CN114626169A

CN114626169A - Traffic network optimization method, device, equipment, readable storage medium and product

Info

Publication number: CN114626169A
Application number: CN202210210044.1A
Authority: CN
Inventors: 白冠男; 李伟
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-03-03
Filing date: 2022-03-03
Publication date: 2022-06-14

Abstract

The disclosure provides a traffic network optimization method, a device, equipment, a readable storage medium and a product, and relates to the field of data processing, in particular to the field of intelligent traffic. The specific implementation scheme is as follows: determining a road network topological graph and a differential operator corresponding to a target traffic road network in a target area; determining spatial information and time sequence information corresponding to each road node according to traffic element information in a preset area around each road node; dividing the road network topological graph into a plurality of local 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 spatial information, the time sequence information and the differential operator 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 can be performed on the basis of the continuous road network data, so that optimization operation on a traffic network is realized.

Description

Traffic network optimization method, device, equipment, readable storage medium and product

Technical Field

The present disclosure relates to intelligent traffic in data processing, and more particularly, to a method, an apparatus, a device, a readable storage medium, and a product for optimizing a traffic network.

Background

The map software mainly implements the Navigation function based on the Satellite positioning information of a Global Navigation Satellite System (GNSS), however, such a scheme faces two challenges: firstly, the reception of satellite signals by mobile equipment is influenced by high-rise buildings and viaducts in urban environment, so that satellite positioning points are inconsistent with reality; secondly, along with the construction of urban and rural areas, the change of the road network becomes frequent, the complicated areas of the road network are gradually increased, and the requirement on the positioning precision is also increased day by day.

In order to realize the description of the traffic network, the current processing method generally abstracts all roads in an area into one or a plurality of connected continuous vectors according to the longitude and latitude and the road shape; then, connecting corresponding vectors at the position of road convergence in reality to form a graph with a topological relation; and finally, adding other auxiliary descriptions such as traffic lights, driving restriction prohibition and the like according to the longitude and latitude positions to obtain the data description.

However, when describing a traffic network by using the above processing method, since roads and other traffic facilities in a data network are discrete data, the data scale is huge, it is difficult to extract sufficient features in large-scale machine learning, and it is difficult to improve the accuracy of an electronic map and the efficiency of data processing.

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 serialized data volumes.

According to a first aspect of the present disclosure, there is provided a traffic 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 spatial 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 topological graph into a plurality of local topological graphs according to the road nodes and the associated nodes with preset connection relations with the road nodes;

for each local topological graph, calculating target continuous data corresponding to the local topological graph according to spatial information and time sequence information corresponding to the road nodes and the associated nodes in the local topological graph and the differential operator;

and optimizing 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 network optimization apparatus, comprising:

the system comprises a determining module, a calculating module and a judging module, wherein the determining module is used for 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 processing module is used for determining spatial 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;

the dividing module is used for dividing the road network topological graph into a plurality of local topological graphs according to the road nodes and the associated nodes with preset connection relations with the road nodes;

the calculation module is used for calculating target continuous data corresponding to each 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;

and the optimization module is used for optimizing the target traffic network according to the target continuous data corresponding to the plurality of local 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 content of the first and second substances,

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 having stored thereon 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 at least one processor of an electronic device can read the computer program, execution of the computer program by the at least one processor 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 can be carried out on the basis of the continuous road network data, so that the optimization operation of a traffic network is realized.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

fig. 1 is a schematic flow chart of a traffic network optimization method according to a first embodiment of the present disclosure;

fig. 2 is a schematic view of a road and an intersection provided by the embodiment of the disclosure;

fig. 3 is a schematic structural diagram of a road network topology provided by the embodiment of the present disclosure;

fig. 4 is a schematic flow chart of a traffic network optimization method according to a second embodiment of the present disclosure;

fig. 5 is a schematic flow chart of a traffic network optimization method provided in the third embodiment of the present disclosure;

fig. 6 is a schematic flow chart of a traffic network optimization method according to a fourth embodiment of the present disclosure;

FIG. 7 is a schematic diagram of target continuous data generation provided by an embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a traffic network optimization apparatus 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 present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those 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 insurance quantity in China and the driving and traveling willingness of residents tend to rise year by year, and accordingly, the greatly increased traveling demands also put forward richer and higher-standard requirements on the map navigation function. In practical applications, the implementation of the navigation function by the map software is mainly based on the satellite positioning information of the GNSS system, however, such a scheme faces two challenges: firstly, the reception of satellite signals by mobile equipment is influenced by high-rise buildings and viaducts in urban environment, so that satellite positioning points are inconsistent with reality; secondly, along with the construction of urban and rural areas, the change of the road network becomes frequent, the complicated areas of the road network are gradually increased, and the requirement on the positioning precision is also increased day by day.

