Building design analog simulation system and method based on BIM

Abstract

The invention discloses a BIM-based building design analog simulation system and method, and relates to the technical field of building design analog simulation, and the method comprises the following steps: associating a construction plan of a building project with elements in a BIM model, enabling each building element and component to be matched with a corresponding construction time period, and forming a dynamic construction timeline; acquiring all construction task data in the same time period, wherein the data comprises resource requirements of each task and dependency relationships among the tasks; according to the method, the dynamic timeline is generated by closely combining the construction plan with the BIM model, and potential resource conflicts are deeply analyzed and predicted by utilizing machine learning. And for the identified resource conflicts, each resource is ensured to be only used for one task in each time period by flexibly splitting tasks and optimizing resource allocation, so that excessive concentration or waste of the resources is avoided, the efficiency of the construction progress is effectively improved, and flexible response can be realized in emergency situations.

Description

Technical Field

[0001] This invention relates to the field of architectural design simulation technology, specifically to a BIM-based architectural design simulation system and method. Background Technology

[0002] Building Information Modeling (BIM)-based architectural design simulation systems are tools that utilize digital technology to comprehensively model, analyze, optimize, and visualize building projects. Through BIM, designers, engineers, and other project members can create a three-dimensional virtual building model, integrating information on the building's structure, function, materials, energy, and other aspects for real-time simulation and analysis. These simulations can cover aspects such as structural strength, energy efficiency, environmental impact, and construction processes, helping teams identify potential problems in advance and optimize designs, reducing errors and improving the accuracy and efficiency of architectural design. Furthermore, BIM supports multi-party collaboration, ensuring that professionals from different fields share information and interact on the same platform, thereby improving the overall quality and delivery efficiency of projects.

[0003] BIM-based architectural design simulation systems, when simulating the construction process in a virtual environment using 4D BIM technology, combine the time dimension (i.e., construction progress) with the traditional 3D building model to achieve a dynamic construction timeline. This dynamic timeline links the construction plan of the building project with various elements and components in the BIM model, ensuring that each building element and construction task is precisely matched with its corresponding time node, thereby achieving comprehensive control and precise monitoring of the construction process. The dynamic timeline can reflect the task arrangement and execution status of each construction stage in real time, helping project teams to rationally plan the construction sequence, time nodes, and resource requirements, effectively avoiding delays, resource conflicts, and waste. Through this visualized progress management, project managers can clearly grasp the status of each construction stage, adjust plans in a timely manner, optimize resource allocation, and ensure the project is completed on time and efficiently. Simultaneously, the dynamic timeline also supports risk prediction, progress tracking, and schedule management, providing data support and decision-making basis for the smooth progress of the project.

[0004] The existing technology has the following shortcomings: However, resource conflicts may arise when multiple construction tasks require the same resources (such as equipment, workers, and materials) within the same timeframe. If the timeline in the BIM model does not precisely match the resource allocation, the dynamic timeline may fail to detect these conflicts in a timely manner. Such resource conflicts can lead to construction stoppages, project delays, and even safety accidents due to resource shortages or overuse of equipment. For example, if multiple work areas simultaneously require large lifting equipment but resources are not allocated appropriately, some work areas may be forced to shut down, thus impacting the overall project schedule and costs.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide a BIM-based architectural design simulation system and method. By tightly integrating the construction plan with the BIM model, a dynamic timeline is generated, and machine learning is used to perform in-depth analysis and prediction of potential resource conflicts. For identified resource conflicts, tasks are flexibly split and resource allocation is optimized to ensure that each resource is used for only one task in each time period, thereby avoiding excessive concentration or waste of resources. This intelligent scheduling method improves the efficiency of construction progress and can flexibly respond to unexpected situations. Ultimately, by optimizing project management, reducing costs, improving safety and engineering quality, the project can be completed on time and efficiently, thus solving the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a BIM-based architectural design simulation method, comprising the following steps: Linking the construction plan of a building project with elements in the BIM model allows each building element and component to be matched with the corresponding construction time period, forming a dynamic construction timeline. Obtain data on all construction tasks within the same time period, including the resource requirements of each task and the dependencies between tasks; After obtaining the construction task data, the features of potential resource conflicts are extracted, the extracted features are deeply analyzed, and the analyzed features are input into a pre-trained machine learning model to intelligently predict the resource conflicts of the current project. When resource conflicts are identified within the same time period, tasks with identified shared resource conflicts are split into multiple sub-tasks. Each sub-task is allocated to different time periods based on resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the number of sub-tasks is adjusted according to the severity of the resource conflict to flexibly respond to various unexpected construction situations.

[0008] Preferably, the specific steps for linking the construction plan of a building project with elements in the BIM model to form a dynamic construction timeline are as follows: Create a BIM model based on the architectural drawings of the building project. The model should include all architectural elements and assign specific attributes to each element. Develop a detailed construction plan based on the project requirements; Associate each task in the construction plan with the building elements or components in the BIM model to ensure that each element in the BIM model has a clear timeline during construction and is constructed according to the schedule of the construction plan. By combining the BIM model and the construction plan, a dynamic construction timeline is created, which arranges the construction tasks of all building elements in chronological order on the timeline, showing the start and end times of construction for each building element and component, as well as the dependencies between tasks.

