Intelligent auxiliary recognition method in the parametric modeling design process for hyperbolic curtain walls

Abstract

The present application provides an intelligent auxiliary recognition method for the parametric modeling design process of a hyperbolic curtain wall. The method includes obtaining a plurality of historical hyperbolic curtain wall models and corresponding historical design data; inputting the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module to output predicted connection optimization information and predicted node design information; training the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; inputting the geometric feature information into a preset second optimization module to output predicted grid division information, obtaining the aesthetic coefficient corresponding to the predicted grid division information, and completing the training of the second optimization module; inputting the geometric feature information and node design information into a preset avoidance detection module to output predicted avoidance conflict information, and completing the training of the avoidance detection module according to the predicted avoidance conflict information and the avoidance method information.

Description

Technical Field

[0001] This application relates to the technical field of building modeling, and particularly to an intelligent auxiliary recognition method for the parametric modeling design process of hyperbolic curtain walls. Background Art

[0002] Hyperbolic curtain walls are widely used in modern architecture due to their complex geometric forms and unique aesthetic effects. However, their design process involves a large number of key links that rely on manual judgment, including node design and connection optimization, grid division, and avoidance conflict detection and optimization. In current technologies, these links usually require separate independent models to be established for optimization, resulting in waste of computing resources, complex model maintenance, and insufficient collaboration effects.

[0003] Therefore, there is an urgent need for a method to solve at least one of the above problems. Summary of the Invention

[0004] This application provides an intelligent auxiliary recognition method for the parametric modeling design process of hyperbolic curtain walls, aiming to solve the problems that hyperbolic curtain walls are widely used in modern architecture due to their complex geometric forms and unique aesthetic effects. However, their design process involves a large number of key links that rely on manual judgment, including node design and connection optimization, grid division, and avoidance conflict detection and optimization. In current technologies, these links usually require separate independent models to be established for optimization, resulting in waste of computing resources, complex model maintenance, and insufficient collaboration effects.

[0005] In a first aspect, this application provides an intelligent auxiliary recognition method for the parametric modeling design process of hyperbolic curtain walls, including:

[0006] Obtain a plurality of historical hyperbolic curtain wall models and corresponding historical design data; the historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information;

[0007] Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; complete the training of the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information;

[0008] Input the geometric feature information into a preset second optimization module, the second optimization module outputs predicted grid division information, obtain the aesthetic coefficient corresponding to the predicted grid division information, and complete the training of the second optimization module according to the aesthetic coefficient;

[0009] Input the geometric feature information and node design information into a preset avoidance detection module. The avoidance detection module outputs predicted avoidance conflict information, and train the avoidance detection module according to the predicted avoidance conflict information and avoidance method information;

[0010] Construct an intelligent auxiliary recognition model based on the trained first optimization module, second optimization module and avoidance detection module, which is used to generate optimization suggestions for the hyperbolic curtain wall model in the hyperbolic curtain wall modeling process. The optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions and avoidance design suggestions.

[0011] In some embodiments, constructing the intelligent auxiliary recognition model based on the trained first optimization module, second optimization module and avoidance detection module includes: inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information and avoidance method information into a preset multi-task learning model. The multi-task learning model calculates the joint loss function corresponding to the first optimization module, second optimization module and avoidance detection module; train the first optimization module, second optimization module and avoidance detection module according to the joint loss function to form an intelligent auxiliary recognition model.

[0012] Exemplarily, inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information and avoidance method information into a preset multi-task learning model includes: calculating a first loss function according to the node design information, connection optimization information, predicted connection optimization information, predicted node design information; calculating a second loss function according to the aesthetics coefficient; calculating a third loss function according to the predicted avoidance conflict information and avoidance method information; input the first loss function, second loss function and third loss function into the multi-task learning model to calculate the joint loss function according to the first loss function, second loss function and third loss function.

[0013] It should be noted that in some embodiments, calculating the joint loss function according to the first loss function, second loss function and third loss function includes: setting a first dynamic weight corresponding to the first loss function; setting a second dynamic weight corresponding to the second loss function; setting a third dynamic weight corresponding to the third loss function; calculating the joint loss function according to the first dynamic weight, first loss function, second dynamic weight, second loss function, third dynamic weight and third loss function.

[0014] It should be noted that in some embodiments, the expression of the joint loss function includes:

[0015] ; wherein, is the combined loss function, is the first dynamic weight, is the first loss function, is the second dynamic weight, is the second loss function, is the third dynamic weight, is the third loss function.

[0016] In some embodiments, obtaining the aesthetics coefficient corresponding to the predicted grid division information includes: obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information; calculating the aesthetics coefficient according to the symmetry index, proportion coordination index, and grid density uniformity index.

[0017] Exemplarily, obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information includes: obtaining the grid similarity on both sides of the symmetry axis corresponding to the predicted grid division information, and using the grid similarity as the symmetry index; obtaining the difference coefficient between the aspect ratio of each grid corresponding to the predicted grid division information and a preset ideal ratio, and using the difference coefficient as the proportion coordination index; obtaining the standard deviation corresponding to the area of each grid, taking the reciprocal of the standard deviation and normalizing it, and outputting the grid density uniformity index.

[0018] Exemplarily, the expression of the aesthetics coefficient includes:

[0019] ;

[0020] wherein, is the aesthetics coefficient, is the first weight, is the symmetry index, is the proportion coordination index, is the grid density uniformity index, is the second weight, is the third weight.

[0021] In some embodiments, before inputting the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, it further includes: obtaining the design environment information corresponding to each historical hyperbolic curtain wall model; generating a format conversion relationship corresponding to the historical design data according to the design environment information; and converting each historical design data into a preset target format according to the format conversion relationship.

