Intelligent building design auxiliary method and system

Abstract

The invention provides an intelligent building design auxiliary method and system, belongs to the technical field of building design, and can improve the design efficiency and quality, reduce design errors, improve the energy efficiency and environmental adaptability of a building, and improve the building design quality. The method comprises the following steps of design condition obtaining, data analysis and processing, scheme generation, scheme optimization and design output, building design is assisted and supported through an intelligent technology, the design efficiency and quality are improved, multiple preliminary design schemes are generated through artificial intelligence, and the design efficiency and quality are improved. According to the system, the design scheme is generated, the generated design scheme is automatically scored and optimized through a preset evaluation index, in addition, the system further supports a user to refine and modify the selected design scheme, and finally design results are output in the forms of drawings, models and the like. The method has the advantages of improving design efficiency, ensuring design quality, facilitating user operation and the like, and is suitable for building design requirements in different fields and scenes.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided design, and in particular to an intelligent building design aiding method and system. Background Art

[0002] Architectural design means that before a building is constructed, the designer, in accordance with the construction task, makes a comprehensive conception of the problems that exist or may occur during the construction process and the use of the building, formulates methods and plans to solve these problems, and expresses these methods and plans in drawings and documents, which serve as a common basis for material preparation, construction organization and the cooperation and collaboration of various types of work in the production and construction work, so that the entire project can be carried out smoothly within the predetermined investment limit and in accordance with the carefully considered predetermined plan in a unified pace, and the completed buildings can fully meet the various requirements and uses expected by users and society.

[0003] Traditional architectural design methods often rely on the designer's experience and creativity, combined with a large amount of data and information for design. This approach is not only inefficient, but also difficult to ensure the quality and accuracy of the design.

[0004] Therefore, the field of architectural design urgently needs to provide an intelligent architectural design assistance method and system that can assist designers in performing more efficient and scientific design work.

[0005] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0006] Purpose of the invention: The technical problem to be solved by the present invention is to provide an intelligent building design auxiliary method in view of the shortcomings of the prior art, aiming to solve the problem that the architectural design method in the prior art often relies on the experience and creativity of the designer and combines a large amount of data and information for design. However, this method is not only inefficient, but also difficult to ensure the quality and accuracy of the design.

[0007] In order to solve the above technical problems, the present invention discloses an intelligent building design auxiliary method, comprising:

[0008] S1. Obtaining design conditions: based on basic parameter data of architectural design input by the user;

[0009] S2. Data analysis and processing: using artificial intelligence algorithms to process and analyze the basic parameter data to obtain analysis results;

[0010] S3, scheme generation: generating multiple possible preliminary design schemes according to the analysis results, automatically scoring the multiple possible preliminary design schemes through preset evaluation indicators, obtaining scoring results, and giving optimization suggestions; the user can select the best preliminary design scheme from the multiple possible preliminary design schemes according to the scoring results and the optimization suggestions;

[0011] S4, solution optimization: obtaining the user's evaluation feedback information on the generated design solution, performing self-learning and optimization based on the evaluation feedback information, and obtaining a new design solution;

[0012] S5. Design output: Output the final design plan in the form of drawings, models, etc.;

[0013] S4 is iteratively executed until the user is satisfied, thereby obtaining the final design solution.

[0014] Preferably, the basic parameter data of the building design in step S1 include the purpose, scale, geographical location and climatic conditions of the building.

[0015] Preferably, the data analysis and processing in step S2 includes selection and analysis of building form, orientation, layout and material selection.

[0016] Preferably, the user input parameters in step S1 include at least one user input parameter selected from the following types: user-conceived content, sensor network, and drone-photographed content.

[0017] Preferably, the artificial intelligence algorithm in step S2 includes at least one artificial intelligence algorithm selected from the following types: machine learning algorithm, deep learning algorithm, evolutionary algorithm, multi-objective optimization algorithm, artificial neural network and fuzzy logic.

[0018] Preferably, the machine learning algorithm is used to process and analyze the basic parameter data and obtain analysis results, and the machine learning algorithm is as follows:

[0019] Linear regression: y = β0 + β1x + ∈,

[0020] In the formula, y is the dependent variable, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0021] Logistic Regression:

[0022] In the formula, is the probability of the architectural design being selected, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0023] Decision Tree: A classification or regression model based on a tree structure.