[0009] Preferably, data on all construction tasks within the same time period is obtained by integrating a project management system or BIM project management platform, specifically as follows: Extract detailed information about each task from the construction plan, including timelines, task descriptions, required resources, and dependencies between tasks. By integrating with the BIM model, the specific resources required for each task are associated, and this data is integrated into a unified platform based on the type, quantity, and construction time of the resources, allowing real-time viewing of construction tasks and the usage of related resources within each time period.

[0010] Preferably, features of potential resource conflicts are extracted. These features include the degree of overlap of multiple construction tasks' demands for the same resource and the degree of uneven utilization of the same resource across multiple tasks. In-depth analysis is performed on the degree of overlap of multiple construction tasks' demands for the same resource and the degree of uneven utilization of the same resource across multiple tasks, generating task overlap density index and resource utilization imbalance index respectively. The task overlap density index and resource utilization imbalance index are used as feature vectors and input into a pre-trained machine learning model. The machine learning model outputs a conflict coefficient, and intelligent prediction of resource conflicts in the current project is performed based on the conflict coefficient.

[0011] Preferably, the specific steps for generating a task overlap density index through in-depth analysis of the overlap of multiple construction tasks' demands for the same resource are as follows: Calculate the overlap of shared resource requirements for each pair of construction tasks within a given time period. i and j The formula for calculating the overlap of demands is: , in, For the task i With the task j The degree of overlap in demand between two entities within a given time period reflects the extent to which they share the same demand for resources. and For the task i and tasks j The execution time interval, that is, the start and end times of the task. and Representing tasks i and tasks j The resource demand at time t. and Task i and tasks j The total resource requirement throughout the entire execution process, i.e., the sum of the resources required by the task; By combining the overlap between all task pairs, an overall task overlap density index is generated, expressed as follows: , in, This is an overall task overlap density index, representing the overall resource overlap among all tasks in the project. For the task i and j The weighting coefficients, n This represents the total number of tasks, i.e., the total number of all tasks participating in the overlap analysis.

[0012] Preferably, the specific steps for generating a resource utilization imbalance index through in-depth analysis of the uneven utilization of the same resource across multiple tasks are as follows: The demand for each resource in each construction task is analyzed, and the demand concentration of that resource is calculated using the following expression: , in: This indicates the concentration of resource demand, representing the degree to which resources are concentrated across all tasks. Indicates in the task w China's resources R The demand, p To adjust the index and control the impact of demand fluctuations, k It is the index of the inner summation, representing the sum of the requirements for a certain resource across all tasks. Indicates the first k The resource requirements of each task; This paper generates a resource utilization imbalance index based on resource demand concentration. This index not only considers demand concentration but also compares the maximum demand ratio with actual supply capacity to quantify the uneven use of resources. The generated expression is as follows: , in: As an indicator of uneven resource utilization, it reflects the overall degree of unevenness in resource demand. This represents the maximum demand for the same resource within that time period. q Adjust the parameters for the index to control the contribution of the proportion of demand to the degree of imbalance.

[0013] Preferably, the conflict coefficient generated by the pre-trained machine learning model when intelligently predicting resource conflicts in the current project is compared and analyzed with a pre-set conflict coefficient reference threshold to determine whether there is a risk of resource conflict in the current project. The specific judgment steps are as follows: If the conflict coefficient is greater than the reference threshold, the current project is deemed to have a risk of resource conflict; if the conflict coefficient is less than or equal to the reference threshold, the current project is deemed not to have a risk of resource conflict.

[0014] Preferably, when resource conflicts are detected within the same time period, tasks with identified shared resource conflicts are split into multiple sub-tasks, and the number of sub-tasks is adjusted according to the severity of the resource conflict. The specific steps are as follows: For tasks identified as having shared resource conflicts, they are broken down into multiple subtasks. Each subtask is allocated to a different time slot based on its specific resource requirements and characteristics. During resource decomposition, it is necessary to ensure that the resources used by each subtask within its allocated time slot do not conflict with those of other tasks. Specifically, an optimization algorithm is used to dynamically adjust the task scheduling so that each resource is occupied by only one subtask within each time slot. The adjustment expression is as follows: , in, The adjusted time period for the sub-tasks. The original task's time period. This refers to the resource requirements of the task. To maximize the availability of resources, The adjustment amount for the time period is determined based on resource requirements and task characteristics; Based on the severity of the identified conflicts, the number of task splits and the allocation of time periods are further adjusted. The specific number of splits is determined by the difference between the conflict coefficient and the conflict coefficient reference threshold. The expression for the split is: , in, The number of subtasks to be split. The current conflict coefficient, As a reference threshold for the conflict coefficient, The maximum allowable conflict coefficient, This represents the number of splits in the original task.

