Power distribution network contact sketch generation method, device, equipment, medium and program

Abstract

The invention provides a power distribution network contact diagram generation method, device and equipment, a medium and a program. Relates to the technical field of power management. The method comprises the steps of obtaining a first image feature, geographic information system (GIS) data and environmental parameters of a power distribution network in a target area, and determining a matching threshold value of each second component based on the environmental parameters and basic attributes of each second component; respectively calculating the matching degree between each first component and each second component; if the matching degree between a first target component in the first component and each second component is lower than a matching threshold value corresponding to the second component, adjusting a first image feature corresponding to the first target component based on GIS data corresponding to the second component to obtain an adjusted second image feature of the first target component; and based on the target image features and GIS data corresponding to each first component, constructing a power distribution network contact diagram. According to the method and the device, an effect of quickly and accurately generating the contact sketch is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power management, and particularly relates to a power distribution network connection diagram generation method and device, equipment, medium and program. BACKGROUND

[0002] Due to the acceleration of urbanization and the growth of electricity demand, the structure of the power distribution network is becoming increasingly complex, which puts higher requirements on the design, operation and maintenance of the power distribution network. How to quickly and accurately grasp the state information of the power distribution network is crucial to ensure power supply reliability.

[0003] In related technologies, the layout of the power distribution network is manually drawn to update the GIS data, which cannot update the layout of the power distribution network in a timely manner, and has the problems of low efficiency and high error rate.

[0004] Therefore, there is an urgent need for a power distribution network connection diagram generation scheme that can quickly and accurately generate a connection diagram. SUMMARY

[0005] The present application provides a power distribution network connection diagram generation method, device, equipment, medium and program to achieve the effect of quickly and accurately generating a connection diagram.

[0006] In a first aspect, the present application provides a power distribution network connection diagram generation method, comprising:

[0007] Obtaining the first image feature, geographic information system (GIS) data and environmental parameters of the power distribution network in the target area, wherein the first image feature includes a plurality of first components, and the GIS data includes a plurality of second components and the basic attributes corresponding to each second component;

[0008] Based on the environmental parameters and the basic attributes of each second component, the matching threshold of each second component is determined respectively;

[0009] The matching degree between each first component and each second component is calculated respectively;

[0010] If the matching degree between the first target component in the first component and each second component is lower than the matching threshold corresponding to the second component, the first image feature corresponding to the first target component is adjusted based on the GIS data corresponding to the second component to obtain the second image feature of the first target component after adjustment. The first target component is any one of the first components;

[0011] Based on the target image feature corresponding to each first component and the GIS data, a power distribution network connection diagram is constructed, and the target image feature includes the first image feature or the second image feature.

[0012] In one possible implementation, the image features include first coordinates, first attributes, and first connectivity relationships for each first component; the GIS data includes second coordinates, second attributes, and second connectivity relationships for each second component; and a simplified power distribution network interconnection diagram is constructed based on the target image features and GIS data corresponding to each first component, including:

[0013] Based on the features of the target image, a second target component is determined for each first component; the second target component is the one that matches the first component the most.

[0014] By using the iterative nearest point algorithm, the first coordinates of each first component and the second coordinates of each second target component are registered to obtain the registered position coordinates of each first component.

[0015] Based on the location coordinates and first connection relationship of each first component, and the second connection relationship of the second target component, the connection relationship between different components in the distribution network interconnection diagram is generated by the shortest path algorithm, and a topology diagram is obtained.

[0016] Based on the first attribute of each first component and the second attribute of each second target component, the attribute characteristics of each first component in the topology diagram are determined, and the distribution network interconnection diagram is obtained.

[0017] In one possible implementation, based on the GIS data corresponding to the second component, the first image features corresponding to the first target component are adjusted to obtain the adjusted second image features of the first target component, including:

[0018] The coordinates of each first component are adjusted using gradient descent to obtain the adjusted first coordinates; and / or, based on the second attribute of the second component corresponding to each first component, the first attribute of each first component is adjusted in the pre-trained generative adversarial network to obtain the adjusted first attribute of each first component.

[0019] Based on the adjusted first coordinates and first attributes of each first component, the image features corresponding to the first component are obtained;

[0020] If the matching degree of the set component is greater than or equal to the matching threshold, the image feature is used as the second image feature corresponding to the set component; wherein, the set component is any one of the first components;

[0021] If the matching degree of the set component is less than the matching threshold, readjust the first coordinate and first attribute of the set component until the matching degree of the obtained image features is equal to or greater than the matching threshold.

[0022] In one possible implementation, the degree of matching between each first component and each second component is calculated, including:

[0023] The distance metric is performed on the first coordinate of each first component and the second coordinate of each second component to obtain the coordinate similarity between each first component and each second component.

[0024] The morphological similarity between each first component and each second component is obtained by comparing the similarity between the first attribute of each first component and the second attribute of each second component.

[0025] The topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component;

[0026] Based on the coordinate similarity, morphological similarity, and topological similarity of each first component, the matching degree between each first component and each second component is obtained.

[0027] In one possible implementation, the topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component, including:

[0028] The first connection relationship of each first component is represented as a first adjacency matrix, and the second connection relationship of each second component is represented as a second adjacency matrix;

[0029] The topological similarity between each first component and each second component is obtained by comparing the ratio of the number of common connections between the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component to the total number of connections.

[0030] In one possible implementation, a matching threshold for each second component is determined based on environmental parameters and the fundamental attributes of each second component, including:

[0031] By using environmental parameters as input to the environmental impact model, the matching deviation of each second component is obtained.

[0032] Based on the basic attributes of each second component and the reliability level of the distribution network, the attribute weight threshold of each second component is obtained;

[0033] Based on the matching deviation and attribute weight threshold of each second component, the matching threshold of each second component is determined.

[0034] In one possible implementation, based on the fundamental attributes of each second component and the reliability level of the distribution network, an attribute weight threshold for each second component is obtained, including:

[0035] Based on the basic attributes of each second component and the reliability level of the distribution network, a judgment matrix for each second component is obtained;

[0036] The weight of each second component is determined based on the eigenvector corresponding to the largest eigenvalue of the judgment matrix of each second component.

[0037] The basic properties of each second component are standardized to obtain the standard properties of each second component.

[0038] Based on the weight of each second component, the standard attributes of each second component are weighted and fused to obtain the weighted attributes of each second component;

[0039] Based on the mapping relationship between the weighted attributes and historical weights of each second component, the attribute weight threshold of each second component is obtained.

[0040] In one possible implementation, the matching threshold for each second component is determined based on the matching deviation and attribute weight threshold of each second component, including:

[0041] Based on the historical matching deviation and matching deviation of each second component, determine the matching deviation confidence level of each second component;

[0042] Based on the historical attribute weight threshold and attribute weight threshold of each second component, the rate of change of attribute weight threshold of each second component is obtained;

[0043] The matching deviation weight and attribute weight of each second component are determined based on the ratio between the matching deviation confidence and the rate of change of the attribute weight threshold for each second component.

[0044] The matching threshold for each second component is determined based on the matching deviation, matching deviation weight, attribute weight, and attribute weight change rate for each second component.

[0045] In one possible implementation, before calculating the matching degree between each first component and each second component, the method further includes:

[0046] An affine transformation is performed on the first coordinate of the first component and the second coordinate between the second component to align the coordinate system corresponding to the first coordinate with the coordinate system corresponding to the second coordinate, thus obtaining the alignment coordinates of each first component;

[0047] The first coordinate in the first image feature is replaced with the alignment coordinate of each first component to obtain the third image feature;

[0048] Accordingly, by comparing the similarity between image features and GIS data, the matching degree of each component is obtained, including:

[0049] By comparing the similarity between the first component in the third image features and each second component in the GIS data, the matching degree between each second component and the first component is obtained.