[0024] Preferably, the deep learning algorithm includes convolutional neural networks, recurrent neural networks, long short-term memory networks, variational autoencoders and generative adversarial networks.

[0025] The present invention also provides an intelligent building design auxiliary system, which includes: an input module for receiving basic parameter data of building design input by a user;

[0026] A data processing module, used to process and analyze the basic parameter data using an artificial intelligence algorithm to obtain analysis results;

[0027] A generation module, used to generate multiple possible preliminary design solutions according to the analysis results;

[0028] A display module, used to display the multiple possible preliminary design solutions using virtual reality technology;

[0029] An evaluation module, used to automatically score the multiple possible preliminary design schemes based on preset evaluation indicators, obtain scoring results, and give optimization suggestions;

[0030] Optimization module, used for self-learning and optimization schemes based on user evaluation feedback information;

[0031] Output module, used to output the final architectural design plan.

[0032] Preferably, the input module is provided with an input interface unit, a data verification unit and a parameter database;

[0033] The data processing module is provided with a data analysis unit, an algorithm processing unit and a calculation engine;

[0034] The generation module is provided with an algorithm generation unit, a three-dimensional modeling unit and a solution library;

[0035] The display module is provided with a virtual reality engine and an interactive interface;

[0036] The evaluation module is provided with an evaluation algorithm unit and a feedback unit; the optimization module is provided with a feedback collection unit and a system optimization unit;

[0037] The output module is provided with a design document generator and a data output unit.

[0038] Preferably, the output mode of the data output unit in the output module includes Bluetooth transmission, LAN transmission, 5G transmission and USB interface transmission.

[0039] Beneficial effects:

[0040] In the present invention, multiple preliminary design schemes are automatically generated through artificial intelligence technology, which reduces the repetitive work of designers. Through automated and intelligent processing, the manual workload of designers is reduced, and the design efficiency is improved. The deep learning algorithm is used to generate and optimize the design scheme, which can ensure the quality and accuracy of the design scheme and improve the rationality and scientificity of the design. The system provides an intuitive user interface and interaction method to facilitate user operation and modification. The system can be expanded and upgraded as needed to meet the design needs of different fields and scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments, and the above and / or other advantages of the present invention will become more clear.

[0042] Figure 1 A workflow diagram of an intelligent building design assistance method provided by one embodiment of the present invention;

[0043] Figure 2 A system framework diagram of an intelligent building design assistance system provided by an embodiment of the present invention;

[0044] Figure 3 A module block diagram of an intelligent building design assistance system provided by one embodiment of the present invention.

[0045] The description of the accompanying drawings is:

[0046] 410. Input module; 411. Input interface unit; 412. Data verification unit; 413. Parameter database; 420. Data processing module; 421. Data analysis unit; 422. Algorithm processing unit; 423. Calculation engine; 430. Generation module; 431. Algorithm generation unit; 432. Three-dimensional modeling unit; 433. Solution library; 440. Display module; 441. Virtual reality engine; 442. Interactive interface; 450. Evaluation module; 451. Evaluation algorithm unit; 452. Feedback unit; 460. Optimization module; 461. Feedback collection unit; 462. System optimization unit; 470. Output module; 471. Design document generator; 472. Data output unit. DETAILED DESCRIPTION

[0047] Example 1

[0048] See also Figure 1 This embodiment discloses an intelligent building design auxiliary method of the present invention, which includes the following steps:

[0049] S1. Obtaining design conditions: generating design tasks based on basic parameter data of architectural design input by the user;

[0050] S2. Data analysis and processing: using artificial intelligence algorithms to process and analyze the basic parameter data to obtain analysis results;

[0051] S3, scheme generation: according to the analysis results, multiple possible preliminary design schemes are generated; based on the preset evaluation indicators, the multiple possible preliminary design schemes are automatically scored to obtain scoring results, and optimization suggestions are given; the user can select the best preliminary design scheme according to the scoring results and the optimization suggestions;

[0052] S4, solution optimization: obtaining the user's evaluation feedback information on the generated design solution, performing self-learning and optimization based on the evaluation feedback information, and obtaining a new design solution;

[0053] S5. Design output: Output the final design plan in the form of drawings, models, etc.;

[0054] The fourth step is iteratively performed until the user is satisfied, thereby obtaining the final design solution.

