Park digital twinborn model construction method, device, equipment and medium

Abstract

The invention relates to a park digital twinborn model construction method and device, equipment and a medium, and effectively solves the technical problems that a digital twinborn model is poor in effect and cannot meet actual requirements, and in the model construction process, the transmission data size is large, the requirement for the computing power is high, and the implementation difficulty is large. The park digital twinborn model construction method comprises the following steps: acquiring real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building in a park; inputting the real-time three-dimensional point cloud data and the real-time satellite remote sensing data into a local digital twinborn construction model to obtain real-time local digital twinborn model parameters; and determining a global digital twinborn model of the park based on the real-time local digital twinborn model parameters.

Description

Technical Field

[0001] The present disclosure relates to the field of digital twin technology and data processing, and in particular to a method, device, equipment and medium for constructing a digital twin model of a park. Background Art

[0002] Building Information Modeling (BIM) has been recognized as the next generation of focus modeling technology in the global construction industry. BIM models contain rich data on the microscopic level of buildings, focusing on the geometric characteristics, spatial structure models and attribute information management of the buildings within the park. Geographic Information System (GIS) uses massive amounts of earth's geographic spatial data as an object to perform technical operations such as collection, storage, visualization, processing, analysis and management. It is widely used in spatial planning, location selection, topological analysis, etc. of park environments. GIS models can provide geographic spatial data from a macro perspective, focusing on the display and analysis of geographic environmental information outside buildings.

[0003] However, in the existing technology, only BIM data is used as the supporting data for the construction of digital twin models, and the model lacks model considerations from a macro-geographical spatial perspective, resulting in the inability of the existing digital twin models to reflect the actual terrain and geographical conditions, and the practicability of the models is poor; some existing technologies use simple superimposed BIM and GIS technology to construct digital twin models, lacking the deep coupling of BIM data and GIS data, and the constructed digital twin models are poor and cannot meet actual needs. In addition, during the model construction process, the amount of data transmitted is huge, which requires high computing power and is difficult to implement. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and medium for constructing a digital twin model of a park, which effectively solves the technical problems that the digital twin model has poor effect and cannot meet actual needs, and in the process of model construction, the amount of data transmitted is huge, the computing power requirements are high, and the implementation is difficult.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for constructing a digital twin model of a park, the method comprising:

[0006] In a possible implementation manner, in the method provided by the embodiment of the present invention, before determining the global digital twin model of the park based on the real-time local digital twin model parameters, the method further includes:

[0007] According to the parameters of the real-time local digital twin model, the real-time local digital twin model is reconstructed using a projection triangulation algorithm;

[0008] Simplify real-time local digital twin models using edge collapsing method.

[0009] In a possible implementation manner, in the method provided by an embodiment of the present invention, determining a global digital twin model of a park based on real-time local digital twin model parameters includes:

[0010] Aggregate multiple local digital twin models to obtain a global digital twin model of the park;

[0011] Visualize the global digital twin model.

[0012] In one possible implementation, in the method provided in the embodiment of the present invention, the local digital twin construction model is trained by the following method:

[0013] Obtain historical 3D point cloud data and historical satellite remote sensing data of each building in the park;

[0014] Determine the parameters of the historical local digital twin model using historical 3D point cloud data and historical satellite remote sensing data;

[0015] Taking historical 3D point cloud data and historical satellite remote sensing data as input, the model parameters corresponding to the output of historical 3D point cloud data and historical satellite remote sensing data are compared with the parameters of the historical local digital twin model;

[0016] The local digital twin construction model is generated based on the difference training between the output model parameters and the historical local digital twin model parameters.

[0017] In a possible implementation, in the method provided by the embodiment of the present invention, after acquiring the historical three-dimensional point cloud data and historical satellite remote sensing data of each building in the park, the method further includes:

[0018] Preprocess historical 3D point cloud data.

[0019] In a possible implementation, in the method provided by an embodiment of the present invention, the local digital twin construction model is generated based on the difference training between the output model parameters and the historical local digital twin model parameters, including:

[0020] Determine the loss function of the local digital twin construction model according to the model parameters and the historical local digital twin model parameters;

[0021] When the loss function is less than a preset value, a local digital twin construction model is obtained.

