Building structure design method and system based on large model assisted decision making

Abstract

The application relates to the technical field of digital building design, in particular to a building structure design method and system based on large model assisted decision-making. The method provided by the application mainly comprises the following steps: constructing an evaluation model of alternative models, obtaining a first score of each alternative model through the evaluation model of alternative models based on current design parameters, selecting an alternative model with the highest score as a target model of current building design, performing multi-target weighted evaluation on current target parameters to obtain a plurality of second scores, and obtaining a comprehensive confidence value based on the first score and the second score of the target model. Through the above method, various models are comprehensively evaluated and sorted, and the use result is fed back according to the comprehensive confidence value, whether the model needs to be replaced or not, so that the model suitable for the best use effect at present is continuously adjusted, the engineer is assisted to work more effectively, and the use effect of the model is improved.

Description

Technical Field

[0001] This invention relates to the field of digital building design technology, and more specifically, to a building structure design method and system based on large model-assisted decision-making. Background Technology

[0002] The structural design based on large model-assisted decision-making uses a large language or multimodal large model as the cognitive center, integrating BIM, finite element method (FEA), standard knowledge base, and engineering case library to build a human-in-the-loop human-machine collaborative decision-making system. The large model is responsible for requirements analysis, scheme generation, standard reasoning, and multi-objective trade-offs, while professional numerical software is responsible for mechanical verification. Finally, engineers complete the final decision, safety verification, and result approval, realizing intelligent assisted decision-making throughout the entire process from scheme selection, modeling, verification, optimization to drawing output.

[0003] However, there is a wide variety of large models available now, and without effective screening of these models to select the appropriate one for the auxiliary design of the building structure, the final design objective may not be achieved, thus reducing the effectiveness of the model. Summary of the Invention

[0004] The purpose of this invention is to provide a building structure design method and system based on large model-assisted decision-making to solve the above-mentioned problems in the prior art.

[0005] This invention is achieved through the following technical solution: In a first aspect, the present invention provides a building structure design method based on large model-assisted decision-making, comprising: Obtain the design parameters of the current building, obtain several alternative models, set several evaluation dimensions, and define scores for the alternative models based on the evaluation dimensions; Construct an evaluation model for alternative models. Based on the current design parameters, obtain the first score of each alternative model through the evaluation model. Sort the first scores from high to low to obtain the score sequence. Select the alternative model with the highest score as the target model for the current architectural design. Based on the current target model, several sets of construction engineering cases are generated through design parameters. Parametric modeling is performed on each set of construction engineering cases and target parameters are output. Multi-objective weighted evaluation is performed on the current target parameters to obtain several second scores. The second score with the highest value is selected as the target construction engineering case. The comprehensive confidence value is obtained based on the first score and the second score of the target model, and a judgment threshold is set. If the overall confidence value is greater than or equal to the judgment threshold, the current target construction project case is saved. If the overall confidence value is less than the judgment threshold, the candidate model ranked after the target model is selected based on the score sequence to generate several sets of construction project cases, and a second score is generated. The target construction project case is output when the overall confidence value is greater than or equal to the judgment threshold. If all models have been traversed and the target construction project case has not been output, an alarm signal is issued and the process is stopped. Obtain the constraint set of the current target construction project case, construct the objective function, solve the objective function based on the constraint set, and output the final target design parameters.

[0006] Preferably, the construction of the candidate model evaluation model includes:

[0007] In the formula, It received the highest rating. The frequency of use of the current model. The average usage frequency of all models. The average storage size for all models. This represents the storage size of the current model. For the first The weights of each evaluation dimension are calculated. For the first Scores for each evaluation dimension This represents the total number of evaluation dimensions.

[0008] Preferably, the parametric modeling and output target parameters for each set of construction project cases include: The alternative models include the Revit family parametric model, the Civil 3D parametric surface model, and the Tekla parametric steel structure model; When the target model is a Revit family parametric model, create a family type sample for the current construction project case, and create new design parameters based on the family type sample; Draw a reference plane, use alignment constraints to label the first building calculation function for each design parameter, generate a beam solid based on the stretch command, create several steel reinforcement models from the beam solid based on the reinforcement command, and lock the reference plane and add building materials; Load the parametric beam, column, and slab families into the Revit project, arrange the components according to the construction drawing grid, set the global parameters of the project, build a parametric nested family of template support system, complete the parametric modeling, and output geometric engineering quantity parameters, material parameters, and structural safety parameters based on the first building calculation function.

