A Building Engineering Cost Control Method and System Based on BIM Forward Design

Abstract

A construction project cost control method and system based on BIM forward design relates to the field of data processing methods specifically applicable to business. In this method, design element information of horizontal and vertical construction areas is collected; a regional cross-node matrix is generated based on the design element information, and a density coefficient is calculated; high-risk cost nodes are identified; the initial value and change value of the design parameters of each high-risk cost node are recorded; a cost fluctuation coefficient is calculated; a parameter adjustment range is determined based on the cost fluctuation coefficient, and optional parameter combinations are screened; the cost value of the high-risk cost node is calculated; when no cost value falls within a preset cost value range, the parameter adjustment range is adjusted according to a preset adjustment plan; when a cost value falls within the preset cost value range, a final design plan for the corresponding parameters is output. This application is used to improve the timeliness and accuracy of construction project cost control.

Description

Technical Field

[0001] The present application belongs to the field of data processing methods specifically applicable to business, and in particular relates to a construction project cost control method and system based on BIM forward design. Background Art

[0002] Construction projects require strict cost control during the construction process. Traditional cost control methods mainly rely on manual statistics and accounting, which not only requires a large workload and is inefficient, but is also prone to data statistical deviations and delays, making it difficult to detect and deal with cost overruns in a timely manner.

[0003] In related technologies, the construction process can be broken down into multiple stages by constructing three-dimensional and four-dimensional BIM models, and actual costs can be compared and analyzed against budget at each stage. If cost deviations exceed a set threshold, this method utilizes BIM and earned value analysis to analyze these deviations and uses construction simulation technology to determine the optimal construction plan, thus forming a closed-loop construction cost control system. This approach, to a certain extent, addresses the challenges of traditional manual accounting and improves the accuracy and timeliness of cost control.

[0004] However, all cost control measures of the above-mentioned related technologies are only implemented during the construction phase. This passive cost control model makes it difficult to deal with many cost risks that can be foreseen and avoided in the design phase in a timely manner, reducing the effectiveness of subsequent cost control measures. Summary of the Invention

[0005] This application provides a construction project cost control method and system based on BIM forward design, which is used to improve the timeliness and accuracy of construction project cost control.

[0006] In the first aspect, the present application provides a construction project cost control method based on BIM forward design, which divides the building space into horizontal construction areas and vertical construction areas in the BIM model;

[0007] Setting layer identification codes in the horizontal construction area and the vertical construction area, and collecting design element information of the horizontal construction area and the vertical construction area based on the layer identification codes;

[0008] Generate a regional cross node matrix based on the design element information, and calculate the density coefficient of the nodes in the regional cross node matrix;

[0009] Mark nodes with a density coefficient greater than a preset threshold as high-risk cost nodes;

[0010] Set up parameter monitoring units at each high-risk cost node to record the initial and changed values of design parameters in real time;

[0011] Calculate the cost fluctuation coefficient based on the change value of the design parameters;

[0012] Determine the parameter adjustment range based on the cost fluctuation coefficient, and select the optional parameter combination that meets the preset design specifications within the parameter adjustment range;

[0013] Update the parameters in the optional parameter combination to the BIM model in sequence, and calculate the cost value of the high-risk cost node based on the updated BIM model;

[0014] When there is no cost value within the preset cost value range, adjusting the parameter adjustment range according to the preset adjustment scheme, and re-performing the step of screening out an optional parameter combination that meets the preset design specification within the parameter adjustment range;

[0015] When there is a cost value within the preset cost value range, the final design solution of the corresponding parameters is output.

[0016] By adopting the above technical solution, by dividing horizontal and vertical construction areas within the BIM model and assigning hierarchical identification codes, design element information for each area can be precisely located and tracked. Calculating the node density coefficient based on the regional cross-node matrix can identify critical nodes with high design complexity and significant cost impact. Setting up parameter monitoring units for these high-risk cost nodes records design parameter changes in real time, and determining a reasonable parameter adjustment range based on the cost fluctuation coefficient effectively prevents cost overruns caused by design changes. Preset design specification constraints are introduced during the parameter screening process to ensure that adjustment plans meet both cost control objectives and project quality requirements. Iterative optimization continuously adjusts parameter ranges until a suitable solution is found, reducing the time and resource waste caused by repeated drawing revisions in traditional design. This BIM-based forward design approach brings cost control to the design stage. Through data-driven and intelligent analysis, it achieves a dynamic balance between design solutions and cost targets, improving the timeliness and accuracy of construction project cost control.

[0017] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the cost fluctuation coefficient based on the change value of the design parameter specifically includes:

[0018] Construct a parameter change curve according to the change value of the design parameter, and calculate the slope of the parameter change curve;

[0019] A cost sensitivity matrix is generated based on the slope, where the rows and columns of the cost sensitivity matrix correspond to different design parameters;

[0020] A recursive neural network is used to train the cost sensitivity matrix to obtain the associated weights;

[0021] The product of the associated weight and the slope is taken as the cost fluctuation coefficient.

[0022] By employing this technical solution, we can quantitatively describe the impact of design parameter changes on cost by constructing a parameter change curve and calculating its slope. The establishment of a cost sensitivity matrix allows for a visual representation of the interplay between different design parameters. Using a recursive neural network for training, the system can autonomously learn and identify parameter variation patterns, extracting key factors influencing cost. The cost fluctuation coefficient, obtained by multiplying the associated weights by the slope, accurately reflects the actual impact of parameter adjustments on cost.

[0023] In conjunction with some embodiments of the first aspect, in some embodiments, determining the parameter adjustment range based on the cost fluctuation coefficient specifically includes:

[0024] Construct a multidimensional parameter space, where each dimension of the multidimensional parameter space corresponds to a design parameter;

[0025] Calculating a parameter adjustment vector based on the cost fluctuation coefficient in a multidimensional parameter space;

[0026] Determine the initial parameter adjustment range according to the direction and modulus of the parameter adjustment vector;

[0027] Genetic algorithm is used to optimize the boundaries of the initial parameter adjustment range to obtain the final parameter adjustment range.

