A method and system for intelligent modeling of urban water and electricity pipe network

Abstract

The present invention provides an intelligent modeling method and system for a city water and electricity pipe network, and relates to the technical field of modeling of a city water and electricity pipe network. The method comprises: determining a proposed observation point in each administrative area in a street view map according to geographic information data of a city road network; searching for a street view image closest to the proposed observation point in the street view map, and obtaining metadata of the street view image; performing target detection on the street view image, identifying typical markers of the city water and electricity pipe network, and determining the spatial coordinates of the typical markers; establishing a cost function based on the geographic information data of the city road network; performing spatial aggregation on buildings in the administrative area to obtain multiple spatial aggregation coordinates of the buildings; utilizing a shortest path algorithm to extend from a source point through an intermediate node to each end point, and outputting a primary water and electricity pipe network model; and correcting the primary water and electricity pipe network model to output a target water and electricity pipe network model. The technical solution of the present invention can quickly establish a city water supply and power supply network model through a small amount of easily accessible data.

Description

Technical Field

[0001] The present invention relates to the technical field of urban water and electricity pipe network modeling, and in particular to an urban water and electricity pipe network intelligent modeling method and system. Background Art

[0002] The water and power pipeline network refers to the infrastructure network used to transmit and distribute water and electricity in a city or region. The intelligent modeling method of the water and power pipeline network is a new modeling technology that combines computer vision, artificial intelligence and urban planning and design. It aims to improve the construction and management efficiency of urban water and power pipeline network systems. Its core idea is to identify relevant infrastructure information through street view target detection technology in a complex urban environment, and combine it with the design rules of urban planning to carry out intelligent water and power pipeline network modeling.

[0003] The establishment of a physical model of urban water and power pipeline networks can provide model support for urban resilience research. On the one hand, by using urban geographic information big data, we can fully explore its potential information and build a large-scale physical model of urban water and power pipeline networks, allowing modeling and analysis under limited data conditions, providing data support for improving urban physical modeling and resilience planning. On the other hand, by providing a modeling method for the physical model of urban water and power pipeline networks, we can provide a reference for urban data management.

[0004] The current urban water and electricity pipeline network modeling method relies too much on manual surveying and mapping, which is costly, labor-intensive and inefficient. In addition, the model is only constructed through the source points and user end points of the water and electricity pipeline network, which is not accurate enough and makes it difficult to complete the modeling of urban system networks that conform to actual projects. Summary of the invention

[0005] In order to solve the technical problems in the prior art that the current urban water and electricity pipeline network modeling method is overly dependent on manual surveying and mapping, has high cost, large manpower requirements and low efficiency, and only builds the model through the water and electricity pipeline network source point and the user end point, which is insufficient in accuracy and difficult to complete the modeling of the urban system network that conforms to the actual project, the present invention provides an urban water and electricity pipeline network intelligent modeling method and system.

[0006] The technical solution provided by the embodiment of the present invention is as follows:

[0007] First aspect

[0008] An embodiment of the present invention provides an intelligent modeling method for urban water and electricity pipe networks, comprising:

[0009] S1: According to the urban road network geographic information data, the proposed observation points in each administrative area are determined in the street view map;

[0010] S2: Searching for a street view image closest to the proposed observation point in the street view map, and obtaining street view image metadata, wherein the street view image metadata includes shooting point coordinates, shooting direction angle, and shooting camera height;

[0011] S3: Perform object detection on street view images and identify typical markers of urban water and electricity pipe networks;

[0012] S4: Determine the spatial coordinates of typical markers by combining the street view image metadata and the proposed observation points;

[0013] S5: Establish a cost function representing the cost of laying water and electricity pipe networks based on the urban road network geographic information data;

[0014] S6: Determine different building space aggregation degrees according to the road network level, perform spatial aggregation on the buildings within the administrative area, and obtain multiple building space aggregation coordinates;

[0015] S7: With the minimum cost function as the goal, typical markers as intermediate nodes, and building space aggregation coordinates as the end point, the shortest path algorithm is used to expand from the source point through the intermediate nodes to each end point, and the primary water and electricity network model is output, where the source point includes the water plant and the distribution station;

[0016] S8: Modify the primary water and electricity pipeline network model according to the administrative area scale and the degree of building space aggregation, and output the target water and electricity pipeline network model.

