CN114626169B - Traffic network optimization method, device, equipment, readable storage medium and product - Google Patents
Traffic network optimization method, device, equipment, readable storage medium and product Download PDFInfo
- Publication number
- CN114626169B CN114626169B CN202210210044.1A CN202210210044A CN114626169B CN 114626169 B CN114626169 B CN 114626169B CN 202210210044 A CN202210210044 A CN 202210210044A CN 114626169 B CN114626169 B CN 114626169B
- Authority
- CN
- China
- Prior art keywords
- road
- road network
- topological graph
- continuous data
- node
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 82
- 238000000034 method Methods 0.000 title claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 35
- 239000011159 matrix material Substances 0.000 claims description 83
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 16
- 239000013598 vector Substances 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 abstract description 8
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/18—Network design, e.g. design based on topological or interconnect aspects of utility systems, piping, heating ventilation air conditioning [HVAC] or cabling
-
- 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
-
- 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)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Chemical & Material Sciences (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The disclosure provides a traffic network optimization method, a traffic network optimization device, traffic network optimization equipment, a traffic network optimization program and a traffic network optimization program. The specific implementation scheme is as follows: determining a road network topological graph corresponding to a target traffic road network in a target area and a differential operator; determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node; dividing a road network topological graph into a plurality of partial topological graphs according to each road node and the corresponding associated node; calculating target continuous data corresponding to the local topological graph according to the space information, time sequence information and differential operators corresponding to the road nodes and the associated nodes in the local topological graph; and carrying out optimization operation on the target traffic network according to the target continuous data. Discrete road network data can be converted into continuous road network data, and further data processing such as feature extraction and the like can be performed based on the continuous road network data, so that the optimization operation of the traffic road network is realized.
Description
Technical Field
The present disclosure relates to intelligent traffic in data processing, and in particular, to a traffic road network optimization method, apparatus, device, readable storage medium, and product.
Background
Map software implementation navigation functions are mainly based on satellite positioning information of global satellite navigation systems (Global Navigation SATELLITE SYSTEM, abbreviated GNSS system), however such a solution faces two challenges: firstly, high-rise buildings and viaducts in urban environments influence the mobile equipment to receive satellite signals, so that satellite positioning points are inconsistent with reality; secondly, along with urban and rural construction, the change of road networks is more frequent, the complex areas of the road networks are increased, and the requirements on positioning accuracy are also increased.
In order to realize the description of the traffic road network, the current processing method generally abstracts all roads in the area into one or a plurality of continuous vectors connected with each other according to longitude and latitude and road shapes; then, at the position where the roads meet in reality, connecting the corresponding vectors to form a graph with topological relation; and finally, adding other auxiliary descriptions such as traffic lights, forbidden lines and the like according to the longitude and latitude positions to obtain a data description.
However, when the processing method is adopted to describe the traffic network, because the roads and other traffic facilities in the data road network are discrete data, the data scale is huge, and enough characteristics are difficult to extract in large-scale machine learning, so that the accuracy of the electronic map and the efficiency of data processing are difficult to improve.
Disclosure of Invention
The present disclosure provides a traffic network optimization method, apparatus, device, readable storage medium and product for converting discretized traffic network data into a continuous data amount.
According to a first aspect of the present disclosure, there is provided a traffic road network optimization method, including:
Determining a road network topological graph corresponding to a target traffic road network in a target area, and calculating a differential operator corresponding to the road network topological graph;
Determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node, wherein the road node is a node corresponding to a road in the road network topological graph;
Dividing the road network topology map into a plurality of local topology maps according to each road node and the associated node with a preset connection relation with the road node;
aiming at each local topological graph, calculating target continuous data corresponding to the local topological graph according to space information and time sequence information corresponding to road nodes and associated nodes in the local topological graph and the differential operator;
And carrying out optimization operation on the target traffic network according to the target continuous data corresponding to the plurality of local topological graphs.
According to a second aspect of the present disclosure, there is provided a traffic road network optimization device, comprising:
the determining module is used for determining a road network topological graph corresponding to the target traffic road network in the target area and calculating a differential operator corresponding to the road network topological graph;
The processing module is used for determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node, wherein the road nodes are nodes corresponding to roads in the road network topological graph;
The dividing module is used for dividing the road network topological graph into a plurality of partial topological graphs according to each road node and the associated node which has a preset connection relation with the road node;
The calculation module is used for calculating target continuous data corresponding to each local topological graph according to the space information and the time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;
And the optimization module is used for performing optimization operation on the target traffic network according to the target continuous data corresponding to the plurality of partial topological graphs.
According to a third aspect of the present disclosure, there is provided an electronic 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 the method of the first aspect.
According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of the first aspect.
According to a fifth aspect of the present disclosure, there is provided a computer program product comprising: a computer program stored in a readable storage medium, from which it can be read by at least one processor of an electronic device, the at least one processor executing the computer program causing the electronic device to perform the method of the first aspect.
According to the technology disclosed by the invention, discrete road network data can be converted into continuous road network data, and further, data processing such as feature extraction and the like can be performed based on the continuous road network data, so that the optimization operation of the traffic road network is realized.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
The drawings are for a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:
Fig. 1 is a flow chart of a traffic road network optimization method according to a first embodiment of the disclosure;
FIG. 2 is a schematic view of a road and junction provided in an embodiment of the disclosure;
fig. 3 is a schematic structural diagram of a road network topology diagram according to an embodiment of the present disclosure;
fig. 4 is a flow chart of a traffic network optimization method according to a second embodiment of the present disclosure;
fig. 5 is a flow chart of a traffic road network optimization method according to a third embodiment of the disclosure;
Fig. 6 is a flow chart of a traffic road network optimization method according to a fourth embodiment of the disclosure;
FIG. 7 is a schematic diagram of generating continuous data of interest according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a traffic road network optimization device according to a fifth embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of an electronic device according to a sixth embodiment of the disclosure.
