Building design scene automatic generation method and system based on artificial intelligence

Abstract

The invention provides an automatic building design scene generation method and system based on artificial intelligence. According to the method, a geometric feature parameter library and a spatial topological relation parameter library of a special-shaped component are integrated, an artificial intelligence optimization engine is used for carrying out conjoint analysis, and a building scene dynamic form constraint map is created. The process comprises the following steps: acquiring three-dimensional data of a construction site by using laser point cloud scanning, and extracting real-time curvature gradient parameters and functional region connection node parameters from the three-dimensional data; and then matching verification is carried out on the parameters and corresponding threshold values and conditions in the dynamic form constraint map, so that a building scene self-adaptive correction parameter set is generated. And finally, building component processing track control points are adjusted based on the parameter set, and a construction instruction containing spatial form and functional topology linkage is formed. According to the technical scheme provided by the invention, the efficiency and flexibility of building design scene automatic generation can be improved.

Description

Technical Field

[0001] This application relates to the technical field of automated generation of architectural design scenarios, and particularly to an automated generation method and system for architectural design scenarios based on artificial intelligence. Background Art

[0002] In modern architectural design and construction, higher technical requirements are put forward for the precise processing of complex curved surfaces and multi-functional area spaces. As architectural forms become more diverse and complex, designers not only need to consider structural aesthetics, but also ensure reasonable layout of functional areas, efficient use of space, and the ability to adapt to changing actual construction conditions. Especially in the design and manufacturing process of special-shaped building components, there is an urgent need for a technical means to achieve real-time spatial form analysis and optimization of functional topological relationships to support the whole-process automated management from design to construction.

[0003] Currently, in modern architectural design and construction, the method of combining parametric modeling with finite element analysis has been widely used. This method allows designers to generate complex geometric shapes by defining a series of control parameters and evaluate the mechanical properties of the structure with the help of finite element analysis tools. In addition, it also supports the combination of the design model with the actual construction environment, thus solving to a certain extent the problem of converting design intentions into construction instructions. This solution utilizes advanced computing technologies and engineering knowledge, making the design process more scientific and reasonable, and at the same time improving the quality and safety of the final product.

[0004] However, although the above solution meets the needs of architectural design to a certain extent, there are still some significant defects. First, due to its dependence on a pre-set parameter set and assumptions, it is difficult to cope with the uncertainties brought by dynamic changes at the construction site. Second, finite element analysis usually takes a long time, which is not conducive to rapid iterative design and immediate adjustment of the construction plan. Finally, when dealing with complex curved surfaces and variable connection points of functional areas, this method often requires a large amount of manual intervention for adjustment and optimization, restricting the improvement of the overall work efficiency. These deficiencies highlight the shortcomings of the existing technical solutions in terms of flexibility and real-time performance. Summary of the Invention

[0005] This application provides an automated generation method and system for architectural design scenarios based on artificial intelligence to solve the problems of low efficiency and poor flexibility in the automated generation of architectural design scenarios in the prior art.

[0006] In a first aspect, this application provides an automated generation method for architectural design scenarios based on artificial intelligence, including: Obtaining a geometric feature parameter library of special-shaped components containing the threshold of the curvature gradient change of the curved surface and a spatial topological relationship parameter library containing the boundary constraint conditions of the functional area for the architectural design scenario; The joint analysis of the surface curvature gradient change threshold and the functional area boundary constraint condition is carried out by an artificial intelligence optimization engine to generate a dynamic form constraint atlas for the building scene; The three-dimensional space lattice data of the construction site is obtained in real time through laser point cloud scanning, and the real-time curvature gradient parameters and functional area connection node parameters in the three-dimensional space lattice data are extracted; The spatial form matching is carried out between the real-time curvature gradient parameters and the surface curvature gradient change threshold in the dynamic form constraint atlas of the building scene. At the same time, the topological relationship verification is carried out between the functional area connection node parameters and the functional area boundary constraint condition to generate a set of adaptive correction parameters for the building scene; Based on the set of adaptive correction parameters for the building scene, the processing trajectory control points of the building components are reconstructed to generate a construction instruction for the building design scene including the linkage of spatial form and functional topology.

[0007] Optionally, the joint analysis of the surface curvature gradient change threshold and the functional area boundary constraint condition by the artificial intelligence optimization engine to generate a dynamic form constraint atlas for the building scene includes: The surface curvature gradient change threshold is decomposed into a curvature gradient feature vector, and the functional area boundary constraint condition is decoupled into a multi-dimensional topological constraint feature vector; The curvature gradient feature vector and the multi-dimensional topological constraint feature vector are mapped to the same coupled analysis space, and a hybrid constraint tensor of the linkage between geometric form and spatial topology is generated through tensor fusion; Based on the hybrid constraint tensor, a dynamic constraint diffusion model is constructed, and the spatial attenuation characteristic of the curvature gradient feature vector drives the node propagation path of the multi-dimensional topological constraint feature vector to form a constraint relationship diffusion network; The constraint relationship diffusion network is reversely corrected and boundary extracted, and a hierarchical dynamic form constraint boundary is generated according to the spatial continuity of the curvature gradient sensitive area and the functional topology conduction chain, and reorganized into a dynamic form constraint atlas for the building scene.

[0008] Optionally, the spatial attenuation characteristic of the curvature gradient feature vector driving the node propagation path of the multi-dimensional topological constraint feature vector to form a constraint relationship diffusion network includes: The curvature gradient feature vector in the hybrid constraint tensor is converted into a spatial attenuation weight matrix, and the multi-dimensional topological constraint feature vector is converted into a topological connection probability field; Based on the spatial attenuation weight matrix, the topological connection probability field is dynamically weighted to generate a directional constraint diffusion channel, and the activation intensity of the constraint diffusion channel is dynamically adjusted by the relationship between the spatial attenuation coefficient and the topological connection probability; Adjust the path connection priority of the topological connection probability field according to the distribution gradient of the spatial attenuation weight, and generate a constrained diffusion network extending from the high-attenuation region to the low-attenuation region; Perform hierarchical clustering on the constrained diffusion network based on the constrained diffusion channels, establish cross-level conduction links through overlapping nodes, and form a constrained relationship diffusion network.

[0009] Optionally, the adjusting the path connection priority of the topological connection probability field according to the distribution gradient of the spatial attenuation weight to generate a constrained diffusion network extending from the high-attenuation region to the low-attenuation region includes: Map the spatial attenuation weight to a spatial gradient field, where the gradient amplitude of each node is the norm of the weight difference of adjacent nodes, and the gradient direction is the neighborhood direction with the fastest weight decrease; Construct a directed connected graph based on the gradient direction, retain only the adjacent gradient edges pointing to nodes with a gradient amplitude lower than the current node for each node, and filter the reverse gradient edges; According to the initial connection probability of each node in the topological connection probability field, superimpose the normalized reciprocal of the gradient amplitude as the path selection weight to generate an attenuation-aware connection priority score; Traverse the nodes from high to low according to the connection priority score, start from the seed node with the largest spatial attenuation weight, and dynamically expand the connection edges along the gradient descent direction to generate a constrained diffusion network extending from the high-attenuation region to the low-attenuation region.

[0010] Optionally, the verifying the topological relationship between the functional area connection node parameters and the functional area boundary constraint conditions to generate an adaptive correction parameter set for the building scene includes: Perform manifold space parameterization decomposition on the real-time curvature gradient parameters, establish an orthogonal parameter coordinate system along the principal curvature direction of the surface, and convert the continuous gradient change into a discretized morphological deviation tensor; Establish a dynamic constraint network for the functional area connection node parameters through a spatial topological relationship parameter library, and generate a surface morphology correction amount field according to the morphological deviation tensor and the functional area boundary constraint conditions; Inject the functional area connection node parameters into the dynamic constraint network, perform topological energy diffusion calculation based on the constraint propagation path of the functional area connection nodes, and generate a topological correction gradient distribution cloud map; Establish a joint optimization space for the surface morphology correction amount field and the topological correction gradient distribution cloud map, construct a morphological and topological joint action potential surface through two-parameter coupling, and perform parameter space correction along the potential gradient descent direction to generate an adaptive correction parameter set for the building scene.