In the prior art, when describing a traffic network, all roads in an area are generally abstracted into one or a plurality of connected continuous vectors according to longitude and latitude and road shapes; then, connecting corresponding vectors at the position of road convergence in reality to form a graph with a topological relation; and finally, adding other auxiliary descriptions such as traffic lights, traffic restriction prohibition and the like according to the longitude and latitude positions to obtain the data description of the traffic network. However, when describing a traffic network by the above method, the roads and other transportation facilities in the data network are discrete data, and thus the data size is enormous. Therefore, enough features are difficult to extract in large-scale machine learning, and accordingly, the difficulty of adapting to local conditions and personalized navigation strategies is improved.

In the process of solving the technical problem, the inventor finds out through research that in order to realize the extraction operation of the road network data characteristics in the large-scale machine learning, the discrete data can be converted into continuous data. Specifically, a road network topological graph corresponding to a target traffic road network in a target area may be determined, and a differential operator corresponding to the road network topological graph may be calculated. And respectively calculating the spatial information and the time sequence information corresponding to each road node, and dividing the road network topological graph to obtain a plurality of local topological graphs. Therefore, for each local topological graph, the calculation of the target continuous data can be carried out according to the spatial information, the time sequence information and the differential operator.

The present disclosure provides a traffic network optimization method, device, apparatus, readable storage medium and product, which are applied to intelligent traffic in data processing, and can convert discrete data into continuous data, and further perform operations such as feature extraction and subsequent road network optimization based on the continuous data.

Fig. 1 is a schematic flow chart of a traffic network optimization method according to an embodiment of the present disclosure, and 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 the embodiment is a traffic network optimization device, which can be coupled to a server, and the server can be connected to a terminal device and a database in a communication manner.

In this embodiment, in order to implement optimization operation on the traffic network of the target area, a technician may send an optimization request through a terminal device, where the optimization request may include identification information of the target area. Correspondingly, the traffic network optimization device may determine a road network topological graph corresponding to the target traffic network of the target area according to the identification information of the target area, where the road network topological graph includes a topological relation formed by roads and intersections. Further, a differential operator corresponding to the road network topological graph can be calculated, so that the discrete data can be continuously processed based on the differential operator.

Step 102, according to traffic element information in a preset area around each road node, determining spatial information and time sequence information corresponding to 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 timing information corresponding to the road node may be obtained from the traffic element information in the preset area around the road node.

Optionally, the traffic element information includes, but is not limited to, a shape of a road network in a preset area around the road node and traffic setting position information, so that calculation of spatial information corresponding to the road node can be achieved 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, and then calculation of time sequence information in the preset area around the road node can be achieved according to the track information.

Step 103, dividing the road network topological graph into a plurality of local topological graphs according to the road nodes and the associated nodes with preset connection relations with the road nodes.

In this embodiment, for each road node in the road network topology map, according to a preset connection relationship, an associated node in the road network topology, which has the preset connection relationship with the road node, may be determined, and the road node and the associated node corresponding to the road node may be determined as one local topology map. Therefore, the road network topological graph can be divided into a plurality of local topological graphs. 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 that a node having two edges with a road node is determined as an associated node.

And 104, aiming at each local topological graph, calculating 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.

In this embodiment, after the road network topological graph is divided into at least one local topological graph, for each local topological graph, the target continuous data corresponding to the local topological graph may be obtained by performing the continuous processing on the local road network discretization data corresponding to the local topological graph according to the spatial information and the timing information corresponding to the road nodes and the spatial nodes in the local topological graph and the differential operator corresponding to the road network topological graph.

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. By converting the discretized road network data into the continuous data, the feature extraction operation can be subsequently performed based on the continuous data. Therefore, the target traffic network can be optimized according to the target continuous data corresponding to the plurality of local topological graphs.

In the traffic network optimization method provided by this embodiment, a road network topological graph corresponding to a target traffic network in a target area is determined, and a differential operator corresponding to the road network topological graph is calculated. And respectively calculating the spatial information and the time sequence information corresponding to each road node, and dividing the road network topological graph to obtain a plurality of local topological graphs. Therefore, for each local topological graph, the calculation of the target continuous data can be carried out according to the spatial information, the time sequence information and the differential operator. Therefore, feature extraction operation can be subsequently carried out on the basis of the continuous data, and further different processing can be carried out on the target continuous data on the basis of different business requirements.