[0015] A BIM-based architectural design simulation system includes a construction plan and BIM model association module, a construction task data acquisition and dependency analysis module, a potential resource conflict analysis and intelligent prediction module, and a task splitting and resource scheduling optimization module. The construction plan and BIM model association module links the construction plan of a building project with the elements in the BIM model, so that each building element and component is matched with the corresponding construction time period, forming a dynamic construction timeline. The construction task data acquisition and dependency analysis module acquires all construction task data within the same time period, including the resource requirements of each task and the dependencies between tasks. The potential resource conflict analysis and intelligent prediction module extracts the features of potential resource conflicts after acquiring construction task data, performs in-depth analysis on the extracted features, and inputs the analyzed features into a pre-trained machine learning model to intelligently predict resource conflicts in the current project. The task splitting and resource scheduling optimization module, when resource conflicts are identified within the same time period, splits the identified tasks with shared resource conflicts into multiple sub-tasks. Each sub-task is allocated to different time periods according to resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the module adjusts the number of sub-tasks based on the severity of resource conflicts to flexibly respond to various unexpected construction situations.

[0016] The technical effects and advantages provided by the present invention in the above technical solution are as follows: This invention tightly integrates construction plans with BIM models to generate dynamic timelines and utilizes machine learning for in-depth analysis and prediction of potential resource conflicts. For identified resource conflicts, tasks are flexibly split and resource allocation is optimized to ensure that each resource is used for only one task within each time period, thus avoiding excessive concentration or waste of resources. This intelligent scheduling method improves the efficiency of construction progress and enables flexible responses to unforeseen circumstances. Ultimately, by optimizing project management, reducing costs, and improving safety and engineering quality, it ensures that projects are completed on time and efficiently. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0018] Figure 1 This is a flowchart of a BIM-based architectural design simulation method according to the present invention.

[0019] Figure 2 This is a schematic diagram of a BIM-based architectural design simulation system according to the present invention. Detailed Implementation

[0020] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that the description of this disclosure will be more complete and fully convey the concept of the exemplary embodiments to those skilled in the art.

[0021] This invention provides, for example Figure 1 The BIM-based architectural design simulation method shown includes the following steps: Linking the construction plan of a building project with elements in the BIM model allows each building element and component to be matched with the corresponding construction time period, forming a dynamic construction timeline. The specific steps are as follows: 1. Create a BIM model; Step-by-step instructions: First, a BIM model needs to be created based on the architectural drawings of the building project. This model should include all architectural elements, such as walls, columns, doors and windows, pipes, electrical systems, etc., and assign specific attributes (such as dimensions, materials, location, etc.) to each element.

[0022] Function: By creating an accurate BIM model, it provides a digital building entity for the subsequent construction process, serving as the basis for all subsequent work and analysis.

[0023] 2. Develop a construction plan; Step-by-step instructions: Develop a detailed construction plan based on project requirements. The construction plan should clearly define the time, sequence, duration, and required resources for each task. Each task should include its specific time frame, task dependencies, and resource requirements.

[0024] Purpose: The purpose of a construction plan is to clarify each stage of the construction process and ensure that the construction tasks are completed on time, thereby helping to achieve controllability and predictability of the overall progress.

[0025] 3. Link construction tasks with BIM elements; Step-by-step instructions: Associate each task in the construction plan with a building element or component in the BIM model. For example, a task might involve installing pipes or supporting structures on a specific floor. In this case, the system needs to bind these tasks to the corresponding components (such as pipes, support columns, etc.) in the BIM model and determine the construction time for each component.

[0026] Function: By associating tasks and elements, it ensures that each element in the BIM model has a clear time schedule during construction, and that each element is constructed according to the construction plan schedule.

[0027] 4. Create a dynamic construction timeline; Step-by-step instructions: Combine the BIM model and construction plan to create a dynamic construction timeline, which arranges the construction tasks of all building elements in chronological order on a timeline. This timeline will display the start and end times of construction for each building element and component, as well as the dependencies between tasks.

[0028] Function: The dynamic construction timeline can intuitively display the overall progress of the project and provide a visual reference for subsequent task scheduling, progress monitoring and resource management, ensuring that the construction progress is controllable and traceable, and effectively predicting potential problems.

[0029] Acquire data on all construction tasks within the same time period, including the resource requirements (such as equipment, personnel, and materials) for each task and the dependencies between tasks; Acquiring data on all construction tasks helps the system gain a comprehensive understanding of the resource requirements and timelines for each task within a given time period, thereby providing input for analyzing and predicting potential resource conflicts.

[0030] Obtaining data on all construction tasks within the same time period can be achieved through an Integrated Project Management System (IPMS) or a BIM project management platform. These systems automatically integrate construction tasks, resource requirements, and dependencies between tasks into a unified data structure. First, the system extracts detailed information for each task from the construction plan, including timeframes, task descriptions, required resources (such as equipment, workers, and materials), and dependencies between tasks (such as prerequisites and successors). Next, through integration with the BIM model, the system associates the specific resources required for each task and integrates this data into a unified platform based on resource type, quantity, and construction time. This allows the project management team to view the construction tasks and related resource usage in real time for each time period, facilitating the rapid identification of potential resource conflicts or dependency bottlenecks and ensuring the smooth progress of construction tasks.

