Building design system for modularization of high-rise building steel structure corridor
By working collaboratively through data collection, feature engineering, comprehensive analysis, and final decision-making modules, the problem of insufficient data processing in traditional construction design systems is solved, enabling efficient and accurate design optimization and ensuring project success.
Patent Information
- Application Number
- CN202411227716.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-12
AI Technical Summary
Traditional construction design systems lack effective data processing and analysis capabilities, resulting in low design efficiency, insufficient accuracy, inability to accurately predict project success factors, increased risk of project failure, and difficulty in meeting industry standards and specifications.
The system employs a data collection module, a feature engineering module, a comprehensive analysis module, and a final decision and analysis module. Through data dimensionality reduction, iterative bipartite tree algorithm, and refined analysis, it identifies key data features, optimizes resource allocation, and ensures the accuracy and adaptability of the design scheme.
It significantly improves the efficiency and accuracy of architectural design, enhances predictability and robustness, ensures that design solutions meet industry standards, reduces the risk of project failure, and improves project success rate and sustainability.
Smart Images

Figure CN118940382A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of construction design, and in particular to a modular construction design system for steel structure corridors of high-rise buildings. Background Art
[0002] The main disadvantage of traditional systems is that they often lack effective data processing and analysis capabilities, resulting in inefficient design and insufficient accuracy. These systems may not use efficient data collection and feature engineering techniques, making them prone to "dimensionality disaster" when processing large amounts of structural design data and environmental data. Data processing becomes cumbersome and error-prone, and key information cannot be effectively identified and retained.
[0003] In addition, some systems are unable to accurately learn and predict key factors for project success from complex data, which greatly reduces the reliability and accuracy of the prediction results. The lack of refined decision-making and analysis processes also means that these systems find it difficult to effectively identify potential problem areas and optimize resource allocation when faced with project prediction failures, thereby reducing the adaptability and robustness of the design solution and increasing the risk of project failure.
[0004] Ultimately, these disadvantages may result in design solutions that fail to meet industry standards and specifications, reducing the success rate and sustainability of the project. They also affect the design team’s decision-making confidence and data reliability, which in turn affects the efficient implementation and smooth completion of the entire construction project. Summary of the invention
[0005] The object of the present invention is to provide a modular construction design system for steel structure corridors of high-rise buildings to solve the problems raised in the above-mentioned background technology.
[0006] To achieve the above object, the present invention provides the following technical solution: a modular construction design system for steel structure corridors of high-rise buildings, characterized in that it includes a data collection module, a feature engineering module, a comprehensive analysis module and a final decision and analysis module, wherein:
[0007] The data collection module is used to collect structural design data and environmental data;
[0008] The feature engineering module uses a data dimension reduction method to perform data feature processing on the structural design data and the environmental data respectively, performs feature decomposition on the structural design data and the environmental data by standardizing the structural design data and the environmental data, and calculates the covariance matrix obtained by the standardization process to determine the principal components, and determines the principal components according to the size of the cumulative contribution rate, and selects the data features corresponding to the principal components, reduces the dimensions of the structural design data and the environmental data into the data features corresponding to the principal components, and generates structural design key data and environmental key data;
[0009] The comprehensive analysis module uses an iterative binary tree algorithm to predict whether the project is successful for the key data of structural design and the key data of the environment. By collecting training data from a public database, the information gain is calculated by calculating entropy and conditional entropy, and the feature with the largest information gain is selected as the data segmentation point; the subsets are recursively divided until all the training data are classified into the same category to generate a constructed iterative binary tree model; based on the constructed iterative binary tree model, the key data of structural design and the key data of the environment in the feature engineering module are predicted whether the project is successful and the branch data is recorded, and the prediction results and branch data are sent to the final decision and analysis module;
[0010] The final decision and analysis module determines whether to further analyze the key structural design data or the key environmental data according to the prediction results of the comprehensive analysis module, specifically including:
[0011] When the prediction result is that the project is successful, a notification that the data is qualified is sent to the designer;
[0012] When the prediction result is project failure, the main data type of the branch data is determined according to the number of data feature types in the branch data, and further analysis is performed on the structural design key data or the environmental key data according to the category to which the main data type of the branch data belongs. The further analysis includes compliance analysis of the structural design key data and climate, topography and geological analysis of the environmental key data.