Detailed Description
Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
With the development of economy and the progress of society, the current private car conservation amount in China and the driving trip will of residents are in a trend of rising year by year, and correspondingly, the greatly increased trip requirement also provides richer and higher standard requirements for map navigation functions. In practical applications, the map software realizes the navigation function mainly based on satellite positioning information of the GNSS system, however, such a scheme faces two challenges: firstly, high-rise buildings and viaducts in urban environments influence the mobile equipment to receive satellite signals, so that satellite positioning points are inconsistent with reality; secondly, along with urban and rural construction, the change of road networks is more frequent, the complex areas of the road networks are increased, and the requirements on positioning accuracy are also increased.
In the prior art, when describing a traffic road network, all roads in an area are generally abstracted into one or a plurality of continuous vectors connected with each other according to longitude and latitude and road shapes; then, at the position where the roads meet in reality, connecting the corresponding vectors to form a graph with topological relation; and finally, adding other auxiliary descriptions such as traffic lights, forbidden lines and the like according to the longitude and latitude positions to obtain the datamation description of the traffic network. However, when the method is used for describing the traffic network, the data scale is huge because the roads and other traffic facilities in the data road network are all discrete data. Therefore, enough characteristics are difficult to extract in large-scale machine learning, and accordingly, the difficulty of adapting to personalized navigation strategies according to local conditions is increased.
In solving the above technical problems, the inventors have found through research that, in order to implement an extraction operation of road network data features in large-scale machine learning, discretized data can be converted into continuous data. Specifically, a road network topology map corresponding to a target traffic road network in a target area can be determined, and a differential operator corresponding to the road network topology map is calculated. And respectively calculating space information and time sequence information corresponding to each road node, and dividing the road network topological graph to obtain a plurality of local topological graphs. Thus, for each partial topological graph, the calculation of the target continuous data can be carried out according to the space information, the time sequence information and the differential operator.
The disclosure provides a traffic road network optimization method, a device, equipment, a readable storage medium and a product, which are applied to intelligent traffic in data processing, and can convert discretized data into continuous data so as to perform operations such as feature extraction, subsequent road network optimization and the like based on the continuous data.
Fig. 1 is a flow chart of a traffic road network optimization method according to a first embodiment of the disclosure, as shown in fig. 1, the method includes:
step 101, determining a road network topological graph corresponding to a target traffic road network in a target area, and calculating a differential operator corresponding to the road network topological graph.
The execution subject of this embodiment is a traffic road network optimization device that can be coupled to a server that can be communicatively connected to a terminal device and a database.
In this embodiment, in order to implement an optimization operation on the traffic road network of the target area, the technician may send an optimization request through the terminal device, where the optimization request may include identification information of the target area. Correspondingly, the traffic road network optimizing device can determine a road network topological graph corresponding to the target traffic road network of the target area according to the identification information of the target area, wherein the road network topological graph comprises a topological relation formed by roads and intersection points. Further, a differential operator corresponding to the road network topological graph can be calculated, so that continuous processing of discrete data can be realized based on the differential operator.
And 102, determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node, wherein the road node is a node corresponding to a road in the road network topological graph.
In this embodiment, for each road node in the road network topology map, the spatial information and the time information corresponding to the road node may be determined according to the traffic element information in the preset area around the road node, where the road node is a node corresponding to a road in the road network topology map.
Optionally, the traffic element information includes, but is not limited to, road network shape and traffic setting position information in a preset area around the road node, so that calculation of spatial information corresponding to the road node can be realized based on the traffic element information. The traffic element information includes, but is not limited to, track information in a preset area around the road node, so that calculation of time sequence information in the preset area around the road node can be realized according to the track information.
And 103, dividing the road network topological graph into a plurality of local topological graphs according to each road node and the associated node with a preset connection relation with the road node.
In this embodiment, for each road node in the road network topology map, an associated node in the road network topology, which has the preset connection relationship with the road node, may be determined according to the preset connection relationship, and the road node and the associated node corresponding to the road node are determined as a local topology map. Thus, the road network topology map can be divided into a plurality of partial topology maps. The preset connection relationship may be the number of edges between the road node and the associated node. For example, the preset connection relationship may be to determine a node having two edges with the road node as an associated node.
Step 104, for each local topological graph, calculating target continuous data corresponding to the local topological graph according to the space information and the time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator.
In this embodiment, after the road network topology map is divided into at least one local topology map, for each local topology map, continuous processing of the local road network discretization data corresponding to the local topology map may be implemented according to spatial information corresponding to the road nodes and the spatial nodes in the local topology map, and the time-series information, and the differential operators corresponding to the road network topology map, to obtain the target continuous data corresponding to the local topology map.
And 105, optimizing the target traffic network according to the target continuous data corresponding to the plurality of local topological graphs.
In this embodiment, after the calculation of the target continuous data corresponding to all the local topological graphs is completed, the continuous data corresponding to the road network topological graph can be obtained. The discretized road network data are converted into continuous data, so that the feature extraction operation can be performed on the basis of the continuous data. Therefore, the optimization operation can be performed on the target traffic network according to the target continuous data corresponding to the plurality of partial topological graphs.
According to the traffic network optimization method, the road network topological graph corresponding to the target traffic network in the target area is determined, and the differential operator corresponding to the road network topological graph is calculated. And respectively calculating space information and time sequence information corresponding to each road node, and dividing the road network topological graph to obtain a plurality of local topological graphs. Thus, for each partial topological graph, the calculation of the target continuous data can be carried out according to the space information, the time sequence information and the differential operator. And then, feature extraction operation can be performed based on the continuous data, and further, different processing can be performed on the target continuous data based on different service requirements.
Further, on the basis of the first embodiment, step 101 includes:
And obtaining a target traffic network corresponding to the target area.
And determining a road network topological graph corresponding to the target traffic road network according to the roads and the intersection points in the target traffic road network.
In this embodiment, after determining a target area to be processed, a target traffic network corresponding to the target area may be obtained, where the target traffic network includes a plurality of roads and intersections between the roads. Therefore, the road network topological graph corresponding to the target traffic road network can be determined according to the roads and the intersection points in the target traffic road network, and the road network topological graph comprises the topological relation formed by the roads and the intersection points.
Fig. 2 is a schematic view of a road and a junction provided in an embodiment of the disclosure, and as shown in fig. 2, a junction 23 exists between a road 21 and a road 22.