[0031] After obtaining the construction task data, the features of potential resource conflicts are extracted, the extracted features are deeply analyzed, and the analyzed features are input into a pre-trained machine learning model to intelligently predict the resource conflicts of the current project. Features of potential resource conflicts are extracted, including the degree of overlap in the demand for the same resource (such as equipment and workers) among multiple construction tasks and the degree of uneven utilization of the same resource across multiple tasks. In-depth analysis is performed on the degree of overlap in the demand for the same resource (such as equipment and workers) among multiple construction tasks and the degree of uneven utilization of the same resource across multiple tasks, generating task overlap density indicators and resource utilization imbalance indicators respectively. These indicators are then used as feature vectors and input into a pre-trained machine learning model. The machine learning model outputs a conflict coefficient, and based on the conflict coefficient, intelligent prediction of resource conflicts in the current project is performed.

[0032] When multiple construction tasks have a high degree of overlap in their demands for the same resources (such as equipment, workers, and materials), it usually indicates a risk of resource conflict in the current project. Specifically, if multiple tasks require the same resources within the same timeframe, and the quantity or capacity of those resources is limited, the resources will be unable to meet the needs of multiple tasks simultaneously. This resource conflict can not only lead to task delays but also cause overuse of resources or wasted idle time, thereby affecting construction progress, increasing costs, and even creating safety hazards. For example, if multiple construction sites simultaneously need to use the same crane, but the equipment cannot support multiple tasks at the same time, it will lead to schedule delays or improper safe operation. Timely identification and handling of such overlapping resource demands are crucial to ensuring the smooth progress of the project.

[0033] The specific steps for generating a task overlap density index through in-depth analysis of the overlap in the demand for the same resources (such as equipment and workers) from multiple construction tasks are as follows: Calculate the overlap in the demand for shared resources (such as equipment, workers, etc.) for each pair of construction tasks within a given time period. i and j The formula for calculating the overlap of demands is: , in, For the task i With the task j The degree of overlap in demand between the two entities within a given time period reflects the extent to which they share the same demand for resources. and For the task i and tasks j The execution time interval, that is, the start and end times of the task. and Representing tasks i and tasks j The resource requirement at time t. Typically, the resource requirement of a task can be expressed as a function that changes over time. and Task i and tasks j The total resource requirement throughout the entire execution process, i.e., the sum of the resources required by the task; This step aims to identify potential conflicts during task execution by calculating the overlap of resource requirements between tasks. If two tasks have similar or overlapping requirements for the same resources within the same time period, the overlap will be high, indicating an increased resource shortage.

[0034] By combining the overlap between all task pairs, an overall task overlap density index is generated, expressed as follows: , in, This is an overall task overlap density index, representing the overall resource overlap among all tasks in the project. A higher task overlap density index indicates a greater likelihood of resource allocation conflicts within the project. For the task i and j The weighting coefficients are typically adjusted based on the urgency of the task's resource requirements. For example, if the task... i and tasks j The resource requirements are relatively high. It can be set to a larger value to highlight the impact of these tasks on resource conflicts. n This represents the total number of tasks, i.e., the total number of all tasks participating in the overlap analysis. This step quantifies the task overlap density of the entire project by integrating the overlap between all task pairs. The task overlap density index considers the impact of all task pairs and can effectively assess the risk of resource conflicts throughout the construction process. A high task overlap density index indicates that multiple tasks may compete for the same resource within a certain period, thus increasing the likelihood of resource conflicts.

[0035] As the task overlap density index reveals, a higher index value, generated from an in-depth analysis of the overlap in the demand for the same resources (such as equipment and workers) among multiple construction tasks, indicates a higher risk of resource conflict in the current project; conversely, a lower index value indicates a lower risk. The task overlap density index measures the degree of overlap in the demand for shared resources among multiple construction tasks within the same time period, reflecting resource scarcity. A higher overlap density means that multiple tasks have a significant demand for the same resource at the same time, leading to unmet resource needs and potentially causing task delays, resource waste, or even safety hazards. Conversely, a lower overlap density indicates that the demand for resources among tasks is more dispersed or balanced, resulting in a lower risk of resource conflict and smoother resource allocation within the project. Therefore, as an indicator reflecting the potential risk of resource conflict, a higher task overlap density index value signifies an increased likelihood of resource conflict.

[0036] When the utilization of the same resource is unevenly distributed across multiple construction tasks, it typically indicates a risk of resource conflict in the current project. Uneven resource utilization means that within the same timeframe, multiple tasks have an excessively concentrated demand for the same resources (such as equipment, workers, and materials), while the actual supply capacity of those resources cannot meet the needs of all tasks. This situation leads to excessive consumption or overloading of resources, resulting in resource shortages, task delays, and even construction halts. The risk of resource conflict not only affects construction progress but may also increase costs, reduce project efficiency, and in some cases, even create safety hazards due to improper resource allocation.