[0050] Secondly, this application provides a distribution network interconnection diagram generation device, comprising:

[0051] The acquisition module is used to acquire the first image features, geographic information system (GIS) data, and environmental parameters of the power distribution network within the target area. The first image features include multiple first components, and the GIS data includes multiple second components and basic attributes corresponding to each second component.

[0052] The processing module is used to determine the matching threshold of each second component based on environmental parameters and the basic attributes of each second component; calculate the matching degree between each first component and each second component; if the matching degree between the first target component in the first component and each second component is lower than the matching threshold corresponding to the second component, adjust the first image feature corresponding to the first target component based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component; the first target component is any component in the first component; and construct a simplified diagram of the power distribution network interconnection based on the target image feature and GIS data corresponding to each first component, wherein the target image feature includes either the first image feature or the second image feature.

[0053] In one possible implementation, the image features include first coordinates, first attributes, and first connectivity relationships for each first component; the GIS data includes second coordinates, second attributes, and second connectivity relationships for each second component; and the processing module is specifically used for:

[0054] Based on the features of the target image, a second target component is determined for each first component; the second target component is the one that matches the first component the most.

[0055] By using the iterative nearest point algorithm, the first coordinates of each first component and the second coordinates of each second target component are registered to obtain the registered position coordinates of each first component.

[0056] Based on the location coordinates and first connection relationship of each first component, and the second connection relationship of the second target component, the connection relationship between different components in the distribution network interconnection diagram is generated by the shortest path algorithm, and a topology diagram is obtained.

[0057] Based on the first attribute of each first component and the second attribute of each second target component, the attribute characteristics of each first component in the topology diagram are determined, and the distribution network interconnection diagram is obtained.

[0058] In one possible implementation, the processing module is specifically used for:

[0059] The coordinates of each first component are adjusted using gradient descent to obtain the adjusted first coordinates; and / or, based on the second attribute of the second component corresponding to each first component, the first attribute of each first component is adjusted in the pre-trained generative adversarial network to obtain the adjusted first attribute of each first component.

[0060] Based on the adjusted first coordinates and first attributes of each first component, the image features corresponding to the first component are obtained;

[0061] If the matching degree of the set component is greater than or equal to the matching threshold, the image feature is used as the second image feature corresponding to the set component; wherein, the set component is any one of the first components;

[0062] If the matching degree of the set component is less than the matching threshold, readjust the first coordinate and first attribute of the set component until the matching degree of the obtained image features is equal to or greater than the matching threshold.

[0063] In one possible implementation, the processing module is specifically used for:

[0064] The distance metric is performed on the first coordinate of each first component and the second coordinate of each second component to obtain the coordinate similarity between each first component and each second component.

[0065] The morphological similarity between each first component and each second component is obtained by comparing the similarity between the first attribute of each first component and the second attribute of each second component.

[0066] The topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component;

[0067] Based on the coordinate similarity, morphological similarity, and topological similarity of each first component, the matching degree between each first component and each second component is obtained.

[0068] In one possible implementation, the processing module is further configured to:

[0069] The first connection relationship of each first component is represented as a first adjacency matrix, and the second connection relationship of each second component is represented as a second adjacency matrix;

[0070] The topological similarity between each first component and each second component is obtained by comparing the ratio of the number of common connections between the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component to the total number of connections.

[0071] In one possible implementation, the processing module is specifically used for:

[0072] By using environmental parameters as input to the environmental impact model, the matching deviation of each second component is obtained.

[0073] Based on the basic attributes of each second component and the reliability level of the distribution network, the attribute weight threshold of each second component is obtained;

[0074] Based on the matching deviation and attribute weight threshold of each second component, the matching threshold of each second component is determined.

[0075] In one possible implementation, the processing module is further configured to:

[0076] Based on the basic attributes of each second component and the reliability level of the distribution network, a judgment matrix for each second component is obtained;

[0077] The weight of each second component is determined based on the eigenvector corresponding to the largest eigenvalue of the judgment matrix of each second component.

[0078] The basic properties of each second component are standardized to obtain the standard properties of each second component.

[0079] Based on the weight of each second component, the standard attributes of each second component are weighted and fused to obtain the weighted attributes of each second component;

[0080] Based on the mapping relationship between the weighted attributes and historical weights of each second component, the attribute weight threshold of each second component is obtained.

[0081] In one possible implementation, the processing module is further configured to:

[0082] Based on the historical matching deviation and matching deviation of each second component, determine the matching deviation confidence level of each second component;

[0083] Based on the historical attribute weight threshold and attribute weight threshold of each second component, the rate of change of attribute weight threshold of each second component is obtained;

[0084] The matching deviation weight and attribute weight of each second component are determined based on the ratio between the matching deviation confidence and the rate of change of the attribute weight threshold for each second component.

[0085] The matching threshold for each second component is determined based on the matching deviation, matching deviation weight, attribute weight, and attribute weight change rate for each second component.

[0086] In one possible implementation, before determining the matching degree between each second component and the first component by comparing the similarity between the first component in the first image features and each second component in the GIS data, the processing module is further configured to:

[0087] An affine transformation is performed on the first coordinate of the first component and the second coordinate between the second component to align the coordinate system corresponding to the first coordinate with the coordinate system corresponding to the second coordinate, thus obtaining the alignment coordinates of each first component;

[0088] The first coordinate in the first image feature is replaced with the alignment coordinate of each first component to obtain the third image feature;

[0089] Accordingly, the matching degree between each first component and each second component is calculated separately, including:

[0090] By comparing the degree of matching between the first component and each second component in the third image features.

[0091] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0092] The memory stores the instructions that the computer executes;

[0093] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0094] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0095] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0096] The distribution network interconnection diagram generation method, apparatus, equipment, medium, and program provided in this application, by acquiring first image features, Geographic Information System (GIS) data, and environmental parameters of the distribution network within a target area, perceive the distribution network from multiple dimensions. This enables real-time monitoring of distribution network status changes and line connectivity, allowing for timely detection of potential problems and faults. Based on environmental parameters and the basic attributes of each second component, a matching threshold is determined for each second component, ensuring that the matching threshold used when matching the first and second components can better adapt to various complex environments and effectively perform matching under different conditions. By comparing the similarity between the first component in the first image features and each second component in the GIS data, the association between the first component in the first image features and each second component in the GIS data is accurately established, yielding the matching degree between each second component and the first component. The matching degree determines any potential differences between the first component in the first image features and each second component in the GIS data. If the matching degree between the second component and each of the first components is lower than the matching threshold corresponding to the second component, it indicates that there may be problems such as recognition errors and inaccurate information in the first image features. Therefore, based on the GIS data corresponding to the second component, the first image features corresponding to the first component are adjusted to obtain the adjusted second image features of each first component. The second image features can more realistically reflect the actual situation of the distribution network equipment. Based on the target image features and GIS data corresponding to each first component, a simplified distribution network interconnection diagram that can display the total components of the distribution network and the connection relationships between components is constructed. Through the simplified distribution network interconnection diagram, the dynamic changes of the distribution network can be captured in a timely manner, avoiding information lag and ensuring the timeliness of distribution network information. Attached Figure Description

[0097] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0098] Figure 1 A schematic diagram illustrating a scenario for the distribution network interconnection diagram generation method provided in this application embodiment;

[0099] Figure 2 A flowchart illustrating the method for generating simplified distribution network interconnection diagrams provided in this application embodiment. Figure 1 ;

[0100] Figure 3 A flowchart illustrating the method for generating simplified distribution network interconnection diagrams provided in this application embodiment. Figure 2 ;

[0101] Figure 4 This is a schematic diagram of the distribution network interconnection diagram generation device provided in the embodiments of this application;

[0102] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0103] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0104] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0105] In related technologies, manually drawing layout diagrams suffers from low efficiency and accuracy. Manually drawn diagrams cannot reflect the actual condition of the distribution network in real time, leading to significant delays in troubleshooting, maintenance, and scheduling. Therefore, there is an urgent need for a solution that can automatically generate simplified distribution network interconnection diagrams.