Further, on the basis of the first embodiment, the step 101 includes:

and acquiring 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 a target area that needs to be processed is determined, a target traffic network corresponding to the target area may be obtained, where the target traffic network includes multiple 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 an intersection provided in the embodiment of the present disclosure, and as shown in fig. 2, an intersection 23 exists between the road 21 and the road 22.

According to the traffic network optimization method provided by the embodiment, 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 discrete data can be converted into continuous data based on the road network topological graph.

Further, on the basis of the first embodiment, the determining a road network topological graph corresponding to a target traffic road network according to roads and junction points in the target traffic road network includes:

the method comprises the steps of taking roads in a target traffic road network as road nodes, and taking an 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 network, the road may be determined as a road node, and an intersection between any two roads may be used as an edge between any two road nodes. And determining a topological relation formed by the road and the intersection points based on the road nodes and the edges among 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 provided by the embodiment of the present disclosure, and as shown in fig. 3, a road may be used as a road node 31, and an intersection point between any two road nodes 31 may be used as an edge 32.

In the traffic network optimization method provided in this embodiment, the road is determined as a road node, and a road network topological graph corresponding to the target traffic network is generated at an intersection between any two roads. Therefore, the road network topological graph can accurately express the topological relation between the road and the intersection point, and the accuracy of subsequent data processing can be improved.

Further, on the basis of the first embodiment, the step 105 includes:

the method comprises the steps of obtaining a road network optimization request, wherein the road network optimization request comprises optimization requirements.

And according to the road network optimization request, adopting a network model corresponding to the optimization requirement to perform data processing on the target continuous data corresponding to the plurality of local 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, and further, the target continuous data can be processed differently based on different business requirements. Specifically, the user may initiate a road network optimization request according to different service requirements. Accordingly, the traffic network optimization device may obtain the network optimization request, where the network optimization request includes optimization requirements. And according to the optimization request, performing data processing on target continuous data corresponding to the local topological graphs by adopting a network model corresponding to the optimization requirement.

For example, traffic requirements include, but are not limited to, trajectory matching, traffic prediction, location drift region identification, and the like. If the current service demand is the prediction of the traffic condition, the target continuous data corresponding to the plurality of local topological graphs can be input into a preset traffic prediction model for prediction operation. Or, target continuous data corresponding to the plurality of local topological graphs can be input into a preset track matching model for track matching operation.

According to the traffic network optimization method provided by the embodiment, the target continuous data corresponding to the plurality of local topological graphs are input to 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 method is suitable for various different scenes.

Further, on the basis of the first embodiment, after the step 104, the method further includes:

and clustering the target continuous data corresponding to the local topological graph by adopting a preset clustering algorithm.

In practical applications, there are large differences between traffic elements in different areas, but after discrete road network data is subjected to continuity processing, dimension reduction and abstract representation, the discrete road network data may have the same continuity data. Therefore, in order to improve the subsequent processing efficiency of the 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 be a K-means algorithm. Alternatively, it may be any one of the clustering algorithms, which the present disclosure does not limit.

According to the traffic network optimization method provided by the embodiment, the target continuous data corresponding to the local topological graph is clustered, so that the data redundancy can be reduced, and the processing efficiency of subsequent road network data is improved.

Fig. 4 is a schematic flow chart of a traffic network optimization method provided in the second embodiment of the present disclosure, where the differential operator is a laplacian operator, and based on the first embodiment, as shown in fig. 4, step 101 includes:

step 401, 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 entry of the road node.

Step 402, generating an entrance degree matrix corresponding to the road network topological graph according to the entrance degrees of all road nodes in the road network topological graph.

Step 403, determining traffic flow and/or importance of an intersection point 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.

And 404, generating a weight matrix corresponding to the road network topological graph according to the weights corresponding to all edges in the road network topological graph.

Step 405, calculating a laplacian matrix corresponding to the road network topological graph according to the entrance matrix and the weight matrix.

In this embodiment, the differential operator may be a laplacian operator. To realize the calculation of the laplacian operator, first, an entry matrix and a weight matrix corresponding to the road network topological graph need to be calculated. The degree of income may specifically be the number of edges pointing to a road node, and the weight may specifically be a flow and an importance degree corresponding to the road.