[0037] The specific steps for generating a resource utilization imbalance index through in-depth analysis of the uneven utilization of the same resource across multiple tasks are as follows: The demand for each resource in each construction task is analyzed, and the demand concentration of that resource is calculated. Resource demand concentration reflects the degree of concentration of resource usage within a given time period; a higher value indicates a more concentrated resource demand, while a lower value indicates a more even distribution of resource usage. The calculation expression is as follows: , in: This indicates the concentration of resource demand, representing the degree to which resources are concentrated across all tasks. Indicates in the task w China's resources R Demand (e.g., the working hours of a particular piece of equipment or a certain type of worker). p To adjust the index and control the impact of demand fluctuations. The larger the value, the more it emphasizes the concentrated impact of tasks with high demand. n (Total number of tasks within that time period). k It is the index of the inner summation, representing the sum of the requirements for a certain resource across all tasks. Indicates the first k The resource requirements of each task; The purpose of this step is to measure the concentration of resource demand and identify which tasks may be overly dependent on a particular resource, thereby initially revealing potential resource conflict risks.

[0038] After calculating the resource demand concentration, a resource utilization imbalance index is generated based on this concentration. This index not only considers demand concentration but also incorporates a comparison between the maximum demand ratio and actual supply capacity to quantify the uneven use of resources. The generated expression is as follows: , in: As an indicator of uneven resource utilization, it reflects the overall degree of unevenness in resource demand. This represents the maximum demand for the same resource within that time period (e.g., the maximum number of hours a device can be used). q Adjust the parameters of the index to control the contribution of the proportion of demand to the degree of imbalance; The purpose of this step is to accurately quantify the degree of resource imbalance by comprehensively considering the concentration of resource demand and the proportion of maximum demand. When the resource utilization imbalance index is high, it indicates that there is a serious imbalance in resource utilization, which may lead to conflicts and project delays.

[0039] The resource utilization imbalance index reveals that a higher index value, generated from an in-depth analysis of the uneven utilization of the same resource across multiple tasks, indicates a higher risk of resource conflict in the current project. Conversely, a lower index indicates a lower risk. Specifically, a high resource utilization imbalance index signifies a highly concentrated demand for the same resource across multiple construction tasks, potentially leading to overuse of resources or demand exceeding supply capacity within the same timeframe. This can result in difficulties in resource scheduling, task delays, and even construction halts. Conversely, a low index indicates a more even distribution of resource demand across tasks, suggesting more rational resource use and less likelihood of severe resource conflict, thus reducing potential project risks. Therefore, the resource utilization imbalance index is an important indicator that helps project managers identify the risk of resource conflict.

[0040] In practical applications, pre-trained machine learning models are obtained by learning and optimizing from a large amount of historical construction project data. During this training process, the model's goal is to output a quantitative value of project resource conflicts—a conflict coefficient—based on different input features (task overlap density indicators and resource utilization imbalance indicators). The training process typically uses a large amount of historical project data, including various construction tasks, resource requirements, schedules, conflict records, and project progress. The machine learning model uses this data to learn the relationship between various features and resource conflicts and adjusts its parameters to enable accurate predictions for new input data.

[0041] During training, the model learns how to combine different features for conflict prediction by continuously adjusting weights (i.e., model parameters). To ensure model effectiveness, different types of machine learning methods are typically employed, such as regression analysis, decision trees, random forests, support vector machines (SVMs), and neural networks. These methods can improve the model's predictive ability through optimization algorithms (such as gradient descent), enabling the model to recognize complex patterns. For example, random forests can capture the non-linear relationship between features and conflicts by combining multiple decision trees, while neural networks can automatically extract deep-level features from large-scale data.

[0042] Once the machine learning model is trained, it can be used to predict resource conflicts in new projects. In practical applications, the model receives data from the current project as input feature vectors, including task overlap density indicators and resource utilization imbalance indicators. By inputting these features into the pre-trained model, the model intelligently predicts resource conflicts in the current project based on its learned knowledge and patterns, outputting a conflict coefficient. This conflict coefficient is essentially a quantitative indicator representing the degree of conflict in resource scheduling and allocation within the current project. A higher conflict coefficient indicates a greater risk of resource conflict, potentially requiring adjustments by project managers.

[0043] For example, suppose in a new construction project, the calculated task overlap density index is 0.8 and the resource utilization imbalance index is 1.5. Inputting these two feature vectors into a pre-trained machine learning model, the model will output a conflict coefficient, for example, 0.9. If the conflict coefficient is high, project managers can promptly identify potential resource conflicts and accordingly adjust resource allocation, task rescheduling, or take other management measures to optimize resource utilization, avoiding project delays and increased costs. In this process, the machine learning model plays a role in intelligent prediction, making project management more scientific and efficient through learning from a large amount of historical data.

[0044] In summary, pre-trained machine learning models, acquired through learning from extensive historical data, can make fast and accurate predictions in current projects. They can analyze input feature vectors, identify potential resource conflicts within the project, and provide corresponding conflict coefficients. This assists project management teams in making more intelligent decisions, proactively identifying risks, and implementing optimization measures. Through this intelligent prediction, project teams can more efficiently schedule resources and manage construction, thereby increasing project success rates and reducing risks.

