Architectural model design and management method, system and storage medium based on cloud computing technology

Abstract

The present invention discloses a method, system, and storage medium for designing and managing architectural models based on cloud computing technology, belonging to the field of cloud computing technology. The method includes periodically collecting relevant parameter information of the architectural model to obtain a basic data set; preprocessing and feature extraction of the basic data set to obtain a feature data set; calculating a complexity assessment value of the architectural model based on the feature data in the feature data set; judging the magnitude of the complexity assessment value and switching to a parallel design mode, a hybrid design mode, or a distributed parallel design mode based on the judgment result; and designing and managing the architectural model based on the current design mode. The present invention assesses the complexity of the architectural model by collecting and processing relevant parameter information of the architectural model, and selects an appropriate design mode for data processing based on the complexity, thereby achieving efficient distribution and management of design tasks on different computing nodes.

Description

Technical Field

[0001] The present invention relates to the field of cloud computing technology, and in particular to a method, system and storage medium for designing and managing architectural models based on cloud computing technology. Background Art

[0002] Against the backdrop of the rapid development of computer technology, the design and management of architectural models are facing significant changes. Traditional architectural model design methods often rely on local computer resources, resulting in insufficient computing power and inefficient data processing. Furthermore, the sheer volume of architectural model data makes efficient storage, management, and processing of this data a critical challenge in the architectural design field.

[0003] The rise and development of cloud computing technology has provided new solutions for the design and management of architectural models. Cloud computing, with its powerful computing capabilities, flexible resource scheduling, and efficient data processing, can effectively address the shortcomings of traditional architectural model design methods. However, how to fully leverage the advantages of cloud computing to achieve efficient design and management of architectural models remains a challenge that requires in-depth research and resolution.

[0004] Although some cloud computing-based architectural model design and management methods have been proposed, these methods often suffer from problems such as low design efficiency, irrational resource allocation, and limited data processing capabilities. Therefore, there is an urgent need for a new method that can fully utilize the advantages of cloud computing technology to achieve efficient and accurate design and management of architectural models. Summary of the Invention

[0005] To solve the above problems, the present invention provides a building model design and management method, system and storage medium based on cloud computing technology. By collecting and processing relevant parameter information of the building model, the complexity of the building model is evaluated, and appropriate design pattern data processing is selected according to the complexity, so as to realize the efficient allocation and management of design tasks on different computing nodes.

[0006] The above objectives can be achieved through the following solutions:

[0007] The architectural model design and management method based on cloud computing technology includes: periodically collecting relevant parameter information of the architectural model to obtain a basic data set; preprocessing and feature extraction of the basic data set to obtain a feature data set; calculating a complexity evaluation value of the architectural model based on feature data in the feature data set; judging the size of the complexity evaluation value and switching to a parallel design mode, a hybrid design mode or a distributed parallel design mode according to the judgment result; and designing and managing the architectural model according to the current design mode.

[0008] Optionally, the preprocessing and feature extraction of the basic data set to obtain a feature data set includes: cleaning, normalizing and discretizing the basic data set to obtain a preprocessed data set; extracting factors affecting the complexity of the building model from a pre-acquired library of building model complexity influencing factors to obtain a geometric feature set, a structural feature set, a material feature set and a functional requirement feature set; and calculating the corresponding preprocessed data in the preprocessed data set based on the corresponding features in the geometric feature set, the structural feature set, the material feature set and the functional requirement feature set to obtain a geometric feature data set, a structural feature data set, a material feature data set and a functional requirement feature data set.

[0009] Optionally, the calculation of the complexity evaluation value of the building model based on the feature data in the feature data set includes: collecting the geometric feature data set, structural feature data set, material feature data set, functional requirement feature data set and complexity evaluation value of the historical building model to construct a historical data set; using the feature data of the geometric feature data set, structural feature data set, material feature data set and functional requirement feature data set as input and the complexity evaluation value as output, using the historical data set to establish and train a model to obtain an evaluation value prediction model, and for the predicted complexity evaluation value K, there is

[0010] K=T1(G*S+T2*S)+T3*M+T4*F,

[0011] In the formula, T1 is the weight coefficient of the influence of the interaction between geometric features and structural features on the complexity evaluation value, T2 is the weight coefficient of the influence of structural features on the interaction between geometric features and structural features, T3 is the weight coefficient of the influence of material features on the complexity evaluation value, T4 is the weight coefficient of the influence of functional requirement features on the complexity evaluation value, G is the vector of the geometric feature data set, S is the vector of the structural feature data set, M is the vector of the material feature data set, and F is the vector of the functional requirement feature data set; the geometric feature data set, the structural feature data set, the material feature data set and the functional requirement feature data set are input into the evaluation value prediction model to calculate the complexity evaluation value of the current building model.