Specifically, for each road node in the road network topological graph, the number of edges pointing to the road node is determined, and the number of the edges is determined as the degree of entry of the road node. For example, a road node corresponds to two edges, that is, the road corresponds to two junctions, and it may be determined that the income degree corresponding to the road node is 2. And generating an entrance matrix corresponding to the road network topological graph according to the entrances of all 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 edges in the road network topological graph. And calculating a Laplace matrix corresponding to the road network topological graph according to the entrance matrix and the weight matrix. After the income degree matrix and the weight matrix are obtained, the laplacian matrix corresponding to the road network topological graph can be determined through the matrix calculation of the income degree matrix and the weight matrix.

According to the traffic network optimization method provided by the embodiment, the corresponding Laplace matrix of the road network topological graph can be accurately determined through the matrix calculation of the corresponding entry matrix and the corresponding weight matrix by calculating the entry matrix and the corresponding weight matrix of the road network topological graph, and a basis is provided for subsequent data processing.

Further, on the basis of any of the above embodiments, step 405 includes:

and performing matrix subtraction on the entrance degree matrix and the weight matrix to obtain a Laplace matrix corresponding to the road network topological graph.

In this embodiment, after the input matrix D and the weight matrix W are obtained, matrix subtraction may be performed on the input matrix D and the weight matrix to obtain the laplacian matrix L corresponding to the road network topological graph. The calculation of the laplacian matrix L may be specifically realized by the formula L ═ D-W.

According to the traffic network optimization method provided by the embodiment, the Laplace matrix corresponding to the road network topological graph can be accurately calculated by performing matrix subtraction on the entrance matrix and the weight matrix, so that a basis is provided for subsequent data processing.

Fig. 5 is a schematic flow chart of a traffic network optimization method provided in a third embodiment of the present disclosure, and based on any of the above embodiments, as shown in fig. 5, step 103 includes:

step 501, a road network division request is obtained, wherein the road network division request includes the preset connection relationship, and the preset connection relationship includes the number of edges between the associated node and the road node.

Step 502, according to the road network division request, determining, for each road node, an associated node in the road network topological graph, where the associated node corresponds to a preset connection relationship with the road node.

Step 503, for each road node, determining the road node and the associated node corresponding to the road node as the local topological graph.

In this embodiment, the preset relationship may specifically be the number of edges between the associated node and the road node. Therefore, the traffic network optimization can obtain a network division request, wherein the network division request comprises the number of edges between the associated nodes and the road nodes.

And according to the road network division request, determining associated nodes which accord with preset connection relations with the road nodes in the road network topological graph aiming at the road nodes. For example, the preset connection relationship may be that a node having two edges with a road node is determined as an associated node. For each road node, the road node and the associated node corresponding to the road node are determined as a local topological graph, so that the network topological graph can be divided into a plurality of local topological graphs.

The preset connection relation can be switched according to different requirements, and the preset connection relation is not limited by the disclosure.

According to the traffic network optimization method provided by the embodiment, the road network division request is obtained, and the associated nodes which accord with the preset connection relation with the road nodes are determined in the road network topological graph aiming at the road nodes according to the road network division request, so that different division operations can be performed on the network topological structure according to different service requirements, and the method is suitable for different application scenes.

Further, on the basis of any of the above embodiments, the traffic element information includes a road network structure, traffic facilities, and trajectory information in a preset area around the road node; step 102 comprises:

and determining a road network structure and traffic facilities in a preset area around the road node as the spatial 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 a road network structure, traffic facilities, and trajectory information in a preset area around the road node. For each road node, a road network structure and traffic facilities in a preset area around the road node may be determined as the spatial information corresponding to the road node. The spatial information is generally static information corresponding to a road node, and can represent whether a road network around the road is complex or not, so that different roads can be distinguished. For example, the road network around the main road is relatively complex, while the road network around the suburban road is relatively simple.

For each road node, track information in a preset area around the road node can be obtained according to a preset time interval, the track information is drawn on a road network topological graph according to a time sequence, and time sequence information corresponding to the road node is obtained. The time sequence information is generally dynamic information corresponding to a road node, and can represent the behavior of vehicles in a preset area around the road, for example, whether the traffic flow is relatively large in the preset area around the road or not.

According to the traffic network optimization method provided by the embodiment, the spatial 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 basis is provided for subsequent processing of the road network data.

Fig. 6 is a schematic flow chart of a traffic network optimization method according to a fourth embodiment of the present disclosure, where on the basis of any 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 the road nodes in the local topological graph and the spatial information and the differential operator corresponding to the associated nodes.