[0022] In a possible implementation, in the method provided by an embodiment of the present invention, the loss function of the local digital twin construction model is determined according to the model parameters and the historical local digital twin model parameters, including:

[0023] The loss function is determined according to the following formula:

[0024] L=E[||(r+γmaxQ(s',a'))-Q(s,a)|| 2 ];

[0025] Among them, L is the loss function; Q(s,a) is the historical local digital twin model parameter; Q(s',a') is the model parameter; r and γ are the parameters of the loss function; E is the square mean function.

[0026] In a second aspect, an embodiment of the present disclosure provides a device for constructing a digital twin model of a park, the device comprising:

[0027] Acquisition unit, used to acquire real-time 3D point cloud data and real-time satellite remote sensing data of each building in the park;

[0028] A processing unit, used to input real-time three-dimensional point cloud data and real-time satellite remote sensing data into a local digital twin construction model to obtain real-time local digital twin model parameters;

[0029] A determination unit is used to determine a global digital twin model of the park based on real-time local digital twin model parameters.

[0030] In a possible implementation manner, in the device provided by the embodiment of the present invention, the determining unit is further configured to:

[0031] According to the parameters of the real-time local digital twin model, the real-time local digital twin model is reconstructed using a projection triangulation algorithm;

[0032] Simplify real-time local digital twin models using edge collapsing method.

[0033] In a possible implementation manner, in the device provided by the embodiment of the present invention, the determining unit is further configured to:

[0034] Aggregate multiple local digital twin models to obtain a global digital twin model of the park;

[0035] Visualize the global digital twin model.

[0036] In a possible implementation manner, the device provided in the embodiment of the present invention further includes a model training unit, which is used to:

[0037] Obtain historical 3D point cloud data and historical satellite remote sensing data of each building in the park;

[0038] Determine the parameters of the historical local digital twin model using historical 3D point cloud data and historical satellite remote sensing data;

[0039] Taking historical 3D point cloud data and historical satellite remote sensing data as input, the model parameters corresponding to the output of historical 3D point cloud data and historical satellite remote sensing data are compared with the parameters of the historical local digital twin model;

[0040] The local digital twin construction model is generated based on the difference training between the output model parameters and the historical local digital twin model parameters.

[0041] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0042] Preprocess historical 3D point cloud data.

[0043] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0044] Determine the loss function of the local digital twin construction model according to the model parameters and the historical local digital twin model parameters;

[0045] When the loss function is less than a preset value, a local digital twin construction model is obtained.

[0046] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0047] The loss function is determined according to the following formula:

[0048] L=E[||(r+γmaxQ(s',a'))-Q(s,a)|| 2 ];

[0049] Among them, L is the loss function; Q(s,a) is the historical local digital twin model parameter; Q(s',a') is the model parameter; r and γ are the parameters of the loss function; E is the square mean function.

[0050] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0051] Memory;

[0052] Processor; and

[0053] Computer programs;

[0054] Among them, the computer program is stored in the memory and is configured to be executed by the processor to implement the method for constructing a digital twin model of a park as described above.

[0055] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for constructing a digital twin model of a park as described above are implemented.

[0056] The present disclosure provides a method for constructing a digital twin model of a park, including:

[0057] First, the real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building in the park are obtained, and then the real-time three-dimensional point cloud data and real-time satellite remote sensing data are input into the local digital twin construction model to obtain the real-time local digital twin model parameters, and finally the global digital twin model of the park is determined based on the real-time local digital twin model parameters. By applying the park digital twin model construction method provided by the present disclosure, the local digital twin construction model is used to automatically obtain the real-time local digital twin model parameters, avoiding the cumbersome manual setting and manual modeling process of the local digital twin model, and improving the efficiency of digital twin construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0060] Figure 1 A schematic diagram of a process for constructing a digital twin model of a park provided in an embodiment of the present disclosure;