[0012] Optionally, the judging of the size of the complexity evaluation value and switching to the parallel design mode, hybrid design mode or distributed parallel design mode according to the judgment result includes: judging whether the complexity evaluation value of the current building model is greater than a preset first threshold; if the complexity evaluation value of the current building model is greater than the first threshold, switching to the distributed parallel design mode; if the complexity evaluation value of the current building model is less than or equal to the first threshold, judging whether the complexity evaluation value of the current building model is greater than a preset second threshold; if the complexity evaluation value of the current building model is greater than the second threshold, switching to the hybrid design mode; if the complexity evaluation value of the current building model is less than or equal to the second threshold, switching to the parallel design mode.

[0013] Optionally, the designing and managing of the building model according to the current design mode includes: when switching to the parallel design mode, performing a demand analysis on the design tasks of the building model; dividing the tasks that need to be processed in parallel to obtain multiple subtasks; setting multiple threads on the computing node, each thread processing one subtask.

[0014] Optionally, the designing and managing of the building model according to the current design mode also includes: when switching to the hybrid design mode, dividing the building model into multiple sub-models; allocating the multiple sub-models to different computing nodes; by switching different computing nodes, inputting design tasks for the sub-model corresponding to each computing node, and performing design task demand analysis; dividing the tasks that need to be processed in parallel and processing them in parallel through multiple threads of the corresponding computing nodes; and merging all sub-models after the design is completed to obtain the final building model.

[0015] Optionally, the designing and managing of the building model according to the current design mode also includes: when switching to the distributed parallel design mode, determining whether the building model is divided into multiple sub-models and assigned to different computing nodes; if not, dividing the building model and assigning it to different computing nodes; if so, partitioning the threads of different computing nodes to obtain geometric feature processing units, structural feature processing units, material feature processing units and functional requirement feature processing units; and making corresponding associations between the geometric feature processing units, the structural feature processing units, the material feature processing units and the functional requirement feature processing units of different computing nodes.

[0016] Optionally, the switching to the distributed parallel design mode also includes: when inputting a design task for the sub-model corresponding to the current computing node, analyzing the characteristic attributes of the input design task, dividing the design task according to the analysis results and assigning it to the geometric feature processing unit, the structural feature processing unit, the material feature processing unit or the functional requirement feature processing unit for processing; the geometric feature processing unit, the structural feature processing unit, the material feature processing unit and the functional requirement feature processing unit of the current computing node copy and send the received divided design task to the feature processing units corresponding to different computing nodes; the feature processing unit corresponding to each computing node processes the received divided design task and applies it according to the requirements of the sub-model corresponding to each computing node; modifying each sub-model by switching the computing node; merging the modified sub-models to obtain the final building model.

[0017] Based on the same inventive concept, the present invention also provides a building model design and management system based on cloud computing technology, the system including: a data acquisition module, used to periodically collect relevant parameter information of the building model to obtain a basic data set; a feature extraction module, used to preprocess and extract features of the basic data set to obtain a feature data set; a model evaluation module, used to calculate the complexity evaluation value of the building model according to the feature data in the feature data set; a design mode switching module, used to judge the size of the complexity evaluation value, and switch to parallel design mode, hybrid design mode or distributed parallel design mode according to the judgment result; a model design module, used to design and manage the building model according to the current design mode.

[0018] Based on the same inventive concept, the present invention also provides a computer storage medium storing one or more programs, which, when executed, can implement any of the aforementioned methods.

[0019] Based on the same inventive concept, the present invention also provides a device including a processor, a communication interface, a memory and a communication bus; the processor, the communication interface and the memory communicate with each other through the communication bus; the processor is used to execute the program stored in the aforementioned computer-readable storage medium.

[0020] Compared with the prior art, the present invention has the following advantages:

[0021] 1. The present invention can efficiently process large amounts of building model data by periodically collecting relevant parameter information of the building model and performing preprocessing and feature extraction. By leveraging the powerful computing power of cloud computing technology, the present invention can quickly complete complexity assessment, design mode switching, and building model design and management tasks, significantly improving data processing efficiency.

[0022] 2. Based on the complexity assessment value of the building model, the present invention can intelligently switch between parallel design mode, hybrid design mode, or distributed parallel design mode to rationally allocate computing resources. This flexible resource scheduling method not only optimizes the utilization of computing resources but also ensures the efficient design and management of building models of varying complexity.

[0023] 3. The present invention constructs an evaluation value prediction model by collecting the geometric features, structural features, material features, functional requirements features and complexity evaluation values ​​of historical building models. This model can accurately predict the complexity evaluation value of the current building model, providing a reliable basis for switching design modes.

[0024] 4. By utilizing cloud computing technology, the present invention avoids the excessive reliance on local computer resources in traditional building model design methods, thereby reducing hardware costs. At the same time, efficient data processing and resource scheduling methods also reduce manpower and time costs, improving overall economic benefits.

[0025] 5. The present invention can ensure the design quality of the building model through intelligent design and management processes; different design modes can optimize the building models of different complexities, thereby improving the accuracy and reliability of the design.

[0026] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 It is a flowchart of a method for designing and managing building models based on cloud computing technology according to an embodiment of the present invention.

[0029] Figure 2 This is a flowchart of an execution of a building model design and management method based on cloud computing technology according to an embodiment of the present invention.