[0106] The distribution network interconnection diagram generation method provided in this application determines the matching threshold for each second component based on environmental parameters and the basic attributes of each second component. This allows the matching threshold used when matching the first and second components to better adapt to various complex environments, enabling effective matching under different conditions. By comparing the similarity between the first component in the first image features and each second component in the GIS data, the association between the first component in the first image features and each second component in the GIS data is accurately established, yielding the matching degree between each second component and the first component. The matching degree can determine potential differences between the first component in the first image features and each second component in the GIS data. If the matching degree between the second component and each first component is lower than the matching threshold corresponding to the second component, it indicates that there may be identification errors or inaccurate information in the first image features. In this case, based on the GIS data corresponding to the second component, the first image features corresponding to the first component are adjusted to obtain the adjusted second image features for each first component. These adjusted second image features more realistically reflect the actual situation of the distribution network equipment. Based on the target image features and GIS data corresponding to each first component, a simplified distribution network interconnection diagram is constructed that can display the total components of the distribution network and the connection relationships between components. This diagram enables timely and real-time capture of dynamic changes in the distribution network, avoiding information lag and ensuring the timeliness of distribution network information.

[0107] Figure 1 This is a schematic diagram illustrating a scenario for the method of generating simplified distribution network interconnection diagrams provided in this application. For example... Figure 1 As shown, the specific application scenarios of this application include data center 11, acquisition center 12, processing center 13, and power distribution network 14. Among them:

[0108] Data center 11 stores GIS data of distribution network 14, first image features of distribution network 14 collected by acquisition center 12, and second and third image features obtained by processing the first image features.

[0109] The acquisition center 12 is equipped with multiple data collectors 121 and identifiers 122. Each data collector 121 can be used to collect image feature data from the power distribution network 14. The identifier 122 is used to identify the first image feature from the image feature data collected by the data collector 121.

[0110] The processing center 13 is used to construct a simplified diagram of the distribution network connection based on the GIS data of the distribution network 14 and the first image features of the distribution network 14 collected by the acquisition center 12, and based on the distribution network connection diagram generation method.

[0111] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0112] Figure 2 A flowchart illustrating the method for generating simplified distribution network interconnection diagrams provided in this application embodiment. Figure 1 .like Figure 2 As shown, the method includes:

[0113] S201. Obtain the first image features, GIS data and environmental parameters of the power distribution network within the target area, wherein the first image features include multiple first components, and the GIS data includes multiple second components and basic attributes corresponding to each second component.

[0114] The first image feature is a layout image of the power distribution network within the target area, captured by a camera pan-tilt-zoom (PTZ) or a camera-capable drone. This first image feature includes image features of multiple first components within the power distribution network within the target area. These first components include electrical equipment such as transformers, switches, and lines. The image features of each first component include its outline, coordinates, shape, and topology. The Geographic Information System (GIS) data includes multiple second components within the power distribution network within the target area and the basic attributes corresponding to each second component. These basic attributes include technical information such as the equipment type, rated load, and geographic coordinates of the second component.

[0115] Environmental parameters refer to environmental information such as temperature, wind speed, humidity, and soil resistivity within the target area that affect the operation of the power distribution network. These environmental parameters influence the performance and matching accuracy of different components within the power distribution network.

[0116] There are some similarities between the second component in the GIS data and the first component in the first image features. Spatially, the geographic features of the second component in the GIS data and the corresponding geographic features of the first component in the first image features may be located in the same or similar geographic locations in the real world. That is, the location coordinates of the first component and the location coordinates of the second component show a certain spatial correspondence. Geometrically, the outline of the second component in the GIS data and the outline of the first component extracted from the first image features may be similar. From a semantic analysis perspective, both the GIS data and the first image features represent information about the power distribution network within the target area. The similarity between the GIS data and the first image features provides a comprehensive and accurate data foundation for constructing a simplified diagram of the power distribution network interconnection.

[0117] For example, a drone equipped with a high-definition camera is used to conduct aerial photography of the power distribution network within a target area, acquiring the first image features of the power distribution network within the target area. GIS data of the power distribution network within the target area is extracted from a local GIS database. A sensor network is deployed within the power distribution network within the target area to collect environmental parameters in real time.

[0118] S202. Based on environmental parameters and the basic attributes of each second component, determine the matching threshold for each second component.

[0119] By analyzing the impact of environmental parameters on the relationship between the second and first components, and considering the fundamental attributes of the second components, a matching threshold is determined for each second component. This allows the matching threshold to adapt to different environmental conditions and component characteristics, thereby improving the accuracy and flexibility of the matching between the second and first components. The matching threshold is the critical value used to determine whether the first and second components are matched. Fundamental attributes are the inherent characteristics of the second component, such as its equipment type, rated capacity, years of operation, and maintenance records.

[0120] S203. Calculate the matching degree between each first component and each second component respectively.

[0121] By measuring the correspondence between a first component in the first image features and a second component in the GIS data, the degree of similarity between the first and second components in terms of coordinates, topology, and morphology is obtained. Then, based on the degree of similarity between the first and second components in terms of coordinates, topology, and morphology, the matching degree between each second component and the first component is obtained.

[0122] Specifically, if the first component includes first component A and first component B, and the second component includes second component a and second component b, then the matching degree includes the similarity between first component A and second component a; the similarity between first component A and second component b; the similarity between first component B and second component a; and the similarity between first component B and second component b.

[0123] By comparing the matching degree between the first and second components from different dimensions such as coordinates, topology, and morphology, we can ensure the comprehensiveness and accuracy of the obtained matching degree between the first and second components, which helps to discover subtle differences between the first and second components.

[0124] Optionally, an object detection algorithm is used to extract the coordinates, topological connectivity, and morphological parameters of the first component from the first image features, while simultaneously parsing the coordinates, topological connectivity, and morphological parameters of the second component from the GIS data. By comparing the coordinate differences, the overlap ratio of the topological connectivity, and the similarity of the morphological parameters between the first and second components, the similarity between the first and second components is calculated, thus obtaining the matching degree between each second component and the first component.

[0125] S204. If the matching degree between the first target component in the first component and each second component is lower than the matching threshold corresponding to the second component, adjust the first image feature corresponding to the first target component based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component; the first target component is any component in the first component.

[0126] When the matching degree between the first target component and the second component is lower than the matching threshold corresponding to the second component, it indicates that the first image features may not accurately reflect the actual state of the distribution network. Adjustments to the first image features are needed to reduce acquisition errors and improve matching accuracy. The first image features corresponding to the first target component are adjusted using the GIS data corresponding to the second component, resulting in the adjusted second image features. These adjustments ensure that all first components can be matched to appropriate locations in the final constructed simplified distribution network interconnection diagram.

[0127] For example, if the matching degree between the coordinates of the second component and each first target component is lower than the matching threshold of the second component, the gradient descent method is used to gradually adjust the position coordinates in the first image features corresponding to the first target component, so that the position coordinates of the first target component gradually approach the position coordinates of the second component with the highest matching degree in the GIS data. Optionally, the learning rate of the gradient descent method is set to 0.001, and the number of iterations is set to 10.

[0128] S205. Based on the target image features and GIS data corresponding to each first component, construct a simplified diagram of the power distribution network connection. The target image features include first image features or second image features.

[0129] The target image feature can be a second image feature that has been adjusted to meet the matching threshold requirement, or it can be the original first image feature. Specifically, if the matching degree between the second component and each first component is equal to or equal to the matching threshold value corresponding to the second component, no adjustment is needed to the first image feature corresponding to the first component, and the target image feature is the first image feature. If the matching degree between the second component and each first component is lower than the matching threshold value corresponding to the second component, the first image feature corresponding to the first component needs to be adjusted, and the target image feature is the second image feature.

[0130] Based on the target image features and GIS data corresponding to each first component, a simplified diagram of the distribution network interconnection is jointly constructed to ensure that each component in the simplified diagram accurately reflects the actual state and location of the distribution network. This makes the constructed simplified diagram of the distribution network interconnection highly accurate and practical, and can provide strong support for the design, operation and maintenance of the distribution network.