[0009] Preferably, when the target model is a Civil 3D parametric surface model, it includes: Send a password to invoke the Civil 3D model to create a new parameter set. The parameter set includes several variables and a second building calculation function. Use the parameter variables to generate a base polygon, create a slope object, and generate slope feature lines based on the parameter slope ratio and excavation depth. The original terrain surface is created based on the original ground point cloud and contour lines. The excavation boundary surface is generated from the foundation pit feature lines, and the support and earthwork parameters are bound to the surface attributes. Send the password to the Civil 3D scheme tool module and script to modify parameters in a loop, and output the surface geometry parameters and earthwork volume parameters based on the second building calculation function.

[0010] Preferably, when the target model is a Tekla parametric steel structure model, it includes: Obtain steel structure modeling and third-party building calculation functions, and construct a custom component of a parameterized portal frame based on the steel structure modeling and third-party building calculation functions; Load the parametric portal frame components into the Tekla model, set the global plant parameters, and arrange the frames in batch arrays to generate parametric components, thus completing the complete benchmark steel structure model of a single plant. The third building calculation function is used to calculate and output the component's geometric parameters, steel quantity parameters, and connection process parameters.

[0011] Preferably, the multi-objective weighted evaluation of the current target parameters to obtain several second scores includes:

[0012] In the formula, As the second-highest score, The total number of target parameters. For the first The weights of each objective parameter are calculated. For the first The specific values ​​of each target parameter. For the first The standard values ​​of the target parameters.

[0013] Preferably, the method for obtaining a comprehensive confidence value based on the first and second scores of the target model includes:

[0014]

[0015] In the formula, For the overall confidence value, , These are the weights used to calculate the first and second scores, respectively. The total cost of the project. For labor costs.

[0016] Preferably, the objective function is constructed by including a total cost index function and a construction period index function, with the objective function being constructed with the sum of the total cost index function and the construction period index function being minimized.

[0017] Preferably, the objective function includes:

[0018]

[0019]

[0020] In the formula, This is a function of the total construction cost exponential. It is a construction period exponential function. Let be the objective function. This is the unit price of the material. For material volume or weight, For workers' daily wages, This refers to the actual construction period. This is the unit price per machine shift. For the main machine shift, The comprehensive cost of safety protection per unit area. For the protected area, This is the current total construction budget. For the planned construction period.

[0021] A building structure design system based on large model-assisted decision-making, used to execute the aforementioned building structure design method based on large model-assisted decision-making, includes: The data processing module is configured to: acquire the design parameters of the current building; acquire several candidate models; set several evaluation dimensions; define scores for the candidate models based on the evaluation dimensions; construct a candidate model evaluation model; obtain a first score for each candidate model based on the current design parameters; sort the first scores from high to low to obtain a score sequence; select the candidate model with the highest score as the target model for the current building design; generate several sets of construction engineering cases based on the current target model and design parameters; perform parametric modeling and output target parameters for each set of construction engineering cases; perform multi-objective weighted evaluation on the current target parameters to obtain several second scores; select the second score with the highest value as the target construction engineering case; obtain a comprehensive confidence value based on the first and second scores of the target model; and set a judgment threshold. The judgment module is configured to save the current target construction project case if the comprehensive confidence value is greater than or equal to the judgment threshold; if the comprehensive confidence value is less than the judgment threshold, it selects the candidate model ranked after the target model based on the score sequence to generate several sets of construction project cases and generates a second score until the comprehensive confidence value is greater than or equal to the judgment threshold, at which point the target construction project case is output. If all models have been traversed and the target construction project case has not yet been output, an alarm signal is issued and the process stops; the constraint set of the current target construction project case is obtained, the objective function is constructed, the objective function is solved based on the constraint set, and the final target design parameters are output.

[0022] The technical solution of the present invention has at least the following advantages and beneficial effects: The method provided by this invention mainly includes constructing an evaluation model for candidate models; obtaining a first score for each candidate model based on current design parameters; selecting the candidate model with the highest score as the target model for the current architectural design; performing a multi-objective weighted evaluation on the current target parameters to obtain several second scores; and obtaining a comprehensive confidence value based on the first and second scores of the target model. Through this method, various models are comprehensively evaluated and ranked. After use based on the ranking, feedback is provided based on the comprehensive confidence value of the usage results to determine whether a model needs to be replaced. This process continuously adjusts the model to best suit the current usage effect, thereby assisting engineers in their work as effectively as possible and improving the model's usability. Attached Figure Description

[0023] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the process of the present invention; Figure 2 This is a schematic diagram of the system structure of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0026] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not imply that the steps in the method flow must be executed in the chronological / logical order indicated by the naming or numbering. The execution order of named or numbered process steps can be changed according to the desired technical objective, as long as the same or similar technical effect is achieved.

