on the overall objective function.
7. The method of claim 6, wherein the method further comprises:
acquiring an adjacency relation between a highway and a national province road, and initializing the overall objective function based on the adjacency relation;
fixing a measurement projection matrix in the overall objective function, and updating a national provincial road flow data matrix by using a singular value threshold algorithm;
and fixing the national provincial road flow data matrix, and updating the measurement projection matrix by using a minimum gradient descent method.
8. A road network traffic flow data restoration device, comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module acquires road network flow data, and the road network flow data comprises expressway flow data and national provincial road flow data;
the data dividing module divides the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing;
the matrix generation module is used for generating a missing matrix according to the first flow data and the second flow data and determining missing elements in the missing matrix;
the missing element module is used for processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions to determine the value of the missing element;
and the filling module is used for filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
9. A road network traffic flow data restoration device, comprising:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein,,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data;
dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing;
generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix;
processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element;
filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
10. A non-transitory computer storage medium storing computer-executable instructions, the computer-executable instructions configured to:
obtaining road network flow data, wherein the road network flow data comprises expressway flow data and national provincial road flow data;
dividing the road network flow data into first flow data and second flow data; the first traffic data is the expressway traffic data and the road network traffic data without loss of the national provincial road traffic data; the second traffic data is road network traffic data in which the expressway traffic data is not missing but the national provincial road traffic data is missing;
generating a missing matrix according to the first flow data and the second flow data, and determining missing elements in the missing matrix;
processing the missing matrix through a sparse missing matrix filling technology and sparse correlation conditions, and determining the value of the missing element;
filling the missing elements in the missing matrix to obtain missing national provincial channel flow data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896112.9A CN116628435B (en) | 2023-07-21 | 2023-07-21 | Road network traffic flow data restoration method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310896112.9A CN116628435B (en) | 2023-07-21 | 2023-07-21 | Road network traffic flow data restoration method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116628435A true CN116628435A (en) | 2023-08-22 |
| CN116628435B CN116628435B (en) | 2023-09-29 |
Family
ID=87602884
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310896112.9A Active CN116628435B (en) | 2023-07-21 | 2023-07-21 | Road network traffic flow data restoration method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116628435B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516417A (en) * | 2017-08-21 | 2017-12-26 | 中国科学院软件研究所 | A kind of real-time highway flow estimation method for excavating spatial and temporal association |
| CN109166309A (en) * | 2018-08-06 | 2019-01-08 | 重庆邮电大学 | A kind of missing data on flows restoration methods towards complicated urban traffic network |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| WO2021169116A1 (en) * | 2020-02-29 | 2021-09-02 | 平安科技（深圳）有限公司 | Intelligent missing data filling method, apparatus and device, and storage medium |
| CN115376318A (en) * | 2022-08-22 | 2022-11-22 | 重庆邮电大学 | Traffic data compensation method based on multi-attribute fusion neural network |
| CN115510174A (en) * | 2022-09-29 | 2022-12-23 | 重庆邮电大学 | Road network pixelation-based Wasserstein generation countermeasure flow data interpolation method |
| CN115599779A (en) * | 2022-11-28 | 2023-01-13 | 中南大学（Cn） | Urban road traffic missing data interpolation method and related equipment |
| CN115658666A (en) * | 2022-10-12 | 2023-01-31 | 苏州大学 | Multi-source data fusion sparse traffic flow completion method and system |
| CN115935147A (en) * | 2022-11-25 | 2023-04-07 | 东南大学 | Traffic data recovery and abnormal value detection method represented by low-rank and sparse tensor |