[0028] By employing this technical solution, parameter adjustment vectors are calculated based on the cost fluctuation coefficient in a multidimensional parameter space, simultaneously considering the combined impact of multiple design parameters. The initial adjustment range is determined based on the direction and modulus of the adjustment vector, ensuring the rationality and feasibility of parameter adjustments. A genetic algorithm is used to optimize the boundaries of the parameter adjustment range. Through population evolution and fitness evaluation, the optimal parameter boundary values are screened, enabling the optimal parameter combination to be found while ensuring overall design coordination. This algorithm automatically searches for the optimal solution, improving design efficiency while ensuring the scientific nature and feasibility of the solution.

[0029] In conjunction with some embodiments of the first aspect, in some embodiments, adjusting the parameter adjustment range according to a preset adjustment scheme specifically includes:

[0030] Calculate the deviation rate between the current cost value and the preset cost value range;

[0031] An adaptive adjustment coefficient is constructed based on the deviation rate, and the adaptive adjustment coefficient increases as the deviation rate increases;

[0032] The product of the adaptive adjustment coefficient and the parameter adjustment range is used as the new parameter adjustment range.

[0033] By adopting the above technical solution, dynamic optimization of the parameter adjustment range is achieved by calculating the cost deviation rate and constructing an adaptive adjustment coefficient. The characteristic that the adaptive adjustment coefficient increases with the deviation rate enables the system to automatically adjust the size of the search range based on the cost control effect. Multiplying the adaptive adjustment coefficient by the parameter adjustment range to obtain a new adjustment range avoids the problems of local optimality or slow convergence that may be caused by fixed step size adjustment. This adaptive adjustment mechanism can dynamically adjust the search strategy according to the actual situation during the optimization process, ensuring rapid approach to the target when the deviation is large, and fine-tuning when approaching the target, thereby improving the efficiency and accuracy of parameter optimization.

[0034] In conjunction with some embodiments of the first aspect, in some embodiments, outputting a final design solution corresponding to the parameters specifically includes:

[0035] Extract multiple sets of parameter combinations that meet the preset cost value range;

[0036] Calculate the construction difficulty index and material utilization rate corresponding to each set of parameter combinations;

[0037] A comprehensive evaluation model was established using historical cost control effects, historical construction difficulty index, and historical material utilization as training data;

[0038] The construction difficulty index and material utilization rate corresponding to each parameter combination are input into the comprehensive evaluation model to obtain the comprehensive score corresponding to each parameter combination;

[0039] The parameter combination with the highest comprehensive score is output as the final design solution.

[0040] By adopting the above technical solution, the system obtains evaluation data in multiple dimensions by extracting multiple sets of parameter combinations that meet the preset cost value range and calculating the construction difficulty index and material utilization rate corresponding to each set of parameter combinations. A comprehensive evaluation model is established using historical cost control effects, historical construction difficulty indexes, and historical material utilization rates as training data. This model incorporates past project experience and can provide a more comprehensive evaluation of new solutions. After inputting the construction difficulty index and material utilization rate corresponding to each set of parameter combinations into the comprehensive evaluation model, the resulting comprehensive score reflects the comprehensive performance of the solution in multiple aspects such as cost control, construction feasibility, and resource utilization. The parameter combination with the highest comprehensive score is selected as the final design solution, ensuring that the output solution not only meets the cost requirements, but also has good construction feasibility and material utilization efficiency, thereby improving the overall quality of the design solution and the reliability of project implementation.

[0041] In conjunction with some embodiments of the first aspect, in some embodiments, after outputting the final design solution corresponding to the parameters, the method further includes:

[0042] Collect real-time parameter data during the construction process and calculate the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design solution;

[0043] When the deviation rate exceeds the preset warning threshold, a warning instruction containing abnormal parameter information is generated;

[0044] According to the abnormal parameter information in the early warning instruction, the adjustable design elements corresponding to the hierarchical identification code are extracted in the associated area of the high-risk cost node corresponding to the abnormal parameter, and a preliminary adjustment plan is generated based on the adjustable design elements;

[0045] The regional cross-node matrix is used to calculate the disturbance impact coefficient of the preliminary adjustment plan on the adjacent construction area, and the adjustment plan with a disturbance impact coefficient less than the safety threshold is selected as the executable plan;

[0046] Calculate the cost-effectiveness ratio of each executable plan and select the plan with the highest cost-effectiveness ratio as the final adjustment plan. The cost-effectiveness ratio is equal to the ratio of the cost reduction after the implementation of the plan to the cost of implementing the plan.

[0047] By adopting the above technical solution, the system realizes dynamic monitoring of the construction process by collecting real-time parameter data during the construction process and calculating the deviation rate from the target parameter data. When the deviation rate exceeds the warning threshold, a warning instruction containing abnormal parameter information is generated, enabling the system to promptly detect abnormal conditions during the construction process. By using the regional cross-node matrix to calculate the disturbance influence coefficient and screening out adjustment plans with a disturbance influence coefficient less than the safety threshold, the negative impact of the adjustment measures on adjacent construction areas is reduced. The cost-effectiveness ratio of each executable plan is calculated and the highest value is selected as the final plan, ensuring that the adjustment measures can not only effectively solve the problem but also have good economic efficiency. This dynamic monitoring and intelligent adjustment mechanism improves the timeliness and accuracy of cost control and reduces the cost risk during the construction process.

[0048] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design solution specifically includes:

[0049] Extract the corresponding target parameter data from the final design solution and establish the corresponding relationship between the real-time parameter data and the target parameter data;

[0050] Calculate the difference between the real-time parameter data and the target parameter data in each set of corresponding relationships respectively;

[0051] Divide the difference by the target parameter data to obtain the deviation rate.