[0045] The machine learning model is not specifically limited here, but it can achieve the task overlap density index. Indicators of uneven resource utilization A comprehensive analysis is conducted to generate the conflict coefficient. Any machine learning model is acceptable. To achieve the technical solution of this invention, this invention provides a specific implementation method; conflict coefficient. The generated expression is: In the formula, , These are the task overlap density indices. Indicators of uneven resource utilization The preset proportional coefficient, and , All are greater than 0. Preset proportional coefficient ( and These are weighted coefficients for the task overlap density index and the resource utilization imbalance index. They play a crucial role in calculating the conflict coefficient, determining the weight of task overlap density and resource utilization imbalance in the overall conflict coefficient. These coefficients help the model distinguish the relative importance of different features during the calculation process. Specifically, and These are the task overlap density indices ( ) and indicators of uneven resource utilization ( The weighting coefficients corresponding to these factors adjust the influence of each feature on the conflict coefficient through weighting. This allows the model to more flexibly adjust the contribution of task overlap density and uneven resource utilization to conflict risk when predicting resource conflicts, based on the characteristics of different projects. For example, if a project has significant time overlap of tasks, then the weight of the task overlap density index (…) The potential for a large conflict coefficient makes it more likely to reflect the risk of time conflicts.

[0046] As can be seen from the conflict coefficient, the larger the performance value of the task overlap density index generated by the in-depth analysis of the degree of overlap of the demand for the same resource (such as equipment, workers, etc.) of multiple construction tasks, the larger the performance value of the resource utilization imbalance index generated by the in-depth analysis of the degree of uneven utilization of the same resource in multiple tasks, that is, the larger the performance value of the conflict coefficient generated when the machine learning model that has been pre-trained intelligently predicts the resource conflict of the current project, the higher the risk of resource conflict in the current project, and vice versa.

[0047] The conflict coefficient generated by the pre-trained machine learning model when intelligently predicting resource conflicts in the current project is compared with a pre-set conflict coefficient reference threshold to determine whether there is a risk of resource conflict in the current project. The specific judgment steps are as follows: If the conflict coefficient is greater than the reference threshold, the current project is deemed to have a risk of resource conflict; if the conflict coefficient is less than or equal to the reference threshold, the current project is deemed not to have a risk of resource conflict.

[0048] When resource conflicts are identified within the same time period, tasks with identified shared resource conflicts are split into multiple sub-tasks. Each sub-task is allocated to different time periods based on resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the number of sub-tasks is adjusted according to the severity of the resource conflict to flexibly respond to various unexpected construction situations, ensure efficient progress of construction, and maximize resource utilization. When resource conflicts are detected within the same time period, tasks with identified shared resource conflicts are split into multiple subtasks. The number of subtasks is adjusted according to the severity of the resource conflict. The specific steps are as follows: For tasks identified as having shared resource conflicts, they are split into multiple subtasks. Each subtask is allocated to a different time slot based on its specific resource requirements and characteristics (such as duration, resource consumption, priority, etc.). During resource splitting, it is necessary to ensure that the resources used by each subtask within its allocated time slot do not conflict with those of other tasks. Specifically, an optimization algorithm is used to dynamically adjust the task scheduling so that each resource is occupied by only one subtask within each time slot. The adjustment expression is as follows: , in, The adjusted time period for the sub-tasks. The original task's time period. This refers to the resource requirements of the task. To maximize the availability of resources, The adjustment amount for the time period is determined based on resource requirements and task characteristics; The purpose of this step is to ensure that each task uses different resources at different times by splitting and rescheduling tasks, thereby avoiding resource conflicts. Through reasonable splitting and scheduling, the construction team can flexibly respond to different resource needs and maintain the continuity and stability of the construction progress.

[0049] Based on the severity of the identified conflicts, the number of task splits and the allocation of time periods are further adjusted. For tasks with severe resource conflicts, the number of subtasks can be increased, and the task execution time can be extended to ensure that each subtask is performed within a separate time period, thereby reducing the impact of resource conflicts. For tasks with mild conflicts, they can be split moderately to avoid excessive splitting that would increase management complexity. The specific number of splits is determined by the difference between the conflict coefficient and the conflict coefficient reference threshold. The expression for splitting is: , in, The number of subtasks to be split. The current conflict coefficient, As a reference threshold for the conflict coefficient, The maximum allowable conflict coefficient, The number of splits for the original task (usually 1); By adjusting the number of task splits based on the severity of the conflict coefficient, the efficiency and complexity of task splitting can be effectively balanced. For tasks with severe conflicts, increasing the number of splits can effectively reduce resource contention and ensure construction progress; while for tasks with less conflict, appropriate splitting can avoid unnecessary complex management, thereby ensuring efficient use of resources.

[0050] Through the above steps, the system can intelligently identify and resolve resource conflicts between tasks. First, conflicts are identified using a conflict coefficient and a reference threshold. Then, tasks are split and rationally scheduled. Finally, the number of tasks split is adjusted based on the severity of the conflict. These steps collectively ensure efficient resource utilization and flexible response to unforeseen circumstances that may arise during construction, thereby guaranteeing the smooth progress of the project.

