Data processing method and system for intelligent building construction

Abstract

The invention provides a data processing method and system for intelligent building construction. The method comprises the following steps: preliminarily aggregating and filtering a multi-source heterogeneous data stream of a building construction site to obtain current construction data; constructing a three-dimensional digital twinborn model according to the current construction data; predicting an optimal construction activity path and a resource allocation scheme of the building construction site by using the three-dimensional digital twinborn model according to the obtained meteorological trend in a period of time in the future, and generating a personalized construction guidance plan according to a prediction result; and optimizing the personalized construction guidance plan, recording each step of operation in the optimized personalized construction guidance plan, generating an operation instruction, and synchronizing the operation instruction to mobile equipment of each related party on site. According to the technical scheme provided by the embodiment of the invention, the overall performance and management efficiency of the construction project are improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of construction management and optimization, and in particular, to a data processing method and system for intelligent construction. Background Art

[0002] In modern construction, the construction site involves a large amount of real-time multi-source heterogeneous data streams, including but not limited to sensor data, video surveillance, weather forecasts, equipment status, and worker locations. These data are essential for optimizing construction processes, improving efficiency, and ensuring safety. However, how to effectively aggregate and filter these data, extract valuable information from them, and apply them to specific construction decisions is a complex and critical technical challenge. In addition, with the expansion of project scale and technological advancement, construction parties need smarter data processing methods to support dynamic adjustment of construction plans, resource allocation, and response to unforeseen environmental changes.

[0003] At present, the construction industry mainly relies on traditional manual records and static planning tools for construction management and resource allocation. Some more advanced construction sites have begun to use digital twin technology and geographic information systems (GIS) to assist decision-making, but these systems usually only provide static three-dimensional models and cannot reflect on-site changes in real time or predict future construction activities. Although some existing optimization algorithms can help plan optimal paths and resource allocation, they often ignore the influence of external factors such as meteorological conditions in actual applications, resulting in inflexible and inaccurate plans. At the same time, there are also lags in information transmission and collaborative management, and there is a lack of effective real-time synchronization mechanisms.

[0004] However, the existing solutions have the following defects: traditional methods are difficult to efficiently process a large amount of multi-source heterogeneous data, and cannot timely extract key data that is instructive for construction from massive information. Most of the existing digital twins and optimization algorithms are based on historical data and static models, and fail to fully consider dynamic factors such as meteorological trends in the future, which affects the accuracy and adaptability of the construction plan. The existing system is insufficient in information sharing and operation records, lacks transparency and traceability, and easily leads to problems of poor communication and unclear responsibilities, especially in the case of multi-party collaboration.

[0005] In order to solve the above problems, the present invention proposes a data processing method for intelligent building construction. By integrating augmented reality technology, geographic information system, adaptive grid division algorithm and mixed integer linear programming algorithm, combined with blockchain technology, it realizes the intelligent management of the whole process from data collection to construction guidance, and significantly improves the overall performance and management efficiency of construction projects. Summary of the invention

[0006] The embodiments of the present application provide a data processing method and system for intelligent building construction, which are used to solve the problems of insufficient overall performance and low management efficiency of construction projects in the prior art.

[0007] In a first aspect, an embodiment of the present application provides a data processing method for intelligent building construction, comprising: Perform preliminary aggregation and filtering of multi-source heterogeneous data streams at the construction site to obtain current construction data; constructing a three-dimensional digital twin model based on the current construction data; Using the three-dimensional digital twin model, based on the acquired meteorological trends in the future, the optimal path and resource allocation plan for the construction activities at the construction site are predicted, and a personalized construction guidance plan is generated based on the prediction results; The personalized construction guidance plan is optimized, and each operation step in the optimized personalized construction guidance plan is recorded, and operation instructions are generated and synchronized to the mobile devices of the relevant parties on site.

[0008] Optionally, constructing a three-dimensional digital twin model according to the current construction data includes: parse structured data and unstructured data from the current construction data using augmented reality technology, and map the structured data and the unstructured data to the physical space of the construction site to obtain a preliminary three-dimensional environment representation; Based on the preliminary three-dimensional environment representation, spatially locate and annotate the attributes of various physical elements in the construction site, establish a spatial relationship network between the various physical elements, and generate a three-dimensional environment representation with position information; Dynamically adjusting the grid density of each area in the three-dimensional environment representation with position information according to a preset threshold value to obtain an optimal three-dimensional environment representation; The entity features in the optimal three-dimensional environment representation are extracted, an initial three-dimensional digital twin model is constructed according to the entity features, and the three-dimensional digital twin model is updated in combination with the historical construction data and the current construction data to generate an enhanced three-dimensional digital twin model.

[0009] Optionally, dynamically adjusting the grid density of each area in the three-dimensional environment representation with position information according to a preset threshold to obtain an optimal three-dimensional environment representation includes: Using a pre-trained importance assessment model, assess the importance of each area in the three-dimensional environment representation with location information to identify key construction areas and non-key construction areas, and generate a regional importance distribution map based on the identified key construction areas and non-key construction areas; According to the regional importance distribution map, combined with the spatial relationship network provided by the geographic information system, the complexity of each construction area is analyzed to identify areas with greater than a preset complexity and areas with less than a preset complexity, and regional complexity analysis results are generated based on the areas with greater than a preset complexity and areas with less than a preset complexity; Based on the regional complexity analysis result, different grid density thresholds are set, a first grid density is used for key construction areas and areas with a complexity greater than a preset value, and a second grid density is used for non-key construction areas and areas with a complexity less than a preset value, and a grid density configuration scheme is generated according to the first grid density and the second grid density; The three-dimensional environment representation with position information is optimized according to the grid density configuration scheme to obtain an optimal three-dimensional environment representation.

[0010] Optionally, the three-dimensional digital twin model is used to predict the optimal path and resource allocation plan for construction activities at the construction site according to the acquired meteorological trend in the future, and a personalized construction guidance plan is generated according to the prediction results, including: Utilizing the three-dimensional digital twin model, extracting the status information and resource distribution of the construction site, and generating a construction status snapshot based on the extracted status information and resource distribution, wherein the status information includes the current progress of the building, the location and status of the equipment, and the stacking location of the materials; and the resource distribution includes the availability of equipment and the working hours of the workers; Acquire and analyze weather data for a period of time in the future, evaluate the impact of different weather conditions on the construction efficiency of the construction site in the analysis results, and generate a meteorological impact assessment report; Based on the actual constraints in the meteorological impact assessment report and the construction status snapshot, construct an optimization problem model including multiple variables to form a set of constraint conditions, wherein the actual constraints include equipment availability and worker working hours, and the multiple variables include time, location, and resource type; Solving the optimization problem model, and generating a preliminary construction guidance plan on the premise that all constraints in the constraint condition set are satisfied; Performing multi-objective optimization on the preliminary construction guidance plan to obtain an optimized construction guidance plan; In combination with preset personalized needs, the optimized construction guidance scheme is adjusted to generate a personalized construction guidance plan.

[0011] Optionally, the optimization problem model is solved to generate a preliminary construction guidance plan on the premise that all constraints in the constraint set are satisfied, including: Constructing an objective function according to the constraint condition set and the plurality of variables, and constructing a mixed integer linear programming mathematical model including decision variable expressions according to the objective function; Based on the actual restrictions in the meteorological impact assessment report and the construction status snapshot, adding constraints in a constraint set to the mixed integer linear programming mathematical model to generate a mixed integer linear programming mathematical model of variable expressions of the mixed integer linear programming model with restrictions; Using a solver to iteratively calculate and solve the mixed integer linear programming model with constraints, and on the basis of satisfying all constraints in the constraint set, confirming the optimal solution that satisfies the needs of improving construction progress and resource utilization; Using the optimal solution, conduct feasibility verification to check whether it meets construction safety standards, quality control and other key performance indicators, and generate a verified solution. The other key performance indicators include resource utilization, environmental protection and cost control; Based on the verified solution, a preliminary construction guidance plan is generated, which includes a timetable, location arrangement and resource allocation plan for specific construction tasks.