[0017] Second aspect

[0018] An embodiment of the present invention provides an urban water and electricity network intelligent modeling system, comprising:

[0019] processor;

[0020] A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the urban water and electricity pipeline network intelligent modeling method as described in the first aspect is implemented.

[0021] The third aspect

[0022] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for intelligent modeling of urban water and electricity pipeline networks as described in the first aspect is implemented.

[0023] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0024] In the present invention, by combining street view images and geographic information data, street view data of multiple observation points are automatically extracted, which reduces the dependence on traditional manual surveys and greatly improves efficiency. By using the shortest path algorithm and cost function analysis, the optimal path can be found during pipeline network planning, reducing the distance and material consumption of pipeline laying, reducing labor and costs. Street view images provide accurate geographic location information and environmental data. Through metadata and marker detection, key nodes and layout locations of urban water and electricity pipeline networks can be determined more accurately, improving modeling accuracy. Models are constructed based on the scale of administrative regions and the degree of aggregation of building space, further improving the accuracy and reliability of water and electricity pipeline networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 A schematic diagram of a process of an intelligent modeling method for a city water and electricity network provided by an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of the structure of an urban water and electricity pipe network intelligent modeling system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0029] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present the concept in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0030] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0031] Reference Manual Attached Figure 1 , showing a flow chart of an urban water and electricity pipeline network intelligent modeling method provided by an embodiment of the present invention.

[0032] The embodiment of the present invention provides a method for intelligent modeling of a city water and electricity pipe network, which can be implemented by an intelligent modeling device for a city water and electricity pipe network, and the intelligent modeling device for a city water and electricity pipe network can be a terminal or a server. The processing flow of the method for intelligent modeling of a city water and electricity pipe network can include the following steps:

[0033] S1: Based on the urban road network geographic information data, determine the proposed observation points in each administrative area in the street view map.

[0034] Geographic information data includes information such as roads, buildings, and terrain, which are used to determine the location and environmental characteristics of observation points. Administrative regions refer to specific geographical areas divided by cities or regions, such as counties, districts, and streets, which are used for regional management and planning. Proposed observation points are key points selected based on geographic information data, which are used for street view image analysis and identification of the locations of urban water and electricity network markers.

[0035] It should be noted that determining the proposed observation points in each administrative area in the street view map based on the urban road network geographic information data can accurately reflect the urban road network structure, ensure that the observation points reasonably cover all important areas, avoid blind spots in data collection, and through the systematic layout of observation points, it can also improve the accuracy and optimization efficiency of the water and electricity pipeline network model, and reduce errors and duplication of work in later planning.

[0036] In a possible implementation, S1 specifically includes:

[0037] S101: Obtain urban road network geographic information.

[0038] Among them, the urban road network geographic information includes the urban road network geographic coordinates and the urban road network level.

[0039] S102: According to the geographical information of the urban road network, proposed observation points within the administrative area are set in the street view map at fixed intervals.

[0040] It should be noted that the advantage of obtaining the geographic information of the urban road network, including geographic coordinates and road network levels, and setting proposed observation points at fixed intervals in the street view map is that it can ensure that the observation points are reasonably distributed and fully covered to reflect the actual conditions of different road levels. This not only improves the accuracy and comprehensiveness of data collection, but also provides a more reliable spatial basis for the subsequent planning of water and power pipelines, optimizes pipeline design, and avoids missing key areas.

[0041] S2: Search the street view map for the street view image closest to the proposed observation point, and obtain the street view image metadata.