[0061] Figure 2 A schematic diagram of a training method for constructing a digital twin model of a park provided in an embodiment of the present disclosure;

[0062] Figure 3 A schematic diagram of the structure of a device for building a digital twin model of a park provided in an embodiment of the present disclosure;

[0063] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0064] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0065] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0066] 1. In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0067] Building Information Modeling (BIM) has been recognized as the next generation of focus modeling technology in the global construction industry. BIM models contain rich data on the microscopic level of buildings, focusing on the geometric characteristics, spatial structure models and attribute information management of the buildings within the park. Geographic Information System (GIS) uses massive amounts of earth's geographic spatial data as an object to perform technical operations such as collection, storage, visualization, processing, analysis and management. It is widely used in spatial planning, location selection, topological analysis, etc. of park environments. GIS models can provide geographic spatial data from a macro perspective, focusing on the display and analysis of geographic environmental information outside buildings.

[0068] However, in the existing technology, only BIM data is used as the supporting data for the construction of digital twin models, and the model lacks model considerations from a macro-geographical spatial perspective, resulting in the inability of the existing digital twin models to reflect the actual terrain and geographical conditions, and the practicability of the models is poor; some existing technologies use simple superimposed BIM and GIS technology to construct digital twin models, lacking the deep coupling of BIM data and GIS data, and the constructed digital twin models are poor and cannot meet actual needs. In addition, during the model construction process, the amount of data transmitted is huge, which requires high computing power and is difficult to implement.

[0069] Figure 1 A schematic diagram of a method for constructing a digital twin model of a park provided in an embodiment of the present disclosure, specifically including the following steps: Figure 1 The following steps S101 to S103 are shown:

[0070] S101. Acquire real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building in the park.

[0071] In the specific implementation, real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building are obtained through sensors installed in each building in the park.

[0072] S102: input the real-time three-dimensional point cloud data and the real-time satellite remote sensing data into the local digital twin construction model to obtain the real-time local digital twin model parameters.

[0073] During the specific implementation, real-time three-dimensional point cloud data and real-time satellite remote sensing data are input into the local digital twin construction model to construct the local digital twin and obtain the real-time local digital twin model parameters.

[0074] S103. Determine the global digital twin model of the park based on the real-time local digital twin model parameters.

[0075] In the specific implementation, the real-time local digital twin model is first reconstructed using the projection triangulation algorithm according to the real-time local digital twin model parameters, and then the real-time local digital twin model is simplified using the edge folding method. Specifically:

[0076] According to the parameters of the real-time local digital twin model, the projection triangulation algorithm is used to reconstruct the surface to obtain the reconstructed real-time local digital twin model. Then, the original vertex data and corresponding patch data of the reconstructed real-time local digital twin model are extracted. Then, the edge folding method is used to simplify the reconstructed real-time local digital twin model to obtain the folded new vertex data corresponding to the original vertex data. The formula is:

[0077] Δ(v)=Δ([v x ,v y ,v z ,1] T )=∑(p T v) 2 =∑K p v;

[0078] Where Δ(v) is the vertex cost of the edge collapsing method; (v x ,v y ,v z ,1) is the original vertex coordinate; v is the original vertex; p is the linear coefficient of the patch where the vertex v is located; K p is the fundamental quadratic error.

[0079] For the new vertex after folding The folding cost formula is:

[0080]

[0081] In the formula, New vertex data after folding The folding cost; is the new vertex after folding; Q1 and Q2 are the K corresponding to Δ(v) p The matrix expression of The corresponding K p The matrix expression of .

[0082] Then, determine whether the patch data of the new vertex data after folding overlaps with the patch data of the original vertex data. If so, delete one of the patch data. Then determine whether the new vertex data after folding of the local digital twin model overlaps with the new vertex data after folding of the adjacent local digital twin model. If so, delete the patch data corresponding to one of the new vertex data after folding. Finally, according to the patch data of all local digital twin models, the local digital twin models are aggregated to obtain the global digital twin model of the park, and the global digital twin model is visualized.