[0131] The distribution network interconnection diagram generation method provided in this application obtains first image features, Geographic Information System (GIS) data, and environmental parameters of the distribution network within a target area. This allows for multi-dimensional perception of the distribution network, enabling real-time monitoring of network status changes and line connectivity, and timely detection of potential problems and faults. Based on environmental parameters and the basic attributes of each second component, a matching threshold is determined for each second component. This ensures that the matching threshold used when matching the first and second components is better adapted to various complex environments, enabling effective matching under different conditions. By comparing the similarity between the first component in the first image features and each second component in the GIS data, the association between the first component in the first image features and each second component in the GIS data is accurately established, yielding the matching degree between each second component and the first component. The matching degree determines potential differences between the first component in the first image features and each second component in the GIS data. If the matching degree between the second component and each of the first components is lower than the matching threshold corresponding to the second component, it indicates that there may be problems such as recognition errors and inaccurate information in the first image features. Therefore, based on the GIS data corresponding to the second component, the first image features corresponding to the first component are adjusted to obtain the adjusted second image features of each first component. The second image features can more realistically reflect the actual situation of the distribution network equipment. Based on the target image features and GIS data corresponding to each first component, a simplified distribution network interconnection diagram that can display the total components of the distribution network and the connection relationships between components is constructed. Through the simplified distribution network interconnection diagram, the dynamic changes of the distribution network can be captured in a timely manner, avoiding information lag and ensuring the timeliness of distribution network information.

[0132] Figure 3 A flowchart illustrating the method for generating simplified distribution network interconnection diagrams provided in this application embodiment. Figure 2 .like Figure 3 As shown, in this embodiment... Figure 2 Based on the embodiments, the method for generating simplified diagrams of distribution network interconnections is described in detail. The method includes:

[0133] Optionally, the image features include the first coordinates, first attributes, and first connectivity of each first component, and the GIS data includes the second coordinates, second attributes, and second connectivity of each second component.

[0134] In one possible implementation, step S202 may further include:

[0135] S2021. Using environmental parameters as input to the environmental impact model, the matching deviation of each second component is obtained.

[0136] The environmental impact model is a pre-trained model that quantifies the influence of different environmental parameters on the performance and matching accuracy of the second component. Trained using historical data and machine learning algorithms, the model predicts matching deviations that will occur when different second components are matched under varying environmental conditions. Matching deviation is the difference between the expected and actual matching degrees between image features and GIS features due to environmental factors, reflecting the degree to which environmental factors affect matching accuracy.

[0137] Optionally, the environmental impact model is a pre-trained random forest model.

[0138] S2022. Based on the basic attributes of each second component and the reliability level of the distribution network, obtain the attribute weight threshold for each second component.

[0139] By considering the fundamental attributes of components and the reliability level of the distribution network, the weights of different fundamental attributes of the second component in the matching threshold calculation can be allocated more rationally, resulting in an attribute weight threshold for each second component, thus improving the targeting and accuracy of the matching. The reliability level of the distribution network is a classification based on factors such as the overall operating status of the distribution network, historical fault records, and load importance, representing the distribution network's tolerance and recovery capability to faults. The attribute weight threshold is used to measure the importance of the fundamental attributes in the matching threshold calculation.

[0140] S2023. Based on the matching deviation and attribute weight threshold of each second component, determine the matching threshold of each second component.

[0141] By comprehensively considering the matching deviation and attribute weight threshold of each second component, it can be ensured that the obtained matching threshold can reflect both the impact of environmental factors and the requirements of the basic attributes of the components and the reliability level of the distribution network, thereby improving the accuracy and reliability of the matching.

[0142] Optionally, the adjustment amount of the matching threshold for each second component is determined based on the matching deviation and attribute weight thresholds. Then, the matching threshold for each second component is determined based on the adjusted matching threshold and the base matching threshold. For example, if the second component is a transformer component with a matching deviation of 0.05, and the weight threshold for "rated capacity" in the attribute weight thresholds is 0.7 and the weight threshold for "operating years" is 0.6, then the adjustment amount of the matching threshold for this transformer component can be determined by weighted summation as: 0.05 * 0.7 + 0.05 * 0.6 = 0.065. Then, based on the base matching threshold of 0.9 for this transformer component, the final matching threshold is obtained as 0.9 - 0.065 = 0.835.

[0143] Optionally, the matching threshold for each second component can be determined directly based on the matching deviation and attribute weight threshold.

[0144] In one possible implementation, step S203 may further include:

[0145] S2031. Perform distance measurement on the first coordinate of each first component and the second coordinate of each second component to obtain the coordinate similarity between each first component and each second component.

[0146] Based on the first coordinates of the first component and the second coordinates of each second component, a distance metric is performed on the first and second coordinates to obtain a distance value between them. This distance value measures the similarity or difference between the first and second coordinates. Then, based on the distance value between the first and second coordinates, the coordinate similarity between each first component and each second component is obtained. Optionally, the distance metric can be Euclidean distance, Manhattan distance, and / or cosine similarity distance.

[0147] Specifically, the coordinate similarity between each first component and each second component is obtained by normalizing or transforming the distance between the first and second coordinates. The coordinate similarity value typically ranges from 0 to 1. The larger the coordinate similarity value, the closer the first component and each second component are in coordinate space, i.e., the higher the coordinate similarity.

[0148] S2032. By comparing the similarity between the first attribute of each first component and the second attribute of each second component, the morphological similarity between each first component and each second component is obtained.

[0149] The first attribute describes the component characteristics of the first component. The second attribute describes the component characteristics of the second component. Component characteristics are used to describe the form and function of the component. By comparing the first attribute of the first component and the second attribute of each second component, the degree of similarity between the first and second components in form or function can be evaluated.

[0150] S2033. Measure the topological similarity between the first connection relationship of each first component and the second connection relationship of each second component to obtain the topological similarity between each first component and each second component.

[0151] The topological similarity between each first component and each second component in the distribution network is obtained by measuring the degree of topological similarity between the first connection relationship of each first component and the second connection relationship of each second component. The first connection relationship describes the electrical connection method of the first component in the distribution network; the second connection relationship describes the electrical connection method of the second component in the distribution network. By analyzing the first connection relationship, the location and function of the first component in the distribution network can be determined. By analyzing the second connection relationship, the location and function of the second component in the distribution network can be determined. Optionally, the electrical connection methods in the distribution network include series and parallel connections.

[0152] Optionally, the method for measuring topological similarity can be either a topological similarity determination method based on the shortest path algorithm or a topological similarity determination method based on the subgraph isomorphism algorithm.

[0153] For example, suppose we assume that topological similarity is determined using a subgraph isomorphism algorithm. First, we extract a first subgraph consisting of a first component and its adjacent components, and a second subgraph consisting of a second component and its adjacent components. Then, we use a subgraph isomorphism algorithm to determine whether the first and second subgraphs are isomorphic. If they are isomorphic, the topological similarity is 1; otherwise, the topological similarity can be quantified based on the degree of isomorphism or by calculating the edit distance between the first and second subgraphs.

[0154] Specifically, the topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component, which may further include:

[0155] Step 1: Represent the first connection relationship of each first component as a first adjacency matrix, and represent the second connection relationship of each second component as a second adjacency matrix.

[0156] The rows and columns of the first adjacency matrix represent the first components in the distribution network, and the elements in the first adjacency matrix indicate whether there is a connection relationship between the first components. The rows and columns of the second adjacency matrix represent the second components in the distribution network, and the elements in the second adjacency matrix indicate whether there is a connection relationship between the second components.