According to the traffic network optimization method, the road network topological graph corresponding to the target traffic network is determined according to the roads and the intersection points in the target traffic network, so that the discretized data can be converted into continuous data based on the road network topological graph later.
Further, on the basis of the first embodiment, the determining, according to the road and the junction in the target traffic network, a road network topology map corresponding to the target traffic network includes:
And taking the road in the target traffic road network as a road node and taking the intersection point between any two roads as an edge.
And generating a road network topological graph corresponding to the target traffic road network according to the road nodes and the edges.
In this embodiment, for each road in the target traffic road network, the road may be determined as a road node, and a junction between any two roads may be used as an edge between the any two road nodes. And determining a topological relation formed by the road and the junction based on the road nodes and edges between the road nodes, and generating a road network topological graph corresponding to the target traffic road network.
Fig. 3 is a schematic structural diagram of a road network topology diagram provided in an embodiment of the present disclosure, as shown in fig. 3, a road may be used as a road node 31, and a junction between any two road nodes 31 may be used as an edge 32.
According to the traffic network optimization method provided by the embodiment, the road is determined to be the road node, and the intersection point between any two roads is used for generating the road network topological graph corresponding to the target traffic network. Therefore, the road network topological graph can accurately express the topological relation between the road and the junction, and further can improve the accuracy of subsequent data processing.
Further, on the basis of the first embodiment, step 105 includes:
Obtaining a road network optimization request, wherein the road network optimization request comprises an optimization requirement.
And according to the road network optimization request, adopting a network model corresponding to the optimization requirement to process the target continuous data corresponding to the plurality of partial topological graphs.
In this embodiment, after the target continuous data is generated according to the target traffic network, the feature extraction operation can be performed based on the target continuous data, so that different processing can be performed on the target continuous data based on different service requirements. Specifically, the user may initiate a road network optimization request according to different service requirements. Accordingly, the traffic road network optimization device can acquire the road network optimization request, wherein the road network optimization request comprises the optimization requirement. And according to the optimization request, adopting a network model corresponding to the optimization requirement to process the target continuous data corresponding to the plurality of partial topological graphs.
For example, business requirements include, but are not limited to, trajectory matching, traffic prediction, location drift region identification, and the like. If the current business requirement is prediction of traffic conditions, target continuous data corresponding to the plurality of local topological graphs can be input into a preset traffic prediction model to perform prediction operation. Or the continuous target data corresponding to the multiple partial topological graphs can be input into a preset track matching model to perform track matching operation.
According to the traffic network optimization method, the target continuous data corresponding to the plurality of partial topological graphs are input into different network models for data processing according to different service requirements, so that the applicability of the target continuous data can be improved, and the traffic network optimization method is applicable to various different scenes.
Further, on the basis of the first embodiment, after step 104, the method further includes:
And clustering the continuous target data corresponding to the local topological graph by adopting a preset clustering algorithm.
In practical application, there is a large difference between traffic elements in different areas, but after discrete road network data is continuously processed, reduced in dimension and expressed again in an abstract way, the discrete road network data may have the same continuous data. Therefore, in order to improve the processing efficiency of the subsequent road network data, reduce the data redundancy and avoid repeated processing, after the processing of the target continuous data corresponding to the local topological graph is completed, a preset clustering algorithm can be adopted to perform clustering operation on the target continuous data corresponding to the local topological graph. The preset clustering algorithm may specifically be a K-means algorithm. Or it may be any clustering algorithm, which is not limited by the present disclosure.
According to the traffic network optimization method, clustering operation is carried out on the target continuous data corresponding to the local topological graph, so that the data redundancy can be reduced, and the processing efficiency of the subsequent road network data can be improved.
Fig. 4 is a flow chart of a traffic network optimization method provided in a second embodiment of the present disclosure, where the differential operator is a laplace operator, and on the basis of the first embodiment, as shown in fig. 4, step 101 includes:
Step 401, determining, for each road node in the road network topology graph, the number of edges pointing to the road node, and determining the number of edges as the ingress of the road node.
Step 402, generating an ingress matrix corresponding to the road network topological graph according to the ingress of all road nodes in the road network topological graph.
Step 403, determining, for each edge in the road network topology graph, a traffic flow and/or importance of a junction corresponding to the edge, and determining a weight of the edge according to the traffic flow and/or importance.
And 404, generating a weight matrix corresponding to the road network topological graph according to weights corresponding to all edges in the road network topological graph.
And 405, calculating a Laplacian matrix corresponding to the road network topological graph according to the degree matrix and the weight matrix.
In this embodiment, the differential operator may specifically be a laplace operator. In order to realize the calculation of the Laplace operator, firstly, an input degree matrix and a weight matrix corresponding to the road network topological graph are required to be calculated. The entering degree may specifically be the number of edges pointing to the road node, and the weight may specifically be the flow and the importance degree corresponding to the road.
Specifically, for each road node in the road network topology graph, the number of edges pointing to the road node is determined, and the number of edges is determined as the ingress of the road node. For example, a road node may have two edges, i.e., the road may have two points of intersection, and the degree of ingress for the road node may be determined to be 2. And generating an entry degree matrix corresponding to the road network topological graph according to the entry degree of all the road nodes in the road network topological graph. And generating a weight matrix corresponding to the road network topological graph according to the weights corresponding to all the edges in the road network topological graph. And calculating a Laplacian matrix corresponding to the road network topological graph according to the input degree matrix and the weight matrix. After the degree matrix and the weight matrix are obtained, the laplace matrix corresponding to the road network topological graph can be determined through matrix calculation of the degree matrix and the weight matrix.
According to the traffic network optimization method, the input degree matrix and the weight matrix corresponding to the road network topological graph are calculated, so that the Laplace matrix corresponding to the road network topological graph can be accurately determined through matrix calculation of the input degree matrix and the weight matrix, and a foundation is provided for subsequent data processing.
Further, based on any of the above embodiments, step 405 includes:
And performing matrix subtraction on the input degree matrix and the weight matrix to obtain a Laplacian matrix corresponding to the road network topological graph.
In this embodiment, after the degree matrix D and the weight matrix W are obtained, matrix subtraction operation may be performed on the degree matrix D and the weight matrix to obtain the laplace matrix L corresponding to the road network topology map. The calculation of the laplace matrix L may be specifically implemented by the formula l=d-W.