[0083] Figure 2 A flow chart of a training method for building a digital twin model of a park provided in an embodiment of the present disclosure, specifically including the following steps: Figure 2 The following steps S201 to S203 are shown:

[0084] S201. Obtain historical three-dimensional point cloud data and historical satellite remote sensing data of each building in the park.

[0085] During the specific implementation, historical three-dimensional point cloud data of buildings in the park and basic equipment outside the buildings, as well as historical satellite remote sensing data of buildings are collected, and an adaptive streamlined point cloud data preprocessing method is used to preprocess the historical three-dimensional point cloud data to obtain preprocessed historical three-dimensional point cloud data. Specifically, a statistical filtering algorithm is first used to denoise the historical three-dimensional point cloud data to obtain denoised historical three-dimensional point cloud data.

[0086] (1) Perform statistical analysis on all point domains in the historical 3D point cloud data to obtain the distance from any point to the domain. The formula is:

[0087]

[0088] Where, d i For any point P i Distance to the field; (x i ,y i ,z i )、(x' i ,y' i ,z' i ) is any point P i The coordinates of and the coordinates of a point in the domain;

[0089] (2) Obtain the mean and standard deviation of the Gaussian distribution of the distance from any point to the domain. The formula is:

[0090]

[0091] Where, μ is the mean of Gaussian distribution; σ is the standard deviation of Gaussian distribution; i is the point cloud indicator; n is the number of point clouds in the field;

[0092] (3) According to the mean and standard deviation of the Gaussian distribution, the distance threshold is obtained, and any point whose distance to the field exceeds the distance threshold is deleted as an outlier. The formula is:

[0093] D dist =μ+σ·std

[0094] Where D dist is the distance threshold; std is the preset standard deviation multiple; then all points in the historical 3D point cloud data are traversed to obtain the historical 3D point cloud data after denoising.

[0095] After preprocessing, the adaptive downsampling algorithm is used to simplify the denoised historical 3D point cloud data to obtain simplified historical 3D point cloud data. Specifically:

[0096] First, the denoised historical 3D point cloud data is divided into several cubic voxels, and then the voxel grids in the cubic voxels are encoded to obtain the spatial index of each voxel grid (h x ,h y ,h z ), and then for any point p in the historical 3D point cloud data after denoising i , use the kd-tree algorithm to search the number of its neighboring points and get the covariance matrix. The formula is:

[0097]

[0098] Where M is the covariance matrix; p i is an arbitrary point; p0 is the centroid of the neighborhood point; i is the point cloud indicator; k is the number of point clouds in the field;

[0099] Then get any point p i The arithmetic mean of the angles between the normal vectors of its neighboring points is used to select the feature points in the historical 3D point cloud data after denoising. The formula is:

[0100]

[0101] In the formula, f i is the arithmetic mean; θ ij For any point p i The angle between the normal vector of its neighboring points;

[0102] If f i ≥ε, any point p i is the feature point, ε is the arithmetic mean threshold;

[0103] Finally, the spatial index (h x ,h y ,h z ), find the feature point closest to the center of gravity of each voxel, and use this feature point to replace all points in the voxel grid, implement downsampling based on the feature points near the center of gravity of the voxel, and obtain the simplified historical 3D point cloud data. The formula is:

[0104] H[a(s)λ+l0] <K max

[0105]

[0106] Where H is the voxel filter function; a(s) is the adaptive growth factor; λ is the growth step of the voxel grid.

[0107] length; l0 is the initial voxel grid edge length; K max is the expected number of point clouds to be set; s is the adaptive growth parameter; N i , N is the number of historical 3D point clouds after denoising and the number of historical 3D point clouds after streamlining.