[0030] Figure 3 It is a schematic diagram of the execution flow of the parallel design mode according to an embodiment of the present invention.

[0031] Figure 4 It is a schematic diagram of the execution flow of the hybrid design mode according to an embodiment of the present invention.

[0032] Figure 5 It is a schematic diagram of the execution flow of the distributed parallel design mode according to an embodiment of the present invention.

[0033] Figure 6 This is a flowchart of an execution of a building model design and management method based on cloud computing technology according to an embodiment of the present invention.

[0034] Figure 7 It is a structural diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0036] Reference Figure 1 One embodiment of the present invention proposes a building model design and management method based on cloud computing technology. By collecting and processing relevant parameter information of the building model, the complexity of the building model is evaluated, and an appropriate design mode is selected according to the complexity, so as to realize efficient allocation and management of design tasks on different computing nodes.

[0037] The method of this embodiment specifically includes:

[0038] Periodically collect relevant parameter information of the building model to obtain the basic data set;

[0039] Specifically, the main purpose here is to collect various parameter information required for the design and management of building models; this parameter information may include but is not limited to the building's geometric dimensions, structural type, material usage, and functional requirements; through periodic collection, it can ensure that the basic data set can timely reflect the latest status of the building model and provide accurate data support for subsequent processing and analysis.

[0040] Preprocessing and feature extraction are performed on the basic data set to obtain a feature data set;

[0041] Specifically, after obtaining the basic data set, it needs to be preprocessed and feature extracted. Preprocessing mainly includes data cleaning, normalization, and discretization to ensure data accuracy and consistency. Feature extraction extracts key factors that reflect the complexity of the building model from the preprocessed data, such as geometric features, structural features, material features, and functional requirements. These features will be used in the subsequent building model complexity assessment.

[0042] Calculating a complexity evaluation value of the building model based on the feature data in the feature data set;

[0043] Specifically, after obtaining the feature data set, an evaluation value prediction model can be established using technologies such as machine learning or deep learning. The model uses the feature data in the feature data set as input and the complexity evaluation value of the building model as output. By training and optimizing the model, it can be enabled to accurately predict the complexity evaluation values ​​of different building models. This evaluation value will serve as the basis for subsequent design mode switching.

[0044] Determine the size of the complexity evaluation value, and switch to a parallel design mode, a hybrid design mode, or a distributed parallel design mode according to the determination result;

[0045] Specifically, such as Figure 2 As shown in the figure, after obtaining the complexity evaluation value of the building model, it is necessary to judge it and select the appropriate design mode according to the judgment result; specifically, the complexity evaluation value can be divided into different intervals according to the preset threshold, and each interval corresponds to a design mode; for example, when the complexity evaluation value is high, the distributed parallel design mode can be selected to fully utilize the parallel processing capabilities of cloud computing technology; when the complexity evaluation value is moderate, the hybrid design mode can be selected to balance computing efficiency and resource utilization; when the complexity evaluation value is low, the parallel design mode can be selected to simplify the design process and improve design efficiency.

[0046] Design and manage building models according to current design patterns.

[0047] Specifically, after selecting a suitable design pattern, the building model can be designed and managed according to the pattern; specifically, the design tasks of the building model can be divided and allocated according to the characteristics and requirements of the design pattern, and corresponding computing nodes and threads can be set to process these tasks in parallel; at the same time, the data and information in the design process can be monitored and managed in real time to ensure the smooth progress of the design tasks and the quality of the final building model.

[0048] Specifically, the architectural model design and management method based on cloud computing technology achieves efficient and accurate design and management of architectural models through the steps of periodically collecting relevant parameter information of architectural models, preprocessing and feature extraction of basic data sets, calculating complexity evaluation values ​​of architectural models, switching design modes according to the evaluation values, and designing and managing according to the design modes.

[0049] Optionally, preprocessing and feature extraction of the basic data set to obtain a feature data set includes:

[0050] Cleaning, normalizing and discretizing the basic data set to obtain a preprocessed data set;

[0051] Specifically, cleaning is to remove redundant, erroneous or missing information in the basic data set. The collected building model parameter information may contain some invalid inputs, such as null values, outliers or duplicate data. The cleaning process will identify and remove these data to ensure the accuracy of subsequent processing; normalization is to convert the data to the same magnitude for comparison and calculation. In the building model, different parameters (such as length, width, height, etc.) may have different dimensions and value ranges. The normalization process converts these parameters into a unified standard, such as converting all values ​​into floating point numbers between 0 and 1; discretization is to convert continuous data into discrete data for easy processing and analysis. Some building model parameters may be continuous (such as temperature, humidity, etc.), and the discretization process converts these continuous data into a series of discrete intervals or categories.

[0052] Extracting factors affecting the complexity of the building model from a pre-acquired library of factors affecting the complexity of the building model, and obtaining a geometric feature set, a structural feature set, a material feature set, and a functional requirement feature set;

[0053] Specifically, key factors are extracted from a pre-acquired library of factors influencing building model complexity. Factors affecting building model complexity may include geometry, structural type, material selection, and functional requirements. When extracting features, specific information related to these aspects is obtained from the factor library.