[0012] Optionally, the mixed integer linear programming model with constraints is iteratively calculated and solved by a solver, and an optimal solution that satisfies the requirements of improving the construction progress and resource utilization is determined on the basis of satisfying all constraints in the constraint set, including: Initialize the solver and set the initial parameters and solution strategy to obtain the solution environment; According to the solution environment, starting a solver to perform iterative calculations on a mixed integer linear programming model with constraints, generating a preliminary solution, and recording an objective function value of the preliminary solution; Based on the objective function value, a solution path in the solution environment is iteratively optimized using a heuristic algorithm until an intermediate solution that satisfies all constraints and has an objective function value better than an existing objective function value is confirmed, and the intermediate solution and the corresponding objective function value are saved as candidate solutions; An optimal solution is determined based on the candidate solutions.

[0013] Optionally, the personalized construction guidance plan is optimized, and each operation step in the optimized personalized construction guidance plan is recorded, and operation instructions are generated and synchronized to mobile devices of relevant parties on site, including: Optimizing the construction tasks of the construction site by using the personalized construction guidance plan and actual constraints and preset priority requirements in the construction status snapshot to obtain an optimized personalized construction guidance plan, wherein the actual constraints include equipment availability and worker working hours, and the priority requirements are based on the urgency and critical path of the project; Assigning a unique identifier to each construction task in the optimized personalized construction guidance plan, and generating an operation instruction set according to the assignment result, wherein the unique identifier is used to track and manage each construction task; The operation instruction set is sent to the mobile devices of all relevant parties at the construction site through a mobile application platform.

[0014] In a second aspect, an embodiment of the present application provides a data processing system for intelligent building construction, including: Aggregation and filtering module, used to perform preliminary aggregation and filtering of multi-source heterogeneous data streams at the construction site to obtain current construction data; A construction module, used to construct a three-dimensional digital twin model according to the current construction data; A prediction module is used to use the three-dimensional digital twin model to predict the optimal path and resource allocation plan of the construction activities at the construction site according to the meteorological trend in the future, and generate a personalized construction guidance plan according to the prediction results; The synchronization module is used to optimize the personalized construction guidance plan, record each operation step in the optimized personalized construction guidance plan, generate operation instructions and synchronize them to the mobile devices of all relevant parties on site.

[0015] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data processing method for intelligent building construction as described in the first aspect above.

[0016] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, which, when executed by a computer, implements a data processing method for intelligent building construction as described in the first aspect.

[0017] In an embodiment of the present application, multi-source heterogeneous data streams at a construction site are preliminarily aggregated and filtered to obtain current construction data; a three-dimensional digital twin model is constructed based on the current construction data; the three-dimensional digital twin model is used to predict the optimal path and resource allocation plan for construction activities at the construction site based on the acquired meteorological trends for a period of time in the future, and a personalized construction guidance plan is generated based on the prediction results; the personalized construction guidance plan is optimized, and each step of the operation in the optimized personalized construction guidance plan is recorded, and operation instructions are generated and synchronized to the mobile devices of all relevant parties on site.

[0018] The technical solution of this application has the following beneficial effects: This application shortens the project duration by optimizing the construction path and resource allocation. Rationally arrange resource use to reduce waste and unnecessary expenditure. Use three-dimensional digital twin models and real-time data streams to ensure that the construction environment is safe and controllable. Accurate spatial positioning and attribute annotation ensure that the construction quality meets the standards. The application of blockchain technology ensures that the operation records cannot be tampered with and enhances information transparency. Operation instructions are synchronized to mobile devices to ensure that all participants have access to the latest information in real time and support feedback mechanisms. Dynamically adjust resource density to maximize resource utilization and reduce idleness and overuse.

[0019] Furthermore, the embodiment of the present application also utilizes augmented reality technology and geographic information system, combined with an adaptive meshing algorithm, to construct a three-dimensional digital twin model based on current construction data, and applies a mixed integer linear programming algorithm to predict the optimal path and resource allocation plan for construction activities in the future, and to generate a personalized construction guidance plan. Specifically, first, augmented reality technology is used to parse and map structured and unstructured data to the physical space of the construction site to form a preliminary three-dimensional environmental representation; then, each physical element is spatially positioned and attributed through GIS, a spatial relationship network is established, and a three-dimensional environmental representation with precise location information is generated; then, an adaptive meshing algorithm is applied to dynamically adjust the grid density of different regions to obtain a refined three-dimensional environmental representation; finally, a computer vision algorithm is used to identify and extract entity features, and the three-dimensional digital twin model is updated in combination with historical and real-time construction data. In addition, based on the three-dimensional digital twin model, a snapshot of the construction status is extracted, future weather data is obtained and analyzed, its impact on construction efficiency is evaluated, an optimization problem model is constructed and solved, and a construction guidance plan that has been optimized and personalized is generated.

[0020] Through the above methods, the overall performance and management efficiency of the construction project have been significantly improved. By building an accurate three-dimensional digital twin model, real-time monitoring and dynamic adjustment of the construction site are achieved, ensuring the optimization of construction progress, cost control and resource utilization. At the same time, considering external factors such as meteorological trends, the flexibility and adaptability of the construction plan are enhanced, and the risks caused by unforeseen conditions are reduced. In addition, the application of blockchain technology ensures the transparency and traceability of operation records, promotes the efficiency of collaboration among all parties, and ensures that all participants can obtain the latest information and provide feedback in real time, thereby comprehensively improving the safety and quality control level of the construction process.

[0021] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0023] Figure 1 A flow chart showing a data processing method for intelligent building construction provided by the present application is shown; Figure 2 A schematic diagram of the structure of a data processing system for intelligent building construction provided by the present application is shown; Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0025] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0027] Figure 1 A flowchart of a data processing method for intelligent building construction is provided for an embodiment of the present application, such as Figure 1 As shown, the method includes: 101. Perform preliminary aggregation and filtering on multi-source heterogeneous data streams at the construction site to obtain current construction data; Multi-source heterogeneous data streams include a large amount of structured and unstructured data generated by various sensors (such as temperature, humidity, pressure), video surveillance systems, GPS positioning devices, RFID tags, drone images, smart devices worn by workers, etc. These data cover various dynamic information on the construction site, such as equipment status, material stacking location, weather conditions, personnel activity trajectories, etc. Through preliminary aggregation and filtering, redundant and noisy data can be removed, and information with direct value to construction management can be extracted to form current construction data. This step ensures that the data set for subsequent processing is both comprehensive and accurate, laying the foundation for building an accurate three-dimensional digital twin model.

[0028] In actual operation, a series of sensors and data collection devices are first deployed at key locations on the construction site to capture various environmental parameters and activity information. Then, the collected data is processed in real time using edge computing nodes or cloud servers, and machine learning algorithms are applied to identify and filter out useful data fragments. For example, outliers are removed through time series analysis, and similar data points are classified using clustering algorithms to generate a data set containing the latest and high-quality construction information. This process not only improves the availability of data, but also reduces the burden of subsequent processing.

[0029] In a large commercial complex construction project, the construction party installed multiple types of sensor networks covering the entire construction site. These sensors transmit data to the central control system once a minute. After preliminary aggregation and filtering, the system can instantly obtain key information such as temperature and humidity changes inside and outside the building, the working status of mechanical equipment, and material transportation routes. Based on this data, construction managers can quickly respond to potential problems, such as adjusting the ventilation system in time to cope with adverse weather conditions and optimizing material stacking areas to improve logistics efficiency.

[0030] 102. Constructing a three-dimensional digital twin model according to the current construction data; Augmented reality (AR) technology is used to parse structured data (such as sensor readings, GPS coordinates) and unstructured data (such as images, videos) from current construction data, and map these data to the physical space of the construction site to form a preliminary three-dimensional environmental representation. Geographic Information System (GIS) is used to spatially locate and attribute each physical element (such as buildings, equipment, and material storage areas), establish a spatial relationship network between them, and generate a three-dimensional environmental representation with precise location information. The adaptive meshing algorithm dynamically adjusts the mesh density of different areas according to the importance or complexity of the physical elements, thereby obtaining a refined three-dimensional environmental representation. Finally, computer vision algorithms are used to identify and extract entity features from the refined three-dimensional environmental representation to generate a three-dimensional digital twin model.