[0157] For example, if the first component includes first component A, first component B, and first component C, where first component A is connected to first component B, and first component B is connected to first component C, then the first connection relationship of the first component is as shown in Table 1:

[0158] Table 1 First Connection Relationship of the First Component

[0159]

[0160] Here, 1 indicates that there is a connection between components, and 0 indicates that there is no connection between components. The first adjacency matrix of the first component can be represented as:

[0161]

[0162] Step 2: By comparing the ratio of the number of common connections between the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component to the total number of connections, the topological similarity between each first component and each second component is obtained.

[0163] By comparing the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component, the number of common connections and the total number of connections between the first and second adjacency matrices are determined. The total number of connections can be the sum of the number of connections in the first and second adjacency matrices, or the average of the number of connections in the first and second adjacency matrices. Then, based on the ratio of the number of connections to the total number of connections, the topological similarity between each first component and each second component is obtained.

[0164] For example, suppose the number of connections shared between the first adjacency matrix of component A in the first component and the second adjacency matrix of component B in the second component is 2, and the total number of connections between the first and second adjacency matrices is 3. Then the topological similarity between component A and component B is 2 / 3 ≈ 0.67.

[0165] S2034. Based on the coordinate similarity, morphological similarity and topological similarity of each first component, obtain the matching degree between each first component and each second component.

[0166] Coordinate similarity, morphological similarity, and topological similarity evaluate the similarity between the first and second components from three aspects: spatial location, morphological features, and topological structure, respectively. Optionally, a weighted average is used to calculate the weighted average of the coordinate similarity, morphological similarity, and topological similarity of the first component to obtain the matching degree between each first component and each second component. Optionally, a multiplicative composite value is calculated based on the coordinate similarity, morphological similarity, and topological similarity of the first component to obtain the matching degree between each first component and each second component.

[0167] In one possible implementation, step S204 above, which adjusts the first image features corresponding to the first component based on the GIS data corresponding to the second component to obtain the adjusted second image features for each first component, may further include:

[0168] S2041. Adjust the coordinates of each first component using gradient descent to obtain the adjusted first coordinates; and / or, based on the second attribute of the second component corresponding to each first component, adjust the first attribute of each first component in the pre-trained generative adversarial network to obtain the adjusted first attribute of each first component.

[0169] Gradient descent minimizes the difference between the first component's first coordinate and the second coordinate in the GIS data by iteratively adjusting the first coordinate of the first component. In each iteration, gradient descent calculates the gradient based on the first coordinate of the first component and adjusts the first coordinate in the opposite direction of the gradient to gradually approach the second coordinate, resulting in the adjusted first coordinate. Generative adversarial networks (GANs) are neural networks trained on attribute datasets, consisting of a generator and a discriminator. GANs can generate adjustment criteria for the first attribute based on the second attribute of the second component and the first attribute of the first component. The first attribute is then adjusted based on these criteria to obtain the adjusted first attribute for each first component. Optionally, the maximum number of iterations for a GAN is set to 10.

[0170] S2042. Based on the adjusted first coordinates and first attributes of each first component, obtain the image features corresponding to the first component.

[0171] By combining the adjusted first coordinates and first attributes of each first component, image features corresponding to the first component are generated. These image features can more accurately reflect the actual state and position of the first component, improving their quality and usability.

[0172] S2043. If the matching degree of the set component is greater than or equal to the matching threshold, the image feature is used as the second image feature corresponding to the set component, wherein the set component is any one of the first components.

[0173] If the matching degree of the set component is greater than or equal to the matching threshold, it means that the matching degree between the set component and the second component is high enough, and the currently generated image features can be used as the second image features of the set component. Here, the set component can be any one of the first components.

[0174] For example, if the first component includes a first component a, when the matching degree between the first component a and the second component is greater than or equal to the matching threshold, it indicates that the matching degree between the first component a and the second component is high enough, and the image features of the first component a are used as the second image features corresponding to the first component a.

[0175] S2044. If the matching degree of the set component is less than the matching threshold, readjust the first coordinate and first attribute of the set component until the matching degree of the obtained image feature is equal to or greater than the matching threshold.

[0176] If the matching degree of a component is less than the matching threshold, it means that the matching degree between the first component and the second component in the first image feature is not high enough. Therefore, it is necessary to readjust the first coordinates and first attributes in the first component and regenerate the image features until the matching degree of the generated image features reaches or exceeds the matching threshold.

[0177] In one possible implementation, the image features include first coordinates, first attributes, and first connectivity relationships for each first component, and the GIS data includes second coordinates, second attributes, and second connectivity relationships for each second component. Step S205 may further include:

[0178] S2051. Based on the features of the target image, determine the second target component corresponding to each first component; the second target component is the second component with the highest matching degree with the first component.

[0179] The second component that best matches each first component is identified as the second target component corresponding to that first component. The second target component is the second component most similar to the first component in the GIS data. Obtaining the second target component corresponding to each first component provides an accurate correspondence for subsequent coordinate registration, connection relationship generation, and attribute feature determination when generating simplified power distribution network interconnection diagrams, ensuring the consistency and accuracy of the power distribution network interconnection diagram generation process.

[0180] For example, if the first component includes: first component A, first component B, and first component C, and the second component includes: second component a, second component b, second component c, and second component d, and the matching degree between first component A and second components a, b, c, and d is calculated to be 0.6, 0.8, 0.5, and 0.7 respectively; the matching degree between first component B and second components a, b, c, and d is 0.7, 0.6, 0.9, and 0.5 respectively; and the matching degree between first component C and second components a, b, c, and d is 0.5, 0.7, 0.6, and 0.8 respectively, then the second component b corresponding to the maximum matching degree of first component A (0.8) is the second target component of first component A; the second component c corresponding to the maximum matching degree of first component B (0.9) is the second target component of first component B; and the second component d corresponding to the maximum matching degree of first component C (0.8) is the second target component of first component C.

[0181] S2052. By using the iterative nearest point algorithm, the first coordinates of each first component and the second coordinates of each second target component are registered to obtain the registered position coordinates of each first component.

[0182] The Iterative Closest Point Algorithm is a classic algorithm for point set registration. Through continuous iteration, it seeks the optimal rigid body transformation between the first coordinates of the first component and the second coordinates of the second target component, minimizing the distance between the transformed point set represented by the second coordinates of the second target component and the point set represented by the first coordinates of the first component.

[0183] The first coordinates of the first component are integrated to form a first coordinate point set, and the second coordinates of the second target component are integrated to form a second coordinate point set. Then, the first and second coordinate point sets are used as input to an iterative nearest-point algorithm. Through continuous iterative calculations of the algorithm, the first coordinate point set is adjusted so that it gradually approaches the second coordinate point set. The first coordinate point set that meets the convergence condition is used as the position coordinates of each first component after registration. This process accurately registers the first coordinates of the first component with the second coordinates of the second target component, eliminating positional deviations between the first and second coordinates, and ensuring that the positions of the components in the generated power distribution network interconnection diagram are consistent with their actual positions.

[0184] S2053. Based on the location coordinates and first connection relationship of each first component, and the second connection relationship of the second target component, the connection relationship between different components in the distribution network interconnection diagram is generated through the shortest path algorithm to obtain the topology diagram.

[0185] First, each first component is treated as a node in the topology graph, and the attributes of the nodes in the topology graph are set according to the position coordinates of the first component. Then, based on the shortest path algorithm and the first connection relationship and the second connection relationship of the second target component, edges that accurately describe the connection relationships between nodes in the topology graph are generated, resulting in the edges of the topology graph. Finally, the topology graph is constructed based on the nodes and edges of the topology graph.

[0186] Optionally, all connections in the first and second connection relationships are used as connections between nodes in the simplified topology graph. For example, if the first component includes first component A, first component B, and first component C, where first component A is connected to first component B, then the first connection relationship of first component A can be represented as [0,1,0]; if the second connection relationship of the second target component corresponding to first component A can be represented as [0,1,1], then the edges of the simplified topology graph are determined to be [0,1,1]. Here, 1 indicates a connection between nodes, and 0 indicates no connection between nodes.