[0054] According to the corresponding features in the geometric feature set, the structural feature set, the material feature set and the functional requirement feature set, the corresponding preprocessed data in the preprocessed data set are calculated to obtain a geometric feature data set, a structural feature data set, a material feature data set and a functional requirement feature data set.

[0055] Specifically, the geometric feature dataset includes the calculation results of the geometric features of the building model, such as length, width, height, surface area, and volume; the structural feature dataset involves information on the structural features of the building model, such as the supporting structure, frame type, and wall type; the material feature dataset includes the calculation results of the type, density, strength, durability and other characteristics of the building materials; the functional requirement feature dataset performs relevant calculations based on the functional requirements of the building model (such as seismic resistance, thermal insulation performance, fire protection requirements, etc.); the basic dataset is converted into a feature dataset with clear geometric, structural, material and functional requirements, providing a solid foundation for the subsequent building model complexity assessment and design mode selection.

[0056] Optionally, the calculating the complexity evaluation value of the building model according to the feature data in the feature data set includes:

[0057] Collect the geometric feature dataset, structural feature dataset, material feature dataset, functional requirement feature dataset and complexity evaluation value of the historical building model to construct a historical dataset;

[0058] Taking the feature data of the geometric feature dataset, structural feature dataset, material feature dataset, and functional requirement feature dataset as input and the complexity evaluation value as output, the historical dataset is used to establish and train the model to obtain the evaluation value prediction model. For the predicted complexity evaluation value K,

[0059] K=T1(G*S+T2*S)+T3*M+T4*F,

[0060] Wherein, T1 is the weight coefficient of the interaction between geometric and structural features on the complexity evaluation value, T2 is the weight coefficient of the influence of structural features on the interaction between geometric and structural features, T3 is the weight coefficient of the influence of material features on the complexity evaluation value, T4 is the weight coefficient of the influence of functional requirement features on the complexity evaluation value, G is the vector of the geometric feature data set, S is the vector of the structural feature data set, M is the vector of the material feature data set, and F is the vector of the functional requirement feature data set;

[0061] The geometric feature data set, the structural feature data set, the material feature data set and the functional requirement feature data set are input into the evaluation value prediction model to calculate the complexity evaluation value of the current building model.

[0062] Specifically, it is first necessary to collect a large number of geometric feature data sets, structural feature data sets, material feature data sets, functional requirement feature data sets and corresponding complexity evaluation values ​​of historical building models; using the feature data of the geometric feature data sets, structural feature data sets, material feature data sets, and functional requirement feature data sets as input, and the complexity evaluation value as output, the historical data sets are used to establish and train the model; during the training process, the influence of geometric features, structural features, material features and functional requirement features on the complexity evaluation value will be learned, thereby obtaining an evaluation value prediction model; after the evaluation value prediction model is established, the geometric feature data sets, structural feature data sets, material feature data sets and functional requirement feature data sets of the new building model can be input into the model; the model will calculate and output the complexity evaluation value of the current building model based on the input feature data.

[0063] For example, assuming that there is a geometric feature data set vector G = (2, 3, 1), a structural feature data set vector S = (4, 1), a material feature data set vector M = (5, 2), a functional requirement feature data set vector F = 7, and weight coefficients T1 = 0.5, T2 = 0.2, T3 = 0.15, and T4 = 0.15, substituting these values ​​into the formula for calculation, we get G*S+T2*S = 2×4+3×1+1×4+1×1+0.2×(4+1) = 17, so T1(G*S+T2*S) = 0.5×17 = 8.5, from which we can get K = 8.5+0.15×(5+2)+0.15×7 = 10.6; therefore, based on this specific set of values, the calculated building model complexity evaluation value is 10.6; this value is a relative evaluation value used to compare the complexity of different building models.

[0064] Optionally, judging the size of the complexity evaluation value and switching the parallel design mode, the hybrid design mode or the distributed parallel design mode according to the judgment result includes:

[0065] Determining whether the complexity evaluation value of the current building model is greater than a preset first threshold;

[0066] If the complexity evaluation value of the current building model is greater than the first threshold, switching to the distributed parallel design mode;

[0067] If the complexity evaluation value of the current building model is less than or equal to the first threshold, determining whether the complexity evaluation value of the current building model is greater than a preset second threshold;

[0068] If the complexity evaluation value of the current building model is greater than the second threshold, switching to the hybrid design mode;

[0069] If the complexity evaluation value of the current building model is less than or equal to the second threshold, the parallel design mode is switched.