Step 602, for each local topological graph, calculating time sequence continuous data corresponding to the local topological graph according to the road nodes in the local topological graph and the time sequence information corresponding to the associated nodes 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-series information corresponding to the road node are determined, respectively, the calculation of the spatial continuous data and the time-series continuous data may be realized based on the spatial information and the time-series information, respectively.

Specifically, for each local topological graph, spatial continuous data corresponding to the local topological graph is calculated according to the road nodes in the local topological graph and the spatial information and the laplacian operator corresponding to the associated nodes. And aiming at each local topological graph, calculating time sequence continuous data corresponding to the local topological graph according to the road nodes in the local topological graph and the time sequence information and the Laplacian corresponding to the associated nodes. And further, target continuous data corresponding to the local topological graph can be calculated according to the space continuous data and the time sequence continuous data.

According to the traffic network optimization method provided by the embodiment, calculation of the spatial continuous data and the time sequence continuous data is realized based on the spatial information and the time sequence information, so that discrete data can be converted into target continuous data, and further, the feature extraction operation of the traffic network data can be realized.

Further, on the basis of any of the above embodiments, step 603 includes:

and adjusting the spatial continuous data and the time sequence continuous data according to a preset data format to obtain the spatial continuous data and the time sequence continuous data with the same data format.

And carrying out data fusion operation on the spatial 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 the spatially continuous data and the time-series continuous data, the data calculation cannot be performed directly. Therefore, in order to implement operations such as data fusion of the spatial continuous data and the time-series continuous data, a data format may be preset, and the spatial continuous data and the time-series continuous data are respectively adjusted according to the preset data format to obtain the spatial continuous data and the time-series continuous data with the same data format. Specifically, a spatial convolution neural network model and a temporal convolution neural network model may be respectively set, the spatial continuous data is adjusted according to a preset data format through the spatial convolution neural network model, and the temporal continuous data is adjusted according to the preset data format through the temporal convolution neural network model, so as to obtain spatial continuous data and time series continuous data with the same data format.

When the spatial continuous data and the time sequence continuous data have the same data format, the spatial continuous data and the time sequence continuous data can be subjected to data fusion operation, 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, and as shown in fig. 7, a preset spatial convolutional neural network model 71 may perform an adjustment operation on spatial continuous data 72 according to a preset data format, and a preset time convolutional neural network model 73 may perform an adjustment operation on time continuous data 74 according to a preset data format. And acquiring spatially continuous data and time-sequence continuous data with the same data format. And performing data fusion operation on the spatial continuous data and the time sequence continuous data with the same data format to obtain fused continuous data 75.

According to the traffic network optimization method provided by the embodiment, the spatial continuous data and the time sequence continuous data are respectively adjusted according to the preset data format, and the spatial continuous data and the time sequence continuous data with the same data format are obtained, so that the format adjustment operation of the spatial continuous data and the time sequence continuous data can be realized, the data fusion operation of the spatial continuous data and the time sequence continuous data can be further realized, and the fused continuous data can be obtained.

Further, on the basis of any of the above embodiments, after the step 101, the method further includes:

and acquiring attribute information corresponding to each road in the target traffic network, wherein the attribute information comprises one or more of the width, the length, the number of the roads, the function level and the traffic condition of the road.

And determining the road characteristic 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:

and performing data splicing operation on the fused continuous data and the road characteristic vector to obtain the target continuous data.

In this embodiment, after the data fusion operation on the spatial continuous data and the time-series 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 network, attribute information corresponding to the road is obtained, where the attribute information includes one or more of the width, length, number of lanes, function level, and traffic condition of the road. And performing data splicing operation on the fused continuous data and the road characteristic vector to obtain target continuous data. Therefore, static and dynamic information and attribute information of the road nodes can be comprehensively considered, and comprehensiveness and accuracy of the generated target continuous data are improved.

Fig. 8 is a schematic structural diagram of a traffic network optimization device according to a fifth embodiment of the present disclosure, and as shown in fig. 8, the device includes: a determination module 81, a processing module 82, a partitioning module 83, a calculation module 84, and an optimization module 85. The determining module 81 is configured to determine a road network topological graph corresponding to a target traffic road network in a target area, and calculate a differential operator corresponding to the road network topological graph. 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 topological graph. The dividing module 83 is configured to divide the road network topological graph into a plurality of local topological graphs according to each road node and associated nodes having a preset connection relationship with the road node. And a calculating module 84, configured to calculate, for each local topological graph, target continuous data corresponding to the local topological graph according to the spatial information and the time sequence information corresponding to the road node and the associated node in the local topological graph, and the differential operator. And the optimization module 85 is configured to perform optimization operation on the target traffic network according to the target continuous data corresponding to the plurality of local topological graphs.

