Urban district planning construction management operation and maintenance method and system based on three-dimensional digital twinning

Abstract

The invention discloses an urban district regulation construction management operation and maintenance method and system based on three-dimensional digital twinning, and the method comprises the steps: collecting multi-source data, including geographic raster data, BIM model data and mobile phone signaling data, of an urban district, and achieving the coordinate alignment of the multi-source data through an LM algorithm; the multi-source data generates feature data composed of coding tables defining urban features through feature engineering, and an octree is constructed based on the feature data; defining leaf nodes of the octree as voxels, and applying multi-scale convolution to each voxel to obtain super voxels with space-time labels; constructing a constraint network based on the super voxels and a construction, management or operation and maintenance specification constraint library; and judging the risk area of the city district by calculating the space-time constraint intensity of the constraint edge, and outputting a corresponding risk area list. According to the invention, the problems of multi-source data integration, real-time dynamic monitoring and risk prediction in the planning, construction, management, operation and maintenance processes of the urban district are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twins, and particularly relates to a method and system for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twins. Background Art

[0002] Currently, in the fields of urban area planning, construction, management, operation and maintenance, a separate management mode of two-dimensional GIS and BIM models, static three-dimensional modeling technology, and decision-making methods dominated by manual experience are mainly adopted. Traditional two-dimensional planning methods rely on plane drawings for spatial layout design, and there are problems such as the lack of three-dimensional spatial information and difficulties in multi-disciplinary collaboration; although the digital twin technology based on a single data source can build three-dimensional models, it cannot integrate dynamic spatio-temporal data such as mobile phone signaling, resulting in a lack of data support for dynamic management such as resource scheduling. Most existing three-dimensional modeling systems adopt a fixed-level spatial index structure, which is difficult to adapt to the dynamic changes of urban characteristics and the requirements of spatio-temporal correlation analysis. In terms of specification constraint processing, existing methods usually adopt a static verification method of manually comparing specification clauses, lacking the ability to monitor the spatio-temporal conflicts of elements such as machinery, materials, and personnel in the construction process in real time. Risk identification mostly relies on discrete sensor data and expert experience judgment, and cannot achieve systematic risk prediction based on spatial topological relationships and spatio-temporal evolution.

[0003] Chinese Patent with Publication No. CN118279506A discloses a 3D urban planning visualization system based on satellite images, including a system structure composed of an application layer, a GIS service layer, a data layer, and a physical layer. The processing method of the system for 3D urban planning is as follows: Sp1: Satellite image setting and data collection. The satellite image setting and data collection is that the application layer in the system connects with the satellite image to collect images within a specified urban area. The satellite image selects the Beidou system, and the satellite image uses oblique photography technology to collect urban data. Sp2: Collection of urban geographical data. The collection of urban geographical data is that the GIS service layer uses geographic information system technology to collect data on urban ground information, geographical conditions, etc. Sp3: Collection of urban color information. The collection of urban color information is that the application layer summarized by the system connects with an unmanned aerial vehicle to collect low-altitude multi-directional panoramic images of the city. Sp4: Data integration and processing. The data integration and processing is to summarize the data collected in steps Sp1 - Sp3 to the data layer in the system for resource integration and data analysis and processing. Sp5: 3D urban modeling. The 3D urban modeling is that the data layer in the system uses real-scene 3D modeling technology to perform 3D urban modeling on the data according to the obtained data information. Sp6: Improvement of the 3D urban model. The improvement of the 3D urban model is that the application layer in the system reads the information in the existing urban BIM model library and performs data comparison of corresponding building information to improve the 3D urban model. Sp7: 3D urban planning. The 3D urban planning is to perform visual planning on the urban area for the 3D urban model completed in step Sp6. This system lacks the integration of real-time feedback and operation and maintenance data during the operation and management of urban areas and cannot provide support for urban operation and maintenance and real-time changes. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for urban area planning, construction, management, and operation and maintenance based on 3D digital twin to solve the technical problems of multi-source data integration, real-time dynamic monitoring, and risk prediction during the planning, construction, management, and operation and maintenance of urban areas.

[0005] The technical solution of the present invention is as follows: On the one hand, the present invention provides a method for urban area planning, construction, management, and operation and maintenance based on 3D digital twin, including the following steps: Collect multi-source data of the urban area, including geographic grid data, BIM model data, and mobile phone signaling data, and achieve coordinate alignment of the multi-source data through the LM algorithm; The multi-source data generates feature data composed of a coding table defining urban features through feature engineering, and an octree is constructed based on the feature data; Define the leaf nodes of the octree as voxels, and apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels; Construct a constraint network based on supervoxels and a construction, management, or operation and maintenance specification constraint library. Nodes in the constraint network are defined as mechanical nodes, material nodes, and personnel nodes, and constraint edges are defined as resource dependence edges and spatial conflict edges; Determine the risk areas of urban areas by calculating the spatio-temporal constraint intensity of the constraint edges, and output a corresponding list of risk areas.