According to the traffic network optimization method, matrix subtraction operation is carried out on the degree matrix and the weight matrix, so that the Laplace matrix corresponding to the road network topological graph can be accurately calculated, and a foundation is provided for subsequent data processing.
Fig. 5 is a flow chart of a traffic road network optimization method according to a third embodiment of the present disclosure, where, on the basis of any one of the foregoing embodiments, as shown in fig. 5, step 103 includes:
Step 501, obtaining a road network division request, wherein the road network division request comprises the preset connection relation, and the preset connection relation comprises the number of edges between the association node and the road node.
Step 502, determining, according to the road network division request, for each road node, an associated node which accords with a preset connection relationship with the road node in the road network topology map.
Step 503, determining, for each road node, the road node and an associated node corresponding to the road node as the local topology map.
In this embodiment, the preset relationship may specifically be the number of edges between the association node and the road node. Thus, traffic road network optimization may obtain a road network partitioning request, where the road network partitioning request includes a number of edges between the associated node and the road node.
According to the road network dividing request, aiming at each road node, determining the associated node which accords with the preset connection relation with the road node in a road network topological graph. For example, the preset connection relationship may be to determine a node having two edges with the road node as an associated node. For each road node, the road node and the associated node corresponding to the road node are determined as the local topology map, so that the network topology map can be divided into a plurality of local topology maps.
The preset connection relationship can be switched according to different requirements, which is not limited in the disclosure.
According to the traffic network optimization method, the road network division request is obtained, and according to the road network division request, the associated node which accords with the preset connection relation with the road node is determined in the road network topological graph aiming at each road node, so that different division operations can be carried out on the network topological structure according to different service requirements, and the traffic network optimization method is suitable for different application scenes.
Further, on the basis of any one of the above embodiments, the traffic element information includes a road network structure, traffic facilities, and track information in a preset area around the road node; step 102 comprises:
And determining the road network structure and traffic facilities in a preset area around the road node as the space information corresponding to the road node.
And acquiring track information in a preset area around the road node according to a preset time interval, and drawing the track information on the road network topological graph according to a time sequence to acquire time sequence information corresponding to the road node.
In this embodiment, the traffic element information may specifically include road network structures, traffic facilities, and track information in a preset area around the road node. For each road node, the road network structure and traffic facilities in a preset area around the road node can be determined as the space information corresponding to the road node. The spatial information is generally static information corresponding to road nodes, which can represent whether road networks around the road are complex or not, and can realize the distinction of different roads. For example, the road network around the main road is complex, while the road network around the suburban road is simple.
For each road node, track information in a preset area around the road node can be acquired according to a preset time interval, and the track information is drawn on a road network topological graph according to a time sequence to acquire time sequence information corresponding to the road node. The timing information is generally dynamic information corresponding to a road node, which can represent the behavior of a vehicle in a preset area around the road, such as whether the traffic flow in the preset area around the road is relatively large.
According to the traffic network optimization method, the space information and the time sequence information corresponding to the road nodes are respectively determined according to the traffic element information, so that the static information and the dynamic information corresponding to the road nodes can be accurately determined, and a foundation is provided for subsequent processing of road network data.
Fig. 6 is a flow chart of a traffic road network optimization method according to a fourth embodiment of the present disclosure, where, on the basis of any one of the foregoing embodiments, as shown in fig. 6, step 104 includes:
step 601, for each local topological graph, calculating spatial continuous data corresponding to the local topological graph according to spatial information corresponding to road nodes and associated nodes in the local topological graph and the differential operator.
Step 602, for each local topological graph, calculating time sequence continuous data corresponding to the local topological graph according to time sequence information corresponding to road nodes and associated nodes in the local topological graph and the differential operator.
And 603, calculating target continuous data corresponding to the local topological graph according to the space continuous data and the time sequence continuous data.
In this embodiment, after the spatial information and the time-sequential information corresponding to the road node are respectively determined, the calculation of the spatially continuous data and the time-sequential data may be implemented based on the spatial information and the time-sequential information, respectively.
Specifically, for each local topological graph, according to the spatial information and the Laplacian corresponding to the road nodes and the associated nodes in the local topological graph, the spatial continuous data corresponding to the local topological graph is calculated. And calculating time sequence continuous data corresponding to the local topological graph according to the time sequence information and the Laplacian operator corresponding to the road nodes and the associated nodes in the local topological graph aiming at each local topological graph. Further, the target continuous data corresponding to the partial topology map can be calculated from the spatially continuous data and the time-series continuous data.
According to the traffic network optimization method, the calculation of the space continuous data and the time sequential continuous data is achieved based on the space information and the time sequential information respectively, so that discretized data can be converted into target continuous data, and further feature extraction operation of the traffic network data can be achieved.
Further, on the basis of any of the above embodiments, step 603 includes:
And respectively adjusting the space continuous data and the time sequence continuous data according to a preset data format to obtain the space continuous data and the time sequence continuous data with the same data format.
And carrying out data fusion operation on the space continuous data and the time sequence continuous data with the same data format to obtain fused continuous data.
And determining the target continuous data according to the fused continuous data.
In this embodiment, since there may be a difference in data format between spatially continuous data and time-series continuous data, the data calculation cannot be directly performed. Therefore, in order to realize operations such as data fusion of the space continuous data and the time sequence continuous data, a data format can be preset, and the adjustment operation is performed on the space continuous data and the time sequence continuous data according to the preset data format, so as to obtain the space continuous data and the time sequence continuous data with the same data format. Specifically, a space convolution neural network model and a time convolution neural network model can be respectively set, the space continuous data is adjusted according to a preset data format through the space convolution neural network model, and the time continuous data is adjusted according to the preset data format through the time convolution neural network model, so that the space continuous data with the same data format and the time continuous data are obtained.
When the space continuous data and the time sequential continuous data have the same data format, the data fusion operation can be carried out on the space continuous data and the time sequential continuous data, and the target continuous data is determined according to the fused continuous data.