[0031] First, AR technology is used to project information extracted from current construction data into a virtual environment at the construction site to create a preliminary three-dimensional representation of the environment. Next, the GIS system accurately locates each physical element in this preliminary model and adds its specific attributes (such as building material type, equipment model). Subsequently, the adaptive meshing algorithm adjusts the mesh fineness according to the importance and complexity of different areas to ensure that the model can reflect both the macro layout and the micro details. Finally, the computer vision algorithm identifies and extracts physical features such as walls, columns, doors and windows, etc., to further improve the three-dimensional digital twin model. This step makes the model not only visual, but also interactive and operable.

[0032] Continuing with the example of the commercial complex project above, the construction team can see the virtual building structure superimposed on the real world when patrolling the site using AR glasses and mobile devices, helping them to understand the design intent more intuitively. At the same time, the GIS system ensures that all physical elements are accurately located and labeled, allowing managers to view specific information at any location through a tablet. The adaptive meshing algorithm allows key construction areas (such as underground foundation projects) to have higher resolution, while low-complexity areas (such as ordinary ground paving areas) remain appropriately simplified. The resulting three-dimensional digital twin model not only supports real-time monitoring, but also simulates different construction scenarios to assist decision-making.

[0033] 103. Using the three-dimensional digital twin model, based on the acquired meteorological trend in the future, predict the optimal path and resource allocation plan for the construction activities at the construction site, and generate a personalized construction guidance plan based on the prediction results; The 3D digital twin model provides a highly accurate virtual copy of the construction site, which can simulate future construction activities by combining historical construction data with current construction data acquired in real time, as well as weather forecasts for a period of time in the future. On this basis, the mixed integer linear programming algorithm considers multiple variables (such as time, location, resource type) and constraints (such as equipment availability, worker working hours), and finds the optimal path and resource allocation plan through mathematical modeling and solving. The generated personalized construction guidance plan not only optimizes the construction schedule and cost, but also takes into account safety standards, quality control and other key performance indicators such as environmental protection and supply chain management.

[0034] First, extract the current construction status snapshot from the 3D digital twin model, including the current progress of the building, the location and status of the equipment, the stacking location of the materials, etc. Then, obtain weather data for a period of time in the future through the long-term weather forecast API, evaluate the impact of different weather conditions on construction efficiency, and generate a meteorological impact assessment report. Next, based on this report and the actual limitations of the construction status snapshot, build an optimization problem model containing multiple variables and form a set of constraints. Finally, apply the mixed integer linear programming algorithm to solve the model, find the solution that makes the construction progress fastest, the cost lowest, or the resource utilization highest, and generate a preliminary construction guidance plan. After multi-objective optimization and personalized customization, a detailed construction guidance plan is finally formed.

[0035] In the aforementioned project, the construction team received a personalized construction guidance plan every morning based on the data updated on the previous day. The plan takes into account the weather forecast for the day. For example, if heavy rain is predicted in the afternoon, work that requires a dry environment, such as concrete pouring, is scheduled in advance and transferred to the morning for completion. At the same time, for some critical tasks, such as crane hoisting operations, the specific execution time will be adjusted according to the wind speed forecast to avoid safety risks caused by bad weather. In addition, by accurately estimating the resources required for different construction stages, unnecessary waiting time and material waste are reduced, significantly improving the overall construction efficiency.

[0036] 104. Optimize the personalized construction guidance plan, record each operation step in the optimized personalized construction guidance plan, generate operation instructions and synchronize them to the mobile devices of the relevant parties on site.

[0037] After optimized configuration, the personalized construction guidance plan ensures that each construction stage has clear operation guidelines, covering specific timetables, location arrangements and resource allocation plans. In order to ensure the timeliness and accuracy of information transmission, an operation recording mechanism supported by blockchain technology is adopted to ensure that each step of the operation cannot be tampered with and is transparent and traceable. Through the mobile application platform, these operation instructions are synchronously sent to the mobile devices of all relevant parties at the construction site, so that all participants can receive the latest guidance information in real time, and support feedback on task completion and problems encountered, which enhances collaboration efficiency and communication fluency.

[0038] First, the personalized construction guidance plan is optimized for multiple objectives to ensure that it not only considers the shortest construction period or the lowest cost, but also takes into account safety standards, quality control and other key performance indicators. Then, each step of the operation is recorded through blockchain technology to ensure the authenticity and integrity of all operation records. Next, the operation instructions are synchronized to the mobile devices of all relevant parties on the construction site using a mobile application platform to ensure that each participant can keep up to date with the latest information. Finally, a feedback mechanism is provided to allow on-site staff to report the completion of tasks and problems encountered so that the plan can be adjusted in time to ensure smooth construction.

[0039] In the commercial complex project, the construction team receives daily updated construction guidance plans through a dedicated mobile app. Each task has detailed operation instructions and time nodes, and all operations are recorded through blockchain technology to ensure that the information is transparent and cannot be tampered with. For example, when a worker completes a task, he can upload a photo or video through the app as proof of completion, and mark whether there are any problems. The project manager can view the progress in real time in the background and make adjustments quickly based on the feedback. This efficient communication method greatly reduces misunderstandings and delays, promotes close collaboration between all parties, and ensures that the project proceeds as planned.

[0040] Through the implementation of steps 101 to 104, the present invention significantly improves the overall performance and management efficiency of construction projects. First, through efficient data aggregation and filtering, the accuracy and timeliness of construction data are ensured; secondly, the three-dimensional digital twin model constructed by augmented reality technology and geographic information system provides accurate construction environment simulation and enhances decision-making support capabilities; thirdly, combined with the prediction of meteorological trends and the application of mixed integer linear programming algorithms, the construction path and resource allocation are optimized, reducing costs and improving flexibility; finally, with the help of the operation recording mechanism and mobile application platform supported by blockchain technology, the transparency and real-time nature of information transmission are achieved, and multi-party collaboration is promoted. Overall, this method not only improves the construction progress and quality control level, but also enhances the safety and resource utilization of the construction process, bringing significant changes to the construction industry.

[0041] In order to solve the accuracy problem of construction site data processing and model building, in some embodiments, building a three-dimensional digital twin model according to the current construction data in step 102 includes: Augmented reality technology is used to parse structured data and unstructured data from the current construction data, and the structured data and the unstructured data are mapped to the physical space of the construction site to obtain a preliminary three-dimensional environment representation; based on the preliminary three-dimensional environment representation, each physical element in the construction site is spatially positioned and attributed, a spatial relationship network between the physical elements is established, and a three-dimensional environment representation with location information is generated; the grid density of each area in the three-dimensional environment representation with location information is dynamically adjusted according to a preset threshold to obtain an optimal three-dimensional environment representation; entity features in the optimal three-dimensional environment representation are extracted, an initial three-dimensional digital twin model is constructed based on the entity features, and the three-dimensional digital twin model is updated in combination with historical construction data and the current construction data to generate an enhanced three-dimensional digital twin model.