[0006] Preferably, the spatio-temporal alignment of multi-source data is achieved through the LM algorithm as follows: Select a group of homologous points in the geographic grid data, BIM model data, and mobile phone signaling data respectively with respect to the target coordinate system Construct an error equation based on the homologous points:

[0007] In the formula, is the error value of the th homologous point, ; is the coordinate of the th homologous point in the target coordinate system; is the coordinate of the th homologous point in the geographic grid data, BIM model data, and mobile phone signaling data; is the rotation matrix; is the translation vector; Solve for the optimal error value through SVD decomposition to obtain the initial rotation matrix and the initial translation vector; Define a coordinate transformation function based on the initial rotation matrix and the initial translation vector; Construct a coordinate transformation optimization function based on the coordinate transformation function:

[0008] In the formula, is the coordinate transformation optimization function of the coordinate ; is the scale factor; is the coordinate point; is the initial rotation matrix; is the initial translation vector; Use the LM algorithm to solve the coordinate transformation optimization function to obtain the optimal rotation matrix and the optimal translation vector, and use the optimal rotation matrix and the optimal translation vector to convert the geographic grid data, BIM model data, and mobile phone signaling data to the target coordinate system to achieve the coordinate alignment of multi-source data.

[0009] Preferably, the multi-source data generates feature data composed of a coding table defining urban features through feature engineering. The construction of an octree based on the feature data is as follows: The feature data includes mechanical features, material features, and personnel features, and the three-dimensional space containing the entire urban area is initialized as the root node; Calculate the difference degree of the feature data within the node. When the difference degree of the feature data within the node is greater than the set threshold, the node is divided into 8 sub-nodes, and each sub-node stores the statistical value of the urban features within the corresponding three-dimensional space. The specific calculation of the feature data difference degree is as follows:

[0010] In the formula, is the difference degree of the feature data of the sub-node , reflecting the dispersion degree of the feature distribution; is the sub-node index of the octree, ; is the urban feature index of the sub-node ; is the statistical value of the th type of urban feature within the sub-node ; is the mean value of all urban features within the sub-node .

[0011] When the octree satisfies any one of the following conditions: the difference degree within the node is less than the set threshold, the preset maximum level is reached, or the node volume is less than the preset value, the node division of the octree is terminated, and the construction of the octree is completed.

[0012] Preferably, the application of multi-scale convolution to each voxel is specifically as follows:

[0013] In the formula, is the coordinate index of the voxel in the three-dimensional space; is the urban feature category; is the time slice; is the enhanced value of the urban feature after multi-scale convolution; is the number of urban features; is the index of the urban feature; is the th type of urban feature; is the feature weight of the th type of urban feature, dynamically calculated through mutual information; is the th type of urban feature; is the corresponding convolution kernel of the

[0014] Preferably, constructing the constraint network based on supervoxels and the construction, management, or operation and maintenance specification constraint library is specifically as follows: When the statistical values and enhanced values of urban features such as mechanical features, material features, and personnel features in a supervoxel exceed the corresponding set thresholds, and the continuous spatial region of the supervoxels exceeding the thresholds has an area greater than a preset area, the central points of the supervoxels within this region are extracted as the corresponding mechanical nodes, material nodes, and personnel nodes; Based on the construction, management, or operation and maintenance specification constraint library, resource dependency edges between the three types of nodes are defined. By calculating the distance between each node, if the node distance is less than the preset distance threshold, the nodes are connected, and this constraint edge is defined as a spatial conflict edge.

[0015] Preferably, the spatio-temporal constraint intensity of the constraint edge is specifically as follows:

[0016] In the formula, is the spatio-temporal intensity of the constraint edge between nodes and during the construction, management, or operation and maintenance stage; is the number of the construction, management, or operation and maintenance stage; and are the node numbers respectively; is the Euclidean distance between nodes and ; is the spatial influence radius, adjusted according to different types of constraint edges; is the time decay coefficient, controlling the speed at which the constraint decays over time; is the planned time of the construction, management, or operation and maintenance stage ; is the reference time of the construction, management, or operation and maintenance stage ; Based on the calculated spatio-temporal constraint intensity of the constraint edge, the initial supervoxel constraint intensity is injected into the supervoxels where the associated nodes are located, expressed as: In the formula,