[0052] By employing this technical solution, the system establishes a benchmark framework for parameter comparison by extracting target parameter data from the final design and establishing a corresponding relationship with real-time parameter data. By calculating the difference between the real-time parameter data and the target parameter data for each corresponding relationship, the degree of deviation of each parameter during the construction process can be accurately quantified. Dividing this difference by the target parameter data yields the deviation rate, which standardizes and uniformly measures the degree of deviation between different parameters. This improves the comparability of different parameter types and facilitates unified early warning judgments and priority sorting by the system.

[0053] In the second aspect, an embodiment of the present application provides a construction project cost control system based on BIM forward design, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0054] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a system, enables the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0055] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a system, enables the system to execute the method described in any possible implementation manner in the first aspect.

[0056] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0057] 1. This application provides a construction project cost control method based on BIM forward design. By dividing horizontal and vertical construction areas in the BIM model and setting hierarchical identification codes, the design element information of each area can be accurately located and tracked. The node density coefficient is calculated based on the regional cross-node matrix, which can identify key nodes with high design complexity and large cost impact. Setting parameter monitoring units for these high-risk cost nodes, recording design parameter changes in real time, and determining a reasonable parameter adjustment range based on the cost fluctuation coefficient can effectively prevent cost overruns caused by design changes. Preset design specification constraints are introduced during the parameter screening process to ensure that the adjustment plan meets both cost control goals and project quality requirements. The parameter range is continuously adjusted through iterative optimization until a suitable solution is found, reducing the time and resource waste caused by repeated revisions of drawings in traditional design. This BIM-based forward design method puts cost control in the design stage, and through data-driven and intelligent analysis, achieves a dynamic balance between design plans and cost targets, improving the timeliness and accuracy of construction project cost control.

[0058] 2. This application provides a construction project cost control method based on BIM forward design. By extracting multiple groups of parameter combinations that meet the preset cost value range and calculating the construction difficulty index and material utilization rate corresponding to each group of parameter combinations, the system obtains evaluation data in multiple dimensions. A comprehensive evaluation model is established using historical cost control effects, historical construction difficulty indexes, and historical material utilization rates as training data. This model incorporates past project experience and can conduct a more comprehensive evaluation of new solutions. After inputting the construction difficulty index and material utilization rate corresponding to each group of parameter combinations into the comprehensive evaluation model, the resulting comprehensive score reflects the comprehensive performance of the solution in multiple aspects such as cost control, construction feasibility, and resource utilization. The parameter combination with the highest comprehensive score is selected as the final design solution to ensure that the output solution not only meets the cost requirements, but also has good construction feasibility and material utilization efficiency, thereby improving the overall quality of the design solution and the reliability of project implementation.

[0059] 3. The present application provides a method for cost control of construction projects based on BIM forward design. By collecting real-time parameter data during the construction process and calculating the deviation rate from the target parameter data, the system realizes dynamic monitoring of the construction process. When the deviation rate exceeds the warning threshold, a warning instruction containing abnormal parameter information is generated, so that the system can promptly detect abnormal conditions during the construction process. By using the regional cross-node matrix to calculate the disturbance influence coefficient and screening out adjustment plans with a disturbance influence coefficient less than the safety threshold, the negative impact of the adjustment measures on adjacent construction areas is reduced. The cost-effectiveness ratio of each executable plan is calculated and the highest value is selected as the final plan, ensuring that the adjustment measures can not only effectively solve the problem but also have good economic efficiency. This dynamic monitoring and intelligent adjustment mechanism improves the timeliness and accuracy of cost control and reduces the cost risk during the construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 This is a flow chart of a construction project cost control method based on BIM forward design in an embodiment of the present application.

[0061] Figure 2 It is a flow chart of a dynamic adjustment method during the construction process in an embodiment of the present application.

[0062] Figure 3 This is a schematic diagram of the physical device structure of a construction project cost control system based on BIM forward design provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The terms used in the following examples 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 and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0064] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0065] The following uses an embodiment and combines Figure 1 , a construction project cost control method based on BIM forward design in an embodiment of the present application is described:

[0066] See also Figure 1 , which is a flow chart of a construction project cost control method based on BIM forward design in an embodiment of the present application.

[0067] S101. Divide the building space into horizontal construction areas and vertical construction areas in the BIM model;

[0068] This step involves logically dividing the building space into different construction areas to facilitate more refined design and management. Horizontal construction areas can be different areas on the same floor, and vertical construction areas can be different floors or different vertical spaces. In addition to dividing by horizontal and vertical directions, it can also be divided according to the function and structure of the building. For example, it can be divided into residential areas, commercial areas, office areas, etc. according to the building's use function, and divided into frame structure areas, shear wall structure areas, etc. according to the building structure.

[0069] The system can use architectural information in the BIM model, such as floors, spaces, and components, to divide building spaces. For example, it can identify different floors in the BIM model and divide each floor into several horizontal construction areas. It can also identify different vertical spaces in the BIM model, such as elevator shafts and pipe shafts, and divide them into vertical construction areas. The system can also consider actual construction needs and reasonably adjust the area division, such as merging or subdividing areas based on factors such as construction sequence and difficulty.

[0070] S102: setting layer identification codes in the horizontal construction area and the vertical construction area, and collecting design element information of the horizontal construction area and the vertical construction area based on the layer identification codes;

[0071] This step is to code and identify the different construction areas and collect design information for each area. A hierarchical identification code can be a combination of letters and numbers that uniquely identifies each construction area. For example, a floor number + area number can be used. Design element information can include area geometry, material properties, equipment information, and more. This information can be extracted from the BIM model or obtained from other design documents.

[0072] The system can automatically generate hierarchical identification codes according to certain coding rules. For example, it can generate codes based on the spatial location of the area, the floor to which it belongs, and other information. When collecting design element information, the API interface provided by the BIM software can be used to read component information and attribute information in the model. Information can also be obtained by parsing design documents in other formats such as IFC files and Excel spreadsheets. At the same time, the system can also structure the collected information, such as storing information from different sources and formats according to a unified data structure for subsequent analysis and utilization.