[0070] Specifically, such as Figure 2 As shown, a first threshold and a second threshold are preset, and these two thresholds are used to divide the complexity evaluation value of the building model into three intervals to decide which design mode to adopt; first, the complexity evaluation value of the current building model is calculated, and then this evaluation value is compared with the preset first threshold; if the complexity evaluation value is greater than the first threshold, it means that the building model is very complex and requires higher parallelism and computing power, so it will switch to the distributed parallel design mode; if the complexity evaluation value is less than or equal to the first threshold but greater than the second threshold, it means that the building model has a certain complexity, but the performance and resource utilization can still be optimized through the hybrid design mode; if the complexity evaluation value is less than or equal to the second threshold, it means that the building model is relatively simple and can be directly processed using the parallel design mode.

[0071] For example, suppose there is a building model design and management, in which the preset first threshold is 10 and the second threshold is 5; now, there is a new building model, whose complexity evaluation value has been calculated through the previous steps and is 8; first, it is determined whether the complexity evaluation value 8 is greater than the first threshold 10; since 8 is less than 10, the condition for switching to the distributed parallel design mode is not met; next, it is determined whether the complexity evaluation value 8 is greater than the second threshold 5; since 8 is greater than 5, the condition for switching to the hybrid design mode is met; based on the judgment result, it is decided to adopt the hybrid design mode to process this building model; this means that parallel computing and serial computing may be used in combination, or different computing tasks may be allocated to different computing nodes to optimize performance and resource utilization; judging and switching design modes according to the size of the complexity evaluation value is a flexible and effective strategy that can help better adapt to building models of different complexities, thereby improving design efficiency and accuracy.

[0072] Optionally, designing and managing the building model according to the current design mode includes:

[0073] When switching to the parallel design mode, a demand analysis is performed on the design tasks of the building model; specifically, when switching to the parallel design mode, a comprehensive demand analysis is first performed on the design tasks of the building model; this includes determining which tasks can be processed in parallel, which tasks need to be processed serially, and the dependencies and priorities between tasks.

[0074] Divide the tasks that need to be processed in parallel into multiple subtasks;

[0075] Specifically, after completing the demand analysis, the tasks that need to be processed in parallel need to be divided into multiple subtasks; these subtasks should be independent of each other, or the dependencies between them can be effectively managed to ensure the efficiency and accuracy of parallel processing.

[0076] Set up multiple threads on the computing node, and each thread processes one subtask.

[0077] Specifically, multiple threads are set up on the computing node, and each thread is responsible for processing a subtask; these threads can run on different processor cores to achieve true parallel processing; by setting a reasonable number of threads and task division, computing resources can be fully utilized and design efficiency can be improved.

[0078] For example, Figure 3 As shown in the figure, suppose there is a complex building model, whose design tasks include structural analysis, material selection, energy consumption simulation and visual rendering. After complexity assessment, it is decided to use parallel design mode to process this building model. First, a demand analysis is conducted to determine which tasks can be processed in parallel. In this example, structural analysis, material selection and energy consumption simulation are independent tasks and can be processed in parallel. Although visual rendering can also be processed in parallel, it depends on the previous analysis results and therefore needs to be started after the previous tasks are completed. The three tasks of structural analysis, material selection and energy consumption simulation are divided into three subtasks. Each subtask contains corresponding calculation and analysis work. Three threads are set on the computing node, which are responsible for processing these three subtasks respectively. The three tasks are independent of each other, so they can run in parallel on different processor cores; at the same time, an additional thread can be set up to monitor and manage these parallel tasks to ensure their correct execution and timely completion; during the execution process, the running status and progress of each thread are continuously monitored. If a thread encounters a problem or requires additional resources, the number of threads can be dynamically adjusted or the task can be reallocated; in addition, the execution of a thread can be paused or resumed as needed to deal with emergencies or changes in priority; when adopting the parallel design mode, detailed demand analysis and task division are required, and threads are reasonably set up to manage parallel tasks; these measures help to make full use of computing resources, improve design efficiency, and ensure the design quality and accuracy of the building model.

[0079] Optionally, the designing and managing the building model according to the current design mode further includes:

[0080] When switching to the hybrid design mode, the building model is divided into multiple sub-models;

[0081] Allocating the multiple sub-models to different computing nodes;

[0082] By switching different computing nodes, input the design task into the sub-model corresponding to each computing node and perform design task requirement analysis;

[0083] Divide the tasks that need to be processed in parallel and process them in parallel through multiple threads of the corresponding computing nodes;

[0084] When all sub-models are designed, they are merged to obtain the final building model.

[0085] Specifically, when switching to the hybrid design mode, the entire building model will first be divided into multiple relatively independent sub-models. These sub-models may be divided based on different parts, functions or design stages of the building; next, the divided sub-models will be assigned to different computing nodes. These computing nodes can be physical servers, virtual machines or cloud computing resources, which have different computing capabilities and resources; on each computing node, the corresponding design tasks will be input and the demand analysis of these tasks will be performed, which includes determining the type, priority, dependencies and required computing resources of the tasks; for tasks that need to be processed in parallel in each sub-model, they will be further divided to obtain multiple sub-tasks, and then multiple threads will be set on the corresponding computing nodes, each thread is responsible for processing a sub-task, and these threads can run in parallel to improve computing efficiency; when the design tasks of all sub-models are completed, they will be merged, which includes integrating the data, analysis results and design achievements of each sub-model to obtain the final building model.