[0013] As a further improvement of the present technical solution, the data collection module collects structural design data and environmental data. The structural design data includes but is not limited to material properties, load data, corridor geometry data and project design costs; the environmental data includes but is not limited to climate data, geological data and noise data.
[0014] As a further improvement of the present technical solution, the cumulative contribution rate in the feature engineering module is the sum of the data variability corresponding to the principal components, wherein the variability is calculated by dividing the eigenvalue by the sum of all eigenvalues, and the data features corresponding to the principal components whose cumulative contribution rate exceeds 90% are selected.
[0015] As a further improvement of the technical solution, the calculation process of the information gain in the comprehensive analysis module is as follows:
[0016] Calculate the entropy of the entire training data: Entropy represents a measure of the impurity of the training data, which determines how much randomness exists in the training data. For each class in the training data, calculate the product of the probability of occurrence and the logarithm of this probability, add up all these products and take the negative value;
[0017] Calculate conditional entropy for each feature: For each feature in the training data, divide the training data into several subsets according to the different values of the feature, and calculate the entropy of each subset, and sum them weighted by the size of each subset to obtain the overall entropy after the data set is divided by this feature;
[0018] Determine information gain: Information gain is equal to the difference between the original entropy of the training data and the conditional entropy after partitioning according to the feature. This difference indicates the degree to which the randomness of the data is reduced by considering this feature.
[0019] As a further improvement of the technical solution, the comprehensive analysis module predicts whether the project is successful and records the branch data based on the constructed iterative binary tree model for the key data of structural design and key data of environment, specifically including:
[0020] Starting from the root node, according to the value of the eigenvalue, the corresponding branch is selected according to the judgment condition, and the data corresponding to the branch is recorded;
[0021] After entering the next node, according to the judgment condition of the current node and the value of the characteristic value, select the corresponding branch to enter the next node;
[0022] From the root node to the leaf node, branch selection is performed according to the value of the feature value until a leaf node is reached. The leaf node corresponds to the prediction result of whether the project is successful, and the prediction result of whether the project is successful and the recorded branch data are sent to the final decision and analysis module.
[0023] As a further improvement of the present technical solution, the final decision and analysis module includes a decision unit and a final analysis unit. The decision unit determines whether to conduct further analysis on the structural design key data or the environmental key data based on the prediction result of whether the project is successful in the comprehensive analysis module; the final analysis unit determines whether to conduct further analysis on the structural design key data or the environmental key data based on the main data type of the branch data.
[0024] As a further improvement of the present technical solution, the main data type of the branch data in the final analysis unit is determined according to the number of data feature types, by calculating the corresponding number of data feature types in the branch data and selecting the one with the larger number of data types in the branch data as the main data type.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] 1. This modular construction design system for steel structure corridors of high-rise buildings greatly improves the efficiency and accuracy of building design through the collaborative work of its four main modules. The data collection module and feature engineering module ensure the quality and availability of design data through efficient data processing technology, providing a solid foundation for subsequent analysis and decision-making. In particular, the data dimensionality reduction method applied by the feature engineering module not only greatly reduces the complexity of data processing, but also retains the most influential information by selecting key data features, thereby avoiding dimensional disasters and improving the efficiency of subsequent analysis. This processing process ensures the consistency of data and the effectiveness of comparison, while reducing information loss, providing optimized and reliable data input for the comprehensive analysis module; the application of the comprehensive analysis module further enhances the prediction ability of the system, accurately identifies and learns the key patterns that determine the success of the project through the iterative binary tree algorithm, and effectively mines the factors that affect the success of the project from complex design and environmental data. This method not only significantly improves the accuracy of the prediction, but also improves the model's adaptive ability to handle data sets of various sizes and complexities, thereby providing in-depth insights for the design team and guiding further project optimization and risk management.