[0017] In the formula, is the coordinate index of the supervoxel; is the initial supervoxel constraint intensity of the supervoxel; Based on the initial supervoxel constraint intensity, the supervoxel constraint intensity is solved through a partial differential equation with a fixed time step:

[0018] In the formula, is the updated supervoxel constraint intensity; is the time step; is the spatial diffusion coefficient; is the Laplacian operator, calculating the diffusion in space; is the time conduction coefficient; is the adjacent supervoxel index; is the coordinate of the constraint strength of the supervoxel; is the distance between supervoxels; Determine the risk level of supervoxels according to the preset supervoxel constraint strength threshold, use the improved DBSCAN algorithm to merge adjacent high-risk supervoxels to form a continuous risk area, and output the corresponding risk area list.

[0019] Preferably, using the improved DBSCAN algorithm to merge adjacent high-risk supervoxels to form a continuous risk area specifically as follows: Set the spatial domain radius and the minimum number of domain points of the clustering cluster based on the weighted sum of the spatial distance and the feature distance of the supervoxels; Insert the high-risk supervoxels into the octree according to their spatial positions, select the unvisited high-risk supervoxels, calculate the number of voxels of adjacent nodes in the neighborhood of the leaf node where the high-risk supervoxel is located. If the number of voxels in the traversed neighborhood is greater than or equal to the minimum number of neighborhood points, mark the high-risk supervoxel as a core point and expand the clustering cluster; For each core point, obtain all the points in its neighborhood. If other core points are included in the neighborhood, add its neighborhood to the current clustering cluster and continue to expand the clustering cluster; if border points are included in the neighborhood, add the border points to the clustering cluster; If there are supervoxels that are not assigned to any clustering cluster during the expansion process, mark them as noise points; Terminate the clustering after all high-risk supervoxels are visited and no new clustering clusters can be expanded, and obtain the final clustering result.

[0020] On the other hand, the present invention provides a city area planning, construction, management and operation and maintenance system based on 3D digital twin, including a data acquisition and processing module, an octree construction module, a supervoxel generation module, a constraint network construction module and a risk area determination module; The data acquisition and processing module is used to collect multi-source data including geographic grid data, BIM model data and mobile phone signaling data in the city area, and realize the coordinate alignment of the multi-source data through the LM algorithm; The octree construction module is used to generate feature data composed of an encoding table defining urban features from the multi-source data through feature engineering, and construct an octree based on the feature data; The supervoxel generation module is used to define the leaf nodes of the octree as voxels, and apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels; A constraint network construction module, configured to construct a constraint network based on supervoxels and a construction, management, or operation and maintenance specification constraint library, where nodes in the constraint network are defined as mechanical nodes, material nodes, and personnel nodes, and constraint edges are defined as resource dependency edges and spatial conflict edges; A risk area determination module, configured to determine the risk area of an urban area by calculating the spatio-temporal constraint intensity of the constraint edges, and output a corresponding risk area list.

[0021] In another aspect, the present invention further provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, it implements the method for urban area planning, construction, management, and operation and maintenance based on three-dimensional digital twin according to any embodiment of the present invention.

[0022] In another aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for urban area planning, construction, management, and operation and maintenance based on three-dimensional digital twin according to any embodiment of the present invention.

[0023] Compared with the prior art, the present invention has the following technical effects: 1. The present invention uses a hybrid coordinate transformation method combining the LM algorithm and SVD decomposition to effectively solve the problem of unified spatial reference of multi-source heterogeneous data including geographic grid data, BIM models, and mobile phone signaling, breaking through the excessive dependence of traditional registration methods on manual point selection. By optimizing the joint solution of the scale factor and the coordinate transformation function, the alignment accuracy of cross-scale and cross-dimensional spatial data is significantly improved, laying a reliable data foundation for subsequent spatio-temporal analysis.

[0024] 2. The present invention dynamically constructs an octree based on the feature difference degree, innovatively realizing the adaptive spatial division of urban features. By introducing the feature statistical value difference degree criterion and the automatic segmentation mechanism, both the fineness control of the spatial division and the integrity expression of urban functional features are ensured. This dynamic spatial indexing method can better adapt to the spatio-temporal dynamic change characteristics of urban area features compared with traditional fixed-level division.

[0025] 3. The present invention designs a spatio-temporal fusion convolution kernel for three-dimensional space voxels, and dynamically calculates the feature weights through the mutual information quantity, realizing the cross-scale fusion of multi-dimensional urban features such as building form features and human flow dynamic features. The method effectively enhances the spatio-temporal representation ability of supervoxels, enabling a single supervoxel to carry both spatial position attributes and express the feature evolution law in the time dimension, providing high-dimensional feature support for subsequent constraint network construction.