[0108] After simplification, the moving least squares method is used to smooth and optimize the simplified historical 3D point cloud data to obtain the pre-processed historical 3D point cloud data. The formula is:

[0109]

[0110] A=(BWB T ) -1 BW

[0111]

[0112] In the formula, For node x i The weight function of this application uses the moving least squares weight function - Gaussian weight function; h is a parameter that affects the smoothing strength of the point cloud. The larger h is, the larger the Gaussian weight function is, and the stronger the point cloud smoothing strength is; B is about the quadratic basis function matrix; W is the weight function The diagonal matrix of y = [y1, y2, ..., y n ] T For node x i The value of is a quadratic basis function; A is a coefficient matrix to be determined, and A=[a1(x), a2(x), ..., a n (x)] T ; a n (x) is the unknown coefficient; f(x) is the fitting function.

[0113] S202. Determine the parameters of the historical local digital twin model using historical three-dimensional point cloud data and historical satellite remote sensing data.

[0114] In the specific implementation, according to the pre-processed historical 3D point cloud data and historical satellite remote sensing data, the GIS+BIM technology is used to construct the historical local digital twin model of the building, and the parameters of the historical local digital twin model are extracted. Specifically, firstly, according to the pre-processed historical 3D point cloud data, the 3D model visualization tool Civil 3D is used to build the 3D space model of the building. Then, the BIM system Revit is used to convert the solid model output by the Civil 3D tool into a BIM model in Sat format through the Dynamo tool. That is, the 3D space model of the building is converted into a BIM model, and the BIM model of the building is established. Then, the plug-in SuperMap Export and install it in Revit. According to the BIM segmentation plan, the BIM model of the building is segmented, layered, and segmented to obtain the segmented BIM components. The area, layer, and segment information is filled into the BIM components as attributes to achieve the segmentation of BIM model components. Preparations are made for the subsequent GIS system import, and then the BIM data of the BIM components are input into the GIS system. In the process of importing the BIM model into the GIS system, in order to ensure the accuracy and completeness of the model information details, it is bound to cause problems such as excessive data volume, slow loading speed, low rendering efficiency, and system memory crash, which will affect the operation function of the GIS system. In order to realize the real-time visualization and analysis function of the BIM model on the GIS system and ensure its accuracy and visualization efficiency, it is necessary to optimize the model, reduce the amount of data, and use the two algorithms of vertex deletion and triangle face folding to simplify or delete the component skeleton, which can well achieve the purpose of lightweight three-dimensional model and reduce the operating pressure of hardware equipment such as computer CPU; finally, according to the historical satellite remote sensing data, the environmental three-dimensional model is constructed in the GIS system, and the BIM data of the BIM components are reconstructed into the GIS model to obtain the reconstructed historical local digital twin model of the building combining BIM and GIS, and the historical local digital twin model parameters are extracted.

[0115] S203. Using historical three-dimensional point cloud data and historical satellite remote sensing data as input, compare the model parameters corresponding to the output of the historical three-dimensional point cloud data and the historical satellite remote sensing data with the historical local digital twin model parameters, and generate a local digital twin construction model based on the difference between the output model parameters and the historical local digital twin model parameters.

[0116] In the specific implementation, according to S202, several historical local digital twin model parameters can be obtained, and the local digital twin model is constructed using the deep reinforcement learning algorithm using the several historical local digital twin model parameters. Specifically, first use (deep The deep reinforcement learning model is constructed by using the Deep Q-network (DQN) algorithm. Deep reinforcement learning allows the intelligent agent to observe the state of the environment by itself. Through the perception processing of deep learning, the intelligent agent can learn to observe the characteristics of the state of the environment. Then, through the decision-making training of reinforcement learning, the entire deep reinforcement learning structure is completed. The basic principle is to estimate the value of each action of the digital twin model through a multi-layer neural network, and then select the optimal action based on these values ​​to complete the digital twin construction task and extract the corresponding digital twin model parameters. Then, the collected historical three-dimensional point cloud data and historical satellite remote sensing data are input into the initial deep reinforcement learning model, and the true values ​​of the historical local digital twin model parameters are input into the initial deep reinforcement learning model for optimization to obtain the predicted values ​​of the historical local digital twin model parameters. Then, according to the predicted values ​​of the historical local digital twin model parameters and the true values ​​of the historical local digital twin model parameters, the loss function value of the local digital twin construction model is obtained. The formula is:

[0117] L=E[||(r+γmaxQ(s',a'))-Q(s,a)|| 2 ]

[0118] Wherein, L is the loss function value of the local digital twin construction model; Q(s,a) is the output model parameter; Q(s',a') is the historical local digital twin model parameter; r and γ are the loss function parameters; E is the square mean function. When the loss function value is less than the preset value, the optimal local digital twin construction model is obtained. The preset value can be set according to demand, and the embodiment of the present disclosure is not limited to this.