[0027] 2. This final decision and analysis module in the modular construction design system of the steel structure corridor of a high-rise building significantly improves the adaptability and robustness of the design through a refined processing flow, ensuring that the design scheme can effectively cope with various environmental challenges. When the prediction results show that the project is successful, the final decision and analysis module not only confirms the eligibility of the design data, but also provides instant feedback to the design team, enhancing the confidence in decision-making and the reliability of the data; when the project prediction fails, the module clearly points out the potential problem areas by carefully analyzing the key ratios of the structural design and environmental data, and focuses on improving the key data areas by optimizing resource allocation, effectively reducing the risk of failure; in addition, according to the main types of branch data, further in-depth analysis is carried out, whether it is the compliance review of the key data of the structural design or the comprehensive environmental analysis of the key data of the environment, the feasibility of the design scheme and the success rate of the project are ensured. This comprehensive analysis process not only greatly improves the sustainability of the project, but also provides strong data support for the architectural design, ensuring that the project can meet industry standards and specifications, while enhancing the reliability and safety of the design scheme; through this process, the design team can identify and deal with potential problem points in a timely manner, thereby ensuring the efficient implementation of the design scheme and the smooth completion of the project. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 It is a schematic diagram of the overall module of the present invention;
[0029] Figure 2 It is a schematic diagram of the final decision-making and analysis module unit of the present invention.
[0030] Legend:
[0031] 100. Data collection module; 200. Feature engineering module; 300. Comprehensive analysis module; 400. Final decision and analysis module; 401. Decision unit; 402. Final analysis unit. DETAILED DESCRIPTION
[0032] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0033] See also Figure 1-2 The present invention provides a technical solution: a modular construction design system for a steel structure corridor of a high-rise building, comprising a data collection module 100, a feature engineering module 200, a comprehensive analysis module 300 and a final decision and analysis module 400.
[0034] The data collection module 100 is used to collect structural design data and environmental data. The structural design data includes but is not limited to material properties, load data, corridor geometry data and project design costs, and the environmental data includes but is not limited to climate data, geological data and noise data.
[0035] The feature engineering module 200 uses a data dimension reduction method to perform data feature processing on the structural design data and the environmental data respectively. The process of performing dimension reduction processing on the structural design data is as follows:
[0036] Preprocess the structural design data, convert the non-numeric types in the order data into numeric types through one-hot encoding, and standardize the converted structural design data so that the mean value of each order data feature is 0 and the standard deviation is 1;
[0037] According to the standardized structural design data, the covariance matrix between the structural design data features is calculated; the covariance matrix is eigen-decomposed to obtain its eigenvalues and corresponding eigenvectors, which respectively reflect the importance and direction of the principal components; the eigenvalues are sorted according to their sizes, and the largest eigenvalue and its corresponding eigenvector are selected in order, and the eigenvector is the basis of the new feature space, wherein the number of principal components to be retained is determined according to the proportion of data variability explained by the eigenvalues, wherein the variability is calculated by dividing the eigenvalue by the sum of all eigenvalues; the data features corresponding to the principal components with a cumulative contribution rate exceeding 90% are selected, and the cumulative contribution rate is the sum of the data variability corresponding to the principal components; the original data is converted to the new feature space using the selected data features, that is, the projection of each data point on these principal components is calculated, the original structural design data is reduced to the data features corresponding to the principal components, and the key data of structural design is generated;
[0038] Similarly, the same data dimension reduction method mentioned above is used to generate environmental key data for environmental data.
[0039] The data dimension reduction method is used to effectively process the structural design data and environmental data, which significantly improves the efficiency and accuracy of the building design system. Through unique hot encoding and standardization, non-numeric data is converted and normalized to ensure the consistency of data format and the effectiveness of comparison. The covariance matrix and eigendecomposition technology are used to extract the most representative principal components from many data features, which not only significantly reduces the complexity of data processing, but also retains the most critical information in the data set. By selecting the principal components that explain most of the data variability, this module effectively compresses the data size and reduces information loss. The benefit of this process is that it greatly improves the efficiency and operability of subsequent analysis. The dimension reduction processing of key structural design data and key environmental data not only speeds up the calculation speed, but also improves the accuracy of data analysis. By reducing the dimension of the data, this method also helps to avoid the "dimensionality disaster", that is, the problem that the sample size required for data analysis grows exponentially with the increase of data dimension. The design team can make more accurate predictions on the feasibility of the project in a shorter time and at a lower computing cost, thereby identifying and avoiding potential risks in the early stages of design and increasing the probability of project success.