[0027] The independently described modules or sub-modules may or may not be physically separated; they may be implemented in software or hardware, and some modules or sub-modules may be implemented in software, with the processor calling the software to implement the function of these modules or sub-modules, while other modules or sub-modules may be implemented in hardware, such as through hardware circuits. Furthermore, some or all of the modules can be selected to achieve the purpose of this application's solution according to actual needs.

[0028] Please refer to Figures 1-2 A building structure design method based on large model-assisted decision-making includes: S100: Obtain the design parameters of the current building, obtain several alternative models, set several evaluation dimensions, and define scores for the several alternative models based on the evaluation dimensions; In this embodiment, the candidate models include Revit family parametric models, Civil 3D parametric surface models, and Tekla parametric steel structure models, wherein the evaluation dimensions include: Modeling evaluation dimensions: frame modeling score, truss modeling score, concrete modeling score; Data generation dimensions: score for the number of parameter types, score for the accuracy of parameter calculation; Building type dimension: residential modeling score, bridge modeling score, water conservancy project modeling score.

[0029] Each model is scored across different dimensions, with each item's score set between 1 and 5 points. A higher score indicates that the current model is better at that particular dimension.

[0030] S200: Construct an evaluation model for alternative models. Based on the current design parameters, obtain the first score of each alternative model through the evaluation model. Sort the first scores from high to low to obtain a score sequence. Select the alternative model with the highest score as the target model for the current architectural design. S300: Based on the current target model, generate several sets of construction engineering cases through design parameters. Perform parametric modeling and output target parameters based on each set of construction engineering cases. Perform multi-objective weighted evaluation on the current target parameters to obtain several second scores. Select the second score with the highest value as the target construction engineering case. Obtain the comprehensive confidence value based on the first score and the second score of the target model, and set the judgment threshold. For example, with design parameters such as architectural CAD floor plan, seismic intensity 7, site type II, height limit 80m, and cost control of 2200 yuan / ㎡, it can output three sets of construction project cases: pure shear wall, 1:3 frame-shear wall, and steel frame.

[0031] S400: If the overall confidence value is greater than or equal to the judgment threshold, save the current target construction project case. If the overall confidence value is less than the judgment threshold, select the candidate model ranked after the target model based on the score sequence to generate several sets of construction project cases and generate a second score until the overall confidence value is greater than or equal to the judgment threshold. Then output the target construction project case. If all models have been traversed and the target construction project case has not been output, issue an alarm signal and stop the step. S500: Obtain the constraint set of the current target construction project case, construct the objective function, solve the objective function based on the constraint set, and output the final target design parameters.

[0032] The method provided by this invention mainly includes: constructing an evaluation model for candidate models; obtaining a first score for each candidate model based on current design parameters; selecting the candidate model with the highest score as the target model for the current architectural design; performing a multi-objective weighted evaluation on the current target parameters to obtain several second scores; and obtaining a comprehensive confidence value based on the first and second scores of the target model. Through this method, various models are comprehensively evaluated and ranked. After use based on the ranking, feedback is provided based on the comprehensive confidence value of the usage results to determine whether a model needs to be replaced. This process continuously adjusts the model to best suit the current usage effect, thereby assisting engineers in their work as effectively as possible and improving the model's usability. In one exemplary embodiment of the present invention, constructing an evaluation model for alternative models includes:

[0033] In the formula, It received the highest rating. The frequency of use of the current model. The average usage frequency of all models. The average storage size for all models. This represents the storage size of the current model. For the first The weights of each evaluation dimension are calculated. For the first Scores for each evaluation dimension This represents the total number of evaluation dimensions.

[0034] The above model integrates the comprehensive scores of several models for each dimension. If a dimension is involved in the design parameters, that dimension is included in the calculation to obtain a relatively objective score value. The usage of each model is also obtained and comprehensively considered to correct the first score. The sum of the calculation weights of all evaluation dimensions is 1.