Further, on the basis of the fifth embodiment, the determining module includes: road network acquisition unit and topological graph determining unit. The road network obtaining unit is used for obtaining a target traffic road network corresponding to the target area. And 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 intersection points in the target traffic road network.

Further, on the basis of the fifth embodiment, the topology 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 an intersection point between any two roads as an edge. And the generating 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 optimization module includes: a request acquisition unit and an optimization unit. The device comprises a request acquisition unit and an optimization unit, wherein the request acquisition unit is used for acquiring a road network optimization request, the road network optimization request comprises an optimization demand, and the optimization unit is used for carrying out data processing on target continuous data corresponding to the local topological graphs by adopting a network model corresponding to the optimization demand 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 target continuous 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 laplacian operator, and the determining module includes: the system comprises an in-degree determining unit, an in-degree matrix generating unit, a weight determining unit, a weight matrix generating unit and a matrix calculating unit. The method comprises a road network topological graph obtaining unit, an entry degree determining unit and a judging unit, wherein the entry degree determining unit is used for determining the number of edges pointing to the road nodes aiming at each road node in the road network topological graph and determining the number of the edges as the entry degree of the road nodes. And the entrance matrix generating unit is used for generating an entrance matrix corresponding to the road network topological graph according to the entrances 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 edge in the road network topological graph, and determining the weight of the edge according to the traffic flow and/or the importance. And the weight matrix generating unit is used for generating a weight matrix corresponding to the road network topological graph according to the weights corresponding to all edges in the road network topological graph. And the matrix calculation unit is used for calculating a Laplace matrix corresponding to the road network topological graph according to the entrance matrix and the weight matrix.

Further, on the basis of any of the above embodiments, the matrix calculation unit includes: and the matrix processing subunit is configured to perform matrix subtraction on the entry matrix and the weight matrix to obtain a laplacian matrix corresponding to the road network topological graph.

Further, on the basis of any of the above embodiments, the dividing module includes: the device comprises an acquisition unit, a node determination unit and a local topological graph unit. The obtaining unit is configured to obtain a road network partitioning request, where the road network partitioning request includes the preset connection relationship, and the preset connection relationship includes the number of edges between the associated node and the road node. And the node determining unit is used for determining the associated nodes which accord with the preset connection relation with the road nodes in the road network topological graph aiming at the road nodes according to the road network division 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 aiming at each road node.

Further, on the basis of any of the above embodiments, the traffic element information includes a road network structure, traffic facilities, and trajectory information in a preset area around the road node; the processing module comprises: a spatial information determination unit and a timing information determination unit. And the spatial information determining unit is used for determining a road network structure and traffic facilities in a preset area around the road node as the spatial information corresponding to the road node. And the time sequence information determining unit is used for 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.

Further, on the basis of any of the above embodiments, the calculation module includes: the device comprises a space continuous data calculation unit, a time sequence continuous data calculation unit and a time sequence continuous data calculation unit. And the spatial continuous data calculation unit is used for calculating spatial continuous data corresponding to the local topological graph according to the road nodes in the local topological graph and the spatial information corresponding to the associated nodes and the differential operator. And the time sequence continuous data calculation unit is used for calculating time sequence continuous data corresponding to the local topological graph according to the road nodes in the local topological graph, the time sequence information corresponding to the associated nodes 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: a regulator subunit, a fusion subunit, and a determination subunit. The adjusting subunit is configured to perform an adjusting operation on the spatial continuous data and the time-series continuous data according to a preset data format, so as to obtain the spatial continuous data and the time-series continuous data with the same data format. And the fusion subunit is used for performing data fusion operation on the spatial 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 above embodiments, the apparatus further includes: attribute information determining module and vector determining module. And 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 the width, the length, the number of lanes, the function level and the traffic condition of the road. And the vector determining module is used for determining the road characteristic vector corresponding to the target traffic road network according to the attribute information corresponding to each road. The determining subunit is to: and performing data splicing operation on the fused continuous data and the road characteristic vector to obtain the target continuous data.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

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 the electronic device can read the computer program, the at least one processor executing the computer program causing the electronic device to perform the solution provided by any of the embodiments described above.