[0022] In some embodiments, after constructing the intelligent auxiliary recognition model based on the first optimization module, the second optimization module, and the avoidance detection module that have completed training, the following steps are further included: generating an optimization effect score based on the hyperbolic curtain wall model, the optimization suggestions, and the optimized hyperbolic curtain wall model during modeling; and completing the optimization of the intelligent auxiliary recognition model based on the optimization effect score, the hyperbolic curtain wall model during modeling, and the optimization suggestions.

[0023] In a second aspect, the present application provides an intelligent auxiliary recognition device for the parametric modeling design process of a hyperbolic curtain wall, including:

[0024] A data acquisition unit for acquiring multiple historical hyperbolic curtain wall models and corresponding historical design data; the historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information;

[0025] A data input unit for inputting the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; training the first optimization module based on the node design information, connection optimization information, predicted connection optimization information, and predicted node design information;

[0026] A feature input unit for inputting the geometric feature information into a preset second optimization module, and the second optimization module outputs predicted grid division information, obtaining the aesthetic coefficient corresponding to the predicted grid division information, and training the second optimization module based on the aesthetic coefficient;

[0027] A training completion unit for inputting the geometric feature information and node design information into a preset avoidance detection module, and the avoidance detection module outputs predicted avoidance conflict information, and training the avoidance detection module based on the predicted avoidance conflict information and the avoidance method information;

[0028] An optimization output unit for constructing an intelligent auxiliary recognition model based on the first optimization module, the second optimization module, and the avoidance detection module that have completed training, and used to generate optimization suggestions for the hyperbolic curtain wall model during the modeling process of the hyperbolic curtain wall, and the optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0029] In a third aspect, the present application provides a computer device, including a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement the method provided in any embodiment of the present application when executing the computer program.

[0030] Fourthly, the present application provides a computer-readable storage medium storing a computer program, and when the computer-readable instructions are executed by a processor, one or more processors are caused to execute the method provided in any embodiment of the present application.

[0031] An intelligent auxiliary recognition method for the parametric modeling design process of a hyperbolic curtain wall provided by an embodiment of the present application. This intelligent auxiliary recognition method is mainly used for the parametric modeling design of a hyperbolic curtain wall, and improves the design efficiency and quality through machine learning technology. The specific technical process is as follows: Obtain multiple hyperbolic curtain wall models and their corresponding design data from past projects. These data at least include node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, etc. Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module. The first optimization module outputs predicted connection optimization information and predicted node design information. Train the first optimization module according to the actual historical node design information and connection optimization information so that it can accurately predict connection optimization and node design. Input the geometric feature information into a preset second optimization module. The second optimization module outputs predicted grid division information. Calculate the aesthetics coefficient corresponding to the predicted grid division information. Train the second optimization module according to the aesthetics coefficient so that it can generate an aesthetic and reasonable grid division scheme. Input the geometric feature information and node design information into a preset avoidance detection module. The avoidance detection module outputs predicted avoidance conflict information. Train the avoidance detection module according to the actual avoidance method information and the predicted avoidance conflict information so that it can accurately detect and optimize avoidance conflicts. Integrate the trained first optimization module, second optimization module, and avoidance detection module into an intelligent auxiliary recognition model. During the modeling process of the hyperbolic curtain wall, this model can generate optimization suggestions for the hyperbolic curtain wall model in the current modeling, including connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0032] Suppose we have a new hyperbolic curtain wall project that requires parametric modeling design. The following are the specific application steps of this method: Collect the hyperbolic curtain wall models and their design data from past projects, such as node design drawings, connection methods, geometric features, avoidance methods, hole distributions, etc. Input the hole distribution information, geometric feature information, and avoidance method information of the new project. The first optimization module outputs the predicted connection optimization information and node design information. Based on the prediction results, designers can adjust the connection method and node design to achieve the optimal effect. Input the geometric feature information of the new project. The second optimization module outputs the predicted grid division information and calculates the aesthetics coefficient. Based on the aesthetics coefficient, designers can select the most suitable grid division scheme. Input the geometric feature information and node design information of the new project. The avoidance detection module outputs the predicted avoidance conflict information. Based on the prediction results, designers can adjust the design to avoid conflicts. The intelligent auxiliary recognition model synthesizes the outputs of the above modules to generate comprehensive optimization suggestions to help designers complete the design task efficiently.

[0033] The method provided has at least the following beneficial effects: Improve design efficiency: By automating predictions and optimizations, the time for manual judgment is reduced, improving design efficiency. Enhance design quality: Based on historical data and machine learning algorithms, the generated optimization suggestions are more scientific and reasonable, enhancing design quality. Reduce resource waste: Avoid the situation of separately establishing independent models for optimization, reducing the waste of computing resources. Simplify model maintenance: Through the integrated intelligent auxiliary recognition model, the workload of model maintenance is simplified. Enhance collaborative effects: The collaborative work between different modules makes the entire design process smoother and more efficient. Improve aesthetics: Through the evaluation of the aesthetics coefficient, it is ensured that the final design is not only functional but also has good visual effects.

[0034] In summary, this intelligent auxiliary recognition method significantly improves the efficiency and quality of the parametric modeling design of hyperbolic curtain walls through machine learning technology, providing strong support for modern architectural design.

[0035] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit this application. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions of the embodiments of this application, the drawings required for the description of the embodiments will be briefly introduced below. 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.

[0037] Figure 1It is a schematic flow chart of steps of an intelligent auxiliary recognition method used in the parametric modeling design process of a hyperbolic curtain wall provided by an embodiment of the present application;

[0038] Figure 2 It is a schematic block diagram of the structure of an intelligent auxiliary recognition device used in the parametric modeling design process of a hyperbolic curtain wall provided by an embodiment of the present application;

[0039] Figure 3 It is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application.

[0040] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. Specific embodiments

[0041] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0042] The flow chart shown in the accompanying drawings is only an example, and does not necessarily include all contents and operations / steps, nor does it necessarily need to be executed in the described order. For example, some operations / steps can be decomposed, combined, or partially merged, so the actual execution order may be changed according to the actual situation.