[0042] In this embodiment, augmented reality (AR) technology is used to parse structured data (such as sensor readings, GPS coordinates, etc.) and unstructured data (such as images, video streams) in the current construction data. These data come from various on-site devices, such as temperature and humidity sensors, high-definition images taken by drones, smart watches worn by workers, etc. Through AR technology, these data can be mapped to the physical space of the construction site in real time to form a preliminary three-dimensional environmental representation. This preliminary model not only includes physical elements such as buildings, equipment, and material stacking areas, but also can intuitively display their spatial distribution and state changes, providing a basis for subsequent refined modeling. Geographic Information System (GIS) is used to accurately locate each physical element in the preliminary three-dimensional environmental representation and add its specific attributes, such as building material type, equipment model, stacking area capacity, etc. The GIS system can establish a spatial relationship network between each physical element to describe the interaction and dependency between them. For example, the location of a crane may directly affect the safe distance of the nearby material stacking area; the capacity limit of a warehouse determines the choice of material transportation route. In this way, the generated three-dimensional environmental representation not only has accurate location information, but also reflects the overall layout and dynamic characteristics of the construction site. Adaptive meshing algorithm is a technology that can automatically adjust the mesh density according to preset rules. It sets different mesh density thresholds according to the importance and complexity of different areas. For critical construction areas (such as underground foundation engineering, steel structure installation areas) and high-complexity areas (such as areas with frequent cross-operations), higher mesh density is used to capture more details; while for non-critical construction areas (such as ordinary wall painting areas) and low-complexity areas, low mesh density is maintained to simplify the model and increase processing speed. This dynamic adjustment ensures that the model can reflect both the macro layout and the micro details, improving the overall accuracy and practicality. Computer vision algorithms are used to identify and extract objects with specific geometric shapes and attributes in a refined three-dimensional environment, such as walls, columns, doors and windows. These physical features are not only the basic units that make up a building, but also key indicators for evaluating construction progress and quality. Through computer vision algorithms, these features can be accurately extracted from complex three-dimensional environments and integrated into the three-dimensional digital twin model. In addition, the model will combine historical construction data with current construction data acquired in real time, and continuously update to reflect the latest construction progress and changes to ensure that the model is always consistent with the actual situation.

[0043] In the embodiment of the present application, first, the structured and unstructured data in the current construction data are parsed using augmented reality technology, and mapped to the physical space of the construction site to form a preliminary three-dimensional environment representation. Then, the various physical elements in the preliminary model are spatially positioned and attributed through the geographic information system, and a spatial relationship network between them is established to generate a three-dimensional environment representation with precise location information. Then, an adaptive meshing algorithm is applied to dynamically adjust the grid density according to the importance and complexity of different regions to obtain a refined three-dimensional environment representation. Finally, a computer vision algorithm is used to identify and extract entity features, generate a three-dimensional digital twin model, and continuously update it in combination with historical and real-time data to ensure the real-time and accuracy of the model. This process not only improves the refinement and practicality of the model, but also enhances the intelligent level of construction site management.

[0044] Here is a specific example: In a large-scale commercial complex construction project, the construction team needed to build an accurate 3D digital twin model to assist in daily management and decision-making.

[0045] First, the construction team deployed a series of sensors and data collection equipment to cover the entire construction site. These devices transmit data to the central control system once a minute. After preliminary aggregation and filtering, the system can instantly obtain key information such as temperature and humidity changes inside and outside the building, the working status of mechanical equipment, and material transportation routes. Through augmented reality technology, these data are mapped to the physical space of the construction site in real time, forming a preliminary three-dimensional environmental representation.

[0046] Secondly, using the geographic information system (GIS), the construction team precisely located each physical element in the preliminary 3D environmental representation and added its specific attributes, such as the type of building materials, equipment model, etc. The GIS system established a spatial relationship network between the various physical elements, allowing managers to view specific information at any location through a tablet. For example, the location of a crane may affect the safe distance of nearby material storage areas, while the capacity limit of a warehouse determines the choice of material transportation routes.

[0047] Next, to further refine the model, the construction team applied an adaptive meshing algorithm. Based on the pre-established importance assessment model, they identified key construction areas (such as underground foundation engineering, steel structure installation areas) and high-complexity areas (such as areas with frequent cross-operations), and used a higher mesh density for these areas. For non-critical construction areas (such as ordinary wall painting areas) and low-complexity areas, a lower mesh density was maintained. This step ensured that the model could reflect both the macro layout and the micro details, significantly improving accuracy.

[0048] Finally, the construction team used computer vision algorithms to identify and extract entity features from the refined 3D environment representation, generating a 3D digital twin model containing entity features such as walls, columns, doors and windows. The model combines historical construction data with current construction data acquired in real time, enabling continuous updates to ensure that it is always consistent with the actual situation. Project managers can now view it through a dedicated mobile app.

[0049] In order to solve the differences in importance and complexity of different construction areas, in some embodiments, the step 102 dynamically adjusts the grid density of each area in the three-dimensional environment representation with location information according to a preset threshold to obtain the optimal three-dimensional environment representation, including: Using a pre-trained importance assessment model, the importance of each area in the three-dimensional environment representation with location information is evaluated to identify key construction areas and non-key construction areas, and a regional importance distribution map is generated based on the identified key construction areas and non-key construction areas; based on the regional importance distribution map, in combination with the spatial relationship network provided by the geographic information system, the complexity of each construction area is analyzed to identify areas with a complexity greater than a preset complexity and areas with a complexity less than a preset complexity, and a regional complexity analysis result is generated based on the areas with a complexity greater than a preset complexity and areas with a complexity less than a preset complexity; based on the regional complexity analysis result, different grid density thresholds are set, a first grid density is used for key construction areas and areas with a complexity greater than a preset complexity, and a second grid density is used for non-key construction areas and areas with a complexity less than a preset complexity, and a grid density configuration scheme is generated based on the first grid density and the second grid density; the three-dimensional environment representation with location information is optimized according to the grid density configuration scheme to obtain an optimal three-dimensional environment representation.

[0050] In this embodiment, the importance assessment model is a tool based on machine learning or expert system for analyzing the importance of each construction area. These data include but are not limited to key parts of the building structure (such as foundations, load-bearing walls), equipment concentration areas, material storage areas, and personnel-intensive areas. By comprehensively considering these factors, the model can identify which areas have a decisive impact on the overall construction progress and quality, thereby distinguishing key construction areas from non-key construction areas, and generating a regional importance distribution map. This map not only helps managers intuitively understand the site layout, but also provides a basis for subsequent resource allocation. The spatial relationship network refers to the topological connection and interaction pattern between various physical elements constructed by the GIS system. By jointly analyzing the regional importance distribution map and the spatial relationship network, a deeper understanding of the internal structure of each area and its interaction with other areas can be obtained. For example, some areas may appear more complex because they contain multiple different types of tasks; other areas may be single task concentration areas, which are relatively simple. Through this analysis, high-complexity areas (such as cross-operation areas) and low-complexity areas (such as ordinary ground paving areas) can be accurately identified, and detailed regional complexity analysis results can be generated. This step ensures the accuracy and rationality of the meshing and avoids unnecessary waste of computing resources. The mesh density threshold is a parameter set according to the importance and complexity of different areas, which is used to guide the work of the adaptive meshing algorithm. Specifically, for those areas that are both critical and complex (such as underground foundation engineering and steel structure installation areas), a higher mesh density (first mesh density) will be used to ensure that the model can capture every detail; while for those relatively less important and simple areas (such as ordinary wall painting areas), a lower mesh density (second mesh density) will be used to simplify the model and increase the processing speed. The generated mesh density configuration scheme specifies in detail the mesh density that should be used in each area, ensuring that the meshing of the entire construction site is both fine and efficient. The adaptive meshing algorithm is a technology that can automatically adjust the mesh density according to preset rules. It will perform different degrees of refinement on different areas based on the previously generated mesh density configuration scheme while maintaining global consistency. The resulting refined three-dimensional environmental representation not only reflects the overall layout of the entire construction site at the macro level, but also shows the specific characteristics of each critical and complex area at the micro level, allowing managers to monitor and manage on-site work in real time through virtual models.

[0051] In an embodiment of the present application, first, a pre-established importance assessment model is used to evaluate the importance of each area in the three-dimensional environment representation with precise location information, and a regional importance distribution map is generated. Then, combined with the spatial relationship network provided by the geographic information system, the complexity of each area is further analyzed to generate a regional complexity analysis result. Then, different grid density thresholds are set according to the above analysis results, and a grid density configuration scheme is formulated. Finally, an adaptive grid division algorithm is applied to refine the three-dimensional environment representation according to this configuration scheme to ensure that key construction areas and high-complexity areas have higher resolution, while non-key construction areas and low-complexity areas remain appropriately simplified. This process not only improves the accuracy and practicality of the model, but also optimizes the efficiency of computing resource utilization.