[0042] The street view image metadata includes the shooting point coordinates, shooting direction angle and shooting camera height.

[0043] It should be noted that obtaining street view image metadata can provide precise spatial positioning and image information, helping to accurately identify and locate markers of water and electricity pipelines. Through these metadata, the spatial coordinates of the markers can be better calculated, thereby improving the accuracy and efficiency of water and electricity pipeline network planning and reducing human errors.

[0044] In a possible implementation, typical markers include city power supply network poles, city power supply network towers, and city water supply manhole covers.

[0045] S3: Perform object detection on street view images and identify typical markers of urban water and electricity pipelines.

[0046] It should be noted that through target detection algorithms such as the YOLO algorithm, key elements of the water and power network, such as electric poles, power towers and manhole covers, can be quickly and accurately extracted. Compared with manual recognition, target detection is more efficient and can cover large urban areas, reduce missed detections and misjudgments, and improve the construction accuracy and planning efficiency of the entire water and power network model.

[0047] S301: In combination with the AdamW optimizer, the sample set of labeled street view images is input into the target detection model for training to adjust the hyperparameters of the target detection model.

[0048] Among them, AdamW optimizer is an improved deep learning optimization algorithm, which combines momentum method and adaptive learning rate, and can automatically adjust the learning rate during gradient descent to adapt to different feature changes. AdamW optimizer is suitable for large-scale neural network training and has stable and efficient convergence. Hyperparameters refer to parameters that are manually set before model training and cannot be automatically learned through training data. Tuning hyperparameters is a key step because appropriate hyperparameter settings can speed up convergence, prevent overfitting or underfitting, and improve the overall performance of the model.

[0049] S302: Input the street view image into the trained object detection model, and output the location information of the typical marker, wherein the location information includes the coordinates of the center point of the typical marker and the typical marker detection frame:

[0050]

[0051] in, Indicates the position of the center point of a typical marker relative to the width of the street view image to which it belongs. represents the position of the center point of the typical marker relative to the height of the street view image to which it belongs, b represents the ratio of the detection frame width to the corresponding street view image width, and h represents the ratio of the detection frame height to the corresponding street view image height.

[0052] S303: Output typical markers corresponding to the position information.

[0053] It should be noted that by combining the AdamW optimizer for target detection model training, the model's hyperparameters can be effectively adjusted to improve the recognition accuracy of typical markers in street view images. On this basis, detailed location information including the coordinates of the marker center point and the detection frame is output, making the spatial positioning of the marker more accurate. This process not only improves the accuracy of water and power network planning, but also reduces false detections and missed detections, and optimizes the performance of the model in complex urban environments.

[0054] S4: Determine the spatial coordinates of typical markers by combining street view image metadata and proposed observation points.

[0055] Among them, spatial coordinates refer to the specific location of a typical marker in three-dimensional space, which is usually composed of three values: longitude, latitude and altitude. These values ​​can accurately describe the location of the marker in geographic space. By obtaining these spatial coordinates, the specific location of water and electricity pipe network facilities in the city can be accurately described, providing basic data for subsequent pipe network design and planning.

[0056] It should be noted that by combining street view image metadata and proposed observation points, the key facilities of the water and electricity pipeline network can be accurately located. Through accurate spatial coordinates, the accuracy of the pipeline network model can be improved, ensuring the reasonable layout of the water and electricity pipeline network, reducing construction errors and the difficulty of subsequent maintenance, and improving the efficiency and scientificity of planning.

[0057] In a possible implementation, S4 specifically includes:

[0058] S401: Initialize a typical marker set and a true typical marker set.

[0059] Among them, the typical marker set is a preliminary set, which contains all possible urban water and electricity network markers identified by the street view image object detection model. These markers include electric poles, electric towers, water well covers, etc. Since these markers are identified by automatic detection, they may contain some false detection or duplicate objects. The true typical marker set is a set that has been further screened and verified, containing accurate and unique markers. By further analyzing the characteristics, position, size and other information of the markers, the detected duplicate or false detection items are filtered out, and the unique and real markers are retained to form a "true" typical marker set.