[0011] Optionally, to establish a joint optimization space for the surface shape correction field and the topological correction gradient distribution cloud map, and construct a joint potential surface of shape and topology through two-parameter coupling, including: Perform spatial discretization on the surface shape correction field to generate a grid-shaped shape correction parameter matrix covering the surface of the building scene, and convert the topological correction gradient distribution cloud map into a node gradient intensity tensor with the same spatial resolution; Establish a spatial mapping relationship between the grid-shaped shape correction parameter matrix and the node gradient intensity tensor, and form a joint parameter space through parameter coordinate registration; Define a two-variable coupling relationship between the surface shape correction field and the topological correction gradient distribution cloud map in the joint parameter space, and construct a two-parameter coupling relationship reflecting the interaction between shape deformation energy and topological constraint energy; Fully differentiate and expand the two-parameter coupling relationship, and combine the surface curvature continuity and topological constraint propagation characteristics to construct a joint potential surface of shape and topology.

[0012] Optionally, based on the building scene adaptive correction parameter set, reconstruct the processing trajectory control points of the building component, and generate a construction instruction for the building design scene including spatial shape and functional topology linkage, including: Decompose the building scene adaptive correction parameter set into a shape correction parameter matrix and a topological correction gradient tensor, where the shape correction parameter matrix includes the three-dimensional displacement components of the surface control points; Perform spatio-temporal discretization on the shape correction parameter matrix based on the parametric coordinate system, and generate an initial distribution of processing trajectory control points according to bicubic spline interpolation; Map the topological correction gradient tensor to the space of the initial distribution of the processing trajectory control points, and apply topological correction weights to the control points along the gradient correlation channel to form a composite control point field; Establish a trajectory optimization model in the composite control point field, eliminate the trajectory mutation between control points through local curvature adaptive adjustment, and transfer the topological correction gradient to adjacent control point clusters to construct a hierarchical control network; Couple the control point clusters in the key feature area with the topological correction gradient to generate a construction instruction for the building design scene including spatial shape and functional topology linkage.

[0013] In a second aspect, the present application provides an artificial intelligence-based automated building design scene generation system, including: An acquisition module, which acquires a geometric feature parameter library of special-shaped components including the threshold of surface curvature gradient change of the building design scene and a spatial topology relationship parameter library including boundary constraint conditions of functional areas; An analysis module that jointly analyzes the surface curvature gradient change threshold and the functional area boundary constraint conditions through an artificial intelligence optimization engine to generate a dynamic form constraint map of the building scene; An extraction module that obtains the three-dimensional spatial lattice data of the construction site in real time through laser point cloud scanning, and extracts the real-time curvature gradient parameters and functional area connection node parameters in the three-dimensional spatial lattice data; A verification module that performs spatial form matching between the real-time curvature gradient parameters and the surface curvature gradient change threshold in the dynamic form constraint map of the building scene, and at the same time verifies the topological relationship between the functional area connection node parameters and the functional area boundary constraint conditions to generate an adaptive correction parameter set for the building scene; A generation module that reconstructs the processing trajectory control points of the building components based on the adaptive correction parameter set of the building scene, and generates a construction instruction for the building design scene that includes the linkage between the spatial form and the functional topology.

[0014] In a third aspect, the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based automatic generation method for a building design scene as described in the first aspect above.

[0015] In a fourth aspect, the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements an artificial intelligence-based automatic generation method for a building design scene as described in the first aspect.

[0016] In the embodiments of the present application, a geometric feature parameter library of special-shaped components including the surface curvature gradient change threshold and a spatial topology relationship parameter library including the functional area boundary constraint conditions of the building design scene are obtained; the surface curvature gradient change threshold and the functional area boundary constraint conditions are jointly analyzed through an artificial intelligence optimization engine to generate a dynamic form constraint map of the building scene; the three-dimensional spatial lattice data of the construction site is obtained in real time through laser point cloud scanning, and the real-time curvature gradient parameters and functional area connection node parameters in the three-dimensional spatial lattice data are extracted; the real-time curvature gradient parameters are subjected to spatial form matching with the surface curvature gradient change threshold in the dynamic form constraint map of the building scene, and at the same time the topological relationship between the functional area connection node parameters and the functional area boundary constraint conditions is verified to generate an adaptive correction parameter set for the building scene; based on the adaptive correction parameter set of the building scene, the processing trajectory control points of the building components are reconstructed, and a construction instruction for the building design scene that includes the linkage between the spatial form and the functional topology is generated.

[0017] The technical solution of the present application has the following beneficial effects: This application realizes the accurate description of complex shapes and spatial layouts in architectural design by establishing a geometric feature parameter library of special-shaped components containing the threshold of surface curvature gradient change and a spatial topological relationship parameter library of functional area boundary constraint conditions, providing basic data support for subsequent optimization. By jointly analyzing the data in the above two libraries using an artificial intelligence optimization engine, a dynamic form constraint map reflecting the balance between design requirements and physical constraints can be intelligently generated, improving the rationality and innovation of architectural design solutions. The laser point cloud scanning technology is used to extract the three-dimensional spatial lattice data of the construction site in real time, and the real-time curvature gradient parameters and functional area connection node parameters are calculated from it, ensuring that the design solution can adapt to the actual situation of the construction site in a timely manner and improving the conversion efficiency from design to construction. By matching and verifying the on-site data with the pre-generated dynamic form constraint map, a set of correction parameters adapted to the actual construction environment is automatically generated, ensuring the accuracy and feasibility of architectural design during specific implementation. Finally, detailed instructions for guiding construction are formed, thus realizing an integrated process from design to manufacturing and then to construction, significantly improving the overall quality and efficiency of construction projects.

[0018] Furthermore, the generation process of the dynamic form constraint map of the architectural scene is refined, that is, by decomposing the threshold of curvature gradient change and the functional area boundary constraint conditions into feature vectors respectively, and creating a mixed constraint tensor through tensor fusion technology in a unified space, a dynamic constraint diffusion model is constructed. This model can drive the node propagation path according to the spatial attenuation characteristics, forming a hierarchical dynamic form constraint boundary reflecting spatial continuity. This process effectively combines the requirements of geometric form and spatial topology, making the generated dynamic form constraint map of the architectural scene more refined and accurate, greatly enhancing the flexibility and adaptability of architectural design, and at the same time improving the quality and practicality of design results.

[0019] These aspects or other aspects of this application will be more clearly understood in the following description of the embodiments. Brief Description of the Drawings

[0020] In order to more clearly illustrate the technical solutions in the embodiments of this application or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 Shows a flowchart of an automated generation method for an architectural design scenario based on artificial intelligence provided by this application; Figure 2 Shows a schematic structural diagram of an automated generation system for an architectural design scenario based on artificial intelligence provided by this application; Figure 3 The structural schematic diagram of a computing device provided by this application is shown. Specific embodiments

[0022] In order to enable those skilled in the art to better understand the solution of this application, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application.

[0023] In some processes described in the specification, claims and the above-mentioned drawings of this application, a plurality of operations that appear in a specific order are included. However, it should be clearly understood that these operations can be executed not in the order in which they appear in this article or in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and these operations can be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do they limit that "first" and "second" are of different types.

[0024] Through the integrated geometric feature parameter library of special-shaped components and the spatial topological relationship parameter library, this solution jointly analyzes the surface curvature gradient change threshold and the functional area boundary constraint conditions in the building design scenario according to the artificial intelligence optimization engine, thereby generating a dynamic form constraint map of the building scenario and realizing the automation and intelligence of building design.

[0025] The technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.

[0026] Figure 1 The flowchart of a method for automatically generating a building design scenario based on artificial intelligence provided by an embodiment of this application is as Figure 1 shown, and this method includes: 101. Obtain a geometric feature parameter library of special-shaped components containing the surface curvature gradient change threshold and a spatial topological relationship parameter library containing the functional area boundary constraint conditions in the building design scenario; In this step, the surface curvature gradient change threshold refers to the maximum curvature change range allowed on a specific surface in building design, which is used to control the change speed and smoothness of the surface shape, and ensure that the building appearance is both beautiful and structurally stable.

[0027] The geometric feature parameter library of special-shaped components is a data set that stores detailed information about the irregularly shaped parts in a building. This information includes the specific dimensions, shapes, and curvature variations of each component, such as the maximum and minimum curvatures, and the curvature change rate. These data are used to guide the precise modeling of complex shapes during the design and construction processes.

[0028] The spatial topological relationship parameter library of the boundary constraint conditions for functional areas records the information about the spatial connection methods and boundary restrictions between different functional areas in a building. For example, the positional relationships of functional areas such as meeting rooms and rest areas, and the widths of passageways, etc., to ensure a reasonable layout and meet the usage requirements.