[0052] Here is a specific example: In a high-rise residential construction project, the construction team needed to build an accurate three-dimensional digital twin model to assist in daily management and decision-making. First, they used the importance assessment model to conduct a comprehensive scan of the entire construction site, identifying key construction areas such as foundation construction areas, steel structure installation areas, and electromechanical equipment installation areas, as well as other non-critical areas such as ordinary wall painting areas, and generated a clear regional importance distribution map. Next, combined with the spatial relationship network provided by the GIS system, the complexity of each area was analyzed, and it was found that areas with frequent cross-operations (such as basements) belonged to high-complexity areas, while simple wall painting areas were low-complexity areas, forming a detailed regional complexity analysis result.

[0053] Based on these analysis results, the construction team set two sets of grid density thresholds: a higher first grid density was used for key construction areas and high-complexity areas to ensure that the model can capture every subtle change; and a lower second grid density was used for non-key construction areas and low-complexity areas to simplify the model and speed up processing. Finally, the adaptive meshing algorithm was applied to refine the three-dimensional environment representation according to the formulated grid density configuration scheme. The generated refined three-dimensional environment representation not only shows the macro layout of the entire construction site, but also reflects the specific characteristics of key areas in detail, such as the location of each steel bar, the status of each equipment, etc. In this way, project managers can arrange daily work tasks more accurately and respond to potential problems in a timely manner, significantly improving the overall management level and construction efficiency of the project.

[0054] In order to solve the optimization problem of the construction activity path and resource allocation plan, and further improve the construction efficiency and the ability to cope with changes in meteorological conditions, in some embodiments, the three-dimensional digital twin model in step 103 is used to predict the optimal path and resource allocation plan of the construction activities at the construction site according to the meteorological trend obtained in the future period, and a personalized construction guidance plan is generated according to the prediction results, including: The three-dimensional digital twin model is used to extract the status information and resource distribution of the construction site, and a construction status snapshot is generated according to the extracted status information and resource distribution, wherein the status information includes the current progress of the building, the location and status of the equipment, and the stacking location of the materials; the resource distribution includes equipment availability and the working hours of the workers; weather data for a period of time in the future is acquired and analyzed, the impact of different weather conditions on the construction efficiency of the construction site in the analysis results is evaluated, and a meteorological impact assessment report is generated; based on the actual restrictions in the meteorological impact assessment report and the construction status snapshot, an optimization problem model including multiple variables is constructed to form a constraint set, the actual restrictions include equipment availability and the working hours of the workers, and the multiple variables include time, location, and resource type; the optimization problem model is solved, and a preliminary construction guidance plan is generated on the premise that all the constraints in the constraint set are met; the preliminary construction guidance plan is multi-objective optimized to obtain an optimized construction guidance plan; the optimized construction guidance plan is adjusted in combination with preset personalized needs to generate a personalized construction guidance plan.

[0055] In this embodiment, the 3D digital twin model is not only a static virtual copy, but also reflects various dynamic information of the construction site in real time. The construction status snapshot is a series of key data points extracted from the model, including the current progress of the building (such as completed floors, remaining workload), the location and status of the equipment (such as whether the crane is working, the oil level of the excavator), and the material stacking location (such as the storage of steel bars and concrete). In this way, managers can get a comprehensive and up-to-date overview of the construction site, providing a basis for subsequent analysis and decision-making.

[0056] In the embodiment of the present application, the meteorological data is derived from a professional weather forecast service or a weather station installed on site, covering multiple parameters such as temperature, humidity, wind speed, and rainfall. Through in-depth analysis of these data, the specific impact of different weather conditions on construction efficiency can be evaluated. For example, strong winds may cause the suspension of high-altitude operations; heavy rain may make the ground slippery and increase the risk of transporting materials. Based on these analysis results, the generated meteorological impact assessment report can help the construction team plan in advance and reduce the negative impact of adverse weather. Practical restrictions include but are not limited to equipment availability (such as a machine that requires regular maintenance), worker working hours (such as statutory working hours restrictions), and site restrictions (such as certain areas can only be constructed during specific time periods). Multiple variables involve time (such as construction schedule), location (such as the specific location of task execution), and resource type (such as the required human and material resources). By taking these factors into consideration, a complex optimization problem model is constructed and a strict set of constraints is formed. This step ensures that the generated solution not only conforms to the actual situation, but also maximizes the satisfaction of various constraints. The mixed integer linear programming algorithm is a mathematical modeling tool for solving multi-objective optimization problems. It can find the optimal solution in a complex problem space, even if there are a large number of variables and constraints. By applying the mixed integer linear programming algorithm, a solution with the fastest construction progress, lowest cost or highest resource utilization can be found under the premise of meeting all constraints. The generated preliminary construction guidance plan provides the basis for the next step of multi-objective optimization. Multi-objective optimization refers to further adjusting and improving the plan based on the preliminary plan by comprehensively considering multiple evaluation criteria (such as progress, cost, safety, quality, etc.). This process not only improves the feasibility and adaptability of the plan, but also ensures that it can achieve the best results under different conditions. The final optimized construction guidance plan is closer to actual needs and has higher operability and reliability. Personalized needs refer to customized adjustments to the optimized construction guidance plan based on the special requirements of specific projects or the preferences of the participants. For example, some projects may pay more attention to environmental protection measures, while others emphasize rapid delivery. Through this customization, the final generated personalized construction guidance plan not only meets the technical optimal solution, but also fully considers humanistic and social factors, achieving all-round optimization.

[0057] In the embodiment of the present application, first, the state information and resource distribution of the construction site are extracted and processed using a three-dimensional digital twin model to generate a construction status snapshot. Then, combined with the meteorological trends in the future, the impact of different weather conditions on construction efficiency is evaluated, and a meteorological impact assessment report is generated. Next, based on this report and the actual limitations of the construction status snapshot, an optimization problem model containing multiple variables is constructed, and a set of constraints is formed. Subsequently, a mixed integer linear programming algorithm is applied to solve the model, find the optimal solution, and generate a preliminary construction guidance plan. On this basis, multi-objective optimization is performed to obtain an optimized construction guidance plan. Finally, the plan is customized in combination with personalized needs to generate a personalized construction guidance plan. The whole process ensures that the construction plan is both scientific and reasonable and flexible, significantly improving construction efficiency and resource utilization.

[0058] Here is a specific example: In a large bridge construction project, the construction team needed to develop the optimal construction activity route and resource allocation plan for the next week to cope with the upcoming typhoon season.

[0059] First, the construction team used the 3D digital twin model to extract and process the status information and resource distribution of the construction site, and generated a construction status snapshot. The snapshot showed that the foundation work of the bridge was 60% complete, a major crane would undergo routine maintenance in two days, and the material storage area currently had sufficient reserves of steel bars and concrete.

[0060] Secondly, based on the construction status snapshot, the construction team obtained and analyzed weather data for the next week, especially the changes in typhoon paths and intensities. They found that a strong typhoon might pass through the construction area in three days, causing strong winds and heavy rains. Based on these data, a detailed meteorological impact assessment report was generated, indicating that high-altitude operations must be stopped during strong winds, and heavy rains may cause the ground to be slippery, affecting the operation of heavy machinery.

[0061] Next, based on the actual constraints in the meteorological impact assessment report and the construction status snapshot (such as crane maintenance and worker working hours), the construction team built an optimization problem model with multiple variables (time, location, resource type) and formed a strict set of constraints. For example, it stipulated that all high-altitude work must be completed before strong winds arrive and that all heavy machinery must be parked in a safe area.

[0062] Then, a mixed integer linear programming algorithm was applied to solve the optimization problem model, and a solution with the fastest construction schedule and the lowest cost was found while satisfying all constraints. The generated preliminary construction guidance suggested speeding up the concrete pouring work before the typhoon arrived and moving some materials to the shelter in advance.