[0055] Specifically, the basic parameter data include building purpose, scale, geographical location and climate conditions.

[0056] In this embodiment, the user can input basic parameter data of the building design through the user interface, or input data imported by sensors or parameters photographed by drones, and these basic parameter data of the building design are analyzed using artificial intelligence;

[0057] Specifically, the processing and analysis of the basic parameter data using an artificial intelligence algorithm includes: building form analysis, building orientation analysis, building layout analysis and material selection analysis;

[0058] The building form analysis includes: recommending a suitable building form based on factors such as geographical location, climatic conditions and building use, the geographical location also including weather forecasts;

[0059] The building orientation analysis includes: optimizing the building orientation according to the geographical location and climate conditions to improve indoor lighting and energy saving effects;

[0060] The building layout analysis includes: generating a reasonable building layout plan according to the building purpose and scale. For example, in residential design, the system may recommend that the bedroom and the living room be placed on both sides of the building to improve living comfort;

[0061] The material selection analysis includes: recommending appropriate building materials according to the purpose, scale and geographical location of the building. For example, in earthquake-prone areas, the system may recommend the use of building materials with better earthquake resistance;

[0062] The algorithms used in weather forecasting for geographical locations include the following:

[0063] Convolutional neural networks: These can be used to process spatial patterns in meteorological data, such as identifying cloud formation and movement;

[0064] The recurrent neural network includes processing time series data, such as temperature and humidity records from weather stations, to predict future weather conditions;

[0065] The time series forecasting model, such as ARIMA, which combines an autoregressive model and a moving average model, is used to forecast time series data.

[0066] The clustering algorithm, such as K-means, is used to cluster the meteorological data and identify similar weather patterns.

[0067] In this embodiment, based on the analysis results, the system generates multiple possible preliminary design schemes and displays them using virtual reality technology. Users can view the three-dimensional models of each preliminary design scheme through virtual reality devices to more intuitively understand the appearance and internal space layout of each preliminary design scheme.

[0068] In this embodiment, the user can evaluate the optimal preliminary design solution and obtain evaluation feedback information. The system performs self-learning and optimization based on the evaluation feedback information. This process can be repeated until the user is satisfied with the design solution, thereby obtaining the final design solution.

[0069] Specifically, the user can evaluate the generated design scheme, including: the user can evaluate the design scheme by scoring, commenting, etc. For example, the user may think that the bedroom layout of a certain scheme is unreasonable and needs to be adjusted.

[0070] Specifically, the system performs self-learning and optimization according to the evaluation feedback information, including: the system adjusts the design scheme according to the evaluation feedback information using an artificial intelligence algorithm. For example, the system may adjust the location of the bedroom to meet the needs of the user.

[0071] Specifically, the final design plan includes detailed architectural drawings, three-dimensional models and related design instructions, which can be used by users for subsequent construction and decoration.

[0072] Specifically, the data analysis and processing in step S2 includes the selection and analysis of building form, orientation, layout and material selection.

[0073] Specifically, the user input parameter in step S1 includes at least one user input parameter selected from the following types: user-conceived content, sensor network, and drone-photographed content.

[0074] Specifically, the artificial intelligence algorithm in step S2 includes at least one artificial intelligence algorithm selected from the following types: machine learning algorithm, deep learning algorithm, evolutionary algorithm, multi-objective optimization algorithm, artificial neural network and fuzzy logic.

[0075] Specifically, the machine learning algorithm includes:

[0076] Linear regression: y = β0 + β1x + ∈,

[0077] In the formula, y is the dependent variable, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0078] Logistic Regression:

[0079] In the formula, is the probability of the architectural design being selected, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0080] Decision Tree: A classification or regression model based on a tree structure.

[0081] In this embodiment, the machine learning algorithm can learn design patterns and user preferences by analyzing a large amount of architectural design data, thereby helping to generate new design solutions. Algorithms such as decision trees and random forests can be used to analyze the relationship between design elements and user satisfaction.

[0082] y represents the dependent variable, which may represent a variable related to building design that needs to be predicted or analyzed in the building design auxiliary method, such as building energy consumption, building cost, etc.

[0083] x represents the independent variable, which may be various factors that affect the dependent variables related to building design, such as the building’s area, number of floors, type of materials used, etc.