[0035] In one exemplary embodiment of the present invention, the parametric modeling and output of target parameters for each set of construction engineering cases include: The alternative models include the Revit family parametric model, the Civil 3D parametric surface model, and the Tekla parametric steel structure model; When the target model is a Revit family parametric model, taking the economical small section scheme and the scheme large span reinforced section scheme as examples, create a family type sample for the current construction project case, and create new design parameters based on the family type sample; Draw a reference plane, use alignment constraints to label the first building calculation function for each design parameter, generate a beam solid based on the stretch command, create several steel reinforcement models from the beam solid based on the reinforcement command, and lock the reference plane and add building materials; Load the parametric beam, column, and slab families into the Revit project, arrange the components according to the construction drawing grid, set the global parameters of the project, build a parametric nested family of template support system, complete the parametric modeling, and output geometric engineering quantity parameters, material parameters, and structural safety parameters based on the first building calculation function.

[0036] Specifically, for a single scheme: Revit details / quantity, select all custom parameters in the fields, and export to Excel; for batch multi-scheme: Dynamo reads the project details table for each scheme in a loop and merges them into a unified comparison table; for interface output: export IFC files, embed parameters into attribute sets, and can connect to a database to read JSON parameters.

[0037] Geometric engineering parameters: volume of a single span beam, area of ​​formwork, total weight of reinforcing steel, total area of ​​supports; structural safety parameters: effective height of section, reinforcement ratio, number of stirrups; material parameters: concrete grade, diameter of reinforcing steel, thickness of protective layer; construction resource parameters: number of support poles, area of ​​formwork materials consumed.

[0038] An exemplary embodiment of the present invention, when the target model is a Civil 3D parametric surface model, includes: Send a password to invoke the Civil 3D model to create a new parameter set. The parameter set includes several variables and a second building calculation function. Use the parameter variables to generate a base polygon, create a slope object, and generate slope feature lines based on the parameter slope ratio and excavation depth. The original terrain surface is created based on the original ground point cloud and contour lines. The excavation boundary surface is generated from the foundation pit feature lines, and the support and earthwork parameters are bound to the surface attributes. Specifically, the parametric route surface of the road centerline is superimposed (the parameters of longitudinal slope, superelevation, and widening are similarly bound to linear functions); parametric components of the support piles are arranged, and the pile spacing and pile length are referenced to the excavation depth function; the original terrain surface, excavation surface, and support structure are combined to form a complete site benchmark case model.

[0039] Send the password to the Civil 3D scheme tool module and script to modify parameters in a loop, and output the surface geometry parameters and earthwork volume parameters based on the second building calculation function.

[0040] Specifically, the surface geometric parameters include: excavation depth, slope ratio, top opening dimensions, slope length, and platform width; earthwork volume parameters include: excavation volume, backfill volume, and spoil volume; support construction parameters include: total shotcrete area, number of support piles, and slope protection area; and cost calculation parameters include: earthwork removal volume and slope protection material consumption area.

[0041] An exemplary embodiment of the present invention, when the target model is a Tekla parametric steel structure model, includes: Obtain steel structure modeling and third-party building calculation functions, and construct a custom component of a parameterized portal frame based on the steel structure modeling and third-party building calculation functions; Load the parametric portal frame components into the Tekla model, set the global plant parameters, and arrange the frames in batch arrays to generate parametric components, thus completing the complete benchmark steel structure model of a single plant. The third building calculation function is used to calculate and output the component's geometric parameters, steel quantity parameters, and connection process parameters.

[0042] Specifically, the geometric parameters of the components are: beam and column cross-sectional dimensions, single span, component length, and plate thickness; the steel quantity parameters are: weight of a single component and total steel consumption of the entire building; the connection process parameters are: total number of bolts, total weld length, and weld leg size; and the processing and construction parameters are: number of components, number of nodes, and total area of ​​cut plates.

[0043] In one exemplary embodiment of the present invention, the multi-objective weighted evaluation of the current target parameter to obtain several second scores includes:

[0044] In the formula, As the second-highest score, The total number of target parameters. For the first The weights of each objective parameter are calculated. For the first The specific values ​​of each target parameter. For the first The standard values ​​of the target parameters.

[0045] The combined confidence value obtained based on the first and second scores of the target model includes:

[0046]

[0047] In the formula, For the overall confidence value, , These are the weights used to calculate the first and second scores, respectively. The total cost of the project. For labor costs.

[0048] The specific usage of the current model can be determined by setting a comprehensive confidence value combined with a judgment threshold. The judgment threshold can be set according to the specific usage criteria, for example, it can be set to 3.