[0063] Furthermore, the preliminary construction guidance plan was optimized with multiple objectives, and considering safety and environmental protection requirements, the construction of temporary protection facilities was increased, and noise and dust emissions were reduced. The optimized construction guidance plan not only improved construction efficiency, but also ensured the safety of workers and the environment.

[0064] Finally, the optimized construction guidance plan was customized based on the project's unique needs (such as the owner's desire to complete a key node as soon as possible) to generate a final personalized construction guidance plan. Project managers can now accurately arrange daily work tasks based on this detailed plan and respond to potential problems in a timely manner, significantly improving the overall management level and construction efficiency of the project.

[0065] Through this series of steps, the construction team not only effectively responded to the impending severe weather, but also optimized resource allocation, ensured construction progress and quality, and achieved the goal of refined management.

[0066] In order to solve the optimization problem of the construction activity path and resource allocation plan and further improve the construction efficiency and resource utilization, in some embodiments, the optimization problem model in step 103 is solved, and a preliminary construction guidance plan is generated on the premise that all constraints in the constraint set are satisfied, including: According to the constraint set and multiple variables, an objective function is constructed, and a mixed integer linear programming mathematical model containing decision variable expressions is constructed according to the objective function; based on the actual restrictions in the meteorological impact assessment report and the construction status snapshot, constraints in the constraint set are added to the mixed integer linear programming mathematical model to generate a mixed integer linear programming mathematical model with variable expressions of the constraint-containing mixed integer linear programming model; the mixed integer linear programming model with constraints is iteratively calculated and solved by a solver, and on the basis of satisfying all constraints in the constraint set, an optimal solution that satisfies the requirements of improving construction progress and improving resource utilization is identified; the optimal solution is used to perform feasibility verification to check whether it meets construction safety standards, quality control and other key performance indicators, and a verified solution is generated, wherein the other key performance indicators include resource utilization, environmental protection and cost control; based on the verified solution, a preliminary construction guidance plan is generated, and the preliminary construction guidance plan includes a schedule, location arrangement and resource allocation plan for specific construction tasks.

[0067] In this embodiment, mixed integer linear programming is a powerful mathematical modeling tool for solving multi-objective optimization problems. It constructs an objective function by defining a series of decision variables (such as time scheduling, location selection, and resource type), aiming to maximize construction efficiency or minimize costs. These variables are derived from the construction status snapshot and the meteorological impact assessment report, covering multiple dimensions such as time, location, and resource type. The constructed objective function not only takes into account key indicators such as construction progress and cost control, but also combines actual constraints (such as equipment availability and worker working hours) to ensure that the model can reflect the real construction environment. Constraints refer to actual restrictions that must be followed, such as equipment maintenance cycles, workers' statutory working hours, and site safety requirements. These conditions come directly from the construction status snapshot and the meteorological impact assessment report, ensuring the feasibility and practicality of the model. By adding these constraints to the mixed integer linear programming mathematical model, a more accurate mixed integer linear programming model with constraints is generated. This step enables the solver to find the optimal solution under the premise of meeting all actual constraints, improving the operability of the solution. The solver is a software tool specifically used to solve complex optimization problems. It uses iterative calculation methods to continuously adjust decision variables and find solutions that make the objective function reach the optimal value under the premise of satisfying all constraints. In the solution process, not only the fastest construction progress is considered, but also the minimization of costs and the maximization of resource utilization. The optimal solution or feasible solution close to the optimal solution finally obtained not only meets the actual construction needs, but also significantly improves the overall benefits of the project. Feasibility verification is an important step to ensure that the generated solution can be smoothly implemented in actual construction. The verification process includes checking whether the solution meets construction safety standards (such as safety measures for high-altitude operations), quality control (such as quality inspection of materials), and other key performance indicators (KPIs), such as resource utilization, environmental protection, and cost control. Through this verification process, solutions that are theoretically optimal but not feasible in actual operation can be excluded, ensuring that the final generated solution is both scientific and reasonable and highly operational. The verified solution will be converted into a specific construction task schedule, location arrangement, and resource allocation plan. These plans specify the specific tasks, execution time, and required resources for each construction stage in detail, providing clear operating guidelines for on-site managers. The preliminary construction guidance plan not only helps the construction team to efficiently arrange daily work tasks, but also supports real-time monitoring and dynamic adjustments to ensure that the project proceeds as planned.

[0068] In the embodiment of the present application, first, according to the constraint set and multiple variables, the objective function is constructed using the mixed integer linear programming mathematical modeling method to obtain a mathematical model containing the decision variable expression. Then, based on the actual restrictions in the meteorological impact assessment report and the construction status snapshot, constraints are added to the model to generate a mixed integer linear programming model with constraints. Then, the solver is applied to iteratively calculate and solve the model to find the optimal solution or a feasible solution close to the optimal solution. Subsequently, the feasibility of these solutions is verified to ensure that they meet the construction safety standards, quality control and other key performance indicators. Finally, based on the verified solution, the timetable, location arrangement and resource allocation plan of the specific construction tasks are generated to form a preliminary construction guidance plan. The whole process ensures the scientificity, rationality and operability of the construction plan, and significantly improves the construction efficiency and resource utilization.

[0069] Here is a specific example: In a large bridge construction project, the construction team needed to develop the optimal construction activity route and resource allocation plan for the next week to cope with the upcoming typhoon season.

[0070] First, the construction team used a mixed integer linear programming mathematical modeling method to construct an objective function based on a set of constraints (such as equipment availability and worker working hours) and multiple variables (such as time, location, and resource type). This objective function aims to maximize construction progress and minimize costs, covering all construction links from steel bar tying to concrete pouring.

[0071] Secondly, based on the meteorological impact assessment report (a strong typhoon is predicted to pass in three days) and the construction status snapshot (60% of the bridge foundation is completed and the main crane needs maintenance in two days), the construction team added strict constraints to the mixed integer linear programming mathematical model and generated a mixed integer linear programming model with restrictions. These constraints ensure that all construction arrangements are within the safety and legal range.

[0072] Next, the solver was applied to iteratively solve the mixed integer linear programming model with constraints. The solver found a solution that has the fastest construction schedule, the lowest cost and the highest resource utilization, while satisfying all constraints. The solution suggested speeding up the concrete pouring before the typhoon arrives and moving some materials to the shelter in advance.

[0073] Furthermore, the construction team verified the feasibility of this optimal solution, checking whether it met the construction safety standards (such as protective measures for high-altitude operations), quality control (such as concrete strength testing), and key performance indicators (such as resource utilization, environmental protection, and cost control). After verification, it was confirmed that the solution was completely feasible in actual operation.

[0074] Finally, based on the verified solution, the construction team generated a schedule, location arrangement and resource allocation plan for specific construction tasks. This detailed preliminary construction guidance plan includes a daily task list, specific execution time and required resources, ensuring that the construction team can efficiently arrange daily work tasks and respond to potential problems in a timely manner.

[0075] Through this series of steps, the construction team not only effectively coped with the upcoming severe weather, but also optimized resource allocation, ensured construction progress and quality, and achieved the goal of refined management. Project managers can now accurately arrange daily work tasks based on this detailed plan and respond to potential problems in a timely manner, significantly improving the overall management level and construction efficiency of the project.

[0076] In order to solve the optimization problem of the construction activity path and resource allocation plan and further improve the solution efficiency and solution quality, in some embodiments, the use of the solver in step 103 performs iterative calculation and solution on the mixed integer linear programming model with constraints, and confirms the optimal solution that satisfies the improvement of construction progress and resource utilization on the basis of satisfying all constraints in the constraint set, including: Initialize the solver and set initial parameters and solution strategy to obtain a solution environment; according to the solution environment, start the solver to iteratively calculate the mixed integer linear programming model with constraints, generate a preliminary solution, and record the objective function value of the preliminary solution; based on the objective function value, use a heuristic algorithm to iteratively optimize the solution path in the solution environment until an intermediate solution that meets all constraints and has an objective function value better than the existing objective function value is confirmed, save the intermediate solution and the corresponding objective function value as a candidate solution; and confirm the optimal solution based on the candidate solutions.