[0084] β0 represents the intercept term, which is the value of the dependent variable when all independent variables are 0; in the architectural design scenario, β0 represents the benchmark energy consumption, cost, etc.

[0085] β1 represents the regression coefficient, which indicates the degree of influence of each independent variable on the dependent variable. For example, it means that for every unit change in the independent variable, the dependent variable changes by an average of units.

[0086] ∈ represents the error term, which includes the impact of factors other than the independent variable on the dependent variable, as well as unobservable factors such as measurement error.

[0087] It represents the probability of a certain architectural design being selected under the condition of given independent variables.

[0088] Specifically, the deep learning algorithms, especially convolutional neural networks (CNN) and generative adversarial networks (GAN), excel in processing complex data patterns and generating new design elements. CNN can be used to process visual data in architectural design, such as building appearance and spatial layout, while GAN can be used to generate new design solutions.

[0089] Specifically, evolutionary algorithms: such as genetic algorithms, ant colony algorithms, etc., can simulate natural selection and evolutionary processes to continuously optimize building design solutions. These algorithms are suitable for optimizing design parameters such as cost, energy efficiency, and material usage.

[0090] Specifically, multi-objective optimization algorithms: such as particle swarm optimization and linear programming, which can help designers find the best balance between multiple design goals, such as functionality, aesthetics, cost, and sustainability;

[0091] Specifically, artificial neural networks: especially recurrent neural networks (RNN) and long short-term memory (LSTM), are suitable for processing sequence data and time series data, which is very useful in building design, such as simulating the energy consumption and environmental impact of buildings during use;

[0092] Specifically, fuzzy logic: is effective in dealing with uncertainty and ambiguity and can be used to handle subjective evaluations and preferences in design.

[0093] In the machine learning algorithm, the specific algorithm is as follows:

[0094] Linear regression: y = β0 + β1x + ∈,

[0095] In the formula, y is the dependent variable, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0096] Logistic Regression:

[0097] In the formula, is the probability of the architectural design being selected, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term;

[0098] Decision tree: A classification or regression model based on a tree structure. There is no single formula, but rather it is based on the node splitting of the tree.

[0099] In deep learning algorithms:

[0100] Convolutional Neural Network (CNN) consists of multiple convolutional layers, pooling layers, and fully connected layers, involving a variety of mathematical operations;

[0101] Recurrent Neural Network (RNN): h t =tanh(W h h t-1 +U h x t +b h , where h t is the hidden state at time step t. The hidden state is a key part of the RNN, which stores the network's memory of the previous input sequence; tanh is the hyperbolic tangent activation function, which is used to compress the input value to the range (-1,1) to help the network handle nonlinear relationships; W h is the weight matrix from hidden state to hidden state, which is used to update the hidden state and reflects the influence of the previous hidden state on the current hidden state; h t-1 is the hidden state at time step t-1, which is the current hidden state h t The previous state of U is used to update the current state; h is the weight matrix input to the hidden state, which is used to convert the current input x t Transformed into an update to the hidden state; x t is the input data at time step t, which is the external input of the current time step; b h is the bias vector of the hidden state, which is used to adjust the activation value of the hidden state.

[0102] Long-short term memory (LSTM): A more complex RNN variant used to process long sequences of data.

[0103] This embodiment also provides an intelligent building design assistance system of the present invention, the system comprising:

[0104] An input module 410 is used to receive basic parameter data of architectural design input by a user, wherein the basic parameter data of architectural design includes design requirements and restriction conditions;

[0105] The data processing module 420 is used to process and analyze the basic parameter data using an artificial intelligence algorithm to obtain analysis results;

[0106] A generating module 430, for generating a plurality of possible preliminary design solutions according to the analysis results;

[0107] A display module 440 is used to display the multiple possible preliminary design solutions using virtual reality technology;

[0108] Evaluation module 450, used to automatically score the multiple possible preliminary design schemes based on preset evaluation indicators, obtain scoring results, and provide optimization suggestions; and allow the user to select the best preliminary design scheme according to the scoring results and the optimization suggestions, and evaluate the best preliminary design scheme to obtain evaluation feedback information;

[0109] The optimization module 460 is used to perform self-learning and optimization according to the user's evaluation feedback information, and repeatedly iterate until the user is satisfied, thereby obtaining the final design solution;

[0110] The output module 470 is used to output the final design solution.