[0029] In the embodiments of the present application, first, all special-shaped components in the building design are scanned with high precision through 3D scanning technology to collect their detailed geometric information, especially the curvature gradient change threshold. Then, professional software is used to convert these raw data into digital models, and they are classified and sorted to form the geometric feature parameter library of special-shaped components. Next, for the boundary constraint conditions of functional areas, the building design drawings or models are analyzed to extract the position coordinates, sizes, and the relative positional relationships and necessary boundary conditions between the two of all functional areas. Finally, the above two types of data are integrated into their respective corresponding databases to provide accurate basic data support for subsequent design optimization.

[0030] 102. Jointly analyze the surface curvature gradient change threshold and the boundary constraint conditions of the functional area through an artificial intelligence optimization engine to generate a dynamic morphological constraint map of the building scene; In this step, the artificial intelligence optimization engine is a technical system that can process a large amount of data and find the best solutions.

[0031] The dynamic morphological constraint map of the building scene is a set of rule systems that describe the specific morphological and spatial relationships to be observed during the building design process. This set of rules comprehensively considers the surface curvature gradient change threshold and the boundary constraint conditions of the functional area, aiming to ensure that the building design is both beautiful and practical.

[0032] In the embodiments of the present application, first, the two parameter libraries created in step 101 are imported into the artificial intelligence optimization engine. Then, a deep learning algorithm is used to jointly analyze the surface curvature gradient change threshold and the boundary constraint conditions of the functional area to identify potential design conflict points and optimization opportunities. Next, based on the analysis results, a series of constraint conditions describing the building morphology and spatial relationships are created, such as the allowable range of the maximum curvature of the surface and the minimum interval distance between functional areas. Finally, these constraint conditions are combined into a comprehensive dynamic morphological constraint map as an important reference for the subsequent design stage.

[0033] 103. Obtain the three-dimensional space lattice data of the construction site in real time through laser point cloud scanning, and extract the real-time curvature gradient parameters and functional area connection node parameters from the three-dimensional space lattice data; In this step, laser point cloud scanning is a technology that uses a laser beam to measure the surface position of an object, and the generated three-dimensional space lattice data contains the position coordinate information of each point within the construction site.

[0034] The real-time curvature gradient parameter is a key index extracted from these coordinate data regarding the change in the curvature degree of the site surface, and is used to evaluate the terrain change situation.

[0035] The functional area connection node parameter is the data that identifies the specific connection positions between different functional areas, such as the specific coordinates and size information of positions like channels and doors, to ensure that the connectivity between functional areas meets the design requirements.

[0036] In the embodiment of the present application, first, deploy laser scanning equipment at the construction site for comprehensive scanning to collect the three-dimensional space lattice data of the construction site. Then, use data analysis tools to extract the real-time curvature gradient parameters and functional area connection node parameters from these data. Next, compare and analyze these parameters with the corresponding data in the parameter library established in the early design stage to verify whether the actual situation on site conforms to the design. Finally, adjust the construction plan or design parameters based on the comparison results to ensure that the actual construction can accurately reflect the requirements of the design scheme.

[0037] 104. Perform spatial form matching between the real-time curvature gradient parameter and the surface curvature gradient change threshold in the dynamic form constraint atlas of the building scene, and at the same time verify the topological relationship between the functional area connection node parameter and the boundary constraint conditions of the functional area to generate an adaptive correction parameter set for the building scene; In this step, the dynamic form constraint atlas of the building scene is a set of rule systems that describe the building form and spatial relationship generated based on the data in the initial stage of building design.

[0038] Spatial form matching refers to comparing the real-time curvature gradient parameter collected on site with the surface curvature gradient change threshold in the constraint atlas to verify whether the on-site conditions meet the design requirements.

[0039] Topological relationship verification is to check whether the functional area connection node parameter conforms to the boundary constraint conditions specified in the design to ensure that the layout between functional areas is reasonable and the connectivity is good.

[0040] In the embodiments of the present application, first, the real-time curvature gradient parameters obtained in step 103 are compared with the surface curvature gradient change thresholds in the building scene dynamic form constraint atlas to identify any inconsistencies. Then, for the problems found, necessary corrections or design adjustments are made. Next, the functional area connection node parameters are verified against the functional area boundary constraint conditions to ensure that the positions and sizes of all connection points meet the design standards. Finally, the above analysis results are integrated to generate a set of building scene adaptive correction parameters to provide guidance for subsequent construction.

[0041] 105. Reconstruct the processing trajectory control points of the building components based on the set of building scene adaptive correction parameters to generate construction instructions for the building design scene that includes the linkage between spatial form and functional topology.

[0042] In this step, the set of building scene adaptive correction parameters is a set of parameters obtained by adjusting the original design scheme according to the actual on-site situation, including the form correction parameter matrix and the topology correction gradient tensor, etc.

[0043] The processing trajectory control points are specific coordinate points used to guide the movement path of the robotic arm or other automated equipment during the manufacturing process of building components.

[0044] The construction instructions for the building design scene that includes the linkage between spatial form and functional topology refer to the final construction guidelines adjusted according to the actual on-site situation, ensuring that the spatial form and functional layout of the building meet both aesthetic requirements and actual usage needs.

[0045] In the embodiments of the present application, first, the set of building scene adaptive correction parameters is decomposed into a form correction parameter matrix and a topology correction gradient tensor, and the initial distribution of the processing trajectory control points is generated according to the bicubic spline interpolation method. Then, the topology correction gradient tensor is mapped to the space of the processing trajectory control points, and correction weights are applied to the control points along the gradient correlation channels to form a composite control point field. Next, a trajectory optimization model is established in this composite control point field, and the trajectory mutations between the control points are eliminated through local curvature adaptive adjustment, and the topology correction gradient is transmitted to the adjacent control point clusters to construct a hierarchical control network. Finally, combining the control point clusters and the topology correction gradient of the key feature regions, construction instructions for the building design scene that includes the linkage between spatial form and functional topology are generated.

[0046] In summary, steps 101 to 105 achieve a seamless connection from the preliminary planning of building design to construction guidance. This not only improves the scientificity and rationality of building design, but also greatly improves the construction efficiency and quality, ensuring that the building works can reflect aesthetic value and meet various actual usage requirements. Each step is closely linked, jointly promoting the successful implementation of the project, and finally delivering a building result that is both beautiful and practical.

[0047] In step 102, the joint analysis of the surface curvature gradient change threshold and the functional area boundary constraint conditions by the artificial intelligence optimization engine generates a dynamic form constraint atlas for the building scene, including: 201. Decompose the surface curvature gradient change threshold into a curvature gradient feature vector, and decouple the functional area boundary constraint conditions into a multi-dimensional topological constraint feature vector; In step 201, the curvature gradient feature vector refers to the data set obtained by decomposing the surface curvature gradient change threshold, which contains information describing the bending degree and its change rate of the building surface. The multi-dimensional topological constraint feature vector is a data set decoupled from the functional area boundary constraint conditions, which describes the spatial connection mode and constraint conditions between different functional areas. These parameters are used for precise adjustment in the subsequent design process to ensure that the design scheme meets the physical and functional requirements.

[0048] In the embodiment of the present application, first, a mathematical algorithm is used to convert the surface curvature gradient change threshold into a series of curvature gradient feature vectors represented by numerical values. Then, the functional area boundary constraint conditions are decoupled into multi-dimensional topological constraint feature vectors by using graphics processing technology. Then, a data analysis method is used to ensure that each feature vector can accurately reflect the characteristics of its corresponding design element. Finally, the two groups of feature vectors are combined to prepare for the next fusion analysis.

[0049] 202. Map the curvature gradient feature vector and the multi-dimensional topological constraint feature vector to the same coupling analysis space, and generate a hybrid constraint tensor that links geometric form and spatial topology through tensor fusion; In step 202, the coupling analysis space is a virtual space environment in which geometric form and spatial topology relationships can be processed simultaneously. The hybrid constraint tensor is a data structure generated by mapping the curvature gradient feature vector and the multi-dimensional topological constraint feature vector to the same space and through tensor fusion technology, which is used to describe the complex relationships in building design. This tensor integrates the dual information of geometric form and spatial topology, providing basic data support for the subsequent construction of a dynamic constraint diffusion model.

[0050] In the embodiment of the present application, first, the two feature vectors are mapped into the same virtual coupling analysis space. Then, a tensor fusion algorithm is applied to generate a hybrid constraint tensor according to the correlation between the feature vectors. Then, this tensor integrates the dual information of geometric form and spatial topology, providing basic data support for the subsequent construction of a dynamic constraint diffusion model. Finally, through this process, a comprehensive understanding and optimization of the building design elements are achieved.