[0026] 4. The present invention innovatively establishes a digital mapping relationship between a specification constraint library and three-dimensional spatial elements. Through the constraint mechanisms of resource dependence edges and spatial conflict edges, it dynamically reflects the spatio-temporal interaction states of machinery, materials, and personnel during the construction process, providing a constraint network framework for risk identification.

[0027] 5. The present invention constructs a supervoxel constraint strength propagation equation based on partial differential equations. By introducing a spatial diffusion coefficient and a time conduction coefficient, it accurately depicts the propagation path and temporal evolution law of risks in three-dimensional space. Compared with traditional discrete risk assessment methods, this method can effectively reveal the spatio-temporal correlation of risk elements, significantly improving the accuracy and continuity of risk area identification in complex urban environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 is the overall flowchart of the urban area planning, construction, management, operation and maintenance method based on three-dimensional digital twin of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present application and with reference to the accompanying drawings.

[0030] Embodiment 1 This embodiment provides an urban area planning, construction, management, operation and maintenance method based on three-dimensional digital twin. Referring to Figure 1 shown, it includes the following steps: Collect multi-source data of the urban area, including geographic grid data, BIM model data, and mobile phone signaling data, and align the coordinates of the multi-source data through the LM algorithm. Specifically, the geographic grid data can be collected through drone aerial survey / satellite remote sensing, the BIM model data is generated by architectural design software, and the mobile phone signaling data is collected through operator base station records.

[0031] As a preferred implementation manner of this embodiment, the spatio-temporal alignment of multi-source data through the LM algorithm is specifically as follows: Select groups of homologous points, such as building corner points and road intersection points, in the geographic grid data, BIM model data, and mobile phone signaling data respectively, and construct an error equation based on the homologous points:

[0032] In the formula, is the error value of the th homologous point, ; is the coordinate of the th homologous point in the target coordinate system; The th coordinate of the same name for the geographic grid data, BIM model data, and mobile phone signaling data; is the rotation matrix (3*3);

[0033] Solve the optimal error value through SVD decomposition to obtain the initial rotation matrix and the initial translation vector.

[0034] Define a coordinate transformation function based on the initial rotation matrix and the initial translation vector.

[0035] Construct a coordinate transformation optimization function based on the coordinate transformation function:

[0036] In the formula, is the coordinate transformation optimization function of the coordinate ; is the scale factor, usually defaulting to 1; is the coordinate point; is the initial rotation matrix; is the initial translation vector.

[0037] Use the LM algorithm to solve the coordinate transformation optimization function to obtain the optimal rotation matrix and the optimal translation vector, and use the optimal rotation matrix and the optimal translation vector to convert the geographic grid data, BIM model data, and mobile phone signaling data to the target coordinate system to achieve coordinate alignment of multi-source data.

[0038] Furthermore, using the LM algorithm to solve the coordinate transformation optimization function to obtain the optimal rotation matrix and the optimal translation vector specifically: S1: Calculate the initial residual:

[0039] In the formula, is the initial residual; is the th coordinate of the same name of the target coordinate system; is the th

[0040] In the formula, is the Jacobian matrix; is the residual matrix; is the optimization parameter, ; S3: Calculate the step size for each group of coordinates of the same name and the target coordinate points through the residual and the Jacobian matrix:

[0041] Wherein, is the step size; is the damping factor; is the identity matrix; S4: Update the optimization parameters according to the step size: ; S5: Adjust the damping factor, and repeat steps S3 - S5 until the step size is less than the set threshold to obtain the optimal rotation matrix and the optimal translation vector.

[0042] To quickly locate the voxel to which any coordinate point belongs and avoid full - space search, in this embodiment, the multi - source data generates feature data composed of a coding table defining urban features through feature engineering, and an octree is constructed based on the feature data. The octree is dynamically updated. When new data is added, only the nodes on the corresponding branch path need to be updated.

[0043] As a preferred implementation manner of this embodiment, the multi - source data generates feature data composed of a coding table defining urban features through feature engineering. The following are some feature extraction examples: Geographical raster data extracts road networks, green space contours, water area ranges through edge detection algorithms, and extracts the proportion of impervious layers through road building area analysis, etc.; BIM model data extracts mechanical structure displacements through sensor data analysis, and extracts building heights, pipeline complexities, structural load - bearing capacities, etc. through geometric analysis; Mobile phone signaling data extracts daytime population density, nighttime population distribution, flow hotspots, etc. through cluster analysis, and uniformly standardizes the extracted feature data.