[0060] S402: numbering each proposed observation point, determining the distance between each proposed observation point and its neighboring proposed observation points, and selecting a preset number of proposed observation points from the neighboring proposed observation points in ascending order of distance.

[0061] It should be noted that those skilled in the art can set the size of the preset number according to actual needs, and the present invention is not limited thereto.

[0062] S403: Determine the shooting direction angle of the typical marker in the street view image corresponding to the selected proposed observation point.

[0063] The shooting direction angle refers to the angle of the camera device in the street view image relative to a certain reference direction when shooting. It indicates the specific direction the camera faces when shooting and is used to describe the orientation of the image. In street view images, the shooting direction angle is very important metadata because it can help determine the relative position and direction of typical markers. In the modeling of urban water and power pipeline networks, the shooting direction angle helps to accurately calculate the spatial coordinates of markers and ensure the accuracy of pipeline network planning.

[0064] S404: Draw a line segment along the shooting direction angle with the selected proposed observation point as the endpoint and the fixed distance threshold as the length.

[0065] It should be noted that those skilled in the art can set the fixed distance threshold value according to actual needs, and the present invention does not limit this herein.

[0066] S405: Calculate the coordinates of the intersections of all line segments and record them in the typical marker set.

[0067] S406: Calculate a uniqueness index of each typical marker according to the street view image metadata and the intersection coordinates, wherein the uniqueness index includes a height of a utility pole, a height of a power tower, and a width of a manhole cover.

[0068] S407: Consider the two typical markers with the closest uniqueness indexes as the same true typical marker.

[0069] S408: Record the intersection points corresponding to the true typical markers into the true typical marker set.

[0070] S409: Consider the intersection points in the true typical marker set as the spatial coordinates of the corresponding typical marker.

[0071] It should be noted that the process of screening typical markers, calculating intersection coordinates and finally generating a set of true typical markers can effectively improve the accuracy and reliability of hydropower pipeline network modeling. The advantage of this step is that it uses the shooting direction angle, fixed distance threshold and marker uniqueness index to ensure the elimination of false detection and duplicate markers, thereby generating true and unique marker coordinates, which not only reduces errors, but also provides accurate geographic information support for subsequent pipeline network planning, improving design efficiency and scientificity.

[0072] S5: Establish a cost function representing the cost of laying water and electricity pipelines based on the urban road network geographic information data.

[0073] Among them, the cost function is a mathematical model used to evaluate the cost of laying water and electricity pipelines. It comprehensively considers factors such as pipeline length, path turning angle and actual construction cost. Through this function, the laying costs of different schemes can be quantified, helping to select the most economical and efficient water and electricity pipeline path, optimize the design plan, and reduce construction and maintenance costs.

[0074] It should be noted that the cost function can comprehensively consider the geographical environment, road structure and laying conditions, and effectively evaluate the costs of different path solutions. The advantage of constructing a cost function is that it can provide a scientific cost optimization basis for pipeline network planning, help select the most economical and reasonable pipeline laying path, reduce unnecessary waste of resources, and improve the overall economy and feasibility of the project.

[0075] In a possible implementation, the cost function is specifically:

[0076]

[0077] Among them, C represents the cost of water and electricity pipeline network, C L represents the pipeline length cost, represents the pipeline angle cost, C T Indicates the pipeline laying cost. The longer the pipeline, the higher the cost, the corner cost is higher than the straight line cost, and the higher the road level, the lower the pipeline laying cost.

[0078] S6: Determine different building space aggregation degrees according to the road network level, perform spatial aggregation on the buildings in the administrative area, and obtain multiple building space aggregation coordinates.