[0051] The aforementioned BIM-based architectural design simulation method enables intelligent prediction and optimized scheduling of construction tasks, significantly improving resource utilization efficiency and reducing construction stagnation and delays caused by resource conflicts. This method tightly integrates the construction plan with the BIM model to form a dynamic timeline and utilizes machine learning for in-depth analysis and prediction of potential conflicts. When resource conflicts are identified, it flexibly splits tasks and adjusts resource allocation to ensure that each resource is used by only one task within a given time period, greatly avoiding excessive resource concentration or waste. Ultimately, this intelligent scheduling and prediction system not only improves the efficiency of construction progress but also allows for flexible responses to unforeseen circumstances, thereby optimizing project management, reducing costs, enhancing project safety and quality, and ensuring timely project completion.

[0052] This invention provides, for example Figure 2 The BIM-based architectural design simulation system shown includes a construction plan and BIM model association module, a construction task data acquisition and dependency analysis module, a potential resource conflict analysis and intelligent prediction module, and a task splitting and resource scheduling optimization module. The construction plan and BIM model association module links the construction plan of a building project with the elements in the BIM model, so that each building element and component is matched with the corresponding construction time period, forming a dynamic construction timeline. The construction task data acquisition and dependency analysis module acquires all construction task data within the same time period, including the resource requirements of each task and the dependencies between tasks. The potential resource conflict analysis and intelligent prediction module extracts the features of potential resource conflicts after acquiring construction task data, performs in-depth analysis on the extracted features, and inputs the analyzed features into a pre-trained machine learning model to intelligently predict resource conflicts in the current project. The task splitting and resource scheduling optimization module, when resource conflicts are identified within the same time period, splits the identified tasks with shared resource conflicts into multiple sub-tasks. Each sub-task is allocated to different time periods according to resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the module adjusts the number of sub-tasks based on the severity of resource conflicts to flexibly respond to various unexpected construction situations.

[0053] The present invention provides a BIM-based architectural design simulation method, which is implemented through the aforementioned BIM-based architectural design simulation system. For details of the specific methods and processes of the BIM-based architectural design simulation system, please refer to the aforementioned embodiment of the BIM-based architectural design simulation method, which will not be repeated here.

[0054] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0055] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0056] The foregoing has only described certain exemplary embodiments of the present invention by way of illustration. Undoubtedly, those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the foregoing drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A BIM-based architectural design simulation method, characterized in that, Includes the following steps: Linking the construction plan of a building project with elements in the BIM model allows each building element and component to be matched with the corresponding construction time period, forming a dynamic construction timeline. Obtain data on all construction tasks within the same time period, including the resource requirements of each task and the dependencies between tasks; After obtaining the construction task data, the features of potential resource conflicts are extracted, the extracted features are deeply analyzed, and the analyzed features are input into a pre-trained machine learning model to intelligently predict the resource conflicts of the current project. When resource conflicts are identified within the same time period, tasks with identified shared resource conflicts are split into multiple sub-tasks. Each sub-task is allocated to different time periods based on resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the number of sub-tasks is adjusted according to the severity of the resource conflict to flexibly respond to various unexpected construction situations.

2. The BIM-based architectural design simulation method according to claim 1, characterized in that, The specific steps to link the construction plan of a building project with elements in the BIM model to form a dynamic construction timeline are as follows: Create a BIM model based on the architectural drawings of the building project. The model should include all architectural elements and assign specific attributes to each element. Develop a detailed construction plan based on the project requirements; Associate each task in the construction plan with the building elements or components in the BIM model to ensure that each element in the BIM model has a clear timeline during construction and is constructed according to the schedule of the construction plan. By combining the BIM model and the construction plan, a dynamic construction timeline is created, which arranges the construction tasks of all building elements in chronological order on the timeline, showing the start and end times of construction for each building element and component, as well as the dependencies between tasks.

3. The BIM-based architectural design simulation method according to claim 1, characterized in that, To obtain data on all construction tasks within the same time period, this is achieved by integrating with a project management system or BIM project management platform, specifically as follows: Extract detailed information about each task from the construction plan, including timelines, task descriptions, required resources, and dependencies between tasks. By integrating with the BIM model, the specific resources required for each task are associated, and this data is integrated into a unified platform based on the type, quantity, and construction time of the resources, allowing real-time viewing of construction tasks and the usage of related resources within each time period.

4. The BIM-based architectural design simulation method according to claim 1, characterized in that, Features of potential resource conflicts are extracted, including the degree of overlap of multiple construction tasks' demands for the same resource and the degree of uneven utilization of the same resource across multiple tasks. In-depth analysis is performed on the degree of overlap of multiple construction tasks' demands for the same resource and the degree of uneven utilization of the same resource across multiple tasks, generating task overlap density indicators and resource utilization imbalance indicators respectively. These indicators are then used as feature vectors and input into a pre-trained machine learning model. The machine learning model outputs a conflict coefficient, and based on this conflict coefficient, intelligent prediction of resource conflicts in the current project is performed.