[0044] Specifically, constructing an octree based on the feature data is as follows: The feature data includes mechanical features, material features, and personnel features. Initialize the three - dimensional space containing the entire urban area as the root node.

[0045] Calculate the difference degree of the feature data within the node. When the difference degree of the feature data within the node is greater than the set threshold (the set threshold can be dynamically adjusted according to the level size, such as , which is the threshold of the th layer, is the adjustment coefficient, is the threshold of the root node level), divide the node into 8 sub - nodes, and each sub - node stores the statistical value of urban features within the corresponding three - dimensional space. The specific calculation of the difference degree of the feature data is as follows:

[0046] Wherein, is the difference degree of the feature data of the sub - node , reflecting the dispersion degree of the feature distribution; is the index of the child node of the octree, ; is the urban feature index of the child node ; is the statistical value of the feature of the th type of urban feature within the child node (such as mean, maximum value, etc.). For example, if the feature is building height, then can be the mean of all building heights within this child node; is the mean of all urban features within the child node

[0047] When the octree meets any of the following conditions: the difference degree within the node is less than the set threshold, reaches the preset maximum level, or the node volume is less than the preset value, terminate the node splitting of the octree and complete the construction of the octree. Specifically, the preset maximum level or the minimum value of the node volume is adaptively adjusted according to the size of the urban area in practical applications.

[0048] Define the leaf nodes of the octree as voxels, and apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels.

[0049] As a preferred implementation manner of this embodiment, applying multi-scale convolution to each voxel specifically means:

[0050] In the formula, is the coordinate index of the voxel in three-dimensional space; is the urban feature category; is the time slice; is the enhanced value of the urban feature after multi-scale convolution; is the number of urban features; is the index of the urban feature; is the th type of urban feature weight, dynamically calculated by mutual information; is the th type of urban feature; is the

[0051] th type of urban feature corresponding convolution kernel. For different features, the convolution kernel parameters can be preset in combination with urban planning experience. For example, in the application scenario of pipeline node analysis, the convolution kernel size can be set to 3*3*3 to extract local features; in the application scenario of traffic flow analysis, the convolution kernel size can be set to 5*5*5 to extract regional features. Furthermore, is calculated as: ​​

[0052] In the formula, is a feature and the target variable (classifying various features into different target variables, such as different pipeline complexity intervals corresponding to different construction risk levels) of the mutual information.

[0053] Based on multi-scale convolution, super-voxels with spatio-temporal labels are obtained, and the super-voxels include coordinates, time slices, urban feature statistical values, and urban feature enhancement values.

[0054] Based on the super-voxels and the construction, management, or operation and maintenance specification constraint library, a constraint network is constructed. The nodes in the constraint network are defined as mechanical nodes, material nodes, and personnel nodes, and the constraint edges are defined as resource dependence edges and spatial conflict edges.

[0055] As a preferred implementation manner of this embodiment, constructing a constraint network based on the super-voxels and the construction, management, or operation and maintenance specification constraint library is specifically as follows: When the urban feature statistical values and urban feature enhancement values of the mechanical features, material features, and personnel features in the super-voxels exceed the corresponding set thresholds (such as the daytime population density representing the personnel feature in the super-voxel exceeds the set threshold), and the continuous spatial area of the super-voxels exceeding the threshold exists with an area greater than the preset area, the center points of the super-voxels in this area are extracted as the corresponding mechanical nodes, material nodes, and personnel nodes. Specifically, the basis for node selection in this embodiment is that the mechanical nodes affect the core elements of construction safety and progress, the material nodes determine resource scheduling and space utilization efficiency; the personnel nodes are involved in the safety management of the area.

[0056] Based on the construction, management, or operation and maintenance specification constraint library (such as the implementation regulations and specification manuals in the construction, management, or operation and maintenance process), the resource dependence edges between the three types of nodes are defined. By calculating the distance between each node, if the node distance is less than the preset distance threshold, the nodes are connected, and this constraint edge is defined as a spatial conflict edge.

[0057] By calculating the spatio-temporal constraint strength of the constraint edges, the risk areas of the urban area are determined, and a corresponding risk area list is output.

[0058] As a preferred implementation manner of this embodiment, the spatio-temporal constraint strength of the constraint edge is specifically as follows:

[0059] In the formula, is in the construction, management, or operation and maintenance stage node , the spatio-temporal strength of the constraint edge between them, reflecting the new progress and environmental changes; is the construction, management, or operation and maintenance stage number; , are the node numbers respectively; is the node , the Euclidean distance between; is the spatial influence radius, adjusted according to different types of constraint edges; is the time decay coefficient, controlling the speed of constraint decay over time; is the construction, management or operation and maintenance stage the planned time of; is the construction, management or operation and maintenance stage the reference time of.