[0051] 203. Construct a dynamic constraint diffusion model based on the mixed constraint tensor, and drive the node propagation path of the multi-dimensional topological constraint eigenvector with the spatial attenuation characteristic of the curvature gradient eigenvector to form a constraint relationship diffusion network; In step 203, the dynamic constraint diffusion model is a simulation system constructed based on the mixed constraint tensor, used to show how the curvature gradient eigenvector affects the node propagation path of the multi-dimensional topological constraint eigenvector to form a constraint relationship diffusion network. This network reflects the interaction relationship between various parts in architectural design. The model helps to identify potential design conflicts and put forward optimization suggestions. The curvature gradient eigenvector refers to a data set formed by quantifying the information of the surface curvature change in architectural design, which contains the specific numerical values of the bending degree and its change rate of the building surface, and is used to accurately describe the morphological characteristics of the building facade or internal space. The spatial attenuation characteristic describes how the curvature gradient eigenvector gradually weakens with the increase of distance, thereby affecting the design parameters of the surrounding area. The node propagation path of the multi-dimensional topological constraint eigenvector is a data set generated based on the spatial connection mode and restriction conditions between different functional areas in architectural design.

[0052] In the embodiment of the present application, first, a dynamic constraint diffusion model is established based on the mixed constraint tensor. Then, the model parameters are set to reflect the influence of the spatial attenuation characteristic of the curvature gradient eigenvector on the multi-dimensional topological constraint eigenvector. Then, the model is run to observe the change of the node propagation path and record the results. Finally, the formed constraint relationship diffusion network provides a basis for subsequent reverse correction, helping to identify and solve potential problems in the design.

[0053] 204. Perform reverse correction and boundary extraction on the constraint relationship diffusion network, generate a hierarchical dynamic form constraint boundary according to the spatial continuity of the curvature gradient sensitive domain and the functional topology conduction chain, and reorganize it into an architectural scene dynamic form constraint atlas.

[0054] In step 204, the hierarchical dynamic form constraint boundary is the result obtained by performing reverse correction and boundary extraction on the constraint relationship diffusion network, aiming to ensure that the architectural design meets specific aesthetic and technical requirements. The reorganized architectural scene dynamic form constraint atlas is a set of comprehensive rule systems used to guide the whole process of architectural design. This step ensures that all design elements meet the preset standards and optimizes the overall layout.

[0055] In the embodiment of the present application, first, perform reverse correction on the generated constraint relationship diffusion network to identify and adjust unreasonable parts. Then, extract the boundary conditions to ensure that all design elements meet the preset standards. Then, generate a hierarchical dynamic form constraint boundary according to the corrected network. Finally, reorganize these boundary conditions into the final architectural scene dynamic form constraint atlas, providing a detailed guide for actual construction.

[0056] In summary, steps 201 to 204 achieve seamless docking of architectural design from concept to actual operation through precise data analysis and intelligent optimization, greatly enhancing the feasibility and aesthetics of the design scheme. At the same time, it also significantly improves the construction quality and efficiency, ensuring that every detail can accurately realize the original intention of the designer, making the final building both visually impactful and practical and efficient.

[0057] In step 203, driving the node propagation path of the multi-dimensional topological constraint feature vector by the spatial decay characteristic of the curvature gradient feature vector to form a constraint relationship diffusion network includes: 301. Convert the curvature gradient feature vector in the hybrid constraint tensor into a spatial decay weight matrix, and convert the multi-dimensional topological constraint feature vector into a topological connection probability field; In step 301, the spatial decay weight matrix is a data set converted based on the curvature gradient feature vector in the hybrid constraint tensor, reflecting the phenomenon that the bending degree of the building surface weakens with the increase of distance. The topological connection probability field is a data set converted from the multi-dimensional topological constraint feature vector, describing the spatial connection possibilities and limiting conditions between different functional areas. These parameters are used to guide precise adjustments in the subsequent design process to ensure that the design scheme meets physical and functional requirements.

[0058] In the embodiment of the present application, first, a mathematical algorithm is used to convert the curvature gradient feature vector into a spatial decay weight matrix to quantify the change rate of the bending degree. Then, graphic processing technology is used to convert the multi-dimensional topological constraint feature vector into a topological connection probability field to evaluate the connection possibilities between different functional areas. Then, through data analysis methods, ensure that each matrix and field can accurately reflect the characteristics of its corresponding design elements. Finally, combine these two sets of data to prepare for the next dynamic weighted analysis.

[0059] 302. Dynamically weight the topological connection probability field based on the spatial decay weight matrix to generate a directional constraint diffusion channel, and the activation intensity of the constraint diffusion channel is dynamically adjusted by the relationship between the spatial decay coefficient and the topological connection probability; In step 302, dynamic weighting refers to the process of adjusting the topological connection probability field according to the spatial decay weight matrix. The constraint diffusion channel is a path structure generated by dynamically weighting the topological connection probability field based on the spatial decay weight matrix, describing how the curvature gradient feature vector in architectural design affects the node propagation path of the multi-dimensional topological constraint feature vector, and has directionality, reflecting the interaction and influence relationship between design elements. The activation intensity of the constraint diffusion channel is dynamically adjusted by the relationship between the spatial decay coefficient and the topological connection probability to ensure that the design meets specific functional and aesthetic requirements.

[0060] Specifically, the spatial attenuation coefficient is used to quantify the attenuation intensity of the building surface curvature gradient with the increase of distance, reflecting the weakening rate of the influence of the bending degree on the adjacent area. The specific calculation formula is: ; Wherein, refers to the curvature gradient eigenvector of the current node (extracted in step 301), refers to the node to the node spatial Euclidean distance; refers to the attenuation rate adjustment factor (preset according to material properties, such as concrete , steel structure ).

[0061] The spatial attenuation weight matrix can be constructed through the above calculation formula.

[0062] Furthermore, the topological connection probability describes the spatial connectivity possibility between different functional areas (such as corridor - hall, equipment room - office area), and is generated by converting the multi - dimensional topological constraint eigenvector. The specific calculation steps are as follows: The first step is feature decomposition: perform principal component analysis (PCA) on the multi - dimensional topological constraint eigenvector to extract the key dimensions ; wherein is the core functional dimension extracted from the original multi - dimensional topological constraint eigenvector through principal component analysis (PCA). Each dimension represents a class of spatial functional attributes, which can be set according to requirements. For example, : connectivity strength (such as corridor width, foyer area), : functional compatibility (such as the affinity between the office area and the meeting room), : pedestrian flow density weight (such as the weight of the hospital emergency area , warehouse weight ), : safety isolation level (such as the isolation requirement between the laboratory and the residential area).

[0063] The second step is probability field modeling, which is achieved through the following formula: ; Wherein, is the topological connection probability from node to node , is the cosine similarity function, and its value range is , for example, similarity > 0.7 → strong functional association (such as ward - nurse station), represents node The dimensionality-reduced feature vector, (such as ), similarly, represents the dimensionality-reduced feature vector of node . is the probability sensitivity parameter (default ). The larger the value, the more sensitive the probability is to changes in similarity.

[0064] Finally, determine the activation intensity of the constrained diffusion channel according to the spatially decaying coefficient and topological connection probability determined above. Specifically, it can be through the constrained diffusion channel activation intensity formula: ; Among them, the adjustment logic is the high attenuation area : Forcefully reduce the activation intensity , inhibit unnecessary connections; the high probability area : Enhance the channel activation intensity in the low attenuation area; represents the gradient adjustment factor, default value = 0.5 (calibrated through experiments), and the gradient term : Dynamically adjust the weight according to the distribution gradient of the spatially decaying weight (step 303) to ensure that the path preferentially points to the low attenuation direction.

[0065] In the embodiments of the present application, first, set the model parameters based on the spatially decaying weight matrix to reflect its influence on the topological connection probability field. Then, apply the dynamic weighting algorithm to adjust the path connectivity priority of the topological connection probability field according to the spatially decaying weight. Then, run the model to observe the changes in the node propagation path and record the results. Finally, the generated directional constrained diffusion channel not only shows the interaction between various parts but also provides optimization suggestions to help identify and solve potential problems in the design.

[0066] 303. Adjust the path connectivity priority of the topological connection probability field according to the distribution gradient of the spatially decaying weight, and generate a constrained diffusion network extending from the high attenuation area to the low attenuation area; In step 303, the path connectivity priority is the order of adjusting the topological connection probability field according to the distribution gradient of the spatially decaying weight. The high attenuation area is processed first, and the low attenuation area is processed second. This priority ensures that key areas in the design (such as emergency evacuation channels) are given priority, while maintaining the rationality and functionality of the overall layout. The constrained diffusion network refers to a network structure extending from the high attenuation area to the low attenuation area, ensuring that the key parts of the design scheme are processed first while maintaining the consistency and coherence of the overall design.