[0187] Optionally, a connection that appears in both the first and second connection relationships is used as the connection relationship between nodes in the topology diagram. For example, if the first component includes first component A, first component B, and first component C, where first component A is connected to first component B, then the first connection relationship of first component A can be represented as [1,1,0]; if the second connection relationship of the second target component corresponding to first component A can be represented as [0,1,1], then the edges of the topology diagram are determined to be [0,1,0].

[0188] S2054. Based on the first attribute of each first component and the second attribute of the second target component corresponding to each first component, determine the attribute characteristics of each first component in the topology diagram to obtain the distribution network interconnection diagram.

[0189] The attributes that are the same between the first attribute of the first component and the second attribute of the corresponding second target component are directly used as the attribute features of the first component in the topology diagram; the average or weighted average of the similar attributes between the first attribute of the first component and the second attribute of the corresponding second target component are used as the attribute features of the first component in the topology diagram.

[0190] For example, if the first attribute of the first component A is a capacity of 100 MVA, and the second attribute of its second target component is a capacity of 120 MVA, the attribute characteristics of the first component A in the topology diagram are determined using a weighted average method. If the weight of the first attribute is 0.4 and the weight of the second attribute is 0.6, then the attribute characteristics of the first component A in the topology diagram are 100 × 0.4 + 120 × 0.6 = 40 + 72 = 112 MVA. Therefore, the capacity of the first component A in the topology diagram is 112 MVA.

[0191] Specifically, step S2022 above may further include:

[0192] Step 1: Based on the basic attributes of each second component and the reliability level of the distribution network, obtain the judgment matrix for each second component.

[0193] Based on the fundamental attributes representing the inherent characteristics of the second component and the reliability level of the distribution network, a judgment matrix for each second component is constructed using the analytic hierarchy process (AHP). The elements in the judgment matrix represent the relative importance ratios between different attributes or factors related to the reliability level. By constructing the judgment matrix, the complex relationship between fundamental attributes and reliability levels can be quantified, making the determination of attribute weight thresholds more reasonable. Furthermore, by performing multi-dimensional weight calculations on the fundamental attributes of the second component according to the reliability level of the distribution network, more accurate and reliable attribute weight thresholds can be obtained.

[0194] For example, if the second component is a transformer, the basic attributes of the transformer include capacity, voltage level, and impedance. The reliability level of the distribution network is divided into three levels: high, medium, and low. Taking capacity and voltage level as examples, if capacity is considered slightly more important than voltage level under a high reliability level, according to the scaling of the analytic hierarchy process (AHP), the element corresponding to capacity and voltage level in the judgment matrix can be set to 3, and the element corresponding to voltage level and capacity can be set to 1 / 3. All attributes and factors related to reliability level are compared sequentially to construct a complete judgment matrix. Optionally, the scaling of the AHP includes scales from 0 to 9, where a scale of 1 represents equal importance, and a scale of 3 represents slightly important.

[0195] Optionally, based on the basic attributes of each second component and the reliability level of the distribution network, the judgment matrix of each second component can be obtained by querying the power database.

[0196] Step 2: Determine the weight of each second component based on the eigenvector corresponding to the largest eigenvalue of the judgment matrix of each second component.

[0197] In the judgment matrix of each second component, find the largest eigenvalue. Then, based on the largest eigenvalue, find the eigenvector corresponding to the largest eigenvalue in the judgment matrix to obtain the target vector for each second component. Normalize the target vector for each second component so that the sum of all components in the target vector is 1, thus determining the weight of each second component.

[0198] For example, if the judgment matrix is ​​a 3×3 matrix, the largest eigenvalue of the judgment matrix can be obtained through mathematical calculation. ,as well as The corresponding feature vector is Then, the feature vectors... After normalization, the weights of the second component are obtained as follows: , where i = 1, 2, 3.

[0199] Step 3: Standardize the basic properties of each second component to obtain the standard properties of each second component.

[0200] Because the dimensions and numerical ranges of different basic attributes may vary significantly, directly using these basic attributes for calculations can lead to either an excessively large or insufficient impact on the results. Therefore, it is necessary to standardize the basic attributes of each second component, mapping the values ​​of different basic attributes to a unified range to obtain the standard attributes of each second component. Optionally, the unified range is [0,1].

[0201] Step 4: Based on the weight of each second component, perform weighted fusion of the standard attributes of each second component to obtain the weighted attributes of each second component.

[0202] Each standard attribute of each second component is multiplied by the weight of that second component to obtain a weighted standard attribute for each second component. Then, the weighted standard attributes of each second component are summed to obtain a weighted attribute. The weighted attribute comprehensively considers the importance and magnitude of different basic attributes, thus more fully reflecting the basic attribute characteristics of the second components.

[0203] Step 5: Based on the mapping relationship between the weighted attributes and historical weights of each second component, obtain the attribute weight threshold of each second component.

[0204] By analyzing the correlation between the weighted attributes and historical weights of each second component, a mapping relationship between the weighted attributes and historical weights of each second component is established. Then, based on this mapping relationship, the attribute weight thresholds corresponding to the weighted attributes of each second component are obtained. These attribute weight thresholds are used to quantitatively evaluate the relative importance and reliability requirements of the second components.

[0205] Optionally, step S2023 above may further include:

[0206] Step 1: Determine the confidence level of the matching deviation for each second component based on the historical matching deviation and matching deviation of each second component.

[0207] Historical matching deviation refers to the deviation data generated by the second component during operation and matching over a past period, reflecting its actual performance historically. By comprehensively considering the historical matching deviation and the actual matching deviation of each second component, the confidence level of the matching deviation for each component is determined. The confidence level of the matching deviation is an indicator that measures the reliability of the current matching deviation. The higher the confidence level of the matching deviation, the more accurately the matching deviation reflects the actual situation of the second component.

[0208] Step 2: Based on the historical attribute weight threshold and attribute weight threshold of each second component, obtain the attribute weight threshold change rate of each second component.

[0209] The historical attribute weight threshold is an attribute weight threshold determined over a preset period of time in the past. The historical attribute weight threshold reflects the evaluation criteria for the importance of the component in the past. This preset period of time can be a specific point in history or a period of time within history.

[0210] Optionally, the change rate of the attribute weight threshold for each second component is obtained by comparing the difference between the historical attribute weight threshold and the attribute weight threshold for each second component with the historical attribute weight threshold. For example, if the historical attribute weight threshold for each second component is 0.6 and the attribute weight threshold is 0.8, then the change rate of the attribute weight threshold is (0.8-0.6) / 0.8=0.25.

[0211] Optionally, based on the trend of historical attribute weight thresholds, the predicted target attribute weight threshold is used, and the ratio of the difference between the target attribute weight threshold and the attribute weight threshold to the target attribute weight threshold is taken as the attribute weight threshold change rate.

[0212] Step 3: Determine the matching deviation weight and attribute weight for each second component based on the ratio between the matching deviation confidence level and the attribute weight threshold change rate for each second component.

[0213] The ratio between the rate of change of the attribute weight threshold for each second component and the confidence level of the matching deviation is used as the matching deviation weight for each second component. The difference between the matching deviation weight for each second component and 1 is used as the attribute weight for each second component.

[0214] For example, if the second component includes second component a, the matching deviation confidence level of second component a is 0.85, and the attribute weight threshold is 0.5, then the matching deviation weight of second component a is 0.5 / 0.85≈0.59, and the attribute weight of the second component is 1-0.59=0.41.

[0215] Optionally, the matching deviation weight and attribute weight of each second component can be obtained by piecewise linear function mapping based on the ratio between the matching deviation confidence and the rate of change of the attribute weight threshold for each second component.

[0216] For example, the piecewise linear function is such that when the ratio between the matching deviation confidence level and the rate of change of the attribute weight threshold is in the range [0, 0.5), the matching deviation weight of each second component is 0.3 and the attribute weight is 0.7. When the ratio between the matching deviation confidence level and the rate of change of the attribute weight threshold is in the range [0.5, 1], the matching deviation weight of each second component is 0.7 and the attribute weight is 0.3.