[0060] The spatio-temporal constraint intensity of the calculated constraint edge injects the initial supervoxel constraint intensity into the supervoxel where the associated node is located, expressed as:

[0061] In the formula, is the coordinate index of the supervoxel; is the initial supervoxel constraint intensity of the supervoxel; The supervoxel constraint intensity is solved through a partial differential equation with a fixed time step according to the initial supervoxel constraint intensity:

[0062] In the formula, is the updated supervoxel constraint intensity; is the time step; is the spatial diffusion coefficient; is the Laplace operator, calculating the diffusion in space, ; is the time conduction coefficient; is the adjacent supervoxel index; is the coordinate the supervoxel constraint intensity of; is the distance between supervoxels.

[0063] Within a single stage, the spatio-temporal intensity value of the constraint edge remains unchanged, and only the supervoxel constraint intensity is updated through the partial differential equation; when entering a new stage, the spatio-temporal intensity value of the constraint edge is recalculated and the supervoxel constraint intensity is re-initialized.

[0064] The risk level of the supervoxel is determined according to the preset supervoxel constraint intensity threshold, and the improved DBSCAN algorithm is used to merge adjacent high-risk supervoxels to form a continuous risk area, and the corresponding risk area list is output.

[0065] As a preferred implementation manner of this embodiment, using the improved DBSCAN algorithm to merge adjacent high-risk supervoxels to form a continuous risk area is specifically: Set the spatial domain radius and the minimum number of domain points of the clustering cluster based on the weighted sum of the spatial distance and the feature distance of the supervoxels.

[0066] Insert the high-risk supervoxels into the octree according to their spatial positions to accelerate neighborhood search without global search. Select unvisited high-risk supervoxels, calculate the number of voxels of adjacent nodes within the neighborhood of the leaf node where the high-risk supervoxel is located. If the number of voxels within the traversed neighborhood is greater than or equal to the minimum number of neighborhood points, mark the high-risk supervoxel as a core point and expand the clustering cluster.

[0067] For each core point, obtain all the points within its neighborhood. If other core points are included in the neighborhood, add its neighborhood to the current clustering cluster and continue to expand the clustering cluster; if boundary points are included in the neighborhood, add the boundary points to the clustering cluster.

[0068] If there are supervoxels that have not been assigned to any clustering cluster during the expansion process, mark them as noise points.

[0069] Terminate the clustering after all high-risk supervoxels have been visited and no new clustering clusters can be expanded to obtain the final clustering result. In addition, when adding new high-risk supervoxels, only check their neighborhood relationships with the existing clustering clusters without recalculating all the data.

[0070] Specifically, the risk area list includes the clustering risk area results and corresponding solutions. The generation of the solutions is further as follows: predefined measure libraries, select the optimal measures for matching based on cost and resource constraints. The matching logic includes the matching of the measure scope of action and the geographical location of the high-risk area and the dominant features of the area targeted by the measure.

[0071] Embodiment 2 Correspondingly, this embodiment provides a city area planning, construction, management, operation and maintenance system based on 3D digital twin. The system is used to implement the 3D digital twin-based city area planning, construction, management, operation and maintenance method as described in Embodiment 1 of the present invention, including a data acquisition and processing module, an octree construction module, a supervoxel generation module, a constraint network construction module and a risk area determination module; The data acquisition and processing module is used to collect multi-source data including geographical grid data, BIM model data and mobile phone signaling data of the city area, and achieve coordinate alignment of the multi-source data through the LM algorithm; The octree construction module is used to generate feature data composed of encoding tables defining city features from the multi-source data through feature engineering, and construct an octree based on the feature data; The supervoxel generation module is used to define the leaf nodes of the octree as voxels, apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels; A constraint network construction module, configured to construct a constraint network based on supervoxels and a construction, management, or operation and maintenance specification constraint library, where nodes in the constraint network are defined as mechanical nodes, material nodes, and personnel nodes, and constraint edges are defined as resource dependency edges and spatial conflict edges; A risk area determination module, configured to determine the risk area of an urban area by calculating the spatio-temporal constraint intensity of the constraint edges, and output a corresponding list of risk areas.

[0072] Embodiment III This embodiment provides an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, it implements the method for planning, construction, management, and operation and maintenance of an urban area based on three-dimensional digital twins as described in Embodiment I of the present invention.