[0079] Among them, spatial aggregation refers to merging or grouping buildings in the city according to their geographical location and spatial distribution characteristics to form several aggregation points. Spatial aggregation simplifies the complex building layout and treats multiple adjacent or dense buildings as a whole coordinate point, thereby reducing the number of nodes that need to be processed. It helps to optimize the calculation efficiency when planning the water and electricity network, simplify the path planning process, and ensure that the network layout is more reasonable and compact. Through spatial aggregation, the overall distribution characteristics of the buildings can be better reflected, thereby improving the feasibility and economy of the water and electricity network design.

[0080] Specifically, first, the urban area is divided into different aggregation areas according to the different levels of the urban road network. For example, the closed area formed by the main road topology occupies a larger area, while the closed area formed by the branch road or alley topology occupies a relatively small area. Then, in each area, spatial aggregation is performed based on the closed areas formed by different levels of road networks and the density of buildings. The specific approach is to regard the buildings in the same closed area as a whole, and obtain their aggregation coordinates by calculating the highest value of building density. This aggregation process simplifies the original building data, reduces the number of points that need to be processed, and forms multiple aggregated building coordinates. These aggregated coordinates will be used for subsequent path planning of water and electricity pipelines to help simplify calculations and optimize pipeline layout.

[0081] It should be noted that by aggregating the buildings in the administrative area at different building spatial aggregation levels, the complex building distribution can be simplified and multiple buildings can be merged into a small number of aggregation points. The advantage of this step is that it can reduce the number of nodes that need to be processed during pipe network planning, improve calculation efficiency, optimize path design, make the layout of the water and electricity pipe network more compact and reasonable, reduce laying costs, and ensure coverage of all important building areas.

[0082] S7: With the minimum cost function as the goal, typical markers as intermediate nodes, and building space aggregation coordinates as the end point, the shortest path algorithm is used to expand from the source point through the intermediate nodes to each end point, and the primary water and electricity network model is output, where the source point includes the water plant and the distribution station.

[0083] Among them, the shortest path algorithm is an algorithm used to find the path with the smallest total cost (for example, distance, time or other cost) from the starting point to the end point.

[0084] It should be noted that this step can generate an efficient and economical primary water and electricity pipeline network model by using typical markers as intermediate nodes and combining cost functions and shortest path algorithms, ensuring optimal resource allocation, reducing construction costs and energy consumption, and improving the overall effect of pipeline network planning.

[0085] In a possible implementation, S7 specifically includes:

[0086] S701: Initialize the source point set, intermediate node set and terminal point set of the urban water and electricity pipeline network.

[0087] S702: Based on the source point set, the intermediate node set and the end point set, the urban water and electricity pipe network is initialized into a road network topology structure to obtain an edge set of the urban water and electricity pipe network.

[0088] Among them, the road network topology refers to the description of the geometry and connection relationship of urban roads or networks through the relationship between nodes and edges. In the modeling of urban water and electricity pipe networks, the road network topology regards the source point, intermediate node, and end point of the water and electricity pipe network as nodes. These nodes are connected to each other through pipes or cables to form edges. The topology focuses on how the nodes are connected, not necessarily the specific physical distance and direction, so it can clearly represent the connection relationship of the pipe network system.

[0089] It should be noted that the edge set of the urban water and power network refers to the connection relationship between different nodes in the topological structure of the water and power network, which is represented as a set of edges. Each edge represents an actual pipeline or cable laying path connecting two nodes. The edge set records all the connection paths in the water and power network and can be optimized according to different cost functions to calculate the optimal path and network layout.

[0090] S703: According to the cost function, cost evaluation is performed on each edge element in the urban water and electricity pipe network edge set.

[0091] S704: According to the evaluation result, the shortest path algorithm is used to traverse each intermediate node from the source point according to the principle of minimum cost, so as to expand to each end point until it is expanded to all end points.

[0092] S705: Output the extended path as a primary water and electricity network model.