[0119] Based on the same concept, the park digital twin model construction method provided in the embodiment of the present disclosure can be implemented through a park digital twin model construction system, and the system architecture mainly includes a terminal layer, an edge layer and a digital twin layer.

[0120] The terminal layer is used to collect historical three-dimensional point cloud data of buildings in the park and basic equipment outside the buildings, as well as historical satellite remote sensing data of the buildings, and upload them to the edge layer through the Internet of Things. The edge layer adopts a 5G edge computing mode to deploy small base stations equipped with edge servers at the edge layer, receive the historical three-dimensional point cloud data of buildings in the park and basic equipment outside the buildings, as well as historical satellite remote sensing data of the buildings uploaded by the terminal layer, and build a local digital twin model with the edge collaborative decision issued by the digital twin layer to obtain a local digital twin model of the park, and upload the local digital twin model parameters to the digital twin layer. The digital twin layer is used to aggregate the global digital twin model according to all local digital twin model parameters of the terminal layer to obtain a global digital twin model of the park.

[0121] The terminal layer includes several three-dimensional point cloud data acquisition terminals, several Internet of Things gateways and several data servers set up inside the park. The three-dimensional point cloud data acquisition terminals are used to collect historical three-dimensional point cloud data of buildings in the park and basic equipment outside the buildings; the Internet of Things gateway is a 5G edge computing gateway, which is used to pre-process the historical three-dimensional point cloud data using an adaptive streamlined point cloud data pre-processing method to obtain the pre-processed historical three-dimensional point cloud data, and send the pre-processed historical three-dimensional point cloud data to the data server; the data server is used to store historical satellite remote sensing data of buildings and surrounding environment.

[0122] The edge layer includes several small base stations and several edge servers, wherein the data server sends the pre-processed historical three-dimensional point cloud data and the historical satellite remote sensing data of the building and the surrounding environment stored internally to the corresponding edge server through the small base station, so as to disperse the digital mapping work of the park buildings to the edge layer and reduce the computing pressure of the digital twin layer; the edge server includes a local digital twin construction module, a model data processing module, a model training module, a local digital twin construction module and an edge collaboration module; the local digital twin construction module is used to construct a historical local digital twin model of the building based on the pre-processed historical three-dimensional point cloud data and the satellite remote sensing data of the building and the surrounding environment sent by the data server, and extract the historical local digital twin model parameters; the model data processing module is used to convert the historical local digital twin model parameters, pre-processed The historical three-dimensional point cloud data and the historical satellite remote sensing data of the building and its surrounding environment are processed to obtain model training data in a data format that meets the input requirements of the deep reinforcement learning model; the model training module is used to construct a local digital twin construction model according to the model training data and the deep reinforcement learning algorithm, and set the local digital twin construction model in the local digital twin construction module; the local digital twin construction module is used to use the local digital twin construction model to construct a local digital twin according to the real-time three-dimensional point cloud data of the buildings in the park and the basic equipment outside the buildings, as well as the real-time satellite remote sensing data of the buildings, to obtain the real-time local digital twin model parameters; the edge collaboration module is used to receive the edge collaboration decisions issued by the digital twin layer, generate edge collaboration instructions, and send them to other edge servers to provide server computing resources for the writing and training of the deep reinforcement learning module.

[0123] The digital twin layer includes an edge collaboration control module, a model aggregation module, a digital twin management module and a model visualization module. The edge collaboration control module is used to generate edge collaboration decisions based on the computing resources of the edge server of the edge layer, and send the edge collaboration decisions to the edge layer; the model aggregation module is used to reconstruct several local digital twin model parameters sent by the edge layer, and aggregate them according to the patch structure of the local digital twin model to obtain the global digital twin model of the park; the digital twin management module is provided with functional modules of business management, inspection management, park management, emergency management and system management, which are used to visualize the global digital twin model of the park.