[0086] For example, Figure 4As shown in the figure, it is assumed that there is a large commercial building project, whose design tasks include structural design, electrical design, water supply and drainage design, interior design and other aspects. After complexity evaluation, it is decided to adopt a hybrid design mode to handle this project; the entire building project is divided into four sub-models: structural sub-model, electrical sub-model, water supply and drainage sub-model and interior sub-model; these four sub-models are assigned to four different computing nodes; among them, the structural sub-model is assigned to a high-performance computing node because structural design requires a lot of computing resources; the electrical sub-model and the water supply and drainage sub-model are assigned to medium-performance computing nodes; and the interior sub-model is assigned to a lower-performance but easily accessible computing node because interior design relies more on the designer's creativity and aesthetics; on each computing node, the corresponding design tasks are input, and the demand analysis of these tasks is performed. For example, on the structural sub-model, the structural design task is input. tasks, and determined the subtasks such as structural analysis, material selection and optimization design that needed to be carried out; for the tasks in the structural sub-model that needed to be processed in parallel, such as structural analysis and optimization design, further division was carried out, and multiple threads were set up for parallel processing. These threads ran in parallel on high-performance computing nodes, greatly improving computing efficiency; when the design tasks of all sub-models were completed, merging processing was carried out, which included integrating the data, analysis results and design achievements of each sub-model to obtain the final commercial building model; during the merging process, data consistency and integrity checks were also carried out to ensure the accuracy and reliability of the final model; when adopting the hybrid design mode, the building model needs to be carefully divided and allocated, and effective task management and parallel processing are carried out on each computing node. These measures help to make full use of computing resources, improve design efficiency, and ensure the design quality and accuracy of the building model.

[0087] Optionally, the designing and managing the building model according to the current design mode further includes:

[0088] When switching to the distributed parallel design mode, determining whether the building model is divided into multiple sub-models and assigned to different computing nodes;

[0089] If not, the building model is divided and assigned to different computing nodes;

[0090] If so, the threads of different computing nodes are partitioned to obtain geometric feature processing units, structural feature processing units, material feature processing units, and functional requirement feature processing units;

[0091] The geometric feature processing units, the structural feature processing units, the material feature processing units and the functional requirement feature processing units of different computing nodes are correspondingly associated.

[0092] Specifically, when switching to the distributed parallel design mode, it is first determined whether the building model has been divided into multiple sub-models and assigned to different computing nodes; if the building model has not been divided, it will be divided into multiple relatively independent sub-models according to the complexity and scale of the model, and these sub-models will be assigned to different computing nodes; for each computing node, its threads will be partitioned to process different feature attributes. These feature processing units include geometric feature processing units, structural feature processing units, material feature processing units, and functional requirement feature processing units; each feature processing unit is responsible for processing design tasks related to its corresponding feature attributes; the same feature processing units on different computing nodes will be associated, and when one of the feature units receives a task, it will copy the task and send it to the same feature units on other computing nodes.

[0093] Optionally, the switching to the distributed parallel design mode further includes:

[0094] When a design task is input to the sub-model corresponding to the current calculation node, characteristic attributes of the input design task are analyzed, and the design task is divided and allocated to the geometric feature processing unit, the structural feature processing unit, the material feature processing unit, or the functional requirement feature processing unit for processing according to the analysis result;

[0095] The geometric feature processing unit, the structural feature processing unit, the material feature processing unit, and the functional requirement feature processing unit of the current computing node copy and send the received divided design tasks to the feature processing units corresponding to different computing nodes;

[0096] The feature processing units corresponding to each computing node process the received divided design tasks and apply them according to the requirements of the sub-models corresponding to each computing node;

[0097] Modify each sub-model by switching the calculation node;

[0098] The modified sub-models are merged to obtain the final building model.

[0099] Specifically, such as Figure 5As shown in the figure, when a design task is input for the sub-model corresponding to the current computing node, the characteristic attributes of the input design task will be analyzed and divided into multiple sub-tasks, and these sub-tasks will be assigned to the corresponding feature processing units for processing; the feature processing unit of the current computing node will copy the received divided design task and send it to the feature processing units corresponding to other computing nodes, so as to ensure that each computing node can obtain all design tasks related to its processing characteristic attributes, thereby realizing parallel processing; the feature processing units corresponding to each computing node will process the received divided design tasks, and after the processing is completed, these design tasks will be applied according to the needs of the sub-model corresponding to each computing node to update the status of the sub-model; during the design process, the user can modify each sub-model by switching computing nodes. When the design tasks of all sub-models are completed, these sub-models will be merged to obtain the final building model.