[0077] In this embodiment, the solution environment refers to a series of configurations and settings required before the solver starts working. Initializing the solver involves selecting a suitable algorithm (such as branch and bound method, cutting plane method) and setting initial parameters (such as maximum number of iterations, tolerance range), which directly affect the speed and accuracy of the solution process. The solution strategy determines how to deal with complex constraints and multi-objective optimization problems, such as whether to give priority to construction progress or cost control. By carefully designing the solution environment, it can be ensured that the solver can find high-quality solutions within a reasonable computing time. The first iteration calculation is the first step in the solution process, which aims to quickly generate a preliminary solution as a reference point. Although this preliminary solution may not be the optimal solution, it provides a benchmark to help subsequent iterations gradually improve. The objective function value reflects the quality of the current solution, usually expressed in numerical form, such as the speed of construction progress, the high or low cost, etc. Recording these values ​​helps to track the progress of the solution and provide basic data for the heuristic algorithm. The heuristic algorithm is a technique used to guide the search direction of the solver, which can help the solver avoid falling into a local optimal solution and thus approach the global optimal solution faster. After each iteration, the heuristic algorithm analyzes the objective function value of the current solution and adjusts the solution path to ensure that the next iteration can produce better results. This process continues until a new solution is found that satisfies all constraints and has a better objective function value. The new solution and its corresponding objective function value will be saved as a candidate solution for final selection. The preset stopping condition refers to the standard for the end of the solution process, such as reaching the maximum number of iterations, the change in the objective function value is less than a certain threshold, or a sufficient number of high-quality candidate solutions are found. When these conditions are met, the solver will select the optimal solution or the feasible solution that is closest to the optimal solution from all candidate solutions. This step ensures that the final solution generated not only meets the actual construction needs, but also significantly improves the overall benefits of the project.

[0078] In the embodiment of the present application, the solver is first initialized using a mixed integer linear programming model with constraints, initial parameters and solution strategies are set, and a solution environment is constructed. Then, the solver is started for the first iterative calculation, a preliminary solution is generated, and the objective function value is recorded. Next, based on the objective function value, a heuristic algorithm is used to optimize the solution path to ensure that each iteration can produce better results and gradually update the solution. Whenever a new solution that satisfies all constraints and whose objective function value is better than the previously recorded value is found, it is saved as a candidate solution. Finally, the iteration is continued until the preset stop condition is reached, and the optimal solution or the feasible solution closest to the optimal solution is selected from all candidate solutions. The whole process ensures the efficiency of the solution and the quality of the solution, and significantly improves the scientificity and rationality of the construction plan.

[0079] Here is a specific example: In a large bridge construction project, the construction team needed to develop the optimal construction activity route and resource allocation plan for the next week to cope with the upcoming typhoon season.

[0080] First, the construction team built a mixed integer linear programming model with constraints based on the meteorological impact assessment report (a strong typhoon was predicted to pass in three days) and the construction status snapshot (60% of the bridge foundation work was completed and the main crane needed maintenance in two days). They chose the branch and bound method as the solution algorithm and set the maximum number of iterations to 50 and the tolerance range to 0.01%. In addition, a solution strategy was developed to prioritize construction progress and safety standards. With these settings, the solution environment was initialized.

[0081] Secondly, based on the above solution environment, the mixed integer linear programming solver was started for the first iteration. The solver quickly generated a preliminary solution, suggesting that the concrete pouring work should be accelerated in the next two days and some materials should be transferred to the safe haven in advance. At the same time, the objective function value of this preliminary solution was recorded to reflect its construction progress and cost.

[0082] Next, based on the objective function value of the first iteration, the construction team uses a heuristic algorithm to optimize the solution path. The heuristic algorithm analyzes the strengths and weaknesses of the current solution and adjusts the solution path to ensure that the next iteration can produce better results. For example, it may increase the scheduling weight of certain critical tasks and reduce the time of non-critical tasks. With each iteration, the solver gradually updates the solution, constantly looking for a new solution that meets all constraints and has a better objective function value. Whenever such a new solution is found, it is saved as a candidate solution and the new objective function value is recorded.

[0083] Furthermore, in the continuous iteration process, the solver continuously optimizes the construction plan until the preset stop condition is reached, that is, the maximum number of iterations is 50 or the change in the objective function value is less than 0.01%. At this point, the construction team selects the optimal solution or the feasible solution closest to the optimal solution from all candidate solutions. This final solution not only takes into account the construction progress and cost control, but also ensures construction safety and quality standards.

[0084] Finally, based on the selected optimal solution, the construction team generated a schedule, location arrangement, and resource allocation plan for specific construction tasks. This detailed preliminary construction guidance plan specifies the specific tasks, execution time, and required resources for each construction phase, ensuring that the construction team can efficiently arrange daily work tasks and respond to potential problems in a timely manner.

[0085] Through this series of steps, the construction team not only effectively coped with the upcoming severe weather, but also optimized resource allocation, ensured construction progress and quality, and achieved the goal of refined management. Project managers can now accurately arrange daily work tasks based on this detailed plan and respond to potential problems in a timely manner, significantly improving the overall management level and construction efficiency of the project.

[0086] This approach not only improves the scientificity and rationality of the construction plan, but also ensures that the project can proceed smoothly in a complex and changing environment, minimizes the impact of adverse factors, and improves overall construction efficiency and resource utilization.

[0087] In order to solve the security issues of optimized configuration of construction tasks and operation records, and further improve the transparency and collaboration efficiency of construction management, in some embodiments, the step 104 optimizes the personalized construction guidance plan, records each operation step in the optimized personalized construction guidance plan, generates operation instructions and synchronizes them to the mobile devices of the relevant parties on site, including: The construction tasks of the construction site are optimized by utilizing the actual constraints and preset priority requirements in the personalized construction guidance plan and the construction status snapshot to obtain an optimized personalized construction guidance plan, wherein the actual constraints include equipment availability and worker working hours, and the priority requirements are based on the urgency and critical path of the project; a unique identifier is assigned to each construction task in the optimized personalized construction guidance plan, and an operation instruction set is generated according to the assignment result, wherein the unique identifier is used to track and manage each construction task; and the operation instruction set is sent to mobile devices of relevant parties at the construction site through a mobile application platform.

[0088] In this embodiment, the personalized construction guidance plan is a preliminary plan generated based on data such as a three-dimensional digital twin model and a meteorological impact assessment report. To ensure its feasibility, the construction tasks need to be optimized in combination with the actual constraints in the construction status snapshot (such as equipment availability, worker working hours) and project priority requirements (such as urgency and critical path). The optimization process not only takes into account the time schedule and technical requirements, but also fully considers the reasonable allocation of human resources and equipment resources to ensure that each task can be performed under the most appropriate conditions. The operation instruction set is a series of detailed construction guidelines that cover the specific execution steps, required resources and precautions for each task. To ensure the accuracy of tracking and management, each construction task is assigned a unique identifier. This identifier serves as an identity tag for the task throughout the construction process, and plays an important role in both operation records and subsequent quality inspections. The generation of the operation instruction set ensures that all construction personnel can obtain consistent and clear operation instructions, reducing the possibility of misunderstandings and errors. Blockchain technology is used to record each step of the operation instruction set to ensure that these records cannot be tampered with and are transparent and traceable. Blockchain is a distributed ledger technology that ensures the authenticity and integrity of data through encryption algorithms. After each operation is completed, the relevant information will be packaged into blocks and added to the chain, forming a continuous and unchangeable record chain. This mechanism not only improves the security and reliability of data, but also enhances trust between all parties and promotes information sharing and collaboration. The mobile application platform is an important tool to connect all relevant parties on the construction site. It is responsible for combining the operation instruction set with the blockchain record and synchronizing it to the mobile device of each construction worker. In this way, each participant can receive the latest construction guidance in real time and feedback the task completion status or problems encountered based on the actual situation. In this way, not only the communication efficiency is improved, but also the timely update and accurate transmission of all information are ensured, and the whole process of construction process is monitored and dynamically adjusted.