[0093] Specifically, by initializing the urban water and electricity pipeline network as a road network topology and using edge sets to represent the connection relationship between nodes, the layout structure of the pipeline network can be systematically described, the edges can be evaluated based on the cost function, and the path design can be optimized using the shortest path algorithm to ensure that the pipeline network is laid at the lowest cost and highest efficiency. This method not only simplifies the planning process of complex pipeline networks, but also improves the economy and rationality of pipeline network design, providing an accurate basis for subsequent construction and maintenance.

[0094] S8: Modify the primary water and electricity pipeline network model according to the administrative area scale and the degree of building space aggregation, and output the target water and electricity pipeline network model.

[0095] It should be noted that the primary water and electricity pipeline network model can be modified according to the scale of administrative regions and the degree of aggregation of building space, and can be optimized and adjusted according to the actual needs and building distribution of different regions. This can ensure that the layout of the water and electricity pipeline network is more in line with regional characteristics, reasonably allocate resources, and avoid excessive laying or insufficient coverage, thereby improving the efficiency, economy and long-term sustainability of the pipeline network, and ultimately generating a target water and electricity pipeline network model that meets actual needs.

[0096] In a possible implementation, S8 specifically includes:

[0097] S801: Calculate the interval distance from each source point to each end point.

[0098] S802: Determine the end point of a multi-source hydropower user using multiple source point resources according to the interval distance.

[0099] S803: Add branch pipe networks at the terminal points of each multi-source hydropower user to form a tree-shaped topology pipe network including branch pipe networks.

[0100] Among them, the tree topology pipeline network is a hierarchical network with a source point as the root node, which is connected to each end user step by step through branches. Each node can only have one parent node, the path is unique, and it is easy to manage. However, when a node or pipeline fails, downstream users may not be able to obtain services.

[0101] S804: Change the tree topology pipe network connection form to a ring topology pipe network.

[0102] Among them, the ring topology pipeline network connects the pipeline network into a closed-loop structure. All nodes are interconnected into a loop. Resources can be transmitted from multiple paths. When a path fails, the ring structure can continue to supply through another path, with higher reliability and redundancy.

[0103] S805: Divide each ring topology pipeline network into a high-level water and power pipeline network and a low-level water and power pipeline network according to the size of the administrative area and the degree of aggregation of building space.

[0104] S806: Connect the high-level hydropower network end point and the low-level hydropower network source point to obtain a target hydropower network model.

[0105] It should be noted that the advantage of this step is that by modifying the tree-topology pipeline network to a ring-topology pipeline network, the reliability and redundancy of the water and electricity pipeline network are improved. The ring structure allows resources to be transmitted through multiple paths. When a path fails, other paths can continue to supply, avoiding service interruption. In addition, hierarchical management based on the size of administrative areas and the degree of building aggregation, dividing the pipeline network into high-level and low-level levels, can optimize resource allocation, improve the efficiency and stability of pipeline network operation, and ensure that the system has stronger risk resistance and management flexibility.

[0106] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0107] In the present invention, by combining street view images and geographic information data, street view data of multiple observation points are automatically extracted, which reduces the dependence on traditional manual surveys and greatly improves efficiency. By using the shortest path algorithm and cost function analysis, the optimal path can be found during pipeline network planning, reducing the distance and material consumption of pipeline laying, reducing labor and costs. Street view images provide accurate geographic location information and environmental data. Through metadata and marker detection, key nodes and layout locations of urban water and electricity pipeline networks can be determined more accurately, improving modeling accuracy. Models are constructed based on the scale of administrative regions and the degree of aggregation of building space, further improving the accuracy and reliability of water and electricity pipeline networks.

[0108] Reference Manual Attached Figure 2 , showing a structural schematic diagram of an urban water and electricity pipeline network intelligent modeling system provided by the present invention.

[0109] The present invention also provides an urban water and electricity pipe network intelligent modeling system 20, which is applied to the above-mentioned urban water and electricity pipe network intelligent modeling method, comprising:

[0110] Processor 201.

[0111] The memory 202 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 201, the urban water and electricity pipeline network intelligent modeling method as described in the method embodiment is implemented.