[0043] It should be understood that in order to facilitate the clear description of the technical solutions in the embodiments of the present invention, in the embodiments of the present invention, terms such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. Those skilled in the art can understand that the terms "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0044] It should be understood that the terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification of the present application and the appended claims, unless otherwise clearly specified in the context, the singular forms of "a", "an" and "the" are intended to include the plural forms.

[0045] It should also be understood that the term " / and" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the related listed items, and includes these combinations.

[0046] The following will describe in detail some embodiments of the present application with reference to the accompanying drawings. Without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0047] Hyperbolic curtain walls are widely used in modern architecture due to their complex geometric forms and unique aesthetic effects. However, their design process involves a large number of key links that rely on manual judgment, including node design and connection optimization, grid division, and avoidance conflict detection and optimization. In current technologies, these links usually require separate independent models to be established for optimization, resulting in waste of computing resources, complex model maintenance, and insufficient collaborative effects.

[0048] Therefore, there is an urgent need for a method to solve at least one of the above problems.

[0049] To solve the above problems, please refer to Figure 1 , as Figure 1 shown, the intelligent auxiliary recognition method provided for the parametric modeling design process of hyperbolic curtain walls includes steps S101 to S105. The intelligent auxiliary recognition method for the parametric modeling design process of hyperbolic curtain walls is executed by a computer device, which can be a single server or a server cluster, or can be a handheld terminal, a laptop, a wearable device, or a robot, etc.

[0050] As Figure 1 shown, the details of steps S101 - S105 are as follows:

[0051] Step S101. Obtain multiple historical hyperbolic curtain wall models and corresponding historical design data; the historical design data includes at least node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information.

[0052] Specifically, the purpose of this step is to construct a comprehensive data set for subsequent model training. The historical hyperbolic curtain wall models can come from actual projects or existing design cases, and the historical design data covers node design information, connection optimization information, geometric feature information (such as curvature, shape, etc.), avoidance method information (how to avoid structural conflicts), hole position distribution information (hole positions and sizes), and connection optimization information (such as what types of connectors are used and their layout methods).

[0053] Exemplarily, data collection: Obtain relevant case materials from the company's database, public repositories, or partners. Ensure diverse data sources, including projects of different regions, scales, and complexities. Data preprocessing: Clean the raw data to remove invalid records, standardize the format for subsequent analysis. Handle missing values, which can be done through interpolation or deletion methods. Normalize or standardize the data to ensure that all features are on the same scale. Feature extraction: Extract the various design parameters mentioned above for each case as feature vectors. Use computer vision techniques to extract geometric features such as curvature and surface smoothness. Convert the text description into a structured data format.

[0054] By establishing a high-quality and diverse training set, a solid foundation is laid for the subsequent machine learning tasks; at the same time, by learning from existing successful experiences, it can help new projects quickly find a starting point for suitable solutions. In addition, the diverse dataset helps improve the generalization ability of the model, enabling it to provide accurate suggestions when facing new projects.

[0055] Step S102. Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; complete the training of the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information.

[0056] Specifically, this stage mainly focuses on automatically deriving reasonable connection schemes and node layouts by leveraging geometric properties and other relevant information. By inputting specific hole position arrangements, basic shape descriptors, etc. into a pre-set algorithm framework, preliminary suggestions regarding the optimal joint configuration and support point settings are expected to be obtained.

[0057] For example, select a neural network architecture suitable for solving regression problems, such as a convolutional neural network (CNN) or a recurrent neural network (RNN). Define a loss function to measure the difference between the predicted value and the true value. Commonly used ones include the mean squared error (MSE) or the mean absolute error (MAE). Adopt a supervised learning mode, send the prepared samples into the network and iterate repeatedly until convergence. Use batch gradient descent or other optimization algorithms to adjust the model parameters. Set appropriate hyperparameters, such as the learning rate, batch size, number of iterations, etc. Examine the generalization ability of the model through means such as cross-validation to ensure that it can also perform well on unseen data. Calculate metrics such as accuracy, recall rate, F1 score, etc. to evaluate the model performance.

[0058] By automatically providing a reliable initial design plan, it reduces the need for manual intervention and speeds up the progress of the entire project; in addition, it can also discover potential design rules and guide the future work direction. Through automated prediction, designers can focus on higher-level design decisions rather than tedious basic work.

[0059] Step S103. Input the geometric feature information into a preset second optimization module. The second optimization module outputs predicted grid division information, obtain the aesthetics coefficient corresponding to the predicted grid division information, and complete the training of the second optimization module according to the aesthetics coefficient.

[0060] Specifically, considering that visual effects are crucial for the building appearance, an evaluation mechanism specifically for the panel segmentation strategy is introduced here. That is, after a certain form is given, try different grid layouts under different combination methods, and score and rank them according to the predefined aesthetic standards, and select the one with the highest score as the recommended result.

[0061] Definition of aesthetic indicators: Extract a set of quantitative systems by combining psychological principles and art theories to judge the quality of various patterns. The factors considered include symmetry, proportion, rhythm, color matching, etc. Development of segmentation algorithm: Implement a series of program codes that can flexibly change the spacing size, angle inclination, etc. Use optimization algorithms such as genetic algorithms and simulated annealing algorithms to find the optimal solution. Integration of scoring system: Combine the two to form a closed-loop feedback loop, and continuously iterate and improve until the requirements are met. Design the user interface so that designers can intuitively see different grid division schemes and their scores.

[0062] It not only ensures that the functional requirements are met, but also takes into account the aesthetic considerations, making the final product more in line with the public aesthetic preferences and enhancing the market competitiveness. Through automated grid division, the design efficiency can be greatly improved, while ensuring the consistency and aesthetics of the design.

[0063] Step S104. Input the geometric feature information and node design information into a preset avoidance detection module. The avoidance detection module outputs predicted avoidance conflict information, and complete the training of the avoidance detection module according to the predicted avoidance conflict information and avoidance method information.