[0040] The comprehensive analysis module 300 receives the key structural design data and the key environmental data from the feature engineering module 200, and uses an iterative binary tree algorithm to predict whether the project is successful based on the key structural design data and the key environmental data, specifically including:
[0041] Iterative binary tree training data collection: Collect training data from public databases. The training data includes key structural design data and key environmental data corresponding to different design projects, as well as labels indicating whether the project is successful.
[0042] Calculate the entropy of the entire training data: Entropy represents a measure of the impurity of the training data, which determines how much randomness exists in the training data. For each class in the training data, calculate the product of the probability of occurrence and the logarithm of this probability, add up all these products and take the negative value;
[0043] Calculate conditional entropy for each feature: For each feature in the training data, divide the training data into several subsets according to the different values of the feature, and calculate the entropy of each subset. Then, weight the sum of the sizes of each subset to obtain the overall entropy after the data set is divided by this feature.
[0044] Determine information gain: Information gain is equal to the difference between the original entropy of the training data and the conditional entropy after partitioning according to the feature. This difference indicates the degree to which the randomness of the data is reduced by considering this feature;
[0045] Select the best segmentation feature: compare the information gain of all features and select the feature with the largest information gain as the segmentation point;
[0046] Recursively divide the subsets: split the dataset by the selected features, and then repeat the above process for each subset until all instances belong to the same category;
[0047] Prediction of the result of whether the project is successful: starting from the root node, according to the value of the characteristic value, the corresponding branch is selected according to the judgment condition, and the data corresponding to the branch is recorded as the basis for subsequent judgments affecting the prediction results; after entering the next node, according to the judgment condition of the current node and the value of the characteristic value, the corresponding branch is selected to enter the next node; from the root node to the leaf node, branch selection is continued according to the value of the characteristic value until the leaf node is reached. The leaf node corresponds to the prediction result of whether the project is successful, and the prediction result of whether the project is successful and the recorded branch data are sent to the final decision and analysis module 400.
[0048] The iterative binary tree algorithm used in the comprehensive analysis module 300, combined with information gain as a feature segmentation mechanism, brings significant benefits to the modular construction design system for the steel structure corridor of the high-rise building; through the iterative binary tree algorithm, the system can effectively learn and identify patterns and associations that determine the success of the project from complex structural design key data and environmental key data; by subdividing the data set into smaller and smaller subsets, each segmentation is based on maximizing information gain, that is, selecting those features that can best reduce the impurity of the data set (increase certainty); information gain is used as the basis for segmentation decisions, ensuring that the algorithm can select the most informative features for predicting the success of the project in each step of segmentation, thereby improving the accuracy of the prediction;
[0049] In addition, the recursive nature of the iterative binary tree algorithm enables the model to adaptively handle data sets of various sizes and complexities, including a large number of structural designs and environmental parameters, without pre-setting fixed rules, which increases the flexibility and applicability of the system. The application of information gain also helps to reduce the risk of overfitting, because it considers the overall impact of the feature on the output variable (i.e., the success or failure of the project) when selecting segmentation features, rather than relying solely on local or accidental data characteristics. This approach ensures the generalization ability of the model and makes the prediction results more reliable and accurate.
[0050] Finally, through the decision paths and feature importance information extracted by the iterative binary tree algorithm, the design team can have a deeper understanding of the key factors affecting project success, providing strong data support for further project optimization and risk management.
[0051] The decision unit 401 in the final decision and analysis module 400 determines whether to further analyze the key data of the structural design or the key data of the environment according to the prediction result of whether the project is successful in the comprehensive analysis module 300 and the recorded branch data. When the prediction result is that the project is successful, it means that the data used by the design system is qualified, and a notification of qualified data is sent to the designer;
[0052] When the prediction result is project failure, it means that the data used by the design system may be unqualified, then the number of corresponding data feature types in the branch data is calculated, where the data feature type is determined according to the type of structural design key data and environmental key data. For example, there are five data in the branch data, three of which are structural design key data and two are environmental key data; and the main data type of the branch data is determined according to the number of data feature types, that is, the one with the larger number of data types in the branch data is selected as the main data type. For example, there are five data in the branch data, three of which are structural design key data and two are environmental key data, then the data type of the branch data is structural design key data.