[0112] The urban water and electricity pipeline network intelligent modeling system 20 provided by the present invention can execute the above-mentioned urban water and electricity pipeline network intelligent modeling method and achieve the same or similar technical effects. To avoid repetition, the present invention will not go into details.

[0113] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0114] In the present invention, by combining street view images and geographic information data, street view data of multiple observation points are automatically extracted, which reduces the dependence on traditional manual surveys and greatly improves efficiency. By using the shortest path algorithm and cost function analysis, the optimal path can be found during pipeline network planning, reducing the distance and material consumption of pipeline laying, reducing labor and costs. Street view images provide accurate geographic location information and environmental data. Through metadata and marker detection, key nodes and layout locations of urban water and electricity pipeline networks can be determined more accurately, improving modeling accuracy. Models are constructed based on the scale of administrative regions and the degree of aggregation of building space, further improving the accuracy and reliability of water and electricity pipeline networks.

[0115] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0116] It should also be understood that the memory in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0117] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0118] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0119] In the present invention, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0120] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0121] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0122] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0123] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0124] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0126] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0127] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for intelligent modeling of a city water and electricity pipe network as described in the method embodiment is implemented.

[0128] A computer-readable storage medium provided by the present invention can implement the steps and effects of the urban water and electricity pipeline network intelligent modeling method of the above-mentioned method embodiment. To avoid repetition, the present invention will not go into details.

[0129] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0130] In the present invention, by combining street view images and geographic information data, street view data of multiple observation points are automatically extracted, which reduces the dependence on traditional manual surveys and greatly improves efficiency. By using the shortest path algorithm and cost function analysis, the optimal path can be found during pipeline network planning, reducing the distance and material consumption of pipeline laying, reducing labor and costs. Street view images provide accurate geographic location information and environmental data. Through metadata and marker detection, key nodes and layout locations of urban water and electricity pipeline networks can be determined more accurately, improving modeling accuracy. Models are constructed based on the scale of administrative regions and the degree of aggregation of building space, further improving the accuracy and reliability of water and electricity pipeline networks.

[0131] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0132] There are a few points to note:

[0133] (1) The drawings of the embodiments of the present invention only involve structures related to the embodiments of the present invention. Other structures may refer to conventional designs.

[0134] (2) For the sake of clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced, that is, these drawings are not drawn according to the actual scale. It is understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, the element may be "directly" "on" or "under" the other element or there may be intermediate elements.

[0135] (3) In the absence of conflict, the embodiments of the present invention and the features therein may be combined with each other to obtain new embodiments.

[0136] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for intelligent modeling of urban water and electricity pipe networks, characterized in that: include: S1: According to the urban road network geographic information data, the proposed observation points in each administrative area are determined in the street view map; S2: searching the street view map for a street view image closest to the proposed observation point, and obtaining street view image metadata, wherein the street view image metadata includes shooting point coordinates, shooting direction angle, and shooting camera height; S3: performing target detection on the street view image to identify typical markers of the urban water and electricity pipeline network; S4: Determine the spatial coordinates of the typical marker by combining the street view image metadata and the proposed observation point; S5: establishing a cost function representing the cost of laying a water and electricity pipeline network based on the urban road network geographic information data; S6: Determine different building space aggregation degrees according to the road network level, perform spatial aggregation on the buildings in the administrative area, and obtain multiple building space aggregation coordinates; S7: Taking the minimum of the cost function as the goal, taking the typical marker as the intermediate node, taking the building space aggregation coordinate as the end point, using the shortest path algorithm to expand from the source point through the intermediate node to each end point, and outputting the primary water and electricity network model, wherein the source point includes the water plant and the power distribution station; S8: Modifying the primary water and electricity pipe network model according to the administrative area scale and the degree of aggregation of the building space, and outputting a target water and electricity pipe network model; Wherein, the S7 specifically includes: S701: Initializing the source point set, intermediate node set and terminal point set of the urban water and electricity pipe network; S702: Initializing the urban water and electricity pipe network into a road network topology structure based on the source point set, the intermediate node set and the end point set, and obtaining an urban water and electricity pipe network edge set; S703: performing cost evaluation on each edge element in the urban water and electricity pipe network edge set according to the cost function; S704: according to the evaluation result, the shortest path algorithm is used to traverse each intermediate node from the source point according to the principle of minimum cost, so as to expand to each end point until it is expanded to all end points; S705: Outputting the extended path as the primary water and electricity pipe network model.

2. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The S1 specifically includes: S101: Acquire the urban road network geographical information, wherein the urban road network geographical information includes urban road network geographical coordinates and urban road network levels; S102: According to the urban road network geographic information, proposed observation points within the administrative area are set in the street view map at fixed intervals.

3. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The typical markers include electric poles of the urban power supply network, electric towers of the urban power supply network and urban water supply well covers.

4. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The S3 specifically includes: S301: In combination with the AdamW optimizer, the sample set of the street view images with labels is input into the target detection model for training to adjust the hyper parameters of the target detection model; S302: Input the street view image into the trained target detection model, and output the location information of the typical marker, wherein the location information includes the coordinates of the center point of the typical marker and the typical marker detection frame: ； in, Indicates the position of the center point of a typical marker relative to the width of the street view image to which it belongs. Indicates the position of the center point of a typical marker relative to the height of the street view image to which it belongs. b Indicates the ratio of the detection box width to the corresponding street view image width. h Indicates the ratio of the detection box height to the corresponding street view image height; S303: Output typical markers corresponding to the position information.

5. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The S4 specifically includes: S401: Initializing a typical marker set and a true typical marker set; S402: numbering each proposed observation point, determining the distance between each proposed observation point and its neighboring proposed observation points, and selecting a preset number of proposed observation points from the neighboring proposed observation points according to the principle of increasing distance; S403: Determine the shooting direction angle of the typical marker in the street view image corresponding to the selected proposed observation point; S404: drawing a line segment along the shooting direction angle with the selected proposed observation point as the endpoint and the fixed distance threshold as the length; S405: Calculate the coordinates of the intersections of all line segments and record them in the typical marker set; S406: Calculating a uniqueness index of each typical marker according to the street view image metadata and the intersection coordinates, wherein the uniqueness index includes a height of a utility pole, a height of a power tower, and a width of a manhole cover; S407: considering the two typical markers with the closest uniqueness indexes as the same true typical marker; S408: Recording the intersection points corresponding to the true typical markers into the true typical marker set; S409: Consider the intersection points in the true typical marker set as the spatial coordinates of the corresponding typical markers.

6. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The cost function is specifically: ； in, C represents the cost of water and electricity pipe network, C L represents the pipeline length cost, represents the pipeline angle cost, C T Represents the pipeline laying cost.

7. The urban water and electricity network intelligent modeling method according to claim 1 is characterized in that: The S8 specifically includes: S801: Calculate the interval distance from each source point to each end point; S802: Determine a multi-source hydropower user end point using multiple source point resources according to the interval distance; S803: adding branch pipe networks at the terminal points of each multi-source hydropower user to form a tree-shaped topology pipe network including the branch pipe networks; S804: Changing the connection form of the tree-shaped topology pipe network to a ring-shaped topology pipe network; S805: Dividing each ring topology pipe network into a high-level water and electricity pipe network and a low-level water and electricity pipe network according to the scale of the administrative area and the degree of aggregation of the building space; S806: Connecting the high-level water and electricity pipe network end point and the low-level water and electricity pipe network source point to obtain the target water and electricity pipe network model.

8. An intelligent modeling system for urban water and electricity pipe networks, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the method for intelligent modeling of an urban water and electricity pipeline network as described in any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the urban water and electricity pipeline network intelligent modeling method as described in any one of claims 1 to 7 is implemented.

Images