Fig. 7 is a schematic diagram of generating target continuous data according to an embodiment of the present disclosure, as shown in fig. 7, the spatial continuous data 72 may be adjusted according to a preset data format by a preset spatial convolutional neural network model 71, and the time continuous data 74 may be adjusted according to a preset data format by a preset time convolutional neural network model 73. Spatially continuous data and temporally continuous data of the same data format are obtained. And performing data fusion operation on the space continuous data and the time continuous data with the same data format to obtain fused continuous data 75.
According to the traffic network optimization method, the space continuous data and the time sequence continuous data are respectively adjusted according to the preset data format, so that the space continuous data and the time sequence continuous data with the same data format are obtained, the format adjustment operation of the space continuous data and the time sequence continuous data can be realized, and further the data fusion operation of the space continuous data and the time sequence continuous data can be realized, and the fused continuous data is obtained.
Further, on the basis of any one of the above embodiments, after step 101, the method further includes:
And acquiring attribute information corresponding to each road in the target traffic road network, wherein the attribute information comprises one or more of the width, length, lane number, function level and traffic condition of the road.
And determining the road feature vector corresponding to the target traffic network according to the attribute information corresponding to each road.
The determining the target continuous data according to the fused continuous data comprises the following steps:
and performing data splicing operation on the fused continuous data and the road feature vector to obtain the target continuous data.
In this embodiment, after the data fusion operation on the space continuous data and the time sequential continuous data is completed, the data splicing operation may be further performed on the fused continuous data and the attribute information corresponding to the road. Specifically, for each road in the target traffic road network, attribute information corresponding to the road is acquired, wherein the attribute information includes one or more of width, length, number of lanes, function level, traffic condition of the road. And performing data splicing operation on the fused continuous data and the road feature vector to obtain target continuous data. Therefore, static and dynamic information and attribute information of the road nodes can be comprehensively considered, and the comprehensiveness and the accuracy of the generated target continuous data are improved.
Fig. 8 is a schematic structural diagram of a traffic road network optimization device according to a fifth embodiment of the present disclosure, where, as shown in fig. 8, the device includes: a determining module 81, a processing module 82, a dividing module 83, a calculating module 84 and an optimizing module 85. The determining module 81 is configured to determine a road network topology map corresponding to a target traffic road network in a target area, and calculate a differential operator corresponding to the road network topology map. And the processing module 82 is configured to determine spatial information and timing information corresponding to each road node according to traffic element information in a preset area around each road node, where the road node is a node corresponding to a road in the road network topology graph. The dividing module 83 is configured to divide the road network topology map into a plurality of local topology maps according to each road node and an associated node having a preset connection relationship with the road node. The calculating module 84 is configured to calculate, for each partial topology map, target continuous data corresponding to the partial topology map according to spatial information and time-sequence information corresponding to road nodes and associated nodes in the partial topology map, and the differential operator. And the optimizing module 85 is configured to perform an optimizing operation on the target traffic network according to the target continuous data corresponding to the multiple local topological graphs.
Further, on the basis of the fifth embodiment, the determining module includes: and the road network acquisition unit and the topology map determination unit. The road network acquisition unit is used for acquiring a target traffic road network corresponding to the target area. And the topology map determining unit is used for determining a road network topology map corresponding to the target traffic road network according to the roads and the junction points in the target traffic road network.
Further, on the basis of the fifth embodiment, the topology map determining unit includes: the system comprises a conversion subunit and a generation subunit, wherein the conversion subunit is used for taking a road in a target traffic road network as a road node and taking a junction point between any two roads as an edge. And the generation subunit is used for generating a road network topological graph corresponding to the target traffic road network according to the road nodes and the edges.
Further, on the basis of the fifth embodiment, the optimizing module includes: a request acquisition unit and an optimization unit. The request acquisition unit is used for acquiring a road network optimization request, the road network optimization request comprises an optimization requirement, and the optimization unit is used for carrying out data processing on the target continuous data corresponding to the plurality of local topological graphs by adopting a network model corresponding to the optimization requirement according to the road network optimization request.
Further, on the basis of the fifth embodiment, the apparatus further includes: and the clustering module is used for clustering the continuous target data corresponding to the local topological graph by adopting a preset clustering algorithm.
Further, on the basis of the fifth embodiment, the differential operator is a laplace operator, and the determining module includes: an importation degree determining unit, an importation degree matrix generating unit, a weight determining unit, a weight matrix generating unit and a matrix calculating unit. The system comprises a determining unit for determining the number of edges pointing to each road node in the road network topological graph, and determining the number of edges as the entering degree of the road node. And the ingress matrix generation unit is used for generating an ingress matrix corresponding to the road network topological graph according to the ingress of all road nodes in the road network topological graph. And the weight determining unit is used for determining the traffic flow and/or the importance of the intersection point corresponding to each side in the road network topological graph, and determining the weight of the side according to the traffic flow and/or the importance. And the weight matrix generation unit is used for generating a weight matrix corresponding to the road network topological graph according to weights corresponding to all edges in the road network topological graph. And the matrix calculation unit is used for calculating the Laplace matrix corresponding to the road network topological graph according to the input degree matrix and the weight matrix.
Further, on the basis of any one of the above embodiments, the matrix calculation unit includes: and the matrix processing subunit is used for performing matrix subtraction on the input degree matrix and the weight matrix to obtain a Laplacian matrix corresponding to the road network topological graph.
Further, on the basis of any one of the above embodiments, the dividing module includes: the node acquisition device comprises an acquisition unit, a node determination unit and a local topological graph unit. The road network dividing request comprises the preset connection relation, and the preset connection relation comprises the number of edges between the association node and the road node. The node determining unit is used for determining association nodes which accord with a preset connection relation with the road nodes in the road network topological graph aiming at each road node according to the road network dividing request. And the local topological graph unit is used for determining the road nodes and the associated nodes corresponding to the road nodes as the local topological graph for each road node.
Further, on the basis of any one of the above embodiments, the traffic element information includes a road network structure, traffic facilities, and track information in a preset area around the road node; the processing module comprises: a spatial information determining unit and a timing information determining unit. And the space information determining unit is used for determining the road network structure and the traffic facilities in the preset area around the road node as the space information corresponding to the road node. The time sequence information determining unit is used for obtaining track information in a preset area around the road node according to a preset time interval, and drawing the track information on the road network topological graph according to a time sequence to obtain the time sequence information corresponding to the road node.