[0073] Embodiment IV This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the method for planning, construction, management, and operation and maintenance of an urban area based on three-dimensional digital twins as described in Embodiment I of the present invention.

[0074] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent the situation where A exists alone, A and B exist simultaneously, or B exists alone. Where A and B may be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c may represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c may be single or multiple.

[0075] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraint conditions of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0076] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described in detail here.

[0077] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or a part of this technical solution can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0078] The above are only the embodiments of the present invention, and thus do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twins, characterized in that, It includes the following steps: Collect multi-source data including geographic grid data, BIM model data, and mobile phone signaling data in the urban area, and achieve coordinate alignment of the multi-source data through the LM algorithm; The multi-source data generates feature data composed of coding tables defining urban features through feature engineering, and constructs an octree based on the feature data; Define the leaf nodes of the octree as voxels, and apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels; Construct a constraint network based on the supervoxels and the construction, management, or operation and maintenance specification constraint library. The nodes in the constraint network are defined as mechanical nodes, material nodes, and personnel nodes, and the constraint edges are defined as resource dependence edges and spatial conflict edges; Determine the risk areas of the urban area by calculating the spatio-temporal constraint strength of the constraint edges, and output the corresponding risk area list.

2. The method for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twin according to claim 1, wherein The specific implementation of coordinate alignment of multi-source data through the LM algorithm is as follows: Select corresponding sets of homologous points from the geographic grid data, BIM model data, and mobile phone signaling data respectively, and construct error equations based on the homologous points: ​ In the formula, is the error value of the th homologous point, ; is the coordinate of the th homologous point in the target coordinate system; is the coordinate of the th homologous point in the geographic grid data, BIM model data, and mobile phone signaling data; is the rotation matrix; is the translation vector; Solve the optimal error value through SVD decomposition to obtain the initial rotation matrix and the initial translation vector; Define a coordinate transformation function based on the initial rotation matrix and the initial translation vector; Construct a coordinate transformation optimization function based on the coordinate transformation function: Wherein, is the coordinate transformation optimization function of the coordinate ; is the scale factor; is the coordinate point; is the initial rotation matrix; is the initial translation vector; Use the LM algorithm to solve the coordinate transformation optimization function to obtain the optimal rotation matrix and the optimal translation vector, and use the optimal rotation matrix and the optimal translation vector to convert the geographic grid data, BIM model data, and mobile phone signaling data to the target coordinate system to achieve coordinate alignment of the multi-source data.

3. The method for urban area planning, construction, management, operation and maintenance based on 3D digital twin according to claim 1, wherein, The specific implementation of generating feature data composed of coding tables defining urban features through feature engineering for the multi-source data and constructing an octree based on the feature data is as follows: The feature data includes mechanical features, material features, and personnel features. Initialize the three-dimensional space containing the entire urban area as the root node; Calculate the difference degree of the feature data within the node. When the difference degree of the feature data within the node is greater than the set threshold, divide the node into 8 sub-nodes. Each sub-node stores the urban feature statistical values within the corresponding three-dimensional space. The calculation of the feature data difference degree is specifically as follows: In the formula, is the difference degree of feature data of the child node, reflecting the dispersion degree of feature distribution; is the index of the child node of the octree, ; is the urban feature index of the child node ; is the feature statistical value of the th type of urban feature within the child node ; is the mean value of all urban features within the child node ; ​ When the octree satisfies any one of the following conditions: the difference degree within the node is less than the set threshold, reaches the preset maximum level, and the node volume is less than the preset value, terminate the node division of the octree and complete the construction of the octree.

4. The method for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twin according to claim 3, characterized in that, The specific implementation of applying multi-scale convolution to each voxel is as follows: In the formula, is the coordinate index of the voxel in the three-dimensional space; is the urban feature category; is the time slice; is the enhanced value of the urban feature after multi-scale convolution; is the number of urban features; is the index of the urban feature; is the feature weight of the -th type of urban feature, dynamically calculated by the mutual information; is the -th type of urban feature; Based on multi-scale convolution, obtain supervoxels with spatio-temporal labels. The supervoxels include coordinates, time slices, urban feature statistical values, and urban feature enhancement values.

5. The method for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twin according to claim 4, characterized in that, The specific implementation of constructing a constraint network based on the supervoxels and the construction, management, or operation and maintenance specification constraint library is as follows: When the urban feature statistical values and urban feature enhancement values of the mechanical features, material features, and personnel features in the supervoxel exceed the corresponding set thresholds, and the continuous spatial area of the supervoxels exceeding the thresholds exists and is greater than the preset area, extract the central points of the supervoxels within this area as the corresponding mechanical nodes, material nodes, and personnel nodes; Define the resource dependence edges between the three types of nodes based on the construction, management, or operation and maintenance specification constraint library. By calculating the distance between each node, if the node distance is less than the preset distance threshold, connect the nodes, and define this constraint edge as a spatial conflict edge.