Fig. 9 is a schematic structural diagram of an electronic device according to a sixth embodiment of the present 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 phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 9, the apparatus 900 includes a computing unit 901 which can perform various appropriate actions and processes in accordance with 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 calculation unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input/output (I/O) interface 905 is also connected to bus 904.

A number of components in the device 900 are connected to the I/O interface 905, including: an input unit 906 such as a keyboard, a mouse, and 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, optical disk, or the like; and a communication unit 909 such as a network card, a modem, a wireless communication transceiver, and 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 telecommunication 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 the computing unit 901 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation 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 in 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 device 900 via ROM 902 and/or communications unit 909. When loaded into RAM 903 and executed by the computing unit 901, a computer program may perform one or more steps of the traffic network optimization method described above. 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 circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a 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 that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes 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 codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. 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. A 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 a pointing device (e.g., a mouse or a 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 can 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, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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 clients and servers. A client and server are generally 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 as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. A traffic network optimization method comprises the following steps:

2. The method of claim 1, wherein the determining a road network topology map corresponding to the target traffic road network in the target area comprises:

acquiring a target traffic road network corresponding to a target area;

3. The method of claim 2, wherein the determining the road network topological graph corresponding to the target traffic road network according to the roads and junctions in the target traffic road network comprises:

taking roads in a target traffic network as road nodes, and taking an intersection point between any two roads as an edge;

4. The method according to any one of claims 1-3, wherein said differential operator is Laplacian, and said calculating the differential operator corresponding to said road network topology map comprises:

determining the number of edges pointing to the road nodes aiming at each road node in the road network topological graph, and determining the number of the edges as the degree of entry 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 an intersection point corresponding to each edge in the road network topological graph, and determining the weight of the edge according to the traffic flow and/or the importance;

generating a weight matrix corresponding to the road network topological graph according to the weights corresponding to all edges in the road network topological graph;

and calculating a Laplace matrix corresponding to the road network topological graph according to the entrance matrix and the weight matrix.

5. The method according to claim 4, wherein said calculating the Laplace matrix corresponding to the road network topology map according to the in-degree matrix and the weight matrix comprises:

and performing matrix subtraction on the entrance matrix and the weight matrix to obtain a Laplacian matrix corresponding to the road network topological graph.

6. The method according to any one of claims 1 to 5, wherein the dividing the road network topology map into a plurality of local topology maps according to each road node and associated nodes having a preset connection relationship with the road node comprises:

acquiring a road network dividing request, wherein the road network dividing request comprises the preset connection relation, and the preset connection relation comprises the number of edges between the associated node and the road node;

according to the road network division request, determining associated nodes which accord with preset connection relations with the road nodes in the road network topological graph aiming at the road nodes;

and aiming at each road node, determining the road node and the associated node corresponding to the road node as the local topological graph.

7. The method according to any one of claims 1 to 6, wherein the traffic element information includes a 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:

determining a road network structure and traffic facilities in a preset area around the road node as spatial information corresponding to the road node;

8. The method according to any one of claims 4 to 7, wherein for each local topological graph, calculating target continuous data corresponding to the local topological graph according to spatial information and timing information corresponding to the road nodes and associated nodes in the local topological graph and the differential operator comprises:

for each local topological graph, calculating spatial continuous data corresponding to the local topological graph according to the road nodes in the local topological graph and the spatial information and the differential operator corresponding to the associated nodes;

aiming at each local topological graph, calculating time sequence continuous data corresponding to the local topological graph according to the road nodes in the local topological graph, the time sequence information corresponding to the associated nodes 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.

9. The method of claim 8, wherein the calculating target continuous data corresponding to the local topological graph according to the spatial continuous data and the time series continuous data comprises:

adjusting the spatial continuous data and the time sequence continuous data according to a preset data format to obtain the spatial continuous data and the time sequence continuous data with the same data format;

performing data fusion operation on the spatial continuous data and the time sequence continuous data with the same data format to obtain fused continuous data;

10. The method according to claim 9, after determining the road network topology map corresponding to the target traffic road network in the target area, further comprising:

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;

determining a road characteristic vector corresponding to the target traffic road network according to the attribute information corresponding to each road;

11. The method according to any one of claims 1-10, wherein said optimizing said target traffic network according to said target continuous data corresponding to said plurality of local topology maps comprises:

obtaining a road network optimization request, wherein the road network optimization request comprises optimization requirements;

and according to the road network optimization request, performing 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.