Further, on the basis of any one of the above embodiments, the computing module includes: a space continuous data calculation unit, a time series continuous data calculation unit and a time series continuous data calculation unit. The space continuous data calculation unit is used for calculating the space continuous data corresponding to the local topological graph according to the space information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator. The time sequence continuous data calculation unit is used for calculating time sequence continuous data corresponding to each local topological graph according to the time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator. And the time sequence continuous data calculation unit is used for calculating target continuous data corresponding to the local topological graph according to the space continuous data and the time sequence continuous data.
Further, on the basis of any one of the above embodiments, the time-series continuous data calculation unit includes: an adjustment subunit, a fusion subunit, and a determination subunit. And the adjusting subunit is used for respectively adjusting the space continuous data and the time sequence continuous data according to a preset data format to obtain the space continuous data and the time sequence continuous data with the same data format. And the fusion subunit is used for carrying out data fusion operation on the space continuous data and the time sequence continuous data with the same data format to obtain fused continuous data. And the determining subunit is used for determining the target continuous data according to the fused continuous data.
Further, on the basis of any one of the foregoing embodiments, the apparatus further includes: the device comprises an attribute information determining module and a vector determining module. The attribute information determining module is used for acquiring attribute information corresponding to each road in the target traffic network, wherein the attribute information comprises one or more of width, length, number of lanes, function level and traffic condition of the road. And the vector determining module is used for determining the road feature vector corresponding to the target traffic road network according to the attribute information corresponding to each road. The determining subunit is configured to: and performing data splicing operation on the fused continuous data and the road feature vector to obtain the target continuous data.
According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.
According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising: a computer program stored in a readable storage medium, from which at least one processor of an electronic device can read, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any one of the embodiments described above.
Fig. 9 is a schematic structural diagram of an electronic device according to a sixth embodiment of the disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.
As shown in fig. 9, the apparatus 900 includes a computing unit 901 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 902 or a computer program loaded from a storage unit 908 into a Random Access Memory (RAM) 903. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other by a bus 904. An input/output (I/O) interface 905 is also connected to the bus 904.
Various components in device 900 are connected to I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, or the like; an output unit 907 such as various types of displays, speakers, and the like; a storage unit 908 such as a magnetic disk, an optical disk, or the like; and a communication unit 909 such as a network card, modem, wireless communication transceiver, or the like. The communication unit 909 allows the device 900 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.
The computing unit 901 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the respective methods and processes described above, such as a traffic network optimization method. For example, in some embodiments, the traffic network optimization method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 900 via the ROM 902 and/or the communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the traffic road network optimization method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the traffic network optimization method by any other suitable means (e.g. by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus such that the program code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and pointing device (e.g., a mouse or trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the internet.
The computer system may include a client and a server. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service ("Virtual PRIVATE SERVER" or simply "VPS") are overcome. The server may also be a server of a distributed system or a server that incorporates a blockchain.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.
The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.
Claims (21)
1. A traffic road network optimization method, comprising:
Determining a road network topological graph corresponding to a target traffic road network in a target area, and calculating a differential operator corresponding to the road network topological graph;
Determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node, wherein the road node is a node corresponding to a road in the road network topological graph;
Dividing the road network topology map into a plurality of local topology maps according to each road node and the associated node with a preset connection relation with the road node;
aiming at each local topological graph, calculating target continuous data corresponding to the local topological graph according to space information and time sequence information corresponding to road nodes and associated nodes in the local topological graph and the differential operator;
Optimizing the target traffic network according to the target continuous data corresponding to the plurality of local topological graphs;
the determining the road network topology map corresponding to the target traffic road network in the target area comprises the following steps:
acquiring a target traffic network corresponding to a target area;
taking a road in a target traffic road network as a road node and taking a junction point between any two roads as an edge; generating a road network topological graph corresponding to the target traffic road network according to the road nodes and edges;
the differential operator is a laplace operator, and the calculating the differential operator corresponding to the road network topological graph includes:
Determining the number of edges pointing to the road nodes for each road node in the road network topological graph, and determining the number of the edges as the degree of entrance of the road nodes; generating an entry matrix corresponding to the road network topological graph according to the entries of all road nodes in the road network topological graph;
Determining traffic flow and/or importance of a junction corresponding to each edge in the road network topological graph, and determining the weight of the edge according to the traffic flow and/or importance; generating a weight matrix corresponding to the road network topological graph according to weights corresponding to all edges in the road network topological graph;
and calculating a Laplacian matrix corresponding to the road network topological graph according to the degree matrix and the weight matrix.
2. The method of claim 1, wherein the calculating the laplace matrix corresponding to the road network topology according to the occupancy matrix and the weight matrix comprises:
And performing matrix subtraction on the input degree matrix and the weight matrix to obtain a Laplacian matrix corresponding to the road network topological graph.
3. The method according to claim 1 or 2, wherein the dividing the road network topology map into a plurality of local topology maps according to each of the road nodes and associated nodes having a preset connection relationship with the road nodes comprises:
obtaining a road network division request, wherein the road network division request comprises the preset connection relation, and the preset connection relation comprises the number of edges between the association node and the road node;
determining associated nodes which accord with a preset connection relation with the road nodes in the road network topological graph aiming at each road node according to the road network division request;
and determining the road nodes and the associated nodes corresponding to the road nodes as the local topological graph for each road node.
4. The method according to claim 1 or 2, wherein the traffic element information includes road network structure, traffic facilities, and trajectory information within a preset area around the road node;
The determining the spatial information and the time sequence information corresponding to each road node according to the traffic element information in the preset area around each road node comprises the following steps:
Determining a road network structure and traffic facilities in a preset area around the road node as space information corresponding to the road node;
And acquiring track information in a preset area around the road node according to a preset time interval, and drawing the track information on the road network topological graph according to a time sequence to acquire time sequence information corresponding to the road node.