[0217] Step 4: Determine the matching threshold for each second component based on the matching deviation, matching deviation weight, attribute weight, and attribute weight change rate for each second component.

[0218] The matching value for each second component is determined by multiplying the matching deviation by its weight. The attribute value for each second component is determined by multiplying the attribute weight by its rate of change. The sum of the matching value and the attribute value for each second component is used as the matching threshold for that component. The matching thresholds obtained through these steps better adapt to the dynamic changes in components, improving the system's matching accuracy.

[0219] In one possible implementation, before determining the matching degree between each second component and the first component by comparing the similarity between the first component in the first image features and each second component in the GIS data, the method further includes:

[0220] Step 1: Perform an affine transformation on the first coordinate of the first component and the second coordinate between the second component to align the coordinate system corresponding to the first coordinate with the coordinate system corresponding to the second coordinate, thereby obtaining the alignment coordinates of each first component.

[0221] Optionally, the first coordinates of the first component are determined based on the coordinate system defined by the first image feature itself. For example, if the first image feature is represented by a remote sensing image and the transformer is the first component, the coordinates of the first component may be row and column coordinates in pixels, with the top left corner of the image as the origin.

[0222] Optionally, the first coordinates of the first component can be defined based on the position coordinates of the camera gimbal or the camera-capable drone that acquires the first image features. For example, image depth analysis is performed on the first image features acquired by the camera gimbal to obtain the polar coordinates of the first component relative to the camera gimbal. Then, the polar coordinates of the first component relative to the camera gimbal are combined with the geographical coordinates of the camera gimbal to obtain the first coordinates of the first component.

[0223] An affine transformation is performed on the first coordinate of the first component and the second coordinate of the second component. Through mathematical operations, points in the coordinate system corresponding to the first coordinate are mapped to the coordinate system corresponding to the second coordinate, thus aligning the coordinate systems of the first and second coordinates to obtain the aligned coordinate system corresponding to the first coordinate. Then, based on this aligned coordinate system, the aligned coordinates of each first component are obtained. This aligned coordinate system allows for positional comparison and analysis of the first and second components within the same coordinate system.

[0224] Step 2: Replace the first coordinate in the first image feature with the alignment coordinate of each first component to obtain the third image feature; accordingly, calculate the matching degree between each first component and each second component, including: by comparing the matching degree between the first component and each second component in the third image feature.

[0225] Based on the first image features, the first coordinates of the first component are replaced with aligned coordinates to obtain a new image feature representation, which is then used as the third image feature. Since the third image feature places the component location information in the first image feature and the location information in the GIS data in the same coordinate system, by comparing the similarity between the first component in the third image feature and each second component in the GIS data to obtain the matching degree between each second component and the first component, errors caused by coordinate system inconsistencies can be eliminated, making the calculation of similarity and matching degree more accurate and reliable.

[0226] Figure 4 This is a schematic diagram of the distribution network interconnection diagram generation device provided in an embodiment of this application. Figure 4 As shown, the power distribution network interconnection diagram generation device 40 provided in this embodiment includes:

[0227] The acquisition module 401 is used to acquire the first image features, geographic information system (GIS) data and environmental parameters of the power distribution network within the target area. The first image features include multiple first components, and the GIS data includes multiple second components and basic attributes corresponding to each second component.

[0228] Processing module 402 is used to determine the matching threshold of each second component based on environmental parameters and the basic attributes of each second component; calculate the matching degree between each first component and each second component; if the matching degree between the first target component in the first component and each second component is lower than the matching threshold corresponding to the second component, adjust the first image feature corresponding to the first target component based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component; the first target component is any component in the first component; and construct a simplified diagram of the power distribution network connection based on the target image feature and GIS data corresponding to each first component, wherein the target image feature includes the first image feature or the second image feature.

[0229] In one possible implementation, the image features include first coordinates, first attributes, and first connectivity relationships for each first component; the GIS data includes second coordinates, second attributes, and second connectivity relationships for each second component; and the processing module 402 is specifically used for:

[0230] Based on the features of the target image, a second target component is determined for each first component; the second target component is the one that matches the first component the most.

[0231] By using the iterative nearest point algorithm, the first coordinates of each first component and the second coordinates of each second target component are registered to obtain the registered position coordinates of each first component.

[0232] Based on the location coordinates and first connection relationship of each first component, and the second connection relationship of the second target component, the connection relationship between different components in the distribution network interconnection diagram is generated by the shortest path algorithm, and a topology diagram is obtained.

[0233] Based on the first attribute of each first component and the second attribute of each second target component, the attribute characteristics of each first component in the topology diagram are determined, and the distribution network interconnection diagram is obtained.

[0234] In one possible implementation, the processing module 402 is specifically used for:

[0235] The coordinates of each first component are adjusted using gradient descent to obtain the adjusted first coordinates; and / or, based on the second attribute of the second component corresponding to each first component, the first attribute of each first component is adjusted in the pre-trained generative adversarial network to obtain the adjusted first attribute of each first component.

[0236] Based on the adjusted first coordinates and first attributes of each first component, the image features corresponding to the first component are obtained;

[0237] If the matching degree of the set component is greater than or equal to the matching threshold, the image feature is used as the second image feature corresponding to the set component; wherein, the set component is any one of the first components;

[0238] If the matching degree of the set component is less than the matching threshold, readjust the first coordinate and first attribute of the set component until the matching degree of the obtained image features is equal to or greater than the matching threshold.

[0239] In one possible implementation, the processing module 402 is specifically used for:

[0240] The distance metric is performed on the first coordinate of each first component and the second coordinate of each second component to obtain the coordinate similarity between each first component and each second component.

[0241] The morphological similarity between each first component and each second component is obtained by comparing the similarity between the first attribute of each first component and the second attribute of each second component.

[0242] The topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component;

[0243] Based on the coordinate similarity, morphological similarity, and topological similarity of each first component, the matching degree between each first component and each second component is obtained.

[0244] In one possible implementation, the processing module 402 is further configured to:

[0245] The first connection relationship of each first component is represented as a first adjacency matrix, and the second connection relationship of each second component is represented as a second adjacency matrix;

[0246] The topological similarity between each first component and each second component is obtained by comparing the ratio of the number of common connections between the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component to the total number of connections.

[0247] In one possible implementation, the processing module 402 is specifically used for:

[0248] By using environmental parameters as input to the environmental impact model, the matching deviation of each second component is obtained.

[0249] Based on the basic attributes of each second component and the reliability level of the distribution network, the attribute weight threshold of each second component is obtained;

[0250] Based on the matching deviation and attribute weight threshold of each second component, the matching threshold of each second component is determined.

[0251] In one possible implementation, the processing module 402 is further configured to:

[0252] Based on the basic attributes of each second component and the reliability level of the distribution network, a judgment matrix for each second component is obtained;

[0253] The weight of each second component is determined based on the eigenvector corresponding to the largest eigenvalue of the judgment matrix of each second component.

[0254] The basic properties of each second component are standardized to obtain the standard properties of each second component.

[0255] Based on the weight of each second component, the standard attributes of each second component are weighted and fused to obtain the weighted attributes of each second component;

[0256] Based on the mapping relationship between the weighted attributes and historical weights of each second component, the attribute weight threshold of each second component is obtained.

[0257] In one possible implementation, the processing module 402 is further configured to:

[0258] Based on the historical matching deviation and matching deviation of each second component, determine the matching deviation confidence level of each second component;

[0259] Based on the historical attribute weight threshold and attribute weight threshold of each second component, the rate of change of attribute weight threshold of each second component is obtained;

[0260] The matching deviation weight and attribute weight of each second component are determined based on the ratio between the matching deviation confidence and the rate of change of the attribute weight threshold for each second component.

[0261] The matching threshold for each second component is determined based on the matching deviation, matching deviation weight, attribute weight, and attribute weight change rate for each second component.