12. The method according to any one of claims 1-11, further comprising, after calculating the target continuous data corresponding to the local topological graph:

and adopting a preset clustering algorithm to perform clustering operation on the target continuous data corresponding to the local topological graph.

13. A traffic network optimization device, comprising:

14. The apparatus of claim 13, wherein the means for determining comprises:

the road network acquisition unit is used for acquiring a target traffic road network corresponding to the target area;

and 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 intersection points in the target traffic road network.

15. The apparatus of claim 14, wherein the topology map determination unit comprises:

the conversion subunit is used for taking the road in the target traffic network as a road node and taking the intersection point between any two roads as an edge;

and the generating 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.

16. The apparatus of any one of claims 13-15, wherein the differential operator is a laplacian operator, the determining means comprising:

an entry degree determining unit, configured to determine, for each road node in the road network topological graph, the number of edges pointing to the road node, and determine the number of edges as an entry degree of the road node;

the entrance matrix generating unit is used for generating an entrance matrix corresponding to the road network topological graph according to the entrances 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 an intersection point corresponding to each edge in the road network topological graph, and determining the weight of the edge according to the traffic flow and/or the importance;

the weight matrix generating unit is used for generating a weight matrix corresponding to the road network topological graph according to the weights corresponding to all edges in the road network topological graph;

and the matrix calculation unit is used for calculating a Laplace matrix corresponding to the road network topological graph according to the entrance matrix and the weight matrix.

17. The apparatus of claim 16, wherein the matrix computation unit comprises:

and the matrix processing subunit is configured to perform matrix subtraction on the entry matrix and the weight matrix to obtain a laplacian matrix corresponding to the road network topological graph.

18. The apparatus of any of claims 13-17, wherein the means for dividing comprises:

an obtaining unit, configured to obtain a road network partitioning request, where the road network partitioning request includes the preset connection relationship, and the preset connection relationship includes the number of edges between the associated node and the road node;

the node determining unit is used for determining associated nodes which accord with a preset connection relation with the road nodes in the road network topological graph aiming at the road nodes according to the road network division 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 aiming at each road node.

19. The apparatus according to any one of claims 13-18, wherein the traffic element information includes a road network structure, traffic facilities, and trajectory information within a preset area around the road node;

the processing module comprises:

the spatial information determining unit is used for determining a road network structure and traffic facilities in a preset area around the road node as the spatial information corresponding to the road node;

and the time sequence information determining unit is used for 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.

20. The apparatus of any of claims 16-19, the computing module comprising:

the spatial continuous data calculation unit is used for calculating spatial continuous data corresponding to the local topological graph according to the road nodes in the local topological graph, the spatial information corresponding to the associated nodes and the differential operator aiming at each local topological graph;

the time sequence continuous data calculation unit is used for calculating time sequence continuous data corresponding to the local topological graph according to the road nodes in the local topological graph, time sequence information corresponding to the associated nodes 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.

21. The apparatus of claim 20, wherein the time-series consecutive data calculation unit comprises:

the adjusting subunit is configured to perform an adjusting operation on the spatial continuous data and the time-series continuous data according to a preset data format, so as to obtain the spatial continuous data and the time-series continuous data with the same data format;

the fusion subunit is configured to perform data fusion operation on the spatial continuous data and the time-series 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.

22. The apparatus of claim 21, 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 the width, the length, the number of lanes, the function level and the traffic condition of the road;

the vector determination module is used for determining the road characteristic vector corresponding to the target traffic road network according to the attribute information corresponding to each road;

the determining subunit is to:

and carrying out data splicing operation on the fused continuous data and the road characteristic vector to obtain the target continuous data.

23. The apparatus of any of claims 13-22, wherein the optimization module comprises:

the device comprises a request acquisition unit, a road network optimization unit and a control unit, wherein the request acquisition unit is used for acquiring a road network optimization request, and the road network optimization request comprises an optimization demand;

and the optimization unit is used for performing data processing on the target continuous data corresponding to the local topological graphs by adopting a network model corresponding to the optimization requirement according to the road network optimization request.

24. The apparatus of any of claims 13-23, further comprising:

and the clustering module is used for clustering the target continuous data corresponding to the local topological graph by adopting a preset clustering algorithm.

25. An electronic device, comprising:

at least one processor; and

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 1-12.

26. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-12.

27. A computer program product comprising a computer program which, when executed by a processor, carries out the steps of the method of any one of claims 1 to 12.