5. The method according to claim 1 or 2, wherein for each local topological graph, calculating the target continuous data corresponding to the local topological graph according to the spatial information and the time-sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator, comprises:
For each local topological graph, calculating the space continuous data corresponding to the local topological graph according to the space information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;
for each local topological graph, calculating time sequence continuous data corresponding to the local topological graph according to time sequence information corresponding to road nodes and associated nodes in the local topological graph and the differential operator;
And calculating target continuous data corresponding to the local topological graph according to the space continuous data and the time sequence continuous data.
6. The method of claim 5, wherein the calculating the target continuous data corresponding to the local topological graph according to the spatially continuous data and the time-series continuous data comprises:
Respectively adjusting the space continuous data and the time sequence continuous data according to a preset data format to obtain the space continuous data and the time sequence continuous data with the same data format;
Performing data fusion operation on the space continuous data and the time sequence continuous data with the same data format to obtain fused continuous data;
And determining the target continuous data according to the fused continuous data.
7. The method of claim 6, further comprising, after the determining the road network topology map corresponding to the target traffic road network in the target area:
Acquiring attribute information corresponding to each road in the target traffic road network, wherein the attribute information comprises one or more of width, length, lane number, function level and traffic condition of the road;
Determining a road feature vector corresponding to the target traffic road network according to the attribute information corresponding to each road;
the determining the target continuous data according to the fused continuous data comprises the following steps:
and performing data splicing operation on the fused continuous data and the road feature vector to obtain the target continuous data.
8. The method according to any one of claims 1-2 and 6-7, wherein the optimizing the target traffic network according to the target continuous data corresponding to the plurality of local topological graphs includes:
Obtaining a road network optimization request, wherein the road network optimization request comprises an optimization requirement;
and according to the road network optimization request, adopting a network model corresponding to the optimization requirement to process the target continuous data corresponding to the plurality of partial topological graphs.
9. The method according to any one of claims 1-2 and 6-7, further comprising, after calculating the target continuous data corresponding to the local topology map:
And clustering the continuous target data corresponding to the local topological graph by adopting a preset clustering algorithm.
10. A traffic road network optimization device, comprising:
the determining module is used for determining a road network topological graph corresponding to the target traffic road network in the target area and calculating a differential operator corresponding to the road network topological graph;
The processing module is used for determining space information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node, wherein the road nodes are nodes corresponding to roads in the road network topological graph;
The dividing module is used for dividing the road network topological graph into a plurality of partial topological graphs according to each road node and the associated node which has a preset connection relation with the road node;
The calculation module is used for calculating target continuous data corresponding to each local topological graph according to the space information and the time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;
the optimization module is used for performing optimization operation on the target traffic network according to the target continuous data corresponding to the plurality of partial topological graphs;
Wherein the determining module comprises:
the road network acquisition unit is used for acquiring a target traffic road network corresponding to the target area;
The topological graph determining unit is used for determining a road network topological graph corresponding to the target traffic road network according to the roads and the junction points in the target traffic road network;
wherein the topology map determining unit includes:
The conversion subunit is used for taking the road in the target traffic road network as a road node and taking the intersection point between any two roads as an edge;
The generation subunit is used for generating a road network topological graph corresponding to the target traffic road network according to the road nodes and the edges;
Wherein the differential operator is a laplace operator, and the determining module includes:
the system comprises an ingress determining unit, a determining unit and a processing unit, wherein the ingress determining unit is used for determining the number of edges pointing to each road node in the road network topological graph and determining the number of edges as the ingress of the road node;
the system comprises an input degree matrix generation unit, a control unit and a control unit, wherein the input degree matrix generation unit is used for generating an input degree matrix corresponding to the road network topological graph according to the input degree of all road nodes in the road network topological graph;
The weight determining unit is used for determining the traffic flow and/or the importance of the intersection point corresponding to each side in the road network topological graph, and determining the weight of the side according to the traffic flow and/or the importance;
The weight matrix generation unit is used for generating a weight matrix corresponding to the road network topological graph according to weights corresponding to all edges in the road network topological graph;
and the matrix calculation unit is used for calculating the Laplace matrix corresponding to the road network topological graph according to the input degree matrix and the weight matrix.
11. The apparatus of claim 10, wherein the matrix calculation unit comprises:
and the matrix processing subunit is used for performing matrix subtraction on the input degree matrix and the weight matrix to obtain a Laplacian matrix corresponding to the road network topological graph.
12. The apparatus of claim 10 or 11, wherein the partitioning module comprises:
The road network dividing request comprises the preset connection relation, wherein the preset connection relation comprises the number of edges between the association node and the road node;
the node determining unit is used for determining association nodes which accord with a preset connection relation with the road nodes in the road network topological graph aiming at each road node according to the road network dividing request;
and the local topological graph unit is used for determining the road nodes and the associated nodes corresponding to the road nodes as the local topological graph for each road node.
13. The apparatus according to claim 10 or 11, wherein the traffic element information includes road network structure, traffic facilities, and trajectory information within a preset area around the road node;
the processing module comprises:
The space information determining unit is used for determining a road network structure and traffic facilities in a preset area around the road node as space information corresponding to the road node;
The time sequence information determining unit is used for obtaining track information in a preset area around the road node according to a preset time interval, and drawing the track information on the road network topological graph according to a time sequence to obtain the time sequence information corresponding to the road node.
14. The apparatus of claim 10 or 11, the computing module comprising:
the space continuous data calculation unit is used for calculating space continuous data corresponding to each local topological graph according to the space information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;
the time sequence continuous data calculation unit is used for calculating time sequence continuous data corresponding to each local topological graph according to the time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;
And the time sequence continuous data calculation unit is used for calculating target continuous data corresponding to the local topological graph according to the space continuous data and the time sequence continuous data.
15. The apparatus of claim 14, wherein the time-series continuous data calculation unit comprises:
The adjusting subunit is used for respectively adjusting the space continuous data and the time sequence continuous data according to a preset data format to obtain the space continuous data and the time sequence continuous data with the same data format;
the fusion subunit is used for carrying out data fusion operation on the space continuous data and the time sequence continuous data with the same data format to obtain fused continuous data;
and the determining subunit is used for determining the target continuous data according to the fused continuous data.