| KR20230048259A (en) * | 2022-09-28 | 2023-04-11 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and apparatus for complementing lane traffic flow data, and method and apparatus for training model |
-
2023
- 2023-07-21 CN CN202310896112.9A patent/CN116628435B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107516417A (en) * | 2017-08-21 | 2017-12-26 | 中国科学院软件研究所 | A kind of real-time highway flow estimation method for excavating spatial and temporal association |
| CN109166309A (en) * | 2018-08-06 | 2019-01-08 | 重庆邮电大学 | A kind of missing data on flows restoration methods towards complicated urban traffic network |
| WO2020133639A1 (en) * | 2018-12-29 | 2020-07-02 | 东北大学 | Intelligent analysis system for magnetic flux leakage detection data in pipeline |
| WO2021169116A1 (en) * | 2020-02-29 | 2021-09-02 | 平安科技（深圳）有限公司 | Intelligent missing data filling method, apparatus and device, and storage medium |
| CN115376318A (en) * | 2022-08-22 | 2022-11-22 | 重庆邮电大学 | Traffic data compensation method based on multi-attribute fusion neural network |
| KR20230048259A (en) * | 2022-09-28 | 2023-04-11 | 베이징 바이두 넷컴 사이언스 테크놀로지 컴퍼니 리미티드 | Method and apparatus for complementing lane traffic flow data, and method and apparatus for training model |
| CN115510174A (en) * | 2022-09-29 | 2022-12-23 | 重庆邮电大学 | Road network pixelation-based Wasserstein generation countermeasure flow data interpolation method |
| CN115658666A (en) * | 2022-10-12 | 2023-01-31 | 苏州大学 | Multi-source data fusion sparse traffic flow completion method and system |
| CN115935147A (en) * | 2022-11-25 | 2023-04-07 | 东南大学 | Traffic data recovery and abnormal value detection method represented by low-rank and sparse tensor |
| CN115599779A (en) * | 2022-11-28 | 2023-01-13 | 中南大学（Cn） | Urban road traffic missing data interpolation method and related equipment |
Non-Patent Citations (2)
| Title |
|---|
| 柏跃龙;彭理群;祁钰茜;赵建东;: "检测数据缺失条件下的交通流估计方法研究", 交通信息与安全, no. 02 * |
| 王维凤;: "支撑上海城乡发展一体化的干线公路发展策略研究", 交通与运输(学术版), no. 02 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116628435B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107958031B (en) | Resident travel OD distribution extraction method based on fusion data | |
| CN111199346B (en) | Utility tunnel supervision method, device, computer equipment and storage medium | |
| CN109474023B (en) | Intelligent power distribution network section real-time updating method and system, storage medium and terminal | |
| CN110390343B (en) | Correction method and system for space meteorological data | |
| CN111260154B (en) | Short-term solar radiation prediction method and device based on CNN-LSTM | |
| CN112614206A (en) | Road center line extraction method and device | |
| CN114152839A (en) | Power distribution network fault positioning method and system under distributed power grid-connected environment | |
| CN116628435B (en) | Road network traffic flow data restoration method, device, equipment and medium | |
| CN116703004A (en) | Water system river basin intelligent patrol method and device based on pre-training model | |
| CN112445702A (en) | Automatic testing method and system based on ant colony algorithm | |
| CN112540159A (en) | Nuclear power plant atmospheric diffusion prediction correction method, system, medium and electronic equipment | |
| CN114219917B (en) | Vulnerability restoration method for laser radar point cloud data | |
| CN113326343B (en) | Road network data storage method and system based on multi-level grids and file indexes | |
| CN110647935B (en) | Method and device for predicting tree growth trend in power transmission line area | |
| CN110968929A (en) | Wind power plant wind speed prediction method and device and electronic equipment | |
| CN113496305A (en) | Data processing method and device | |
| CN116722542A (en) | Photovoltaic output abnormality detection method and device, computer equipment and storage medium | |
| KR20170069396A (en) | Very short range microscale weather forecast model for real-time forecasting | |
| CN116304699A (en) | Critical sample set generation method and system based on new energy multi-station short circuit ratio | |
| CN115689067A (en) | Solar irradiance prediction method, device and storage medium | |
| CN113592148A (en) | Optimization method and system for improving distribution route of vehicle and unmanned aerial vehicle | |
| CN104899209A (en) | Optimization method and device for open type data processing service | |
| CN110659170A (en) | Vehicle-mounted T-BOX test system | |
| CN116629348B (en) | Intelligent workshop data acquisition and analysis method and device and computer equipment | |
| CN113708382B (en) | Camera positioning and selecting method and device based on fault severity minimization |
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 |