6. The method for urban area planning, construction, management, operation and maintenance based on 3D digital twin according to claim 1, wherein, The spatio-temporal constraint strength of the constraint edge is specifically: Wherein, is the spatio-temporal intensity of the constraint edge between nodes at the construction, management or operation and maintenance stage; , is the serial number of the construction, management or operation and maintenance stage; and , are the serial numbers of the nodes respectively; is the Euclidean distance between nodes and ; is the spatial influence radius, which is adjusted according to different types of constraint edges; is the time decay coefficient, which controls the decay speed of the constraint over time; is the planned time of the construction, management or operation and maintenance stage ; is the reference time of the construction, management or operation and maintenance stage ; Inject the initial supervoxel constraint strength into the supervoxels where the associated nodes are located according to the spatio-temporal constraint strength of the calculated constrained edges, expressed as: In the formula, is the coordinate index of the supervoxel; is the initial supervoxel constraint strength of the supervoxel; Solve the supervoxel constraint strength through a partial differential equation with a fixed time step according to the initial supervoxel constraint strength: In the formula, is the updated supervoxel constraint strength; is the time step; is the spatial diffusion coefficient; is the Laplacian operator, calculating the diffusion in space; is the time conduction coefficient; is the adjacent supervoxel index; is the coordinate of the supervoxel constraint strength; is the distance between supervoxels; Determine the supervoxel risk level according to a preset supervoxel constraint strength threshold, and use the improved DBSCAN algorithm to merge adjacent high-risk supervoxels to form a continuous risk area, and output the corresponding risk area list.

7. The method for urban area planning, construction, management, operation and maintenance based on three-dimensional digital twin according to claim 6, wherein, The specific process of using the improved DBSCAN algorithm to merge adjacent high-risk supervoxels to form a continuous risk area is as follows: Set the spatial domain radius and the minimum number of domain points of the clustering cluster based on the weighted sum of the spatial distance and the feature distance of the supervoxels; Insert the high-risk supervoxels into the octree according to their spatial positions, select unvisited high-risk supervoxels, and calculate the number of voxels of adjacent nodes in the neighborhood of the leaf node where the high-risk supervoxel is located. If the number of voxels in the traversed neighborhood is greater than or equal to the minimum number of neighborhood points, mark the high-risk supervoxel as a core point and expand the clustering cluster; For each core point, obtain all the points in its neighborhood. If the neighborhood contains other core points, add its neighborhood to the current clustering cluster and continue to expand the clustering cluster; if the neighborhood contains border points, add the border points to the clustering cluster; If there are supervoxels that are not assigned to any clustering cluster during the expansion process, mark them as noise points; Terminate the clustering after all high-risk supervoxels have been visited and no new clustering clusters can be expanded, and obtain the final clustering result.

8. A city area planning, construction, management, operation and maintenance system based on three-dimensional digital twin, characterized in that, The system is used to implement the method for urban area planning, construction, management and operation and maintenance based on 3D digital twin described in any one of claims 1-7, including a data acquisition and processing module, an octree construction module, a supervoxel generation module, a constraint network construction module and a risk area determination module; The data acquisition and processing module is used to collect multi-source data including geographic grid data, BIM model data and mobile phone signaling data in the urban area, and realize the coordinate alignment of the multi-source data through the LM algorithm; The octree construction module is used to generate feature data composed of a coding table defining urban features from the multi-source data through feature engineering, and construct an octree based on the feature data; The supervoxel generation module is used to define the leaf nodes of the octree as voxels, and apply multi-scale convolution to each voxel to obtain supervoxels with spatio-temporal labels; The constraint network construction module is used to construct a constraint network based on the supervoxels and a construction, management or operation and maintenance specification constraint library. The nodes in the constraint network are defined as mechanical nodes, material nodes and personnel nodes, and the constrained edges are defined as resource dependence edges and spatial conflict edges; The risk area determination module is used to determine the risk area of the urban area by calculating the spatio-temporal constraint strength of the constrained edges, and output the corresponding risk area list.

9. An electronic device, the electronic device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the method for urban area planning, construction, management and operation and maintenance based on 3D digital twin described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method for planning, construction, management, operation and maintenance of urban areas based on three-dimensional digital twins according to any one of claims 1 to 7.

Images