[0064] Specifically, when there are other components, how to arrange one's own position skillfully to avoid collision becomes a major challenge. For this reason, a functional component specifically responsible for checking and eliminating such potential hazards is specially set up.

[0065] Research on Conflict Detection Algorithm: Draw on classic practices in the field of computer graphics, such as using a spatial partitioning tree to accelerate query speed. Utilize collision detection algorithms, such as OBB (Oriented Bounding Box) or AABB (Axis-Aligned Bounding Box), to detect potential conflicts. Implementation of Automatic Correction Function: Once a problem is detected, immediately take measures to correct it, which may involve fine-tuning the coordinate system offset or modifying local construction details, etc. Provide multiple correction options for designers to choose from to meet different design requirements.

[0066] User Interface Design: To make it easier for designers to understand the current situation and modification plans, intuitive operation guides need to be provided. Design visualization tools to display the conflict areas and proposed correction paths.

[0067] Greatly reduces the probability of errors caused by carelessness, ensuring the engineering quality; at the same time, it also improves work efficiency and avoids the trouble brought by repeated rework. Through automated conflict detection and correction, designers can complete the design faster and ensure the feasibility of the design.

[0068] Step S105. Construct an intelligent auxiliary recognition model based on the trained first optimization module, second optimization module, and avoidance detection module, which is used to generate optimization suggestions for the hyperbolic curtain wall model during the hyperbolic curtain wall modeling process. The optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0069] Specifically, integrate all the tools introduced above to form a complete intelligent auxiliary system, which can automatically generate a relatively complete draft of construction drawings after the user inputs a small amount of basic information.

[0070] Development through APIs: Write the necessary application programming interfaces to enable smooth communication between various parts. Ensure the stability and security of the interfaces to prevent data leakage or tampering. Testing and Debugging: Conduct comprehensive functional and performance tests to find and fix existing defects. Use various testing methods such as unit testing and integration testing to ensure the reliability and stability of the system. Write detailed user manuals and technical documents to facilitate others' understanding and use. Include content such as installation guides, usage instructions, and common question answers. Provide training courses for designers and engineers to help them familiarize themselves with the operation and use of the system. Provide online support and community forums to solve problems encountered by users during the use process.

[0071] It has significantly improved the intelligent level of the architectural design industry, promoted technological innovation and development; at the same time, it has also brought convenience to the vast number of practitioners, allowing them to devote more energy to more creative activities. By comprehensively applying each subsystem, designers can quickly generate high-quality design solutions, improving the overall design efficiency and quality.

[0072] Through the above five steps, we have constructed a complete intelligent auxiliary recognition system, which can effectively improve the efficiency and quality of hyperbolic curtain wall design. Each step has been carefully designed and optimized to ensure that the system can provide accurate and reliable design suggestions. This method not only reduces the need for manual intervention, but also greatly improves the consistency and aesthetics of the design, bringing revolutionary changes to the architectural design industry.

[0073] The provided intelligent auxiliary recognition method is mainly used for the parametric modeling design of hyperbolic curtain walls, improving the design efficiency and quality through machine learning technology. The specific technical process is as follows: Obtain multiple hyperbolic curtain wall models and their corresponding design data from past projects. This data includes at least node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, etc. Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module. The first optimization module outputs predicted connection optimization information and predicted node design information. According to the actual historical node design information and connection optimization information, train the first optimization module so that it can accurately predict connection optimization and node design. Input the geometric feature information into a preset second optimization module. The second optimization module outputs predicted grid division information. Calculate the aesthetics coefficient corresponding to the predicted grid division information. Train the second optimization module according to the aesthetics coefficient so that it can generate a beautiful and reasonable grid division plan. Input the geometric feature information and node design information into a preset avoidance detection module. The avoidance detection module outputs predicted avoidance conflict information. Train the avoidance detection module according to the actual avoidance method information and the predicted avoidance conflict information so that it can accurately detect and optimize avoidance conflicts. Integrate the trained first optimization module, second optimization module, and avoidance detection module into an intelligent auxiliary recognition model. During the hyperbolic curtain wall modeling process, this model can generate optimization suggestions for the hyperbolic curtain wall model in the current modeling, including connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0074] Suppose we have a new hyperbolic curtain wall project that requires parametric modeling design. The following are the specific application steps of this method: Collect hyperbolic curtain wall models and their design data from past projects, such as node design drawings, connection methods, geometric features, avoidance methods, hole position distributions, etc. Input the hole position distribution information, geometric feature information, and avoidance method information of the new project. The first optimization module outputs predicted connection optimization information and node design information. Based on the prediction results, designers can adjust the connection method and node design to achieve the optimal effect. Input the geometric feature information of the new project. The second optimization module outputs predicted grid division information and calculates the aesthetics coefficient. Based on the aesthetics coefficient, designers can select the most suitable grid division scheme. Input the geometric feature information and node design information of the new project. The avoidance detection module outputs predicted avoidance conflict information. Based on the prediction results, designers can adjust the design to avoid conflicts. The intelligent auxiliary recognition model synthesizes the outputs of the above modules to generate comprehensive optimization suggestions to help designers efficiently complete the design task.

[0075] The method provided has at least the following beneficial effects: Improve design efficiency: Through automated prediction and optimization, the time for manual judgment is reduced, improving design efficiency. Enhance design quality: Based on historical data and machine learning algorithms, the generated optimization suggestions are more scientific and reasonable, enhancing design quality. Reduce resource waste: Avoid the situation of separately establishing independent models for optimization, reducing the waste of computing resources. Simplify model maintenance: Through the integrated intelligent auxiliary recognition model, the workload of model maintenance is simplified. Enhance collaborative effect: The collaborative work between different modules makes the entire design process smoother and more efficient. Improve aesthetics: Through the evaluation of the aesthetics coefficient, it is ensured that the final design is not only highly functional but also has good visual effects.