[0053] The decision unit 401 significantly improves the overall efficiency and accuracy of the modular construction design system for high-rise steel structure corridors by finely processing the prediction results and branch data in the comprehensive analysis module 300; when the project prediction is successful, the eligibility of the design data is confirmed, providing instant feedback to the design team, enhancing the confidence in decision-making and the reliability of the data. In the case of project prediction failure, by carefully analyzing the proportion of key structural design data and key environmental data in the branch data, this strategy not only points out the problem areas where the data may exist, but also optimizes resource allocation, ensuring that the team can focus on improving those data areas that are most likely to affect the success rate of the project. In addition, this method also helps to identify and avoid potential risks in advance, and through further analysis and adjustment of key data, the risk of project failure is reduced, and the overall design quality and project success rate are improved. This process not only speeds up the decision-making process and reduces unnecessary workload, but also significantly improves the feasibility and reliability of construction projects by ensuring the compliance and accuracy of data.
[0054] The final analysis unit 402 further analyzes the structural design key data or the environmental key data according to the category to which the main data type of the branch data belongs, specifically including:
[0055] When the main data type of the branch data is key structural design data, the final analysis unit 402 in the final decision and analysis module 400 further analyzes the key structural design data in the feature engineering module 200, and ensures the compliance of each data by comparing the key structural design data with industry standards and specifications, which includes but is not limited to verifying the properties of materials to confirm whether they meet specific performance standards; checking the load data to ensure that they correctly reflect the maximum pressure that the building may withstand; and reviewing the geometric data to confirm the accuracy of the design drawings; using statistical analysis to identify outliers in the data set, sensitivity analysis to evaluate the impact of changes in key design parameters on the overall project, and trend analysis to compare the deviation of project data from historical data or industry standards; these technologies are combined to enable the design team to understand the true situation of the data from multiple dimensions, and promptly identify and deal with potential problem points, such as material properties that do not meet requirements or inaccurate load calculations, thereby ensuring the feasibility of the design plan and the success rate of the project;
[0056] When the main data type of the branch data is environmental key data, the final analysis unit 402 in the final decision and analysis module 400 further analyzes the environmental key data in the feature engineering module 200, and the specific methods used include but are not limited to climate, topography and geological analysis; in terms of climate analysis, the methods include collecting and evaluating meteorological station data, historical climate records and future climate model forecasts to help evaluate climate characteristics such as temperature fluctuations, precipitation, wind speed in the region, and predict the possibility of extreme climate events, such as floods, droughts, heat waves or cold waves; this analysis helps to understand how climate conditions affect building design and material selection, such as the need for better insulation materials or waterproof design to cope with specific climatic conditions; in terms of terrain and geological analysis, methods include using topographic maps, satellite images, geological survey reports, and field investigation data to assess the terrain characteristics and geological conditions of the construction site, which involves analyzing factors such as soil type, rock structure, groundwater level, slope and stability; through these analyses, identify geological problems that may pose risks to the construction project, such as landslides, ground subsidence or seismic activity, as well as special construction techniques or reinforcement measures that need to be considered. For example, if geological analysis shows that an area has high seismic activity, the design team needs to consider earthquake-resistant design and the selection of building materials to ensure the stability and safety of the building.
[0057] The final analysis unit 402, this complex analysis process, greatly improves the adaptability and robustness of the design, ensuring that the construction project can effectively respond to various environmental challenges, thereby greatly improving the probability of project success and sustainability.
[0058] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments, and the above embodiments and descriptions are only preferred examples of the present invention, and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, and these changes and improvements all fall within the scope of the present invention to be protected.