[0073] S103, generating a regional cross node matrix based on the design element information, and calculating the density coefficient of the nodes in the regional cross node matrix;

[0074] This step identifies key design nodes by analyzing the relationships between different construction areas. The regional intersection node matrix represents the relationships between areas, with each element indicating whether two areas intersect or connect. The node density coefficient indicates the closeness of the relationship between a node and other nodes. A larger density coefficient indicates a node with more connections and a higher importance in design and construction.

[0075] The system can automatically generate a regional intersection node matrix based on design element information. For example, the geometric boundaries of different regions can be compared to determine whether they intersect or contact each other. Alternatively, the attribute information of different regions can be analyzed to determine whether they are related in terms of function, material, and other aspects. In generating the matrix, factors such as the type and strength of the associations between regions can be considered and assigned different weights. The node density coefficient can be calculated by analyzing the elements related to the node in the matrix, for example, by calculating the number of non-zero elements related to the node or the sum of their weights.

[0076] S104: Mark nodes with a density coefficient greater than a preset threshold as high-risk cost nodes;

[0077] This step determines the node's risk level in cost control based on its density coefficient. A preset threshold can be set based on experience or historical data. When a node's density coefficient exceeds this threshold, it indicates that the node has complex relationships with many other nodes, posing a high risk of cost overruns during design and construction. Therefore, it is marked as a high-risk cost node.

[0078] The system automatically calculates the density coefficient for each node and compares it to a preset threshold. Nodes exceeding this threshold are marked in the BIM model or other management system, for example, using a special color or icon. The system also generates a list of high-risk nodes, including their location, relationships, and potential risk factors, to facilitate focused monitoring and management by project managers.

[0079] S105. Set a parameter monitoring unit at each high-risk cost node to record the initial value and change value of the design parameter in real time;

[0080] This step involves real-time monitoring of high-risk cost nodes and recording changes in their design parameters. Design parameters can be key attributes or indicators related to the node, such as spatial dimensions, material usage, and equipment specifications. Parameter monitoring units can be sensors or software modules that automatically collect and record the values of design parameters. By recording the initial and changing values of design parameters in real time, the dynamic evolution of the node design can be monitored, providing data support for subsequent cost analysis and optimization.

[0081] The system can configure appropriate parameter monitoring units based on the type and characteristics of high-risk cost nodes. For example, for spatial nodes, equipment such as laser scanners and total stations can be used to collect real-time spatial geometric dimensions; for material nodes, technologies such as barcodes and RFID can be used to record material procurement and usage; and for equipment nodes, IoT sensors can be used to monitor equipment operating parameters and energy consumption data. Furthermore, the system can integrate and synchronize monitoring data from various sources to form a unified parameter change curve, facilitating trend analysis and early warning.

[0082] S106. Calculate the cost fluctuation coefficient based on the change value of the design parameter;

[0083] The system calculates the cost fluctuation coefficient based on the changing values of the design parameters, specifically including: constructing a parameter change curve based on the changing values of the design parameters and calculating the slope of the parameter change curve; generating a cost sensitivity matrix based on the slope, with the rows and columns of the cost sensitivity matrix corresponding to different design parameters; using a recursive neural network to train the cost sensitivity matrix to obtain associated weights; and taking the product of the associated weights and the slope as the cost fluctuation coefficient.

[0084] This step analyzes the impact of design parameter changes on cost and calculates the sensitivity coefficient to cost fluctuations. First, based on the data recorded by the parameter monitoring unit, a curve is constructed showing the change of each design parameter over time. The slope of the curve is calculated at different time points. The slope reflects the speed and magnitude of the parameter change. The slopes of the different parameters are then arranged in a certain order to form a cost sensitivity matrix. Each element of the matrix represents the degree of impact of a parameter on cost. Next, a recursive neural network is used to train the matrix. By continuously adjusting the weights of the neurons, the intrinsic correlations between the parameters are learned, resulting in a set of correlation weights. Finally, the correlation weights are multiplied by the parameter slope to obtain the cost fluctuation coefficient. The size of the coefficient indicates the contribution of the parameter change to the cost fluctuation.

[0085] The system can train a general recursive neural network model based on historical project data, such as records of design parameter changes and cost changes, and then use this model in new projects to analyze cost fluctuations. When training the model, common optimization algorithms such as gradient descent and Adam can be used to adjust the weights and biases of neurons to improve the model's fitting accuracy and generalization capabilities. Regularization techniques such as L1 / L2 regularization and Dropout can also be used to prevent model overfitting and improve model stability and robustness. When using the model, fine-tuning or incremental learning can be performed based on the characteristics of the new project to better adapt it to the new data environment.

[0086] S107: Determine a parameter adjustment range based on the cost fluctuation coefficient, and select an optional parameter combination that meets a preset design specification within the parameter adjustment range;

[0087] The system determines the parameter adjustment range based on the cost fluctuation coefficient. Specifically, it constructs a multidimensional parameter space, with each dimension corresponding to a design parameter. Within this space, it calculates a parameter adjustment vector based on the cost fluctuation coefficient. It then determines the initial parameter adjustment range based on the direction and modulus of the parameter adjustment vector. Finally, it uses a genetic algorithm to optimize the boundaries of the initial parameter adjustment range to determine the final parameter adjustment range. Within this parameter adjustment range, it then selects optional parameter combinations that meet the preset design specifications.

[0088] This step further optimizes design parameters based on the analysis of cost fluctuations to find the most cost-effective parameter combination. First, all design parameters are mapped into a multidimensional space, where each dimension represents a parameter and the size of the dimension represents the parameter's range of values. Then, a parameter adjustment vector is calculated based on the cost fluctuation coefficient. The direction of the vector represents the optimization direction of the parameter adjustment, and the modulus represents the optimization amplitude of the adjustment. Next, an initial parameter adjustment range is determined in the parameter space, centered on the current parameter value and using the adjustment vector as the radius. Finally, heuristic search techniques such as genetic algorithms are used to iteratively optimize within the initial range. Through operations such as selection, crossover, and mutation, the boundaries of the parameter range are continuously adjusted until a parameter adjustment range with optimal cost and meeting the design specifications is found. Within this range, multiple feasible parameter combinations can be enumerated or randomly sampled for subsequent detailed design and evaluation.