[0076] In summary, this intelligent auxiliary recognition method significantly improves the efficiency and quality of hyperbolic curtain wall parametric modeling design through machine learning technology, providing strong support for modern architectural design.

[0077] In some embodiments, constructing the intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module includes: Inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model, and the multi-task learning model calculates the joint loss functions corresponding to the first optimization module, second optimization module, and avoidance detection module; Training the first optimization module, second optimization module, and avoidance detection module according to the joint loss function to form an intelligent auxiliary recognition model.

[0078] By collecting and organizing historical hyperbolic curtain wall models and their corresponding design data, extracting node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, etc. Select a neural network architecture suitable for multi-task learning, such as a structure with shared layers and multiple output heads. Define the loss functions for each task (the first loss function, the second loss function, the third loss function). Calculate the joint loss function and use dynamic weights to adjust the importance of each task. Input the extracted data into the multi-task learning model. Update the model parameters through the backpropagation algorithm to minimize the joint loss function. Perform multiple iterations until the model converges or reaches the predetermined number of training epochs. Use methods such as cross-validation to evaluate the model performance. Adjust the model structure and hyperparameters according to the evaluation results to further optimize the model.

[0079] Exemplarily, inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetic coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model includes: calculating a first loss function according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; calculating a second loss function according to the aesthetic coefficient; calculating a third loss function according to the predicted avoidance conflict information and the avoidance method information; inputting the first loss function, the second loss function, and the third loss function into the multi-task learning model to calculate the joint loss function according to the first loss function, the second loss function, and the third loss function.

[0080] Use the mean squared error (MSE) or mean absolute error (MAE) as the first loss function. Calculate the difference between the actual node design information and the predicted node design information. Calculate the aesthetic coefficient using an aesthetic scoring standard. Calculate the difference between the actual aesthetic coefficient and the predicted aesthetic coefficient. Calculate the third loss function: use binary cross-entropy or other classification loss functions to calculate the avoidance conflict information. Calculate the difference between the actual avoidance conflict information and the predicted avoidance conflict information. Weightedly sum the above three loss functions to obtain the joint loss function. Adjust the importance of each task through dynamic weights.

[0081] It should be noted that in some embodiments, calculating the joint loss function according to the first loss function, the second loss function, and the third loss function includes: setting a first dynamic weight corresponding to the first loss function; setting a second dynamic weight corresponding to the second loss function; setting a third dynamic weight corresponding to the third loss function; calculating the joint loss function according to the first dynamic weight, the first loss function, the second dynamic weight, the second loss function, the third dynamic weight, and the third loss function.

[0082] The dynamic weights can be adjusted according to the performance of each task during the training process. For example, if the loss of a certain task is large, its weight can be increased so that it accounts for a larger proportion in the joint loss function.

[0083] It should be noted that in some embodiments, the expression of the joint loss function includes:

[0084] ; where is the joint loss function, is the first dynamic weight, is the first loss function, is the second dynamic weight, is the second loss function, is the third dynamic weight, is the third loss function.

[0085] It can be adjusted according to the performance of each task during the training process. For example, if the loss of a certain task is large, the corresponding value can be reduced, thereby increasing its weight in the joint loss function. The joint loss function is calculated using the above formula. The model parameters are adjusted by the gradient descent method or other optimization algorithms to minimize the joint loss function.

[0086] In some embodiments, obtaining the aesthetic coefficient corresponding to the predicted grid division information includes: obtaining the symmetry index, the ratio coordination index, and the grid density uniformity index corresponding to the predicted grid division information; calculating the aesthetic coefficient according to the symmetry index, the ratio coordination index, and the grid density uniformity index.

[0087] Obtaining the symmetry index: Calculate the grid similarity on both sides of the axis of symmetry corresponding to the grid division information. The higher the similarity, the better the symmetry.

[0088] Obtaining the ratio coordination index: Calculate the difference coefficient between the aspect ratio of each grid and the preset ideal ratio. The smaller the difference, the better the ratio coordination.

[0089] Obtaining the grid density uniformity index: Calculate the standard deviation corresponding to the area of each grid. Take the reciprocal of the standard deviation and normalize it to obtain the grid density uniformity index.

[0090] Exemplarily, obtaining the symmetry index, ratio coordination index, and grid density uniformity index corresponding to the predicted grid division information includes: obtaining the grid similarity on both sides of the symmetry axis corresponding to the predicted grid division information, and using the grid similarity as the symmetry index; obtaining the difference coefficient between the aspect ratio of each grid corresponding to the predicted grid division information and a preset ideal ratio, and using the difference coefficient as the ratio coordination index; obtaining the standard deviation corresponding to the area of each grid, taking the reciprocal of the standard deviation and normalizing it, and outputting the grid density uniformity index.

[0091] Calculate the symmetry index: Compare the grid layouts on both sides of the symmetry axis and calculate the similarity. The higher the similarity, the better the symmetry.

[0092] Calculate the ratio coordination index: Preset an ideal ratio (such as the golden ratio), and calculate the difference between the actual aspect ratio of each grid and the ideal ratio. The smaller the difference, the better the ratio coordination.

[0093] Calculate the grid density uniformity index: Calculate the standard deviation of the area of each grid. Take the reciprocal of the standard deviation and normalize it to obtain the grid density uniformity index.

[0094] Exemplarily, the expression of the aesthetics coefficient includes:

[0095] ;

[0096] Wherein, is the aesthetics coefficient, is the first weight, is the symmetry index, is the ratio coordination index, is the grid density uniformity index, is the second weight, is the third weight.

[0097] Determine , , values according to experience or experiments. The weights can reflect the importance of different indicators in the aesthetics evaluation. Substitute the values of each indicator to calculate the aesthetics coefficient. By adjusting the weights, the influence of different indicators on aesthetics can be changed.

[0098] In some embodiments, before inputting the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, it further includes: obtaining the design environment information corresponding to each historical hyperbolic curtain wall model; generating a format conversion relationship corresponding to the historical design data according to the design environment information; and converting each historical design data into a preset target format according to the format conversion relationship.