[0111] The various modules in the intelligent building design assistance system disclosed in this embodiment have clear division of labor and work in coordination, which improves the efficiency and quality of the design; the system uses virtual reality technology, so that users can intuitively view and experience the design scheme, which improves the satisfaction and practicality of the design; the system is optimized according to user feedback and evaluation results to meet the needs and expectations of different users; the modular design facilitates the maintenance and upgrading of the system; the system automatically generates multiple preliminary design schemes through artificial intelligence technology, which reduces the repetitive work of designers, reduces the manual workload of designers through automated and intelligent processing, improves the design efficiency, and uses deep learning algorithms to generate and optimize design schemes, which can ensure the quality and accuracy of the design schemes and improve the rationality and scientificity of the design.

[0112] Specifically, the input module 410 is provided with an input interface unit 411 , a data verification unit 412 and a parameter database 413 .

[0113] The user interacts with the system through the input interface unit 411 to input basic parameter data of the building design. The data input form provides a structured input method, and the parameter database 413 is used to store and manage the input data. The input content is verified through the data verification unit 412;

[0114] Specifically, the data processing module 420 is provided with a data analysis unit 421 , an algorithm processing unit 422 and a calculation engine 423 .

[0115] The data analysis unit 421 is responsible for cleaning and verifying the input data to ensure the accuracy and consistency of the data. The algorithm processing unit 422 includes various algorithms, such as structural analysis algorithms, energy consumption analysis algorithms, and illumination analysis algorithms, and the algorithm processing unit 422 performs in-depth analysis and calculations on the data. The computing engine 423 is responsible for executing these algorithms and generating analysis results.

[0116] Specifically, the generation module 430 is provided with an algorithm generation unit 431, a three-dimensional modeling unit 432 and a solution library 433. The algorithm generation unit 431 generates a plurality of possible preliminary design solutions according to the analysis results generated by the data processing module 420. The three-dimensional modeling unit 432 converts these preliminary design solutions into three-dimensional models for subsequent display and evaluation. The solution library 433 is used to store these possible preliminary design solutions for subsequent query and modification.

[0117] Specifically, the display module 440 is provided with a virtual reality engine 441 and an interactive interface 442. The system provides an intuitive user interface and interactive mode, which is convenient for users to operate and modify. The system can be expanded and upgraded as needed to meet the design requirements of different fields and scenes. The virtual reality engine 441 is responsible for converting the generated three-dimensional model into a virtual reality scene. The user can rotate, zoom, view, etc. through the interactive interface 442 to intuitively experience the design solution in three-dimensional form.

[0118] Specifically, the evaluation module 450 is provided with an evaluation algorithm unit 451 and a feedback unit 452. The evaluation algorithm unit 451 performs multi-dimensional evaluations on the above-mentioned multiple possible preliminary design schemes, such as functionality, safety, economy, etc., and gives an evaluation report. The feedback unit 452 collects the user's evaluation opinions in order to improve the design scheme.

[0119] Specifically, the optimization module 460 is provided with a feedback collection unit 461 and a system optimization unit 462. The feedback collection unit 461 is responsible for collecting feedback from users and the evaluation module 450, and the system optimization unit 462 adjusts input parameters or design solution generation logic according to the feedback to continuously improve system performance and design solution quality.

[0120] Specifically, the output module 470 is provided with a design document generator 471 and a data output unit 472. The design document generator 471 generates detailed design documents, such as construction drawings, material lists, etc. according to the final design plan, and the data output unit 472 is responsible for outputting these documents to users or construction units.

[0121] Specifically, the output mode of the data output unit 472 in the output module 470 includes Bluetooth transmission, LAN transmission, 5G transmission and USB interface transmission.

[0122] During the implementation process, the user first provides basic parameter data of the building design, such as the building's purpose, scale and geographical location, through the input module 410; then, the data processing module 420 processes and analyzes the input data using an artificial intelligence algorithm; then, based on the analysis results, a plurality of possible preliminary design schemes are generated in the generation module 430, and the user can intuitively view these preliminary design schemes through the interactive interface 442 in the display module 440, and evaluate these preliminary design schemes through the evaluation module 450. Based on the evaluation feedback information, the optimization module 460 will self-learn the system and optimize the design scheme, and finally, the output module 470 will output the evaluated and optimized design scheme as the final building design scheme to the user.