[0049] In one exemplary embodiment of the present invention, the objective function is constructed by including a total cost index function and a construction period index function, with the objective function being constructed with the sum of the total cost index function and the construction period index function being minimized.

[0050] Specifically, the objective function includes:

[0051]

[0052]

[0053] In the formula, This is a function of the total construction cost exponential. It is a construction period exponential function. Let be the objective function. This is the unit price of the material. For material volume or weight, For workers' daily wages, This refers to the actual construction period. This is the unit price per machine shift. For the main machine shift, The comprehensive cost of safety protection per unit area. For the protected area, This is the current total construction budget. For the planned construction period.

[0054] This invention also provides a building structure design system based on large model-assisted decision-making, used to execute the above-described building structure design method based on large model-assisted decision-making, including: The data processing module is configured to: acquire the design parameters of the current building; acquire several candidate models; set several evaluation dimensions; define scores for the candidate models based on the evaluation dimensions; construct a candidate model evaluation model; obtain a first score for each candidate model based on the current design parameters; sort the first scores from high to low to obtain a score sequence; select the candidate model with the highest score as the target model for the current building design; generate several sets of construction engineering cases based on the current target model and design parameters; perform parametric modeling and output target parameters for each set of construction engineering cases; perform multi-objective weighted evaluation on the current target parameters to obtain several second scores; select the second score with the highest value as the target construction engineering case; obtain a comprehensive confidence value based on the first and second scores of the target model; and set a judgment threshold. The judgment module is configured to save the current target construction project case if the comprehensive confidence value is greater than or equal to the judgment threshold; if the comprehensive confidence value is less than the judgment threshold, it selects the candidate model ranked after the target model based on the score sequence to generate several sets of construction project cases and generates a second score until the comprehensive confidence value is greater than or equal to the judgment threshold, at which point the target construction project case is output. If all models have been traversed and the target construction project case has not yet been output, an alarm signal is issued and the process stops; the constraint set of the current target construction project case is obtained, the objective function is constructed, the objective function is solved based on the constraint set, and the final target design parameters are output.

[0055] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0056] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. This computer software product, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] The above are merely preferred embodiments of the present invention and are not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A building structure design method based on large model-assisted decision-making, characterized in that, include: Obtain the design parameters of the current building, obtain several alternative models, set several evaluation dimensions, and define scores for the alternative models based on the evaluation dimensions; Construct an evaluation model for alternative models. Based on the current design parameters, obtain the first score of each alternative model through the evaluation model. Sort the first scores from high to low to obtain the score sequence. Select the alternative model with the highest score as the target model for the current architectural design. Based on the current target model, several sets of construction engineering cases are generated through design parameters. Parametric modeling is performed on each set of construction engineering cases and target parameters are output. Multi-objective weighted evaluation is performed on the current target parameters to obtain several second scores. The second score with the highest value is selected as the target construction engineering case. The comprehensive confidence value is obtained based on the first score and the second score of the target model, and a judgment threshold is set. If the overall confidence value is greater than or equal to the judgment threshold, the current target construction project case is saved. If the overall confidence value is less than the judgment threshold, the candidate model ranked after the current target model is selected based on the score sequence to generate several sets of construction project cases, and a second score is generated. The target construction project case is output when the overall confidence value is greater than or equal to the judgment threshold. If all models have been traversed and the target construction project case has not been output, an alarm signal is issued and the step is stopped. Obtain the constraint set of the current target construction project case, construct the objective function, solve the objective function based on the constraint set, and output the final target design parameters.

2. The building structure design method based on large model-assisted decision-making according to claim 1, characterized in that, The construction of alternative models and the evaluation model include: In the formula, It received the highest rating. The frequency of use of the current model. The average usage frequency of all models. The average storage size for all models. This represents the storage size of the current model. For the first The weights of each evaluation dimension are calculated. For the first Scores for each evaluation dimension This represents the total number of evaluation dimensions.

3. The building structure design method based on large model-assisted decision-making according to claim 1, characterized in that, The parametric modeling and output target parameters for each set of construction project cases include: The alternative models include the Revit family parametric model, the Civil 3D parametric surface model, and the Tekla parametric steel structure model; When the target model is a Revit family parametric model, create a family type sample for the current construction project case, and create new design parameters based on the family type sample; Draw a reference plane, use alignment constraints to label the first building calculation function for each design parameter, generate a beam solid based on the stretch command, create several steel reinforcement models from the beam solid based on the reinforcement command, and lock the reference plane and add building materials; Load the parametric beam, column, and slab families into the Revit project, arrange the components according to the construction drawing grid, set the global parameters of the project, build a parametric nested family of template support system, complete the parametric modeling, and output geometric engineering quantity parameters, material parameters, and structural safety parameters based on the first building calculation function.