Claims
1. A modular construction design system for steel structure corridors in high-rise buildings, characterized by: The method comprises a data collection module (100), a feature engineering module (200), a comprehensive analysis module (300) and a final decision and analysis module (400), wherein: The data collection module (100) is used to collect structural design data and environmental data; The feature engineering module (200) uses a data dimension reduction method to perform data feature processing on the structural design data and the environmental data respectively, performs standardization processing on the structural design data and the environmental data, calculates the covariance matrix obtained by the standardization processing, performs feature decomposition to determine the principal component, determines the principal component according to the size of the cumulative contribution rate, selects the data feature corresponding to the principal component, reduces the dimension of the structural design data and the environmental data into the data feature corresponding to the principal component, and generates structural design key data and environmental key data; The comprehensive analysis module (300) uses an iterative binary tree algorithm to predict whether the project is successful for the key data of structural design and the key data of environment, collects training data from a public database, calculates entropy and conditional entropy, thereby calculating information gain and selecting the feature with the largest information gain as a data segmentation point; recursively divides the subsets until all the training data are classified into the same category to generate a constructed iterative binary tree model; predicts whether the project is successful for the key data of structural design and the key data of environment in the feature engineering module (200) based on the constructed iterative binary tree model, and records branch data, and sends the prediction results and branch data to the final decision and analysis module (400); The final decision and analysis module (400) determines whether to further analyze the key structural design data or the key environmental data according to the prediction result of the comprehensive analysis module (300), specifically including: When the prediction result is that the project is successful, a notification that the data is qualified is sent to the designer; When the prediction result is project failure, the main data type of the branch data is determined according to the number of data feature types in the branch data, and further analysis is performed on the structural design key data or the environmental key data according to the category to which the main data type of the branch data belongs. The further analysis includes compliance analysis of the structural design key data and climate, topography and geological analysis of the environmental key data.
2. The modular construction design system for steel structure corridors of high-rise buildings according to claim 1 is characterized in that: The data collection module (100) collects structural design data and environmental data, wherein the structural design data includes but is not limited to material properties, load data, corridor geometry data and project design costs; and the environmental data includes but is not limited to climate data, geological data and noise data.
3. The modular construction design system for steel structure corridors of high-rise buildings according to claim 2 is characterized in that: The cumulative contribution rate in the feature engineering module (200) is the sum of the data variability corresponding to the principal components, wherein the variability is calculated by dividing the eigenvalue by the sum of all eigenvalues, and the data features corresponding to the principal components with a cumulative contribution rate exceeding 90% are selected.
4. The modular construction design system for steel structure corridors of high-rise buildings according to claim 3 is characterized by: The calculation process of information gain in the comprehensive analysis module (300) is as follows: Calculate the entropy of the entire training data: Entropy represents a measure of the impurity of the training data, which determines how much randomness exists in the training data. For each class in the training data, calculate the product of the probability of occurrence and the logarithm of this probability, add up all these products and take the negative value; Calculate conditional entropy for each feature: For each feature in the training data, divide the training data into several subsets according to the different values of the feature, and calculate the entropy of each subset, and sum them weighted by the size of each subset to obtain the overall entropy after the data set is divided by this feature; Determine information gain: Information gain is equal to the difference between the original entropy of the training data and the conditional entropy after partitioning according to the feature. This difference indicates the degree to which the randomness of the data is reduced by considering this feature.
5. The modular construction design system for steel structure corridors of high-rise buildings according to claim 4 is characterized in that: The comprehensive analysis module (300) predicts whether the project is successful and records branch data based on the constructed iterative binary tree model for the key data of structural design and key data of environment, specifically including: Starting from the root node, according to the value of the eigenvalue, the corresponding branch is selected according to the judgment condition, and the data corresponding to the branch is recorded; After entering the next node, according to the judgment condition of the current node and the value of the characteristic value, select the corresponding branch to enter the next node; From the root node to the leaf node, branch selection is performed according to the value of the characteristic value until a leaf node is reached. The leaf node corresponds to the prediction result of whether the project is successful, and the prediction result of whether the project is successful and the recorded branch data are sent to the final decision and analysis module (400).
6. The modular construction design system for steel structure corridors of high-rise buildings according to claim 5 is characterized by: The final decision and analysis module (400) comprises a decision unit (401) and a final analysis unit (402). The decision unit (401) determines whether to further analyze the key structural design data or the key environmental data according to the prediction result of whether the project is successful in the comprehensive analysis module (300); and the final analysis unit (402) determines whether to further analyze the key structural design data or the key environmental data according to the main data type of the branch data.
7. The modular construction design system for high-rise building steel structure corridors according to claim 6 is characterized by: The main data type of the branch data in the final analysis unit (402) is determined based on the number of data feature types, by calculating the number of corresponding data feature types in the branch data and selecting the one with the larger number of data types in the branch data as the main data type.
Citation Information
Cited By
Engineering cost intelligent management and control platform based on large model
CN120087980A