[0067] In the embodiments of the present application, first, the spatial attenuation weight is mapped to a spatial gradient field, and the gradient magnitude and direction of each node are calculated. Then, a directed connected graph is constructed based on the gradient direction, and the adjacent gradient edges pointing to nodes with a gradient magnitude lower than the current node are retained. Next, the normalized reciprocal of the gradient magnitude is superimposed as the path selection weight to generate an attenuation-aware connection priority score. Finally, the nodes are traversed from high to low according to the connection priority score to generate a constrained diffusion network extending from the high-attenuation region to the low-attenuation region, ensuring that key regions are preferentially processed.

[0068] 304. Perform hierarchical clustering on the constrained diffusion network based on the constrained diffusion channels, establish cross-level conduction links through overlapping nodes, and form a constrained relationship diffusion network.

[0069] In step 304, hierarchical clustering is a process of classifying and organizing the constrained diffusion network. By establishing cross-level conduction links through overlapping nodes, information at different levels is integrated. This method helps to optimize the overall layout and ensure that all design elements meet the preset standards. The constrained relationship diffusion network refers to the final network structure formed through hierarchical clustering, which shows the interactions between various parts and provides comprehensive design optimization suggestions to ensure that the design scheme is both beautiful and practical.

[0070] In the embodiments of the present application, first, hierarchical clustering is performed on the generated constrained diffusion network to identify overlapping nodes. Then, cross-level conduction links are established to integrate information at different levels. Next, the model is run to verify the effectiveness and connectivity of the paths. Finally, the formed constrained relationship diffusion network not only shows the interactions between various parts but also provides comprehensive design optimization suggestions to ensure that the design scheme is both beautiful and practical.

[0071] In summary, steps 301 to 304 achieve seamless docking of building design from concept to actual operation through precise data analysis and intelligent optimization, greatly enhancing the feasibility and aesthetics of the design scheme. At the same time, the construction quality and efficiency are also significantly improved, ensuring that every detail can accurately realize the designer's original intention, making the final building both visually impactful and practical and efficient, especially performing well in dealing with emergencies. This method not only solves complex design challenges but also optimizes the overall layout and improves the user experience.

[0072] The adjustment of the path connectivity priority of the topological connection probability field according to the distribution gradient of the spatial attenuation weight in step 303 to generate a constrained diffusion network extending from the high-attenuation region to the low-attenuation region includes: 401. Map the spatial attenuation weight to a spatial gradient field, where the gradient magnitude of each node is the norm of the weight difference between adjacent nodes, and the gradient direction is the neighborhood direction with the fastest weight decrease; In step 401, the spatial gradient field is the result of mapping the spatial attenuation weights into a virtual space. The gradient magnitude of each node represents the norm of the weight difference between adjacent nodes (i.e., the difference in the rate of curvature change), and the gradient direction points to the neighborhood direction where the weight drops fastest. This structure helps identify the key regions that need to be processed preferentially in the design. The gradient magnitude refers to the absolute value of the weight difference between each node and its adjacent nodes, which is used to measure the importance of the node and its influence on the surrounding nodes. The gradient direction describes the neighborhood direction where the weight drops fastest, guiding how to extend the path from the high-attenuation region to the low-attenuation region.

[0073] In the embodiment of the present application, first, the spatial attenuation weights are mapped into a spatial gradient field, and the gradient magnitude and direction of each node are calculated. Then, the gradient direction of each node is determined as the neighborhood direction where the weight drops fastest through a mathematical algorithm. Next, these information are used to construct a preliminary spatial gradient field to ensure that the gradient magnitude of each node accurately reflects its importance. Finally, these data are integrated to form a detailed spatial gradient field, providing a basis for subsequent steps.

[0074] 402. Construct a directed connected graph based on the gradient direction, retain only the adjacent gradient edges pointing to nodes with a gradient magnitude lower than the current node for each node, and filter out the reverse gradient edges; In step 402, the directed connected graph is a graphical structure constructed based on the gradient direction, where only the adjacent gradient edges pointing to nodes with a gradient magnitude lower than the current node are retained for each node, and the reverse gradient edges are filtered out. This method ensures the effectiveness and connectivity of the path. The gradient edge in the directed connected graph refers to the directional connection from one node to another node, and only the edges pointing to nodes with a gradient magnitude lower than the current node are retained.

[0075] In the embodiment of the present application, first, a directed connected graph is constructed based on the gradient direction, and the adjacent gradient edges pointing to nodes with a gradient magnitude lower than the current node are retained. Then, all the reverse gradient edges are filtered out to ensure the effectiveness and connectivity of the path. Next, the model is run to verify the effectiveness of the path, and the results are recorded. Finally, the formed directed connected graph provides clear path guidance for subsequent steps, ensuring that the key regions are processed preferentially.

[0076] 403. According to the initial connection probabilities of the nodes in the topological connection probability field, superimpose the normalized reciprocal of the gradient magnitude as the path selection weight to generate an attenuation-aware connection priority score; In step 403, the path selection weight is the normalized reciprocal of the sum of the initial connection probabilities of each node in the topological connection probability field and the gradient magnitude. This method ensures that the path selection not only considers the connection possibility of the functional intervals but also takes into account the influence of curvature changes. The attenuation-aware connection priority score, generated by the path selection weight, reflects the priority of each node in the path selection. Nodes with higher scores are preferentially selected to ensure that the design solution meets the physical and functional requirements.

[0077] In the embodiment of the present application, first, the normalized reciprocal of the sum of the initial connection probabilities of each node in the topological connection probability field and the gradient magnitude is used as the path selection weight. Then, these weights are used to generate the attenuation-aware connection priority score. Next, the model is run to evaluate the effectiveness of the path selection and the results are recorded. Finally, the generated connection priority score provides a clear basis for path selection in subsequent steps, ensuring that the design solution is both aesthetically pleasing and practical.

[0078] 404. Traverse the nodes from high to low according to the connection priority score, starting from the seed node with the maximum spatial attenuation weight, and dynamically expand the connection edges along the gradient descent direction to generate a constrained diffusion network extending from the high attenuation region to the low attenuation region.

[0079] In step 404, the seed node is the starting node with the maximum spatial attenuation weight and is used to start the path expansion process. The selection of the seed node is crucial for the entire path expansion process. Dynamically expanding the connection edges is a process of gradually expanding the path along the gradient descent direction starting from the seed node. This method ensures that the path extends from the high attenuation region to the low attenuation region, optimizing the overall layout.

[0080] In the embodiment of the present application, first, start from the seed node with the maximum spatial attenuation weight and dynamically expand the connection edges along the gradient descent direction. Then, traverse the nodes from high to low according to the connection priority score and gradually expand the path. Next, run the model to verify the effectiveness of the path expansion and record the results. Finally, the generated constrained diffusion network extending from the high attenuation region to the low attenuation region not only shows the interaction between the parts but also provides comprehensive design optimization suggestions, ensuring that the design solution is both aesthetically pleasing and practical.

[0081] In summary, steps 401 to 404 achieve seamless connection from the concept to the actual operation of building design through precise data analysis and intelligent optimization, greatly enhancing the feasibility and aesthetics of the design scheme. At the same time, it also significantly improves the construction quality and efficiency, making the final building both visually impactful and practical and efficient, especially performing well in dealing with emergencies. This method not only solves complex design challenges but also optimizes the overall layout and improves the user experience. The generation of the constrained diffusion network ensures that the design scheme can meet both aesthetic requirements and functional needs, especially being prominent in terms of people flow management and emergency evacuation.

[0082] In step 104, verifying the topological relationship between the functional area connection node parameters and the functional area boundary constraint conditions to generate an adaptive correction parameter set for the building scene includes: 501. Perform manifold space parameterization decomposition on the real-time curvature gradient parameters, establish an orthogonal parameter coordinate system along the principal curvature direction of the surface, and convert the continuous gradient change into a discretized form deviation tensor. In step 501, the real-time curvature gradient parameters refer to a data set describing the surface curvature change rate. Manifold space parameterization decomposition simplifies complex geometric shapes into forms that can be analyzed and processed. The orthogonal parameter coordinate system consists of two mutually perpendicular coordinate axes and is used as a reference frame to define positions and directions on the surface. The form deviation tensor is a quantitative representation of the difference between the actual shape and the ideal shape of the surface. These data work together to achieve precise description of complex surface shapes.