[0123] The present invention provides a method and system for assisting intelligent building design. There are many methods and approaches to implement the technical solution. The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. All components not specified in this embodiment can be implemented by existing technologies.

Claims

1. An intelligent building design auxiliary method, characterized in that: include: S1. Obtaining design conditions: based on basic parameter data of architectural design input by the user; S2. Data analysis and processing: using artificial intelligence algorithms to process and analyze the basic parameter data to obtain analysis results; S3, scheme generation: generating multiple possible preliminary design schemes according to the analysis results, automatically scoring the multiple possible preliminary design schemes according to preset evaluation indicators, obtaining scoring results, and providing optimization suggestions; The user can select the best preliminary design scheme from the multiple possible preliminary design schemes according to the scoring results and the optimization suggestions; S4, solution optimization: obtaining the user's evaluation feedback information on the generated design solution, performing self-learning and optimization based on the evaluation feedback information, and obtaining a new design solution; S5. Design output: Output the final design plan in the form of drawings, models, etc.; S4 is iteratively executed until the user is satisfied, thereby obtaining the final design solution.

2. The intelligent building design assisting method according to claim 1, characterized in that: The basic parameter data of the building design in step S1 include the purpose, scale, geographical location and climatic conditions of the building.

3. The intelligent building design assisting method according to claim 2, characterized in that: The data analysis and processing in step S2 includes the selection and analysis of building form, orientation, layout and material selection.

4. The intelligent building design assisting method according to claim 3, characterized in that: The user input parameter in step S1 includes at least one user input parameter selected from the following types: user-conceived content, sensor network, and drone-photographed content.

5. The intelligent building design assisting method according to claim 4, characterized in that: The artificial intelligence algorithm in step S2 includes at least one artificial intelligence algorithm selected from the following types: machine learning algorithm, deep learning algorithm, evolutionary algorithm, multi-objective optimization algorithm, artificial neural network and fuzzy logic.

6. The intelligent building design assisting method according to claim 5, characterized in that: The machine learning algorithm is used to process and analyze the basic parameter data and obtain analysis results. The machine learning algorithm is as follows: Linear regression: y = β0 + β1x + ∈, In the formula, y is the dependent variable, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term; Logistic Regression: In the formula, is the probability of the architectural design being selected, x is the independent variable, β0 is the intercept term, β1 is the regression coefficient, and ∈ is the error term; Decision Tree: A classification or regression model based on a tree structure.

7. The intelligent building design assisting method according to claim 6, characterized in that: The deep learning algorithms include convolutional neural networks, recurrent neural networks, long short-term memory networks, variational autoencoders, and generative adversarial networks.

8. An intelligent building design auxiliary system, characterized in that: The system includes: An input module (410) is used to receive basic parameter data of architectural design input by a user; A data processing module (420) is used to process and analyze the basic parameter data using an artificial intelligence algorithm to obtain analysis results; A generation module (430) is used to generate a plurality of possible preliminary design solutions according to the analysis results; A display module (440) is used to display the multiple possible preliminary design solutions using virtual reality technology; An evaluation module (450) is used to automatically score the multiple possible preliminary design solutions based on preset evaluation indicators, obtain scoring results, and provide optimization suggestions; An optimization module (460), used for self-learning and optimizing solutions according to user evaluation feedback information; The output module (470) is used to output the final architectural design solution.

9. The intelligent building design assistance system according to claim 8, characterized in that: The input module (410) is provided with an input interface unit (411), a data verification unit (412) and a parameter database (413); The data processing module (420) is provided with a data analysis unit (421), an algorithm processing unit (422) and a calculation engine (423); The generation module (430) is provided with an algorithm generation unit (431), a three-dimensional modeling unit (432) and a solution library (433); The display module (440) is provided with a virtual reality engine (441) and an interactive interface (442); The evaluation module (450) is provided with an evaluation algorithm unit (451) and a feedback unit (452); the optimization module (460) is provided with a feedback collection unit (461) and a system optimization unit (462); The output module (470) is provided with a design document generator (471) and a data output unit (472).

10. The intelligent building design support system according to claim 9, characterized in that: The output mode of the data output unit (472) in the output module (470) includes Bluetooth transmission, local area network transmission, 5G transmission and USB interface transmission.

Images