[0099] Obtain design environment information: Collect the design environment information of each historical hyperbolic curtain wall model, such as project location, climate conditions, material types, etc.

[0100] Generate format conversion relationships: According to the design environment information, define the conversion rules from the original data format to the target format. For example, unify dimensions in different units into the same unit, convert text descriptions into numerical features, etc.

[0101] Data conversion: Use the generated format conversion relationships to convert each historical design data into the target format. Ensure that all data is processed on the same scale and in the same format. This ensures data consistency and standardization, improves the accuracy and efficiency of model training, reduces errors caused by inconsistent data formats, and enhances the robustness of the system.

[0102] In some embodiments, after constructing the intelligent auxiliary recognition model according to the first optimization module, the second optimization module, and the avoidance detection module that have completed training, it further includes: generating an optimization effect score based on the hyperbolic curtain wall model, optimization suggestions, and the optimized hyperbolic curtain wall model during modeling; optimizing the intelligent auxiliary recognition model according to the optimization effect score, the hyperbolic curtain wall model during modeling, and the optimization suggestions.

[0103] Generate an optimization effect score: Calculate the changes in various performance indicators based on the hyperbolic curtain wall models before and after optimization. For example, calculate the degree of improvement in aesthetics, the degree of improvement in structural stability, etc. Synthesize various indicators to generate an optimization effect score. According to the optimization effect score, adjust the parameters of the intelligent auxiliary recognition model. For example, adjust the dynamic weights in the multi-task learning model, improve the definition of the loss function, etc. Retrain the model to improve its performance in actual applications. Continuously optimize the model through the feedback mechanism, improving the practicality and accuracy of the model. This enables the intelligent auxiliary recognition system to better adapt to different design requirements and provide higher-quality design suggestions.

[0104] Please refer to Figure 2 as shown in Figure 2 FIG. 200 is a schematic structural diagram of an intelligent auxiliary recognition device 200 for the parametric modeling design process of a hyperbolic curtain wall provided by an embodiment of the present application. The intelligent auxiliary recognition device 200 for the parametric modeling design process of a hyperbolic curtain wall is used to execute the steps of the intelligent auxiliary recognition method for the parametric modeling design process of a hyperbolic curtain wall shown in the above embodiments. The intelligent auxiliary recognition device 200 for the parametric modeling design process of a hyperbolic curtain wall can be a single server or a server cluster, or the intelligent auxiliary recognition device 200 for the parametric modeling design process of a hyperbolic curtain wall can be a terminal, and the terminal can be a handheld terminal, a laptop computer, a wearable device, or a robot, etc.

[0105] such asFigure 2 As shown in Figure 2 , the intelligent auxiliary recognition device 200 used in the parametric modeling design process of the hyperbolic curtain wall includes:

[0106] A data acquisition unit 201, configured to acquire a plurality of historical hyperbolic curtain wall models and corresponding historical design data; the historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information;

[0107] A data input unit 202, configured to input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; the first optimization module is trained according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information;

[0108] A feature input unit 203, configured to input the geometric feature information into a preset second optimization module, and the second optimization module outputs predicted grid division information, obtain an aesthetics coefficient corresponding to the predicted grid division information, and the second optimization module is trained according to the aesthetics coefficient;

[0109] A training completion unit 204, configured to input the geometric feature information and node design information into a preset avoidance detection module, and the avoidance detection module outputs predicted avoidance conflict information, and the avoidance detection module is trained according to the predicted avoidance conflict information and avoidance method information;

[0110] An optimization output unit 205, configured to construct an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, and is used to generate optimization suggestions for the hyperbolic curtain wall model in the modeling process during the hyperbolic curtain wall modeling, and the optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0111] In some embodiments, constructing the intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module includes: inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model, and the multi-task learning model calculates a joint loss function corresponding to the first optimization module, second optimization module, and avoidance detection module; the first optimization module, second optimization module, and avoidance detection module are trained according to the joint loss function to form an intelligent auxiliary recognition model.

[0112] Exemplarily, inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model includes: calculating a first loss function based on the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; calculating a second loss function based on the aesthetics coefficient; calculating a third loss function based on the predicted avoidance conflict information and avoidance method information; and inputting the first loss function, second loss function, and third loss function into the multi-task learning model to calculate the joint loss function based on the first loss function, second loss function, and third loss function.

[0113] It should be noted that in some embodiments, calculating the joint loss function based on the first loss function, second loss function, and third loss function includes: setting a first dynamic weight corresponding to the first loss function; setting a second dynamic weight corresponding to the second loss function; setting a third dynamic weight corresponding to the third loss function; and calculating the joint loss function based on the first dynamic weight, first loss function, second dynamic weight, second loss function, third dynamic weight, and third loss function.

[0114] It should be noted that in some embodiments, the expression of the joint loss function includes:

[0115] ; where is the joint loss function, is the first dynamic weight, is the first loss function, is the second dynamic weight, is the second loss function, is the third dynamic weight, is the third loss function.

[0116] In some embodiments, obtaining the aesthetics coefficient corresponding to the predicted grid division information includes: obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information; and calculating the aesthetics coefficient based on the symmetry index, proportion coordination index, and grid density uniformity index.

[0117] Exemplarily, obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information includes: obtaining the grid similarity on both sides of the axis of symmetry corresponding to the predicted grid division information, where the grid similarity serves as the symmetry index; obtaining the difference coefficient between the aspect ratio of each grid corresponding to the predicted grid division information and a preset ideal ratio, where the difference coefficient serves as the proportion coordination index; obtaining the standard deviation corresponding to the area of each grid, taking the reciprocal of the standard deviation and normalizing it, and outputting the grid density uniformity index.

[0118] Exemplarily, the expression of the aesthetics coefficient includes:

[0119] ;

[0120] Where is the aesthetics coefficient, is the first weight, is the symmetry index, is the proportion coordination index, is the grid density uniformity index, is the second weight, is the third weight.