[0083] In the embodiment of this application, first, use a specific algorithm to perform manifold space parameterization decomposition on the obtained real-time curvature gradient parameters to simplify the surface model. Then, construct an orthogonal parameter coordinate system according to the principal curvature direction to facilitate subsequent calculations. Then, through this coordinate system, convert the continuous gradient change into a discretized form deviation tensor to more accurately capture surface details. Finally, based on the data obtained from the above process, complete the preliminary quantitative description of the surface shape.

[0084] 502. Establish a dynamic constraint network for the functional area connection node parameters through the spatial topological relationship parameter library, and generate a surface form correction quantity field according to the form deviation tensor and the functional area boundary constraint conditions. In step 502, the spatial topological relationship parameter library is a data set storing various possible spatial connection modes and their corresponding constraint conditions. The dynamic constraint network is a network model that can automatically adjust its structure according to input parameters. The form deviation tensor and the functional area boundary constraint conditions are used as inputs to guide the direction and degree of surface form correction. The surface form correction quantity field refers to a set of specific values indicating how the surface needs to be adjusted.

[0085] In the embodiments of the present application, first, a dynamic constraint network is established based on relevant information extracted from the spatial topological relationship parameter library. Then, using the morphological deviation tensor and the functional area boundary constraint conditions as inputs, the correction amount required for each node is calculated through an optimization algorithm. Next, these correction amounts are integrated to form a surface morphology correction amount field. Finally, subsequent correction work is guided by this amount field.

[0086] 503. Inject the functional area connection node parameters into the dynamic constraint network, perform topological energy diffusion calculation based on the constraint propagation path of the functional area connection nodes, and generate a topological correction gradient distribution cloud map. In step 503, the constraint propagation path refers to the way information or constraint conditions are transmitted in the network. Topological energy diffusion calculation is a method for simulating the distribution of energy within a system. The topological correction gradient distribution cloud map is a map used to visually display the intensity of the correction requirements at each point.

[0087] In the embodiments of the present application, first, the functional area connection node parameters are injected into the established dynamic constraint network. Then, information is transmitted according to the preset constraint propagation path. Next, the topological energy diffusion calculation method is used to evaluate the energy state of each node and generate a topological correction gradient distribution cloud map. Finally, the best correction strategy is determined by analyzing this cloud map.

[0088] 504. Establish a joint optimization space between the surface morphology correction amount field and the topological correction gradient distribution cloud map, construct a morphological and topological joint action potential energy surface through two-parameter coupling, and perform parameter space correction along the direction of the potential energy gradient descent to generate an adaptive correction parameter set for the building scene.

[0089] In step 504, the joint optimization space refers to a multi-dimensional parameter space that simultaneously considers morphological and topological characteristics. Two-parameter coupling means adjusting two different parameters simultaneously to achieve an optimal solution. The morphological and topological joint action potential energy surface is a mathematical model that reflects the mutual influence between morphological and topological characteristics. The direction of the potential energy gradient descent is the path of change for finding the minimum value of the potential energy.

[0090] In the embodiments of the present application, first, a joint optimization space is established between the surface morphology correction amount field and the topological correction gradient distribution cloud map. Then, the two-parameter coupling technology is used to explore the optimal solution within this space. Next, the parameters are adjusted along the direction of the potential energy gradient descent until the most suitable correction scheme is found. Finally, an adaptive correction parameter set for the building scene containing all necessary adjustment information is generated.

[0091] In summary, steps 501 to 504 significantly improve the ability to handle complex surfaces in the building design process, make the transition between functional areas more natural and smooth, and at the same time enhance the safety and aesthetics of the overall structure.

[0092] In step 504, the joint optimization space of the surface form correction amount field and the topological correction gradient distribution nephogram is established, and the potential energy surface of the combined action of form and topology is constructed through two-parameter coupling, including: 601. Perform spatial discretization on the surface form correction amount field to generate a grid-shaped form correction parameter matrix covering the building scene surface, and convert the topological correction gradient distribution nephogram into a node gradient intensity tensor with the same spatial resolution; In step 601, the grid-shaped form correction parameter matrix is a parameter set generated by spatially discretizing the surface form correction amount field, and includes the displacement correction components (Δx, Δy, Δz) of each grid node in three-dimensional space; the node gradient intensity tensor is a matrix of topological constraint intensity scalar values corresponding to each node after converting the topological correction gradient distribution nephogram to the same grid resolution. Among them, the surface form correction amount field stores the deformation adjustment amounts of each point on the building surface, and the topological correction gradient distribution nephogram reflects the spatial distribution intensity of the constraint conditions during the structural topology optimization process.

[0093] In the embodiment of the present application, first, the finite element mesh division technology is used to discretize the building surface into quadrilateral or triangular element meshes, and each mesh vertex is used as a parameter node. Then, through the deformation gradient calculation module, the spatial gradient distribution data of the surface form correction amount field is extracted to generate a parameter matrix including the correction amounts in the x / y / z three directions. Then, the topological correction gradient distribution nephogram is processed by the bilinear interpolation algorithm to adjust its original resolution to be consistent with the form correction mesh, and a gradient intensity value in the 0-1 interval corresponding to each node is formed. Finally, through the alignment of the three-dimensional space coordinate system, the spatial positions of the form correction parameters and the topological gradient parameters are ensured.

[0094] 602. Establish the spatial mapping relationship between the grid-shaped form correction parameter matrix and the node gradient intensity tensor, and form a joint parameter space through parameter coordinate registration; In step 602, the spatial mapping relationship refers to the mathematical correspondence rule between the form correction parameters and the topological gradient parameters in terms of spatial position; the joint parameter space is a multi-dimensional parameter set space formed by the form correction parameter matrix and the gradient intensity tensor through coordinate registration, and includes the combined data of the deformation parameters and the topological constraint intensities of each node.

[0095] In the embodiments of the present application, first, a coordinate system transformation model between the shape correction grid and the topological gradient grid is established, and the rotation and translation deviations between the two sets of grids are eliminated by using the affine transformation algorithm. Then, through the node index matching technology, a bidirectional association mapping table is established between each shape correction node and the topological gradient node at the corresponding position. Next, a five-dimensional parameter space data structure including node coordinates, shape correction vectors, and topological gradient values is constructed. Finally, through the spatial topological relationship verification algorithm, the mapping abnormal points in the grid boundary area are detected and repaired.

[0096] 603. Define the bivariate coupling relationship between the surface shape correction quantity field and the topological correction gradient distribution nephogram in the joint parameter space, and construct a two-parameter coupling relationship reflecting the interaction between the shape deformation energy and the topological constraint energy; In step 603, the bivariate coupling relationship refers to the interaction between the shape correction quantity and the topological constraint. The two-parameter coupling relationship is a mathematical model used to describe how these two variables interact to achieve the optimal solution. The shape deformation energy reflects the energy required for shape change, while the topological constraint energy represents the energy barrier that needs to be overcome to maintain a specific connection pattern. These terms work together to reveal the internal connection between shape and topology.

[0097] In the embodiments of the present application, first, the bivariate coupling relationship between the surface shape correction quantity field and the topological correction gradient distribution nephogram is defined in the joint parameter space. Then, an optimization algorithm is used to determine the optimal two-parameter coupling relationship, which can reflect the interaction between the shape deformation energy and the topological constraint energy. Next, the effectiveness of this relationship is verified through simulation and calculation. Finally, a tightly connected mathematical model between shape and topology is established through this process.

[0098] 604. Expand the total differential of the two-parameter coupling relationship, and combine the surface curvature continuity and the topological constraint propagation characteristics to construct a potential energy surface of the joint action of shape and topology.

[0099] In step 604, the total differential expansion is a mathematical method used to analyze the change trend of complex functions. The curvature continuity refers to the smoothness of the curvature change at each point on the surface. The topological constraint propagation characteristics describe how the topological conditions spread throughout the system. The potential energy surface of the joint action of shape and topology is a visualization tool that shows the interaction effect of shape and topological characteristics. These concepts work together to guide design decisions.

[0100] In the embodiments of the present application, first, the double-parameter coupling relationship is fully differentiated and expanded to deeply understand its variation law. Then, combined with the continuity of the surface curvature and the propagation characteristics of topological constraints, a potential energy surface of the combined action of morphology and topology is constructed. Then, the potential energy surface is visualized through computer-aided design software to intuitively evaluate the effects of various design schemes. Finally, a design scheme that comprehensively considers morphological and topological factors is obtained through this series of steps.