[0100] For example, suppose there is a large-scale comprehensive building project that requires three-dimensional modeling and structural design; due to the large scale of the project, after complexity assessment, it is decided to adopt a distributed parallel design mode to speed up the design process; the entire building project is divided into multiple sub-models, such as building appearance model, internal structure model, equipment model, etc., and these sub-models are assigned to different computing nodes; for each computing node, its threads are divided into geometric feature processing units, structural feature processing units and material feature processing units. The geometric feature processing unit is responsible for processing design tasks related to building appearance; the structural feature processing unit is responsible for processing design tasks related to building structure; the material feature processing unit is responsible for processing design tasks related to building materials; when design tasks are input into the building appearance model, these tasks will be analyzed, and tasks related to geometric features will be assigned to the geometric feature processing unit for processing. At the same time, tasks related to structural features will be processed by the geometric feature processing unit. The tasks related to the design will be assigned to the structural feature processing unit for processing, and the tasks related to the material features will be assigned to the material feature processing unit for processing; the geometric feature processing unit will copy the received design tasks and send them to the geometric feature processing units corresponding to other computing nodes, and the structural feature processing unit and the material feature processing unit will also perform similar copying and distribution operations; the feature processing unit corresponding to each computing node will process the received design tasks and apply them according to the needs of the sub-model. During the design process, each sub-model can be modified and adjusted by switching the computing node; when the design tasks of all sub-models are completed, these sub-models will be merged to obtain the final comprehensive building model; by dividing the building model into multiple sub-models and assigning them to different computing nodes, and partitioning the threads of the computing nodes to process different feature attributes, parallel processing and efficient management of design tasks are achieved.

[0101] Based on the same inventive concept, Figure 6 As shown, the present invention also provides a building model design and management system based on cloud computing technology, the system comprising:

[0102] The data acquisition module is used to periodically collect relevant parameter information of the building model to obtain the basic data set;

[0103] A feature extraction module is used to preprocess and extract features from the basic data set to obtain a feature data set;

[0104] A model evaluation module, configured to calculate a complexity evaluation value of the building model based on the feature data in the feature data set;

[0105] A design mode switching module is used to judge the size of the complexity evaluation value and switch to a parallel design mode, a hybrid design mode or a distributed parallel design mode according to the judgment result;

[0106] The model design module is used to design and manage building models according to the current design mode.

[0107] Based on the above disclosed content, the present invention also provides an electronic device. Figure 7 As shown, the electronic device of an embodiment of the present invention includes at least one electrically connected processor and at least one storage medium, wherein the storage medium is electrically connected to the processor, wherein the storage medium stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method as described above.

[0108] Based on the same inventive concept, the present invention also provides a storage medium, which stores instructions that can be executed by the at least one processor. The instructions are executed by the at least one processor to enable the at least one processor to execute the method as described above.

[0109] It should be noted that the electrical connections between the above-mentioned units do not necessarily mean connections between circuits. Indirect connections can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above description is only an exemplary embodiment of the present invention and is not intended to limit the scope of the present invention.

[0110] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. Those skilled in the art will readily conceive of other embodiments of the present invention after considering the disclosure of the specification and practical truths. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary technical means in the art not described herein.

Claims

1. A building model design and management method based on cloud computing technology, characterized in that: The method comprises: Periodically collect relevant parameter information of the building model to obtain the basic data set; Preprocessing and feature extraction are performed on the basic data set to obtain a feature data set; Calculating a complexity evaluation value of the building model based on the feature data in the feature data set; The size of the complexity evaluation value is judged, and the parallel design mode, the hybrid design mode or the distributed parallel design mode is switched according to the judgment result; including: judging whether the complexity evaluation value of the current building model is greater than a preset first threshold; if the complexity evaluation value of the current building model is greater than the first threshold, switching to the distributed parallel design mode; if the complexity evaluation value of the current building model is less than or equal to the first threshold, judging whether the complexity evaluation value of the current building model is greater than a preset second threshold; if the complexity evaluation value of the current building model is greater than the second threshold, switching to the hybrid design mode; if the complexity evaluation value of the current building model is less than or equal to the second threshold, switching to the parallel design mode; Design and manage building models based on current design paradigms, including: When switching to the parallel design mode, a demand analysis is performed on the design task of the building model; the task that needs to be processed in parallel is divided into multiple subtasks; multiple threads are set on the computing node, and each thread processes one subtask; When switching to the hybrid design mode, the building model is divided into multiple sub-models; the multiple sub-models are assigned to different computing nodes; by switching different computing nodes, design tasks are input to the sub-model corresponding to each computing node, and design task requirements analysis is performed; tasks that require parallel processing are divided and processed in parallel by multiple threads of the corresponding computing nodes; after all sub-models are designed, they are merged to obtain the final building model; When switching to the distributed parallel design mode, determine whether the building model is divided into multiple sub-models and assigned to different computing nodes; if not, divide the building model and assign it to different computing nodes; if so, partition the threads of different computing nodes to obtain geometric feature processing units, structural feature processing units, material feature processing units and functional requirement feature processing units; and make corresponding associations among the geometric feature processing units, structural feature processing units, material feature processing units and functional requirement feature processing units of different computing nodes.