[0089] The system can automatically construct a multidimensional parameter space and adjustment vectors based on design specifications and optimization objectives. For example, all design parameters and their value ranges can be extracted from BIM models or design documents to form the basic structure of the parameter space. Different dimensions can be weighted or normalized based on the importance or sensitivity of the parameters to highlight the impact of key parameters. The component values of the adjustment vector in each dimension can be determined based on the sign and magnitude of the cost fluctuation coefficient to guide the direction and magnitude of parameter optimization. When executing a genetic algorithm, algorithm parameters such as population size, crossover probability, and mutation probability can be flexibly set to balance optimization efficiency and accuracy. At the same time, constraints or penalty functions, such as building specifications and performance indicators, can be introduced to guide and limit the optimization process and ensure the compliance and feasibility of parameter combinations.

[0090] S108, updating the parameters in the optional parameter combination to the BIM model in sequence, and calculating the cost value of the high-risk cost node based on the updated BIM model;

[0091] This step is to apply the optimized parameter combination to the BIM model and evaluate its impact on cost. First, the parameter values in each set of optional parameter combinations are updated to the corresponding components or attributes of the BIM model in turn to generate a new BIM model instance. Then, based on the updated BIM model, the cost values of high-risk cost nodes are recalculated to evaluate the cost improvement effect of parameter adjustment. The cost calculation here can be for a single node or for the entire project, and some cost estimation or cost accounting methods can be used, such as bill of quantities pricing, parametric cost model, etc. By comparing the cost values under different parameter combinations, the parameter combination with the best cost or that meets expectations can be found as the basis for subsequent detailed design and construction.

[0092] The system can provide some tools or interfaces to achieve automatic synchronization and updating of parameter combinations and BIM models. For example, a parametric modeling plug-in can be developed to directly map the numerical values of the parameter combination to the parametric variables of the BIM model to achieve automatic generation and updating of the model; or a data exchange middleware can be developed to import the numerical values of the parameter combination into the BIM software through standard formats such as IFC to achieve batch modification and updating of the model. When calculating node costs, the system can call the built-in quantity calculation or pricing function of the BIM software to directly obtain the engineering quantity and price information in the model; or an independent cost calculation engine can be developed to estimate and summarize the costs of components or attributes in the model based on some pre-made cost templates or rules.

[0093] It should be noted that steps S109 and S110 are parallel steps and have no temporal order.

[0094] S109: When no cost value exists within the preset cost value range, adjusting the parameter adjustment range according to the preset adjustment scheme;

[0095] When no cost value falls within the preset cost value range, the parameter adjustment range is adjusted according to the preset adjustment scheme, and the step of selecting an optional parameter combination that meets the preset design specification within the parameter adjustment range is re-executed. Adjusting the parameter adjustment range according to the preset adjustment scheme specifically includes: calculating the deviation rate between the current cost value and the preset cost value range; constructing an adaptive adjustment coefficient based on the deviation rate, wherein the adaptive adjustment coefficient increases as the deviation rate increases; and multiplying the adaptive adjustment coefficient by the parameter adjustment range as the new parameter adjustment range.

[0096] This step is to further adjust the parameter range on the basis of parameter optimization so that the cost value is as close to the preset interval as possible. When it is found that the cost values of all optional parameter combinations are not within the preset interval, it means that the current parameter adjustment range is not reasonable enough and a secondary adjustment is required. First, the deviation rate between the current cost value and the preset interval boundary is calculated. The larger the deviation rate, the farther the current parameter combination is from the target interval. Then, an adaptive adjustment coefficient is constructed based on the deviation rate. The size of the coefficient is positively correlated with the deviation rate, that is, the larger the deviation rate, the larger the adjustment coefficient. Finally, the adjustment coefficient is multiplied by the original parameter adjustment range to obtain a new adjustment range. The new range is adaptively scaled according to the size of the deviation rate on the basis of the original range, so that the cost value of the parameter combination sampled within the new range is more likely to fall into the preset interval. The adjusted parameter range can be re-substituted into step S107 for the next round of optimization iteration until a parameter combination that meets the requirements is found.

[0097] The system can pre-set some commonly used cost ranges and adjustment plans for users to choose from and refer to. Cost ranges can be determined based on factors such as the project budget, contract, and market conditions, such as setting upper and lower limits, target values, and warning lines for costs. Adjustment plans can be formulated based on some empirical rules or optimization strategies, such as fixed-ratio adjustment, gradual adjustment, and sensitivity adjustment. When calculating the deviation rate, some common measurement methods can be used, such as absolute error, relative error, and mean square error. When constructing the adaptive adjustment coefficient, some common mapping functions can be used, such as linear functions, logarithmic functions, and exponential functions. Machine learning algorithms, such as regression analysis and neural networks, can also be used to learn the optimal mapping relationship from historical data.

[0098] S110 : When there is a cost value within a preset cost value range, output a final design solution of the corresponding parameters.

[0099] When there is a cost value within the preset cost value range, the final design scheme of the corresponding parameters is output, which specifically includes: extracting multiple groups of parameter combinations that meet the preset cost value range; calculating the construction difficulty index and material utilization rate corresponding to each group of parameter combinations; establishing a comprehensive evaluation model with historical cost control effects, historical construction difficulty index and historical material utilization rate as training data; inputting the construction difficulty index and material utilization rate corresponding to each group of parameter combinations into the comprehensive evaluation model to obtain the comprehensive score corresponding to each group of parameter combinations; and outputting the parameter combination with the highest comprehensive score as the final design scheme.