[0101] In summary, steps 601 to 604 realize the collaborative design of the deformation optimization of the building surface and the improvement of the structural performance by establishing a combined action model of morphological correction and topological constraints. In the commercial complex project, this method effectively solves the problem of balancing the aesthetic form and structural efficiency in the special-shaped surface building, reduces the stress concentration at the key nodes by more than 30%, increases the construction error tolerance by 50%, and optimizes the economic index of the overall scheme by more than 18%.

[0102] Reconstructing the processing trajectory control points of the building components based on the building scene adaptive correction parameter set in step 105 to generate a construction instruction for the building design scene including the linkage of spatial form and functional topology, including: 701. Decompose the building scene adaptive correction parameter set into a morphological correction parameter matrix and a topological correction gradient tensor, where the morphological correction parameter matrix contains the three-dimensional displacement components of the surface control points; In step 701, the building scene adaptive correction parameter set is a set of data used to guide the optimization of the building form and topology obtained from previous analyses. The morphological correction parameter matrix is a data structure that describes the three-dimensional displacements of the surface control points, while the topological correction gradient tensor is a data structure that quantitatively describes the changing trend of the topological constraint conditions. These concepts work together to achieve an accurate description of the building form and the internal topological relationship.

[0103] In the embodiments of the present application, first, the correction parameter set is decomposed into two independent data streams of morphology and topology through a data decoupling module. The morphological correction parameter matrix is stored in a three-dimensional tensor structure, and each element contains a triple of data: the control point number, the original coordinates, and the correction vector. The topological correction gradient tensor is converted into a relative intensity value matrix in the 0-1 interval through normalization processing. Finally, a spatial index comparison table for the two sets of data is established to ensure that the node numbers and physical positions strictly correspond.

[0104] 702. Perform spatio-temporal discretization processing on the morphological correction parameter matrix based on the parametric coordinate system, and generate an initial distribution of the processing trajectory control points according to bicubic spline interpolation; In step 702, the parametric coordinate system is a reference framework that defines how to represent the position of an object mathematically. Space-time discretization is the process of converting continuous space and time information into a set of discrete data points. Bicubic spline interpolation is a technique used for smooth curve fitting. These concepts work together to generate an initial distribution of the machining trajectory control points.

[0105] In the embodiment of the present application, first, space-time discretization processing is performed on the shape correction parameter matrix based on the established parametric coordinate system. Then, the bicubic spline interpolation technique is applied to generate an initial distribution of the machining trajectory control points according to the processed data. Next, through the evaluation and adjustment of the initial distribution, it is ensured that it meets the actual machining requirements. Finally, this process lays the foundation for the subsequent optimization of the control points.

[0106] 703. Map the topological correction gradient tensor to the space of the initial distribution of the machining trajectory control points, and apply a topological correction weight to the control points along the gradient correlation channel to form a composite control point field; In step 703, the topological correction gradient tensor mapping refers to converting the topological constraint conditions into a data form that can be used to guide the adjustment of the control points. The composite control point field is a spatial environment that integrates shape correction and topological correction information. The gradient correlation channel is a path for transmitting topological correction information. These terms work together to achieve precise adjustment of the control points.

[0107] In the embodiment of the present application, first, a three-dimensional spatial attenuation model of the topological gradient is constructed, and the gradient intensity propagates along the force transmission path of the component according to an exponential function. Then, the gradient correlation channel is searched in the initial control point distribution, and the spatial topological relationship of the control points is established by triangulation. Next, the weight factor ω is calculated according to the position of the control point in the gradient channel, and the initial control point coordinates are weighted and adjusted. Finally, a composite data field including the original coordinates, correction vectors, and gradient weights is generated.

[0108] 704. Establish a trajectory optimization model in the composite control point field, eliminate the trajectory mutation between control points through local curvature adaptive adjustment, and transmit the topological correction gradient to adjacent control point clusters to construct a hierarchical control network; In step 704, the trajectory optimization model is a mathematical model used to find the optimal machining path. Local curvature adaptive adjustment is a technique for dynamically adjusting the path according to the local characteristics of the surface. The hierarchical control network is a management strategy that assigns different levels according to the importance of different control points. These data work together to construct an efficient machining path.

[0109] In the embodiments of the present application, first, the moving least squares method is used to construct a local surface, and the curvature change rate between control points is calculated. Then, auxiliary control points are inserted into the mutation section, and the trajectory is refitted using a fifth-degree polynomial curve. Next, a control point influence attenuation model is constructed based on the gradient tensor, with the gradient influence weight of the core node set to 0.8, the secondary node to 0.5, and the basic node to 0.2. Finally, a hierarchical association relationship is established through the breadth-first search algorithm to form a tree-shaped control network structure.

[0110] 705. Couple the control point cluster of the key feature area with the topological correction gradient to generate a construction instruction for the building design scenario that includes the spatial form and functional topology linkage.

[0111] In step 705, the key feature area refers to the part of the building structure with special functions or aesthetic values. The control point cluster is a set of interrelated control points used to accurately describe the geometric shape changes within a specific area. The topological correction gradient is a data structure that quantitatively describes the change trend of topological constraint conditions. Spatial coupling refers to the process of combining different types of parameters or data sets through spatial position relationships.

[0112] In the embodiments of the present application, first, the key feature areas in the building design are identified, and the corresponding control point clusters are determined. Then, based on the topological correction gradient generated in the previous step, the required spatial adjustment amount for the control point cluster within each key feature area is calculated. Next, the spatial coupling technology is used to combine the topological correction gradient with the specific position information of the control point cluster to ensure that each key feature area meets both the overall form requirements and the local functional requirements. Finally, based on the above processing results, a construction instruction for the building design scenario that includes the spatial form and functional topology linkage is generated to provide clear guidance for actual construction.

[0113] In summary, steps 701 to 705 achieve the collaborative optimization of the processing trajectory of building components and the structural performance through the coupling control of the two parameters of form and topology. It significantly improves the processing ability for complex forms and topological relationships in the building design process, not only optimizing the building appearance but also enhancing the rationality and safety of the internal space layout. At the same time, it also improves the accuracy and operability of the construction instructions, thus effectively promoting the smooth implementation of the project.

[0114] Figure 2 The following is a schematic structural diagram of an artificial intelligence-based automated building design scenario generation system provided by the embodiments of the present application, as Figure 2 shown. The system includes: An acquisition module 21 that acquires a geometric feature parameter library of special-shaped components including the threshold of the curved surface curvature gradient change of the building design scenario and a spatial topology relationship parameter library including the boundary constraint conditions of the functional areas. The analysis module 22 jointly analyzes the surface curvature gradient change threshold and the functional area boundary constraint condition through an artificial intelligence optimization engine to generate a dynamic form constraint atlas of the building scene; The extraction module 23 obtains the three-dimensional space lattice data of the construction site in real time through laser point cloud scanning, and extracts the real-time curvature gradient parameters and functional area connection node parameters in the three-dimensional space lattice data; The verification module 24 performs spatial form matching between the real-time curvature gradient parameter and the surface curvature gradient change threshold in the dynamic form constraint atlas of the building scene, and at the same time verifies the topological relationship between the functional area connection node parameter and the functional area boundary constraint condition to generate an adaptive correction parameter set for the building scene; The generation module 25 reconstructs the processing trajectory control points of the building components based on the adaptive correction parameter set of the building scene to generate a construction instruction for the building design scene including the linkage of spatial form and functional topology.

[0115] Figure 2 The described automatic generation system of the building design scene based on artificial intelligence can execute Figure 1 The automatic generation method of the building design scene based on artificial intelligence described in the illustrated embodiment, and its implementation principle and technical effects will not be elaborated. For the automatic generation system of the building design scene based on artificial intelligence in the above embodiment, the specific ways for each module and unit to execute operations have been described in detail in the embodiment of the method, and will not be elaborated here.

[0116] In a possible design, Figure 2 The automatic generation system of the building design scene based on artificial intelligence in the illustrated embodiment can be implemented as a computing device, such as Figure 3 shown, and the computing device can include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, and among them, the one or more computer instructions are called and executed by the processing component 32.

[0117] The processing component 32 is used for the automatic generation method of the building design scene based on artificial intelligence in the above Figure 1 described embodiment.