5. The BIM-based architectural design simulation method according to claim 4, characterized in that, The specific steps for generating a task overlap density index by conducting in-depth analysis of the overlap of multiple construction tasks' demands for the same resource are as follows: Calculate the overlap of shared resource requirements for each pair of construction tasks within a given time period. i and j The formula for calculating the overlap of demands is: , in, For the task i With the task j The degree of overlap in demand between two entities within a given time period reflects the extent to which they share the same demand for resources. and For the task i and tasks j The execution time interval, that is, the start and end times of the task. and Representing tasks i and tasks j The resource demand at time t. and Task i and tasks j The total resource requirement throughout the entire execution process, i.e., the sum of the resources required by the task; By combining the overlap between all task pairs, an overall task overlap density index is generated, expressed as follows: , in, This is an overall task overlap density index, representing the overall resource overlap among all tasks in the project. For the task i and j The weighting coefficients, n This represents the total number of tasks, i.e., the total number of all tasks participating in the overlap analysis.

6. The BIM-based architectural design simulation method according to claim 5, characterized in that, The specific steps for generating a resource utilization imbalance index through in-depth analysis of the uneven utilization of the same resource across multiple tasks are as follows: The demand for each resource in each construction task is analyzed, and the demand concentration of that resource is calculated using the following expression: , in: This indicates the concentration of resource demand, representing the degree to which resources are concentrated across all tasks. Indicates in the task w China's resources R The demand, p To adjust the index and control the impact of demand fluctuations, k It is the index of the inner summation, representing the sum of the requirements for a certain resource across all tasks. Indicates the first k The resource requirements of each task; This paper generates a resource utilization imbalance index based on resource demand concentration. This index not only considers demand concentration but also compares the maximum demand ratio with actual supply capacity to quantify the uneven use of resources. The generated expression is as follows: , in: As an indicator of uneven resource utilization, it reflects the overall degree of unevenness in resource demand. This represents the maximum demand for the same resource within that time period. q Adjust the parameters for the index to control the contribution of the proportion of demand to the degree of imbalance.

7. The BIM-based architectural design simulation method according to claim 4, characterized in that, The conflict coefficient generated by the pre-trained machine learning model when intelligently predicting resource conflicts in the current project is compared with a pre-set conflict coefficient reference threshold to determine whether there is a risk of resource conflict in the current project. The specific judgment steps are as follows: If the conflict coefficient is greater than the reference threshold, the current project is deemed to have a risk of resource conflict; if the conflict coefficient is less than or equal to the reference threshold, the current project is deemed not to have a risk of resource conflict.

8. The BIM-based architectural design simulation method according to claim 7, characterized in that, When resource conflicts are detected within the same time period, tasks with identified shared resource conflicts are split into multiple sub-tasks. The number of sub-tasks is adjusted according to the severity of the resource conflict. The specific steps are as follows: For tasks identified as having shared resource conflicts, they are broken down into multiple subtasks. Each subtask is allocated to a different time slot based on its specific resource requirements and characteristics. During resource decomposition, it is necessary to ensure that the resources used by each subtask within its allocated time slot do not conflict with those of other tasks. Specifically, an optimization algorithm is used to dynamically adjust the task scheduling so that each resource is occupied by only one subtask within each time slot. The adjustment expression is as follows: , in, The adjusted time period for the sub-tasks. The original task's time period. This refers to the resource requirements of the task. To maximize the availability of resources, The adjustment amount for the time period is determined based on resource requirements and task characteristics; Based on the severity of the identified conflicts, the number of task splits and the allocation of time periods are further adjusted. The specific number of splits is determined by the difference between the conflict coefficient and the conflict coefficient reference threshold. The expression for the split is: , in, The number of subtasks to be split. The current conflict coefficient, As a reference threshold for the conflict coefficient, The maximum permissible conflict coefficient, This represents the number of splits in the original task.

9. A BIM-based architectural design simulation system, used to implement the BIM-based architectural design simulation method according to any one of claims 1-8, characterized in that, It includes a module for linking construction plans with BIM models, a module for acquiring construction task data and analyzing dependencies, a module for analyzing potential resource conflicts and intelligent prediction, and a module for task splitting and resource scheduling optimization. The construction plan and BIM model association module links the construction plan of a building project with the elements in the BIM model, so that each building element and component is matched with the corresponding construction time period, forming a dynamic construction timeline. The construction task data acquisition and dependency analysis module acquires all construction task data within the same time period, including the resource requirements of each task and the dependencies between tasks. The potential resource conflict analysis and intelligent prediction module extracts the features of potential resource conflicts after acquiring construction task data, performs in-depth analysis on the extracted features, and inputs the analyzed features into a pre-trained machine learning model to intelligently predict resource conflicts in the current project. The task splitting and resource scheduling optimization module, when resource conflicts are identified within the same time period, splits the identified tasks with shared resource conflicts into multiple sub-tasks. Each sub-task is allocated to different time periods according to resource requirements and task characteristics, ensuring that each resource is used for only one sub-task in each time period. Furthermore, the module adjusts the number of sub-tasks based on the severity of resource conflicts to flexibly respond to various unexpected construction situations.

Images