[0100] This step involves selecting the optimal design solution after finding a parameter combination that meets the cost requirements. First, from all available parameter combinations, those with cost values within a preset range are selected as candidate solutions. Then, for each candidate solution, its corresponding construction difficulty index and material utilization rate are calculated. The construction difficulty index reflects the complexity and risk level of the solution in actual construction and can be comprehensively evaluated by factors such as the number of components, construction technology, and construction deadline. The material utilization rate reflects the economic and environmental performance of the solution in terms of material use and can be comprehensively evaluated by factors such as material consumption, waste generation, and recycling. Next, a comprehensive evaluation model is developed using historical project data to measure the overall effectiveness of the design solution. This model uses historical project cost control results, construction difficulty index, and material utilization rates as training samples. Using machine learning algorithms such as multivariate regression and support vector machines, a functional relationship is fitted between each indicator and the overall performance. Finally, the construction difficulty index and material utilization rate of the candidate solutions are substituted into the model to predict their overall scores, and the solution with the highest score is selected as the final design solution. This plan not only meets the cost requirements, but also takes into account factors such as construction difficulty and material utilization, and is an overall optimal design solution.

[0101] The system can provide some tools or algorithms to assist in the evaluation and selection of design solutions. When calculating the construction difficulty index, qualitative or quantitative evaluation methods, such as the analytic hierarchy process (AHP) and the fuzzy comprehensive evaluation method, can be used to decompose, quantify, and weight the various factors affecting construction difficulty to obtain a comprehensive difficulty index. When calculating material utilization, methods such as bill of materials analysis or logistics simulation can be used to statistically analyze and optimize the types, quantities, and sizes of materials involved in the design solution to improve material utilization efficiency and turnover. When establishing a comprehensive evaluation model, feature engineering or data mining techniques, such as correlation analysis and factor analysis, can be used to uncover the inherent connections and dominant patterns between various indicators and the overall effect, thereby constructing an evaluation model with strong explanatory power and good generalization capabilities. When using the evaluation model, cross-validation or test set prediction methods can be used to verify and optimize the accuracy and robustness of the model, continuously improving the practicality and reliability of the model.

[0102] In the above embodiment, by dividing the horizontal and vertical construction areas in the BIM model and setting hierarchical identification codes, the design element information of each area can be accurately located and tracked. Based on the calculation of the node density coefficient based on the regional cross-node matrix, key nodes with high design complexity and large cost impact can be identified. Setting parameter monitoring units for these high-risk cost nodes, recording the changes in design parameters in real time, and determining a reasonable parameter adjustment range through the cost fluctuation coefficient can effectively prevent cost overruns caused by design changes. Introducing preset design specification constraints in the parameter screening process ensures that the adjustment plan meets both cost control goals and project quality requirements. By continuously adjusting the parameter range through iterative optimization until a suitable solution is found, the time and resource waste caused by repeated modification of drawings in traditional design is reduced. This BIM-based forward design method puts cost control in the design stage, and through data-driven and intelligent analysis, it achieves a dynamic balance between design plans and cost targets, thereby improving the timeliness and accuracy of construction project cost control.

[0103] Based on the above-mentioned construction project cost control method based on BIM forward design, in order to deal with the parameter deviation that may occur during the construction phase, this application also provides a dynamic adjustment method during the construction process. This method monitors the deviation between the construction parameters and the design target values in real time and activates an intelligent adjustment mechanism when necessary to ensure cost controllability during the project implementation. Figure 2 , a dynamic adjustment method in a construction process in an embodiment of the present application is described:

[0104] See also Figure 2 , which is a flow chart of a dynamic adjustment method during a construction process in an embodiment of the present application.

[0105] S201, collecting real-time parameter data during the construction process, and calculating the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design solution;

[0106] Collect real-time parameter data during the construction process and calculate the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design scheme, specifically including: extracting the corresponding target parameter data from the final design scheme, establishing a corresponding relationship between the real-time parameter data and the target parameter data; calculating the difference between the real-time parameter data and the target parameter data in each set of corresponding relationships; dividing the difference by the target parameter data to obtain the deviation rate.

[0107] This step involves real-time monitoring and deviation analysis of the construction process to promptly identify and address anomalies that could impact costs. Real-time parameter data can be collected through various sensors, monitoring equipment, and manual recording, covering key aspects and indicators of the construction process, such as material usage, project progress, and labor input. Target parameter data are the optimal parameter values determined during the design phase and represent the benchmark and goal for cost control. By comparing the differences between real-time data and target data, the degree of deviation from the design can be quantitatively assessed, providing a basis for subsequent early warning and adjustment.

[0108] The system can automatically collect and transmit various construction site parameter data through technologies such as the Internet of Things and data acquisition cards, and then correlate and compare it with design data such as BIM models and schedules. For example, RFID tags can be attached to construction materials to track their issuance and consumption in real time; GPS positioning and working status sensors can be installed on construction machinery to monitor its operating time and efficiency in real time; and cameras, laser scanners, and other equipment can be used to record three-dimensional images and point cloud data of the construction site in real time for comparison and verification with the BIM model. The deviation rate can be calculated by dividing the difference between the real-time value and the target value by the target value. The sign of the deviation rate represents the direction of deviation from the target, and the absolute value of the deviation rate represents the degree of deviation from the target.

[0109] S202: When the deviation rate exceeds a preset warning threshold, a warning instruction including abnormal parameter information is generated;

[0110] This step determines whether an early warning signal is needed based on the results of the deviation analysis, prompting project managers to take countermeasures. The early warning threshold is a pre-set critical value based on the project's risk tolerance and management requirements. When the parameter deviation rate exceeds this threshold, it means that the construction has deviated significantly from the design. Continuing this process may lead to cost overruns or quality issues, necessitating attention and intervention. The early warning instruction includes information such as the specific parameter name, deviation rate, time, and location of the abnormal deviation, allowing managers to quickly identify the problem, analyze the cause, and develop countermeasures.

[0111] The system can preset warning thresholds for common parameters, such as a 10% increase in material prices, a 20% decrease in labor efficiency, and a 5% delay in construction schedules. It also allows users to customize warning rules and thresholds for key parameters. When a parameter deviation rate exceeds a threshold, the system automatically generates a warning instruction and promptly sends it to the relevant responsible person via SMS, email, or app push notifications. The content of the warning instruction can vary in detail and presentation, including text descriptions, data tables, and trend charts, depending on factors such as parameter type and degree of deviation.