16. The apparatus of claim 15, the apparatus further comprising:
the attribute information determining module is used for acquiring attribute information corresponding to each road in the target traffic network, wherein the attribute information comprises one or more of width, length, number of lanes, function grade and traffic condition of the road;
The vector determining module is used for determining a road feature vector corresponding to the target traffic road network according to the attribute information corresponding to each road;
The determining subunit is configured to:
and performing data splicing operation on the fused continuous data and the road feature vector to obtain the target continuous data.
17. The apparatus of any of claims 10-11, 15-16, wherein the optimization module comprises:
the request acquisition unit is used for acquiring a road network optimization request, wherein the road network optimization request comprises an optimization requirement;
and the optimizing unit is used for carrying out data processing on the target continuous data corresponding to the plurality of partial topological graphs by adopting a network model corresponding to the optimizing requirement according to the road network optimizing request.
18. The apparatus of any one of claims 10-11, 15-16, further comprising:
and the clustering module is used for clustering the continuous target data corresponding to the local topological graph by adopting a preset clustering algorithm.
19. An electronic 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 the method of any one of claims 1-9.
20. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-9.
21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of any of claims 1-9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210210044.1A CN114626169B (en) | 2022-03-03 | 2022-03-03 | Traffic network optimization method, device, equipment, readable storage medium and product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210210044.1A CN114626169B (en) | 2022-03-03 | 2022-03-03 | Traffic network optimization method, device, equipment, readable storage medium and product |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114626169A CN114626169A (en) | 2022-06-14 |
CN114626169B true CN114626169B (en) | 2024-09-03 |
Family
ID=81899486
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210210044.1A Active CN114626169B (en) | 2022-03-03 | 2022-03-03 | Traffic network optimization method, device, equipment, readable storage medium and product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114626169B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115424446B (en) * | 2022-11-03 | 2023-02-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Road network topology simplification method for traffic organization evaluation |
CN115935027B (en) * | 2023-01-19 | 2024-08-06 | 北京百度网讯科技有限公司 | Data processing method of target object topological graph and training method of graph classification model |
CN116910951B (en) * | 2023-07-04 | 2024-01-23 | 天津大学 | Regional heating pipe network optimization design method and device |
CN117933519B (en) * | 2024-03-21 | 2024-06-11 | 腾讯科技(深圳)有限公司 | Road network optimization method and related device |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111583652A (en) * | 2020-05-21 | 2020-08-25 | 北京易华录信息技术股份有限公司 | Topological modeling method and system for traffic network |
CN111652434A (en) * | 2020-06-02 | 2020-09-11 | 百度在线网络技术(北京)有限公司 | Road network data processing method and device, electronic equipment and computer storage medium |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8103435B2 (en) * | 2007-07-27 | 2012-01-24 | George Mason Intellectual Properties, Inc. | Near real-time traffic routing |
US11715369B2 (en) * | 2016-08-15 | 2023-08-01 | University Of Southern California | Latent space model for road networks to predict time-varying traffic |
EP3611709A1 (en) * | 2018-08-15 | 2020-02-19 | Aurelius Bernet | Traffic flow simulator |
CN112907985A (en) * | 2019-11-19 | 2021-06-04 | 杭州海康威视数字技术股份有限公司 | Method and device for dividing traffic control area |
CN112241814B (en) * | 2020-10-20 | 2022-12-02 | 河南大学 | Traffic prediction method based on reinforced space-time diagram neural network |
CN112820105B (en) * | 2020-12-31 | 2022-08-26 | 银江技术股份有限公司 | Road network abnormal area processing method and system |
CN114036135A (en) * | 2021-10-13 | 2022-02-11 | 中国科学技术大学 | Method and system for estimating urban mobile source pollution emission by using incomplete information |
-
2022
- 2022-03-03 CN CN202210210044.1A patent/CN114626169B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111583652A (en) * | 2020-05-21 | 2020-08-25 | 北京易华录信息技术股份有限公司 | Topological modeling method and system for traffic network |
CN111652434A (en) * | 2020-06-02 | 2020-09-11 | 百度在线网络技术(北京)有限公司 | Road network data processing method and device, electronic equipment and computer storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN114626169A (en) | 2022-06-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114626169B (en) | Traffic network optimization method, device, equipment, readable storage medium and product | |
CN113989451B (en) | High-precision map construction method and device and electronic equipment | |
CN114034295B (en) | High-precision map generation method, device, electronic equipment, medium and program product | |
CN112763995B (en) | Radar calibration method and device, electronic equipment and road side equipment | |
CN112884837B (en) | Road positioning method, device, equipment and storage medium | |
CN114387410B (en) | Road data fusion map generation method and device and electronic equipment | |
CN113971723B (en) | Method, device, equipment and storage medium for constructing three-dimensional map in high-precision map | |
CN112883236B (en) | Map updating method and device, electronic equipment and storage medium | |
CN114387319A (en) | Point cloud registration method, device, equipment and storage medium | |
CN114036253A (en) | High-precision map data processing method and device, electronic equipment and medium | |
CN113298910A (en) | Method, apparatus and storage medium for generating traffic sign line map | |
CN112558072A (en) | Vehicle positioning method, device, system, electronic equipment and storage medium | |
CN113587937A (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
CN113762397B (en) | Method, equipment, medium and product for training detection model and updating high-precision map | |
CN113932796A (en) | High-precision map lane line generation method and device and electronic equipment | |
CN113139258B (en) | Road data processing method, device, equipment and storage medium | |
CN113450794B (en) | Navigation broadcasting detection method and device, electronic equipment and medium | |
CN115797961A (en) | Lane line change detection method, lane line change detection device, electronic apparatus, and storage medium | |
CN114170282A (en) | Point cloud fusion method and device, electronic equipment and medium | |
CN115127565A (en) | High-precision map data generation method and device, electronic equipment and storage medium | |
CN113986866A (en) | Processing method, device, equipment and medium for large-scale point cloud data | |
CN114036247A (en) | High-precision map data association method and device, electronic equipment and storage medium | |
CN114170300A (en) | High-precision map point cloud pose optimization method, device, equipment and medium | |
CN116465394B (en) | Road network structure generation method and device based on vehicle track data | |
CN113806387A (en) | Model training method, high-precision map change detection method and device and electronic equipment |
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 |