[0121] In some embodiments, before inputting the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, it further includes: obtaining the design environment information corresponding to each historical hyperbolic curtain wall model; generating a format conversion relationship corresponding to the historical design data according to the design environment information; and converting each historical design data into a preset target format according to the format conversion relationship.

[0122] In some embodiments, after constructing the intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, it further includes: generating an optimization effect score according to the hyperbolic curtain wall model, optimization suggestions, and the optimized hyperbolic curtain wall model during modeling; and optimizing the intelligent auxiliary recognition model according to the optimization effect score, the hyperbolic curtain wall model during modeling, and the optimization suggestions.

[0123] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the intelligent auxiliary recognition device and each module in the above-described hyperbolic curtain wall parametric modeling design process can refer to the corresponding processes in the embodiments of the intelligent auxiliary recognition method for hyperbolic curtain wall parametric modeling design described in the above embodiments, and will not be elaborated here.

[0124] The above intelligent auxiliary recognition method in the parametric modeling design process of the hyperbolic curtain wall can be implemented in the form of a computer program, which can run on a device such as Figure 2 shown.

[0125] Please refer to Figure 3 , Figure 3 which is a schematic block diagram of the structure of the computer device provided by an embodiment of the present application. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the memory may include a storage medium and an internal memory.

[0126] The storage medium can store an operating device and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can be made to execute any one of the intelligent auxiliary recognition methods in the parametric modeling design process of the hyperbolic curtain wall.

[0127] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0128] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can be made to execute any one of the intelligent auxiliary recognition methods in the parametric modeling design process of the hyperbolic curtain wall.

[0129] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art can understand that Figure 3 the structure shown in

[0130] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the terminal to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0131] Wherein, in one embodiment, the processor is configured to run a computer program stored in a memory to implement the following steps:

[0132] Obtain a plurality of historical hyperbolic curtain wall models and corresponding historical design data; the historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information;

[0133] Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; train the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information;

[0134] Input the geometric feature information into a preset second optimization module, the second optimization module outputs predicted grid division information, obtain the aesthetic coefficient corresponding to the predicted grid division information, and train the second optimization module according to the aesthetic coefficient;

[0135] Input the geometric feature information and node design information into a preset avoidance detection module, the avoidance detection module outputs predicted avoidance conflict information, and train the avoidance detection module according to the predicted avoidance conflict information and avoidance method information;

[0136] Construct an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, which is used to generate optimization suggestions for the hyperbolic curtain wall model in the modeling process during hyperbolic curtain wall modeling, and the optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0137] In some embodiments, constructing the intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module includes: inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetic coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model, and the multi-task learning model calculates the joint loss function corresponding to the first optimization module, second optimization module, and avoidance detection module; train the first optimization module, second optimization module, and avoidance detection module according to the joint loss function to form an intelligent auxiliary recognition model.

[0138] Exemplarily, inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetics coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model includes: calculating a first loss function according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; calculating a second loss function according to the aesthetics coefficient; calculating a third loss function according to the predicted avoidance conflict information and avoidance method information; and inputting the first loss function, second loss function, and third loss function into the multi-task learning model to calculate the joint loss function according to the first loss function, second loss function, and third loss function.

[0139] It should be noted that in some embodiments, calculating the joint loss function according to the first loss function, second loss function, and third loss function includes: setting a first dynamic weight corresponding to the first loss function; setting a second dynamic weight corresponding to the second loss function; setting a third dynamic weight corresponding to the third loss function; and calculating the joint loss function according to the first dynamic weight, first loss function, second dynamic weight, second loss function, third dynamic weight, and third loss function.

[0140] It should be noted that in some embodiments, the expression of the joint loss function includes:

[0141] ; where is the joint loss function, is the first dynamic weight, is the first loss function, is the second dynamic weight, is the second loss function, is the third dynamic weight, is the third loss function.

[0142] In some embodiments, obtaining the aesthetics coefficient corresponding to the predicted grid division information includes: obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information; and calculating the aesthetics coefficient according to the symmetry index, proportion coordination index, and grid density uniformity index.

[0143] Exemplarily, obtaining the symmetry index, the proportional coordination index, and the grid density uniformity index corresponding to the predicted grid division information includes: obtaining the grid similarity on both sides of the symmetry axis corresponding to the predicted grid division information, where the grid similarity serves as the symmetry index; obtaining the difference coefficient between the aspect ratio of each grid corresponding to the predicted grid division information and a preset ideal ratio, where the difference coefficient serves as the proportional coordination index; obtaining the standard deviation corresponding to the area of each grid, taking the reciprocal of the standard deviation and normalizing it, and outputting the grid density uniformity index.

[0144] Exemplarily, the expression of the aesthetics coefficient includes:

[0145] ;

[0146] where is the aesthetics coefficient, is the first weight, is the symmetry index, is the proportional coordination index, is the grid density uniformity index, is the second weight, is the third weight.

[0147] In some embodiments, before inputting the hole position distribution information, the geometric feature information, and the avoidance method information into a preset first optimization module, it further includes: obtaining the design environment information corresponding to each historical hyperbolic curtain wall model; generating a format conversion relationship corresponding to the historical design data according to the design environment information; and converting each historical design data into a preset target format according to the format conversion relationship.

[0148] In some embodiments, after constructing an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, it further includes: generating an optimization effect score according to the hyperbolic curtain wall model, optimization suggestions, and the optimized hyperbolic curtain wall model during modeling; and optimizing the intelligent auxiliary recognition model according to the optimization effect score, the hyperbolic curtain wall model during modeling, and the optimization suggestions.

[0149] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described computer device and each module can refer to the corresponding processes in the embodiments of the intelligent auxiliary recognition method for the parametric modeling design process of the hyperbolic curtain wall described in the above embodiments, and will not be elaborated here.