4. The building structure design method based on large model-assisted decision-making according to claim 3, characterized in that, When the target model is a Civil 3D parametric surface model, it includes: Send a password to invoke the Civil 3D model to create a new parameter set. The parameter set includes several variables and a second building calculation function. Use the parameter variables to generate a base polygon, create a slope object, and generate slope feature lines based on the parameter slope ratio and excavation depth. The original terrain surface is created based on the original ground point cloud and contour lines. The excavation boundary surface is generated from the foundation pit feature lines, and the support and earthwork parameters are bound to the surface attributes. Send the password to the Civil 3D scheme tool module and script to modify parameters in a loop, and output the surface geometry parameters and earthwork volume parameters based on the second building calculation function.

5. The building structure design method based on large model-assisted decision-making according to claim 4, characterized in that, When the target model is a Tekla parametric steel structure model, it includes: Obtain steel structure modeling and third-party building calculation functions, and construct a custom component of a parametric portal frame based on the steel structure modeling and third-party building calculation functions; Load the parametric portal frame components into the Tekla model, set the global plant parameters, and arrange the frames in batch arrays to generate parametric components, thus completing the complete benchmark steel structure model of a single plant. The third building calculation function is used to calculate and output the component's geometric parameters, steel quantity parameters, and connection process parameters.

6. The building structure design method based on large model-assisted decision-making according to claim 1, characterized in that, The multi-objective weighted evaluation of the current target parameters yields several second scores, including: In the formula, As the second-highest score, The total number of target parameters. For the first The weights of each objective parameter are calculated. For the first The specific values ​​of each target parameter. For the first The standard values ​​of the target parameters.

7. The building structure design method based on large model-assisted decision-making according to claim 6, characterized in that, The comprehensive confidence value obtained based on the first and second scores of the target model includes: In the formula, For the overall confidence value, , These are the weights used to calculate the first and second scores, respectively. The total cost of the project. For labor costs.

8. The building structure design method based on large model-assisted decision-making according to claim 1, characterized in that, The objective function is constructed by including a total cost index function and a construction period index function, with the goal of minimizing the sum of the total cost index function and the construction period index function.

9. The building structure design method based on large model-assisted decision-making according to claim 8, characterized in that, The objective function includes: In the formula, This is a function of the total construction cost exponential. It is a construction period exponential function. Let be the objective function. This is the unit price of the material. For material volume or weight, For workers' daily wages, This refers to the actual construction period. This is the unit price per machine shift. For the main machine shift, The comprehensive cost of safety protection per unit area. For the protected area, This is the current total construction budget. For the planned construction period.

10. A building structure design system based on large model-assisted decision-making, characterized in that, The building structure design method based on large model-assisted decision-making as described in any one of claims 1-9 includes: The data processing module is configured to: acquire the design parameters of the current building; acquire several candidate models; set several evaluation dimensions; define scores for the candidate models based on the evaluation dimensions; construct a candidate model evaluation model; obtain a first score for each candidate model based on the current design parameters; sort the first scores from high to low to obtain a score sequence; select the candidate model with the highest score as the target model for the current building design; generate several sets of construction engineering cases based on the current target model and design parameters; perform parametric modeling and output target parameters for each set of construction engineering cases; perform multi-objective weighted evaluation on the current target parameters to obtain several second scores; select the second score with the highest value as the target construction engineering case; obtain a comprehensive confidence value based on the first and second scores of the target model; and set a judgment threshold. The judgment module is configured to save the current target construction project case if the comprehensive confidence value is greater than or equal to the judgment threshold; if the comprehensive confidence value is less than the judgment threshold, it selects the candidate model ranked after the target model based on the score sequence to generate several sets of construction project cases and generates a second score until the comprehensive confidence value is greater than or equal to the judgment threshold, at which point the target construction project case is output. If all models have been traversed and the target construction project case has not yet been output, an alarm signal is issued and the process stops; the constraint set of the current target construction project case is obtained, the objective function is constructed, the objective function is solved based on the constraint set, and the final target design parameters are output.

Images