[0112] S203. Based on the abnormal parameter information in the early warning instruction, extract the adjustable design elements corresponding to the hierarchical identification codes in the associated region of the high-risk cost node corresponding to the abnormal parameter, and generate a preliminary adjustment plan based on the adjustable design elements;

[0113] This step is to automatically generate possible adjustment plans after identifying abnormal parameters, providing decision-making references for project managers. Since abnormal parameters may involve multiple construction areas and links, if a parameter is adjusted rashly, it may have an adverse chain reaction on other areas and links. Therefore, a systematic and associative adjustment strategy is needed. First, based on the location information of the abnormal parameters, the affected construction areas and their hierarchical identification codes are extracted within the associated area of the corresponding high-risk cost node; then, based on the hierarchical identification code, the design elements that can be adjusted in the area are found, such as material brand, equipment model, construction process, etc.; finally, a series of possible adjustment plans are generated based on the adjustable elements, such as replacing a certain material brand, optimizing a certain equipment combination, improving a certain construction process, etc., as alternative options for subsequent evaluation and decision-making.

[0114] The system can match and recommend corresponding adjustment strategies and plans from the knowledge base based on characteristics such as the type, deviation rate, and correlation of abnormal parameters. The knowledge base can pre-store standard solutions to common problems, such as material price increases - changing brands or suppliers, low labor efficiency - optimizing processes or adding equipment, and project delays - increasing resources or optimizing paths. It can also store successful cases from historical projects, providing reference and inspiration for current projects through case-based reasoning and transfer learning. When generating adjustment plans, the system can also use digital tools such as BIM to quickly model and simulate the plan's design parameters, correlation effects, etc., to evaluate the plan's feasibility and effectiveness.

[0115] S204: Calculate the disturbance impact coefficient of the preliminary adjustment plan on the adjacent construction area using the regional cross-node matrix, and select the adjustment plan with the disturbance impact coefficient less than the safety threshold as the executable plan;

[0116] After generating preliminary adjustment plans, this step evaluates the potential risks and impacts of their implementation and selects relatively safe and controllable executable options. Because each construction area has varying degrees of interconnectedness and influence with other areas, adjusting parameters in one area will inevitably cause certain disturbances and impacts on adjacent areas, such as impacts on resource utilization, schedule coupling, and process integration. If not properly handled, these may lead to new cost risks or quality issues. Therefore, it is necessary to utilize the previously constructed regional cross-node matrix to quantitatively analyze the perturbation impact coefficient of each adjustment plan on adjacent areas. The larger the impact coefficient, the higher the risk and cost of implementing the plan. Finally, the plan with a perturbation impact coefficient below the safety threshold is selected as the alternative for implementation in the next step.

[0117] The system can calculate the coefficient of the disturbance impact of an adjustment plan on another region based on parameters such as the correlation strength and node distance in the regional cross-node matrix. For example, the weighted average of the correlation strength can be used to measure the degree of mutual influence between two regions in terms of cost, progress, resources, etc.; the inverse of the node distance or an exponential decay function can be used to measure the propagation and attenuation law of the disturbance in space; and algorithms such as graph cut sets and shortest paths can be used to measure the key channels and bottlenecks of the disturbance in the network topology. When setting safety thresholds, you can refer to industry standards, expert experience, historical data, etc., and set corresponding tolerances and control lines for different types and degrees of disturbance impacts. You must avoid being too conservative and missing optimization opportunities, and avoid being too aggressive and inducing greater risks.

[0118] S205. Calculate the cost-benefit ratio of each executable plan, and select the plan with the highest cost-benefit ratio as the final adjustment plan.

[0119] Calculate the cost-effectiveness ratio of each executable plan and select the plan with the highest cost-effectiveness ratio as the final adjustment plan. The cost-effectiveness ratio is equal to the ratio of the cost reduction after the implementation of the plan to the cost of implementing the plan.

[0120] After screening multiple feasible options, this step involves further evaluating and comparing them from an economic perspective, selecting the option with the best cost-effectiveness as the final adjustment solution. Since each feasible solution requires a certain amount of resources and costs, such as material costs, labor hours, and machine shifts, while also generating certain positive benefits, such as reduced deviation rates, less waste, and improved efficiency, it is necessary to comprehensively consider the solution's input-output ratio, aiming to maximize benefits with limited costs. The cost-effectiveness ratio can be measured by the ratio of the cost savings after implementation to the implementation cost of the solution. A larger ratio indicates a more economical and feasible solution. Finally, the solution with the highest cost-effectiveness ratio is selected as the optimal solution, and the adjustment is formally implemented.

[0121] The system can estimate the implementation costs and potential benefits of an executable plan based on factors such as the design elements and adjustment range involved. For example, tools such as BIM models and bills of quantities can be used to quickly calculate the changes in resource requirements such as materials, labor, and machinery caused by the plan. Cost estimation models and standard unit prices can be used to convert the cost increases or decreases corresponding to changes in resource requirements. Deviation rate correction models and production functions can be used to predict the degree of improvement in indicators such as deviation rate and production efficiency after the plan is implemented. Benefit quantification models and sensitivity analysis can be used to convert the monetary value of improved indicators into cost savings or improved benefits. When comparing the cost-benefit ratios of different plans, factors such as the implementation difficulty, risk level, and time schedule must also be considered. Plans with different attributes must be given appropriate weights and priorities to select the plan with the highest overall score.

[0122] In the above embodiment, by collecting real-time parameter data during the construction process and calculating the deviation rate from the target parameter data, the system realizes dynamic monitoring of the construction process. When the deviation rate exceeds the warning threshold, a warning instruction containing abnormal parameter information is generated, so that the system can promptly detect abnormal conditions during the construction process. By using the regional cross-node matrix to calculate the disturbance influence coefficient and screening out adjustment plans with a disturbance influence coefficient less than the safety threshold, the negative impact of the adjustment measures on adjacent construction areas is reduced. The cost-effectiveness ratio of each executable plan is calculated and the highest value is selected as the final plan, ensuring that the adjustment measures can not only effectively solve the problem but also have good economic efficiency. This dynamic monitoring and intelligent adjustment mechanism improves the timeliness and accuracy of cost control and reduces the cost risk during the construction process.