[0124] Figure 3 The schematic diagram of the structure of the digital twin model construction device of the park provided in the embodiment of the present disclosure is as follows. The digital twin model construction device 300 of the park provided in the embodiment of the present disclosure can execute the processing flow provided in the above-mentioned method for constructing the digital twin model of the park, such as Figure 3As shown, the digital twin model construction device 700 of the park includes an acquisition unit 301, a processing unit 302 and a determination unit 303, wherein:

[0125] The acquisition unit 301 is used to acquire real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building in the park;

[0126] The processing unit 302 is used to input the real-time three-dimensional point cloud data and the real-time satellite remote sensing data into the local digital twin construction model to obtain the real-time local digital twin model parameters;

[0127] The determination unit 303 is used to determine the global digital twin model of the park based on the real-time local digital twin model parameters.

[0128] In a possible implementation manner, in the device provided by the embodiment of the present invention, the determining unit 303 is further configured to:

[0129] According to the parameters of the real-time local digital twin model, the real-time local digital twin model is reconstructed using a projection triangulation algorithm;

[0130] Simplify real-time local digital twin models using edge collapsing method.

[0131] In a possible implementation manner, in the device provided by the embodiment of the present invention, the determining unit 303 is further configured to:

[0132] Aggregate multiple local digital twin models to obtain a global digital twin model of the park;

[0133] Visualize the global digital twin model.

[0134] In a possible implementation manner, the device provided in the embodiment of the present invention further includes a model training unit, which is used to:

[0135] Obtain historical 3D point cloud data and historical satellite remote sensing data of each building in the park;

[0136] Determine the parameters of the historical local digital twin model using historical 3D point cloud data and historical satellite remote sensing data;

[0137] Taking historical 3D point cloud data and historical satellite remote sensing data as input, the model parameters corresponding to the output of historical 3D point cloud data and historical satellite remote sensing data are compared with the parameters of the historical local digital twin model;

[0138] The local digital twin construction model is generated based on the difference training between the output model parameters and the historical local digital twin model parameters.

[0139] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0140] Preprocess historical 3D point cloud data.

[0141] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0142] Determine the loss function of the local digital twin construction model according to the model parameters and the historical local digital twin model parameters;

[0143] When the loss function is less than a preset value, a local digital twin construction model is obtained.

[0144] In a possible implementation manner, in the device provided by the embodiment of the present invention, the model training unit is specifically used for:

[0145] The loss function is determined according to the following formula:

[0146] L=E[||(r+γmaxQ(s',a'))-Q(s,a)|| 2 ];

[0147] Among them, L is the loss function; Q(s,a) is the historical local digital twin model parameter; Q(s',a') is the model parameter; r and γ are the parameters of the loss function; E is the square mean function.

[0148] Figure 3 The campus digital twin model building device of the illustrated embodiment can be used to execute the technical solution of the above-mentioned method embodiment. Its implementation principle and technical effects are similar and will not be repeated here.

[0149] In addition, combined Figure 1-Figure 3 The method and device for constructing a digital twin model of a park described in the embodiments of the present application can be implemented by an electronic device. Figure 4 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0150] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 to a random access memory (RAM) 403 to implement the campus digital twin model construction method of the embodiment described in the present disclosure. In RAM 403, various programs and data required for the operation of the electronic device 400 are also stored. The processing device 401, ROM 402, and RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0151] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0152] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart, thereby implementing the voice control method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0153] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0154] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0155] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0156] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device:

[0157] Obtain real-time 3D point cloud data and real-time satellite remote sensing data of each building in the park;

[0158] Input real-time 3D point cloud data and real-time satellite remote sensing data into the local digital twin construction model to obtain real-time local digital twin model parameters;

[0159] Determine the global digital twin model of the park based on the real-time local digital twin model parameters.