[0118] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0119] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An artificial intelligence-based automated generation method for building design scenarios, characterized in that, Including: Obtain a geometric feature parameter library of special-shaped components including the threshold of surface curvature gradient change and a spatial topological relationship parameter library including boundary constraint conditions of functional areas for the building design scenario; Conduct a joint analysis on the threshold of surface curvature gradient change and the boundary constraint conditions of functional areas through an artificial intelligence optimization engine to generate a dynamic form constraint map of the building scenario; Obtain the three-dimensional space lattice data of the construction site in real time through laser point cloud scanning, and extract the real-time curvature gradient parameters and functional area connection node parameters from the three-dimensional space lattice data; Perform spatial form matching between the real-time curvature gradient parameters and the threshold of surface curvature gradient change in the dynamic form constraint map of the building scenario, and at the same time verify the topological relationship between the functional area connection node parameters and the boundary constraint conditions of the functional areas to generate an adaptive correction parameter set for the building scenario; Reconstruct the processing trajectory control points of building components based on the adaptive correction parameter set of the building scenario, and generate construction instructions for the building design scenario including the linkage of spatial form and functional topology.

2. The method according to claim 1, wherein The conduct a joint analysis on the threshold of surface curvature gradient change and the boundary constraint conditions of functional areas through an artificial intelligence optimization engine to generate a dynamic form constraint map of the building scenario, including: Decompose the threshold of surface curvature gradient change into a curvature gradient feature vector, and decouple the boundary constraint conditions of functional areas into a multi-dimensional topological constraint feature vector; Map the curvature gradient feature vector and the multi-dimensional topological constraint feature vector to the same coupling analysis space, and generate a hybrid constraint tensor of the linkage between geometric form and spatial topology through tensor fusion; Based on the hybrid constraint tensor, construct a dynamic constraint diffusion model, and drive the node propagation path of the multi-dimensional topological constraint feature vector by the spatial attenuation characteristics of the curvature gradient feature vector to form a constraint relationship diffusion network; Perform reverse correction and boundary extraction on the constraint relationship diffusion network, generate a hierarchical dynamic form constraint boundary according to the spatial continuity of the curvature gradient sensitive area and the functional topology conduction chain, and reorganize it into a dynamic form constraint map of the building scenario.

3. The method according to claim 2, wherein The drive the node propagation path of the multi-dimensional topological constraint feature vector by the spatial attenuation characteristics of the curvature gradient feature vector to form a constraint relationship diffusion network, including: Convert the curvature gradient feature vector in the hybrid constraint tensor into a spatial attenuation weight matrix, and convert the multi-dimensional topological constraint feature vector into a topological connection probability field; Dynamically weight the topological connection probability field based on the spatial attenuation weight matrix to generate a directional constraint diffusion channel, and the activation intensity of the constraint diffusion channel is dynamically adjusted by the relationship between the spatial attenuation coefficient and the topological connection probability; Adjust the path connection priority of the topological connection probability field according to the distribution gradient of the spatial attenuation weight, and generate a constraint diffusion network extending from the high attenuation area to the low attenuation area; Perform hierarchical clustering on the constraint diffusion network based on the constraint diffusion channel, and establish a cross-level conduction link through overlapping nodes to form a constraint relationship diffusion network.

4. The method according to claim 3, wherein Adjusting the path connection priority of the topological connection probability field according to the distribution gradient of the spatial attenuation weight to generate a constrained diffusion network extending from a high-attenuation region to a low-attenuation region includes: Mapping the spatial attenuation weight to a spatial gradient field, where the gradient amplitude of each node is the norm of the weight difference between adjacent nodes, and the gradient direction is the neighborhood direction with the fastest weight decrease; Constructing a directed connected graph based on the gradient direction, retaining only the adjacent gradient edges pointing to nodes with a gradient amplitude lower than the current node for each node, and filtering the reverse gradient edges; According to the initial connection probabilities of the nodes in the topological connection probability field, superimposing the normalized reciprocal of the gradient amplitude as the path selection weight to generate an attenuation-aware connection priority score; Traversing the nodes from high to low according to the connection priority score, starting from the seed node with the maximum spatial attenuation weight, and dynamically expanding the connection edges along the gradient descent direction to generate a constrained diffusion network extending from a high-attenuation region to a low-attenuation region.

5. The method according to claim 1, wherein Verifying the topological relationship between the functional area connection node parameters and the functional area boundary constraint conditions to generate an adaptive correction parameter set for the building scene includes: Performing manifold space parameterization decomposition on the real-time curvature gradient parameters, establishing an orthogonal parameter coordinate system along the principal curvature direction of the surface, and converting the continuous gradient change into a discretized morphological deviation tensor; Establishing a dynamic constraint network for the functional area connection node parameters through a spatial topological relationship parameter library, and generating a surface morphology correction amount field according to the morphological deviation tensor and the functional area boundary constraint conditions; Injecting the functional area connection node parameters into the dynamic constraint network, performing topological energy diffusion calculation based on the constraint propagation path of the functional area connection nodes, and generating a topological correction gradient distribution cloud map; Establishing a joint optimization space for the surface morphology correction amount field and the topological correction gradient distribution cloud map, constructing a morphological and topological joint action potential surface through two-parameter coupling, and performing parameter space correction along the potential gradient descent direction to generate an adaptive correction parameter set for the building scene.

6. The method according to claim 5, wherein Establishing the joint optimization space for the surface morphology correction amount field and the topological correction gradient distribution cloud map, and constructing a morphological and topological joint action potential surface through two-parameter coupling includes: Performing spatial discretization processing on the surface morphology correction amount field to generate a grid-shaped morphological correction parameter matrix covering the building scene surface, and converting the topological correction gradient distribution cloud map into a node gradient intensity tensor with the same spatial resolution; Establishing a spatial mapping relationship between the grid-shaped morphological correction parameter matrix and the node gradient intensity tensor, and forming a joint parameter space through parameter coordinate registration; Defining the two-variable coupling relationship between the surface morphology correction amount field and the topological correction gradient distribution cloud map in the joint parameter space, and constructing a two-parameter coupling relationship reflecting the interaction between the morphological deformation energy and the topological constraint energy; Performing total differential expansion on the two-parameter coupling relationship, and constructing a morphological and topological joint action potential surface in combination with the surface curvature continuity and the topological constraint propagation characteristics.

7. The method according to claim 1, characterized in that Reconstructing the processing trajectory control points of building components based on the building scene adaptive correction parameter set, and generating a construction instruction for the building design scene including spatial form and functional topology linkage, comprising: Decomposing the building scene adaptive correction parameter set into a form correction parameter matrix and a topology correction gradient tensor, wherein the form correction parameter matrix includes three-dimensional displacement components of surface control points; Performing spatio-temporal discretization processing on the form correction parameter matrix based on a parametric coordinate system, and generating an initial distribution of processing trajectory control points according to bicubic spline interpolation; Mapping the topology correction gradient tensor to the space of the initial distribution of the processing trajectory control points, and applying a topology correction weight to the control points along the gradient correlation channel to form a composite control point field; Establishing a trajectory optimization model in the composite control point field, adaptively adjusting the local curvature to eliminate trajectory mutations between control points, and transmitting the topology correction gradient to adjacent control point clusters to construct a hierarchical control network; Coupling the control point clusters in the key feature area with the topology correction gradient in space to generate a construction instruction for the building design scene including spatial form and functional topology linkage.

8. An artificial intelligence-based automated building design scenario generation system, characterized in that, Including: An acquisition module for acquiring a geometric feature parameter library of special-shaped components including the threshold of surface curvature gradient change and a spatial topology relationship parameter library including boundary constraint conditions of functional areas for the building design scene; An analysis module for jointly analyzing the threshold of surface curvature gradient change and the boundary constraint conditions of the functional areas through an artificial intelligence optimization engine to generate a dynamic form constraint map of the building scene; An extraction module for obtaining the three-dimensional spatial lattice data of the construction site in real time through laser point cloud scanning, and extracting the real-time curvature gradient parameters and functional area connection node parameters in the three-dimensional spatial lattice data; A verification module for performing spatial form matching between the real-time curvature gradient parameters and the threshold of surface curvature gradient change in the dynamic form constraint map of the building scene, and simultaneously verifying the topological relationship between the functional area connection node parameters and the boundary constraint conditions of the functional areas to generate a building scene adaptive correction parameter set; A generation module for reconstructing the processing trajectory control points of building components based on the building scene adaptive correction parameter set, and generating a construction instruction for the building design scene including spatial form and functional topology linkage.

9. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based automatic generation method for a building design scene as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, A computer program is stored, and when the computer program is executed by a computer, it implements an artificial intelligence-based automatic generation method for a building design scene as described in any one of claims 1 to 7.

Images