[0123] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a construction project cost control system based on BIM forward design provided in an embodiment of the present application.

[0124] It should be noted that Figure 3 The structure of the system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0125] like Figure 3As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0126] The following components are connected to the I / O interface 305: an input section 306 including a camera, infrared sensor, and the like; an output section 307 including a liquid crystal display (LCD) and speakers; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0127] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0128] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take any of a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0129] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0130] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiments, or may exist independently and not incorporated into the system. The storage medium carries one or more computer programs, and when executed by a processor of a system, the system implements the methods provided in the above embodiments.

[0131] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0132] As used in the above embodiments, the term “when…” may be interpreted as “if…” or “after…” or “in response to determining…” or “in response to detecting…”, depending on the context. Similarly, the phrases “upon determining…” or “if (stated condition or event) is detected” may be interpreted as “if determining…” or “in response to determining…” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0133] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive).

[0134] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A construction project cost control method based on BIM forward design, characterized by: include: Divide the building space into horizontal construction areas and vertical construction areas in the BIM model; Setting layer identification codes in the horizontal construction area and the vertical construction area, and collecting design element information of the horizontal construction area and the vertical construction area based on the layer identification codes; Generate a regional intersection node matrix based on the design element information, and calculate the density coefficient of the nodes in the regional intersection node matrix; Marking nodes whose density coefficient is greater than a preset threshold as high-risk cost nodes; A parameter monitoring unit is set at each high-risk cost node to record the initial value and change value of the design parameter in real time; Calculating a cost fluctuation coefficient based on a change in the design parameter; Determining a parameter adjustment range based on the cost fluctuation coefficient, and screening out an optional parameter combination that meets a preset design specification within the parameter adjustment range; Updating the parameters in the optional parameter combination to the BIM model in sequence, and calculating the cost value of the high-risk cost node based on the updated BIM model; When no cost value is within the preset cost value range, adjusting the parameter adjustment range according to a preset adjustment scheme, and re-performing the step of screening out an optional parameter combination that meets the preset design specification within the parameter adjustment range; When the cost value is within the preset cost value range, outputting a final design solution of the corresponding parameters; Collecting real-time parameter data during the construction process, and calculating the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design solution; When the deviation rate exceeds a preset warning threshold, a warning instruction containing abnormal parameter information is generated; According to the abnormal parameter information in the early warning instruction, extracting the adjustable design elements corresponding to the hierarchical identification code in the associated area of the high-risk cost node corresponding to the abnormal parameter, and generating a preliminary adjustment plan based on the adjustable design elements; Calculating the disturbance impact coefficient of the preliminary adjustment plan on the adjacent construction area using the regional cross-node matrix, and selecting the adjustment plan with the disturbance impact coefficient less than the safety threshold as the executable plan; The cost-benefit ratio of each executable plan is calculated, and the plan with the highest cost-benefit ratio is selected as the final adjustment plan. The cost-benefit ratio is equal to the ratio of the cost reduction value after the plan is implemented to the cost of implementing the plan.

2. The method according to claim 1, characterized in that The calculating of the cost fluctuation coefficient according to the change value of the design parameter specifically includes: Constructing a parameter change curve according to the change value of the design parameter, and calculating the slope of the parameter change curve; generating a cost sensitivity matrix based on the slope, wherein rows and columns of the cost sensitivity matrix respectively correspond to different design parameters; Using a recursive neural network to train the cost sensitivity matrix to obtain associated weights; The product of the association weight and the slope is used as the cost fluctuation coefficient.

3. The method according to claim 1, characterized in that Determining the parameter adjustment range based on the cost fluctuation coefficient specifically includes: Constructing a multidimensional parameter space, where each dimension of the multidimensional parameter space corresponds to a design parameter; calculating a parameter adjustment vector in the multidimensional parameter space based on the cost fluctuation coefficient; Determining an initial parameter adjustment range according to the direction and modulus of the parameter adjustment vector; A genetic algorithm is used to optimize the boundaries of the initial parameter adjustment range to obtain a final parameter adjustment range.

4. The method according to claim 1, wherein The adjusting the parameter adjustment range according to the preset adjustment scheme specifically includes: Calculating the deviation rate between the current cost value and the preset cost value interval; constructing an adaptive adjustment coefficient based on the deviation rate, wherein the adaptive adjustment coefficient increases as the deviation rate increases; The product of the adaptive adjustment coefficient and the parameter adjustment range is used as a new parameter adjustment range.

5. The method according to claim 1, wherein The final design scheme of the output corresponding parameters specifically includes: Extracting multiple groups of parameter combinations that meet the preset cost value range; Calculating the construction difficulty index and material utilization rate corresponding to each set of parameter combinations; A comprehensive evaluation model was established using historical cost control effects, historical construction difficulty index, and historical material utilization as training data; Inputting the construction difficulty index and material utilization rate corresponding to each group of the parameter combinations into the comprehensive evaluation model to obtain a comprehensive score corresponding to each group of the parameter combinations; The parameter combination with the highest comprehensive score is output as the final design solution.

6. The method according to claim 5, characterized in that The calculating of the deviation rate between the real-time parameter data and the target parameter data corresponding to the final design solution specifically includes: Extracting corresponding target parameter data from the final design solution, and establishing a corresponding relationship between the real-time parameter data and the target parameter data; Calculating the difference between the real-time parameter data and the target parameter data in each group of the corresponding relationships respectively; The deviation rate is obtained by dividing the difference by the target parameter data.

7. A construction project cost control system based on BIM forward design, characterized by: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1 to 6.

8. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to perform the method according to any one of claims 1 to 6.

9. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to perform the method according to any one of claims 1 to 6.

Images