[0160] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0161] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0162] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0163] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0164] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0165] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0166] The present disclosure provides a method for constructing a digital twin model of a park, including:

[0167] First, the real-time three-dimensional point cloud data and real-time satellite remote sensing data of each building in the park are obtained, and then the real-time three-dimensional point cloud data and real-time satellite remote sensing data are input into the local digital twin construction model to obtain the real-time local digital twin model parameters, and finally the global digital twin model of the park is determined based on the real-time local digital twin model parameters. By applying the park digital twin model construction method provided by the present disclosure, the local digital twin construction model is used to automatically obtain the real-time local digital twin model parameters, avoiding the cumbersome manual setting and manual modeling process of the local digital twin model, and improving the efficiency of digital twin construction.

[0168] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0169] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0170] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0171] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0172] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0173] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for constructing a digital twin model of a park, characterized in that: The method comprises: Obtain real-time 3D point cloud data and real-time satellite remote sensing data of each building in the park; Inputting the real-time three-dimensional point cloud data and the real-time satellite remote sensing data into a local digital twin construction model to obtain real-time local digital twin model parameters; A global digital twin model of the park is determined based on the real-time local digital twin model parameters.

2. The method according to claim 1, characterized in that Before determining the global digital twin model of the park based on the real-time local digital twin model parameters, the method further includes: Reconstructing the real-time local digital twin model using a projection triangulation algorithm according to the real-time local digital twin model parameters; The real-time local digital twin model is simplified using an edge collapse method.

3. The method according to claim 2, characterized in that Determining the global digital twin model of the park based on the real-time local digital twin model parameters includes: Aggregating the multiple local digital twin models to obtain a global digital twin model of the park; The global digital twin model is visualized.

4. The method according to claim 3, characterized in that The local digital twin construction model is trained by the following method: Obtain historical 3D point cloud data and historical satellite remote sensing data of each building in the park; Determining historical local digital twin model parameters using the historical three-dimensional point cloud data and the historical satellite remote sensing data; Taking the historical three-dimensional point cloud data and the historical satellite remote sensing data as input, comparing the model parameters outputted corresponding to the historical three-dimensional point cloud data and the historical satellite remote sensing data with the historical local digital twin model parameters; The local digital twin construction model is generated based on the difference training between the output model parameters and the historical local digital twin model parameters.

5. The method according to claim 4, characterized in that After acquiring the historical three-dimensional point cloud data and historical satellite remote sensing data of each building in the park, the method further includes: The historical three-dimensional point cloud data is preprocessed.

6. The method according to claim 5, characterized in that The training of generating the local digital twin construction model based on the difference between the output model parameters and the historical local digital twin model parameters includes: Determining a loss function of the local digital twin construction model according to the model parameters and the historical local digital twin model parameters; When the loss function is less than a preset value, the local digital twin construction model is obtained.

7. The method according to claim 6, characterized in that The determining the loss function of the local digital twin construction model according to the model parameters and the historical local digital twin model parameters includes: The loss function is determined according to the following formula: L=E[||(r+γmaxQ(s',a'))-Q(s,a)|| 2 ]; Among them, L is the loss function; Q(s,a) is the historical local digital twin model parameter; Q(s',a') is the model parameter; r and γ are the parameters of the loss function; E is the square mean function.

8. A device for constructing a digital twin model of a park, characterized in that: The device comprises: Acquisition unit, used to acquire real-time 3D point cloud data and real-time satellite remote sensing data of each building in the park; A processing unit, used for inputting the real-time three-dimensional point cloud data and the real-time satellite remote sensing data into a local digital twin construction model to obtain real-time local digital twin model parameters; A determination unit is used to determine the global digital twin model of the park based on the real-time local digital twin model parameters.

9. An electronic device, characterized in that: include: Memory; processor; as well as Computer programs; Wherein, the computer program is stored in the memory and is configured to be executed by the processor to implement the method for constructing a digital twin model of a park as described in any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, a method for constructing a digital twin model of a park as described in any one of claims 1 to 7 is implemented.

Images