2. The architectural model design and management method based on cloud computing technology according to claim 1 is characterized in that: The preprocessing and feature extraction of the basic data set to obtain the feature data set includes: Cleaning, normalizing and discretizing the basic data set to obtain a preprocessed data set; Extracting factors affecting the complexity of the building model from a pre-acquired library of factors affecting the complexity of the building model, and obtaining a geometric feature set, a structural feature set, a material feature set, and a functional requirement feature set; According to the corresponding features in the geometric feature set, the structural feature set, the material feature set and the functional requirement feature set, the corresponding preprocessed data in the preprocessed data set are calculated to obtain a geometric feature data set, a structural feature data set, a material feature data set and a functional requirement feature data set.

3. The architectural model design and management method based on cloud computing technology according to claim 2 is characterized in that: The calculation of the complexity evaluation value of the building model according to the feature data in the feature data set includes: Collect the geometric feature dataset, structural feature dataset, material feature dataset, functional requirement feature dataset and complexity evaluation value of the historical building model to construct a historical dataset; Taking the feature data of the geometric feature dataset, structural feature dataset, material feature dataset, and functional requirement feature dataset as input and the complexity evaluation value as output, the historical dataset is used to establish and train the model to obtain the evaluation value prediction model. For the predicted complexity evaluation value K, K=T1(G*S+T2*S)+T3*M+T4*F, Wherein, T1 is the weight coefficient of the interaction between geometric and structural features on the complexity evaluation value, T2 is the weight coefficient of the influence of structural features on the interaction between geometric and structural features, T3 is the weight coefficient of the influence of material features on the complexity evaluation value, T4 is the weight coefficient of the influence of functional requirement features on the complexity evaluation value, G is the vector of the geometric feature data set, S is the vector of the structural feature data set, M is the vector of the material feature data set, and F is the vector of the functional requirement feature data set; The geometric feature data set, the structural feature data set, the material feature data set and the functional requirement feature data set are input into the evaluation value prediction model to calculate the complexity evaluation value of the current building model.

4. The architectural model design and management method based on cloud computing technology according to claim 1 is characterized in that: The switching to the distributed parallel design mode further includes: When a design task is input to the sub-model corresponding to the current calculation node, characteristic attributes of the input design task are analyzed, and the design task is divided and allocated to the geometric feature processing unit, the structural feature processing unit, the material feature processing unit, or the functional requirement feature processing unit for processing according to the analysis result; The geometric feature processing unit, the structural feature processing unit, the material feature processing unit, and the functional requirement feature processing unit of the current computing node copy and send the received divided design tasks to the feature processing units corresponding to different computing nodes; The feature processing units corresponding to each computing node process the received divided design tasks and apply them according to the requirements of the sub-models corresponding to each computing node; Modify each sub-model by switching the calculation node; The modified sub-models are merged to obtain the final building model.

5. The architectural model design and management system based on cloud computing technology is characterized by: The system comprises: The data acquisition module is used to periodically collect relevant parameter information of the building model to obtain the basic data set; A feature extraction module is used to preprocess and extract features from the basic data set to obtain a feature data set; A model evaluation module, configured to calculate a complexity evaluation value of the building model based on the feature data in the feature data set; A design mode switching module is used to judge the size of the complexity evaluation value and switch to a parallel design mode, a hybrid design mode or a distributed parallel design mode according to the judgment result; it includes: judging whether the complexity evaluation value of the current building model is greater than a preset first threshold; if the complexity evaluation value of the current building model is greater than the first threshold, switching to the distributed parallel design mode; if the complexity evaluation value of the current building model is less than or equal to the first threshold, judging whether the complexity evaluation value of the current building model is greater than a preset second threshold; if the complexity evaluation value of the current building model is greater than the second threshold, switching to the hybrid design mode; if the complexity evaluation value of the current building model is less than or equal to the second threshold, switching to the parallel design mode; Model design module, used to design and manage building models according to current design patterns; Among them, the model design module is also used to: When switching to the parallel design mode, a demand analysis is performed on the design task of the building model; the task that needs to be processed in parallel is divided into multiple subtasks; multiple threads are set on the computing node, and each thread processes one subtask; When switching to the hybrid design mode, the building model is divided into multiple sub-models; the multiple sub-models are assigned to different computing nodes; by switching different computing nodes, design tasks are input to the sub-model corresponding to each computing node, and design task requirements analysis is performed; tasks that require parallel processing are divided and processed in parallel by multiple threads of the corresponding computing nodes; after all sub-models are designed, they are merged to obtain the final building model; When switching to the distributed parallel design mode, determine whether the building model is divided into multiple sub-models and assigned to different computing nodes; if not, divide the building model and assign it to different computing nodes; if so, partition the threads of different computing nodes to obtain geometric feature processing units, structural feature processing units, material feature processing units and functional requirement feature processing units; and make corresponding associations among the geometric feature processing units, structural feature processing units, material feature processing units and functional requirement feature processing units of different computing nodes.

6. A computer storage medium, characterized in that One or more programs are stored. When the one or more programs are executed, the architectural model design and management method based on cloud computing technology described in any one of claims 1 to 4 can be implemented.

Images