[0262] In one possible implementation, before obtaining the matching degree between each second component and the first component by comparing the similarity between the first component in the first image features and each second component in the GIS data, the processing module 402 is further configured to:

[0263] An affine transformation is performed on the first coordinate of the first component and the second coordinate between the second component to align the coordinate system corresponding to the first coordinate with the coordinate system corresponding to the second coordinate, thus obtaining the alignment coordinates of each first component;

[0264] The first coordinate in the first image feature is replaced with the alignment coordinate of each first component to obtain the third image feature;

[0265] Accordingly, the matching degree between each first component and each second component is calculated separately, including:

[0266] By comparing the degree of matching between the first component and each second component in the third image features.

[0267] The distribution network interconnection diagram generation device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0268] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0269] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0270] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0271] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0272] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0273] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings of this application's embodiments are not limited to only one bus or one type of bus.

[0274] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0275] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed, implement any of the methods described above.

[0276] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0277] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0278] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0279] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0280] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0281] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0282] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0283] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for generating a simplified diagram of a power distribution network interconnection, characterized in that, include: Acquire first image features, geographic information system (GIS) data, and environmental parameters of the power distribution network within the target area, wherein the first image features include multiple first components, and the GIS data includes multiple second components and basic attributes corresponding to each second component; Based on the environmental parameters and the basic attributes of each second component, a matching threshold for each second component is determined. Calculate the matching degree between each of the first component and each of the second components; If the matching degree between the first target component in the first component and each of the second components is lower than the matching threshold corresponding to the second component, the first image feature corresponding to the first target component is adjusted based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component; the first target component is any one of the first components. Based on the target image features corresponding to each first component and the GIS data, a simplified diagram of the power distribution network connection is constructed, wherein the target image features include the first image features or the second image features.

2. The method according to claim 1, characterized in that, The image features include first coordinates, first attributes, and first connectivity relationships for each of the first components; the GIS data includes second coordinates, second attributes, and second connectivity relationships for each of the second components; and the construction of a simplified power distribution network interconnection diagram based on the target image features corresponding to each first component and the GIS data includes: Based on the target image features, a second target component is determined for each of the first components; the second target component is the component with the highest matching degree to the first component. By using the iterative nearest point algorithm, the first coordinates of each first component and the second coordinates of each second target component are registered to obtain the registered position coordinates of each first component. Based on the location coordinates and first connection relationship of each first component, and the second connection relationship of the second target component, the connection relationship between different components in the power distribution network interconnection diagram is generated by the shortest path algorithm to obtain the topology diagram; Based on the first attribute of each first component and the second attribute of each second target component, the attribute characteristics of each first component in the topology diagram are determined to obtain the distribution network interconnection diagram.

3. The method according to claim 2, characterized in that, The step of adjusting the first image feature corresponding to the first target component based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component includes: The coordinates of each first component are adjusted using gradient descent to obtain the adjusted first coordinates; and / or, based on the second attribute of the second component corresponding to each first component, the first attribute of each first component is adjusted in the pre-trained generative adversarial network to obtain the adjusted first attribute of each first component. Based on the adjusted first coordinates and first attributes of each first component, the image features corresponding to the first component are obtained; If the matching degree of the set component is greater than or equal to the value of the matching threshold, the image feature is used as the second image feature corresponding to the set component; wherein, the set component is any one of the first components; If the matching degree corresponding to the set component is less than the matching threshold, the first coordinate and first attribute of the set component are readjusted until the matching degree corresponding to the obtained image feature is equal to or greater than the matching threshold.

4. The method according to claim 2, characterized in that, The step of calculating the matching degree between each of the first components and each of the second components includes: Distance metric is performed on the first coordinate of each first component and the second coordinate of each second component to obtain the coordinate similarity between each first component and each second component; The morphological similarity between each first component and each second component is obtained by comparing the similarity between the first attribute of each first component and the second attribute of each second component. The topological similarity between the first connection relationship of each first component and the second connection relationship of each second component is measured to obtain the topological similarity between each first component and each second component; Based on the coordinate similarity, morphological similarity, and topological similarity of each of the first components, the matching degree between each of the first components and each of the second components is obtained.

5. The method according to claim 4, characterized in that, Measuring the topological similarity between the first connection relationship of each first component and the second connection relationship of each second component to obtain the topological similarity between each first component and each second component includes: The first connection relationship of each first component is represented as a first adjacency matrix, and the second connection relationship of each second component is represented as a second adjacency matrix; The topological similarity between each first component and each second component is obtained by comparing the ratio of the number of common connections between the first adjacency matrix corresponding to each first component and the second adjacency matrix corresponding to each second component to the total number of connections.

6. The method according to claim 1, characterized in that, The step of determining the matching threshold for each of the second components based on the environmental parameters and the basic attributes of each second component includes: The environmental parameters are used as input to the environmental impact model to obtain the matching deviation of each of the second components; Based on the basic attributes of each second component and the reliability level of the distribution network, the attribute weight threshold of each second component is obtained; The matching threshold for each of the second components is determined based on the matching deviation and the attribute weight threshold for each of the second components.

7. The method according to claim 6, characterized in that, The method of obtaining the attribute weight threshold for each second component based on the basic attributes of each second component and the reliability level of the distribution network includes: Based on the basic attributes of each second component and the reliability level of the distribution network, a judgment matrix for each second component is obtained; The weight of each second component is determined based on the eigenvector corresponding to the largest eigenvalue of the judgment matrix of each second component; The basic attributes of each of the second components are standardized to obtain the standard attributes of each of the second components; Based on the weight of each second component, the standard attributes of each second component are weighted and fused to obtain the weighted attribute of each second component; Based on the mapping relationship between the weighted attributes and historical weights of each second component, the attribute weight threshold of each second component is obtained.

8. The method according to claim 6, characterized in that, The step of determining the matching threshold for each of the second components based on the matching deviation and the attribute weight threshold for each of the second components includes: Based on the historical matching deviation of each second component and the matching deviation, determine the matching deviation confidence level of each second component; Based on the historical attribute weight threshold and the attribute weight threshold of each second component, the change rate of the attribute weight threshold of each second component is obtained; The matching deviation weight and attribute weight of each second component are determined based on the ratio between the matching deviation confidence level and the attribute weight threshold change rate of each second component. The matching threshold of each second component is determined based on the matching deviation, the matching deviation weight, the attribute weight, and the attribute weight change rate of each second component.

9. The method according to claim 2, characterized in that, Before calculating the matching degree between each of the first component and each of the second components, the method further includes: An affine transformation is performed on the first coordinate of the first component and the second coordinate between the second component to align the coordinate system corresponding to the first coordinate with the coordinate system corresponding to the second coordinate, thereby obtaining the alignment coordinates of each first component; The first coordinate in the first image feature is replaced by the alignment coordinate of each of the first components to obtain the third image feature; Accordingly, calculating the matching degree between each of the first components and each of the second components includes: By comparing the degree of matching between the first component and each of the second components in the third image features.

10. A device for generating simplified diagrams of power distribution network interconnections, characterized in that, include: The acquisition module is used to acquire first image features, geographic information system (GIS) data, and environmental parameters of the power distribution network within the target area. The first image features include multiple first components, and the GIS data includes multiple second components and basic attributes corresponding to each second component. The processing module is configured to: determine a matching threshold for each second component based on the environmental parameters and the basic attributes of each second component; calculate the matching degree between each first component and each second component; if the matching degree between the first target component in the first component and each second component is lower than the matching threshold corresponding to the second component, adjust the first image feature corresponding to the first target component based on the GIS data corresponding to the second component to obtain the adjusted second image feature of the first target component; the first target component is any one of the first components; and construct a simplified diagram of the power distribution network interconnection based on the target image feature corresponding to each first component and the GIS data, wherein the target image feature includes either the first image feature or the second image feature.

11. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1-9.

13. A computer program product, characterized in that, Includes a computer program, which, when executed, implements the method according to any one of claims 1-9.

Images