[0150] The present application also provides a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to implement the steps of the intelligent auxiliary recognition method in the parametric modeling design process of a hyperbolic curtain wall as provided in any embodiment of the present application.

[0151] Among them, the computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk equipped on the computer device, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc.

[0152] Exemplarily, this medium is used to implement the following steps:

[0153] Obtain a plurality of historical hyperbolic curtain wall models and corresponding historical design data; the historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information;

[0154] Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; complete the training of the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information;

[0155] Input the geometric feature information into a preset second optimization module, the second optimization module outputs predicted grid division information, obtain the aesthetic coefficient corresponding to the predicted grid division information, and complete the training of the second optimization module according to the aesthetic coefficient;

[0156] Input the geometric feature information and node design information into a preset avoidance detection module, the avoidance detection module outputs predicted avoidance conflict information, and complete the training of the avoidance detection module according to the predicted avoidance conflict information and avoidance method information;

[0157] Construct an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, which is used to generate optimization suggestions for the hyperbolic curtain wall model in the modeling process during the hyperbolic curtain wall modeling, and the optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

[0158] It should be noted that those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described storage medium and each module can refer to the corresponding processes in the embodiments of the intelligent auxiliary recognition method in the parametric modeling design process of the hyperbolic curtain wall described in the above embodiments, and will not be elaborated herein.

[0159] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An intelligent auxiliary recognition method for the parametric modeling design process of a hyperbolic curtain wall, characterized in that, Including: Obtain multiple historical hyperbolic curtain wall models and corresponding historical design data; The historical design data at least includes node design information, connection optimization information, geometric feature information, avoidance method information, hole position distribution information, and connection optimization information; Input the hole position distribution information, geometric feature information, and avoidance method information into a preset first optimization module, and the first optimization module outputs predicted connection optimization information and predicted node design information; Complete the training of the first optimization module according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; Input the geometric feature information into a preset second optimization module, and the second optimization module outputs predicted grid division information, and obtain the aesthetic coefficient corresponding to the predicted grid division information, including: obtaining the symmetry index, proportion coordination index, and grid density uniformity index corresponding to the predicted grid division information; calculating the aesthetic coefficient according to the symmetry index, proportion coordination index, and grid density uniformity index; completing the training of the second optimization module according to the aesthetic coefficient; the expression of the aesthetic coefficient includes: ; wherein, is the aesthetics coefficient, is the first weight, is the symmetry index, is the proportion coordination index, is the grid density uniformity index, is the second weight, is the third weight; Input the geometric feature information and node design information into a preset avoidance detection module, and the avoidance detection module outputs predicted avoidance conflict information, and complete the training of the avoidance detection module according to the predicted avoidance conflict information and avoidance method information; Construct an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, which is used to generate optimization suggestions for the hyperbolic curtain wall model in the modeling process during the hyperbolic curtain wall modeling, and the optimization suggestions include one or more of connection optimization suggestions, node design suggestions, grid division suggestions, and avoidance design suggestions.

2. The method according to claim 1, wherein The constructing an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module includes: Input the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetic coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model, and the multi-task learning model calculates the joint loss function corresponding to the first optimization module, second optimization module, and avoidance detection module; Complete the training of the first optimization module, second optimization module, and avoidance detection module according to the joint loss function to form an intelligent auxiliary recognition model.

3. The method according to claim 2, wherein The inputting the node design information, connection optimization information, predicted connection optimization information, predicted node design information, aesthetic coefficient, predicted avoidance conflict information, and avoidance method information into a preset multi-task learning model includes: Calculate a first loss function according to the node design information, connection optimization information, predicted connection optimization information, and predicted node design information; Calculate a second loss function according to the aesthetic coefficient; Calculate a third loss function according to the predicted avoidance conflict information and avoidance method information; Input the first loss function, the second loss function, and the third loss function into the multi-task learning model to calculate the joint loss function according to the first loss function, the second loss function, and the third loss function.

4. The method according to claim 3, wherein The calculating the joint loss function according to the first loss function, the second loss function, and the third loss function includes: Set a first dynamic weight corresponding to the first loss function; Set a second dynamic weight corresponding to the second loss function; Set a third dynamic weight corresponding to the third loss function; Calculate the joint loss function according to the first dynamic weight, the first loss function, the second dynamic weight, the second loss function, the third dynamic weight, and the third loss function.

5. The method according to claim 4, characterized in that The expression of the joint loss function includes: ； Among them, is the said combined loss function, is the said first dynamic weight, is the said first loss function, is the said second dynamic weight, is the said second loss function, is the said third dynamic weight, is the said third loss function.

6. The method according to claim 1, characterized in that The obtaining the symmetry index, the proportional coordination index, and the grid density uniformity index corresponding to the predicted grid division information includes: Obtain the grid similarity on both sides of the symmetry axis corresponding to the predicted grid division information, and use the grid similarity as the symmetry index; Obtain the difference coefficient between the aspect ratio of each grid corresponding to the predicted grid division information and a preset ideal ratio, and use the difference coefficient as the proportional coordination index; Obtain the standard deviation corresponding to the area of each grid, take the reciprocal of the standard deviation and normalize it, and output the grid density uniformity index.

7. The method according to claim 1, wherein Before inputting the hole position distribution information, the geometric feature information, and the avoidance method information into a preset first optimization module, it further includes: Obtain the design environment information corresponding to each historical hyperbolic curtain wall model; Generate a format conversion relationship corresponding to the historical design data according to the design environment information; Convert each piece of historical design data into a preset target format according to the format conversion relationship.

8. The method according to claim 1, wherein After constructing an intelligent auxiliary recognition model according to the trained first optimization module, second optimization module, and avoidance detection module, it further includes: Generate an optimization effect score according to the hyperbolic curtain wall model, the optimization suggestions, and the optimized hyperbolic curtain wall model in the modeling; Complete the optimization of the intelligent auxiliary recognition model according to the optimization effect score, the hyperbolic curtain wall model in the modeling, and the optimization suggestions.

Images