[0089] In the embodiment of the present application, the personalized construction guidance plan is first used to optimize the construction tasks in combination with the actual restrictions and priority requirements in the construction status snapshot, and an optimized construction guidance plan is generated. Then, based on the optimized construction guidance plan, an operation instruction set containing a clear operation guide is constructed, and a unique identifier is assigned to each construction task. Next, blockchain technology is applied to record each step of the operation instruction set, and a blockchain record that cannot be tampered with and is transparent and traceable is generated. Finally, the operation instruction set is combined with the blockchain record, and synchronized to the mobile devices of the relevant parties at the construction site through the mobile application platform, supporting real-time feedback of task completion and problems encountered. The whole process ensures the efficient execution of construction tasks and the security and reliability of data, and significantly improves the transparency and collaboration efficiency of construction management.

[0090] Here is a specific example: In a large-scale commercial complex construction project, the construction team needs to ensure that daily task arrangements are both scientific and reasonable, and flexible to cope with the ever-changing construction environment and emergencies.

[0091] First, the construction team generated a personalized construction guidance plan based on the previous 3D digital twin model, meteorological impact assessment report and other data. This plan takes into account the weather forecast for the next few days, the current construction progress and the distribution of resources. To ensure its feasibility, the construction team optimized the construction tasks based on the actual limitations in the construction status snapshot (such as a crane needs maintenance, some workers are about to end their statutory working hours) and the priority requirements of the project (such as construction in certain areas must be completed within a specific time). Finally, an optimized construction guidance plan was obtained, which detailed the specific arrangements for each task.

[0092] Secondly, based on the optimized construction guidance plan, the construction team built an operation instruction set with clear operation guidelines. Each construction task is assigned a unique identifier for tracking and management. For example, the unique identifier of the concrete pouring task is "C-001" and the unique identifier of the steel bar tying task is "F-002". These identifiers ensure that each task can be traced throughout the construction process, which is convenient for subsequent quality inspection and responsibility tracing.

[0093] Next, the construction team applied blockchain technology to record each step of the operation instruction set, generating a blockchain record that cannot be tampered with, is transparent and traceable. Whenever a task is completed or a problem is encountered, the relevant information will be packaged into blocks and added to the chain. For example, when the concrete pouring task is completed, the construction workers will upload photos or videos through their mobile devices as proof of completion, and this information will be recorded in the blockchain to ensure authenticity.

[0094] Finally, the construction team combined the operating instruction set with the blockchain records and synchronized them to the mobile devices of all relevant parties at the construction site through a dedicated mobile application platform. Each construction worker can receive the latest construction instructions in real time and provide feedback on the completion of the task or the problems encountered based on the actual situation. For example, if a task encounters unexpected difficulties, the construction worker can report the specific situation through the application, and the project manager can immediately view and make corresponding adjustments. In addition, the mobile application platform also provides real-time communication functions, which promotes close collaboration between all parties and ensures that the project proceeds smoothly as planned.

[0095] Through this series of steps, the construction team not only effectively optimized the arrangement of construction tasks, but also ensured the security and reliability of operation records. Project managers can now accurately arrange daily work tasks based on this detailed plan and respond to potential problems in a timely manner, significantly improving the overall management level and construction efficiency of the project. This method not only improves the transparency and collaboration efficiency of construction management, but also ensures that the project can proceed smoothly in a complex and changing environment, minimizes the impact of adverse factors, and improves the overall construction quality and resource utilization.

[0096] This approach not only improves the transparency and collaboration efficiency of construction management, but also ensures that the project can proceed smoothly in a complex and changing environment, minimizes the impact of adverse factors, and improves the overall construction quality and resource utilization. Through the real-time feedback mechanism, the construction team can respond to problems quickly to ensure that the construction progress is not delayed while maintaining high quality standards. Figure 2 A structural diagram of a data processing system for intelligent building construction is provided for an embodiment of the present application. Figure 2 As shown, the system includes: Aggregation and filtering module 21, used to perform preliminary aggregation and filtering on multi-source heterogeneous data streams at the construction site to obtain current construction data; A construction module 22, used to construct a three-dimensional digital twin model according to the current construction data; A prediction module 23 is used to use the three-dimensional digital twin model to predict the optimal path and resource allocation plan of the construction activities at the construction site according to the meteorological trend in the future, and generate a personalized construction guidance plan according to the prediction results; The synchronization module 24 is used to optimize the personalized construction guidance plan, record each operation step in the optimized personalized construction guidance plan, generate operation instructions and synchronize them to the mobile devices of the relevant parties on site.

[0097] Figure 2 The data processing system for intelligent building construction can perform Figure 1 The implementation principle and technical effect of the data processing method for intelligent building construction described in the embodiment are not described in detail. The specific way in which each module and unit performs operations in the data processing system for intelligent building construction in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0098] In one possible design, Figure 2 The data processing system for intelligent building construction of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0099] The processing component 32 is used for the above Figure 1 The data processing method of the intelligent building construction in the embodiment.

[0100] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0101] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0102] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0103] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0104] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0105] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0106] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 XX method of the illustrated embodiment.

[0107] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0108] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data processing method for intelligent building construction, characterized in that: include: Perform preliminary aggregation and filtering of multi-source heterogeneous data streams at the construction site to obtain current construction data; Constructing a three-dimensional digital twin model according to the current construction data, wherein the three-dimensional digital twin model generates a basic model through multi-source data fusion and spatial mapping, and is formed by dynamic grid optimization and continuous data iteration after establishing a spatial relationship network of physical elements; Using the three-dimensional digital twin model, based on the acquired meteorological trends in the future, predict the optimal path and resource allocation plan for construction activities at the construction site, and generate a personalized construction guidance plan based on the prediction results; Optimizing the personalized construction guidance plan, recording each operation step in the optimized personalized construction guidance plan, generating operation instructions and synchronizing them to mobile devices of all relevant parties on site; Wherein, constructing a three-dimensional digital twin model according to the current construction data includes: parse structured data and unstructured data from the current construction data using augmented reality technology, and map the structured data and the unstructured data to the physical space of the construction site to obtain a preliminary three-dimensional environment representation; Based on the preliminary three-dimensional environment representation, spatially locate and annotate the attributes of various physical elements in the construction site, establish a spatial relationship network between the various physical elements, and generate a three-dimensional environment representation with position information; Dynamically adjusting the grid density of each area in the three-dimensional environment representation with position information according to a preset threshold value to obtain an optimal three-dimensional environment representation; The entity features in the optimal three-dimensional environment representation are extracted, an initial three-dimensional digital twin model is constructed according to the entity features, and the three-dimensional digital twin model is updated in combination with the historical construction data and the current construction data to generate an enhanced three-dimensional digital twin model.

2. The method according to claim 1, characterized in that Dynamically adjusting the grid density of each area in the three-dimensional environment representation with position information according to a preset threshold to obtain an optimal three-dimensional environment representation, including: Using a pre-trained importance assessment model, assess the importance of each area in the three-dimensional environment representation with location information to identify key construction areas and non-key construction areas, and generate a regional importance distribution map based on the key construction areas and the non-key construction areas; According to the regional importance distribution map, combined with the spatial relationship network provided by the geographic information system, the complexity of each construction area is analyzed to identify areas with greater than a preset complexity and areas with less than a preset complexity, and regional complexity analysis results are generated based on the areas with greater than a preset complexity and areas with less than a preset complexity; Based on the regional complexity analysis result, different grid density thresholds are set, a first grid density is used for key construction areas and areas with a complexity greater than a preset value, and a second grid density is used for non-key construction areas and areas with a complexity less than a preset value, and a grid density configuration scheme is generated according to the first grid density and the second grid density; The three-dimensional environment representation with position information is optimized according to the grid density configuration scheme to obtain an optimal three-dimensional environment representation.

3. The method according to claim 1, characterized in that The three-dimensional digital twin model is used to predict the optimal path and resource allocation plan for the construction activities at the construction site according to the meteorological trend in the future, and a personalized construction guidance plan is generated according to the prediction results, including: Utilizing the three-dimensional digital twin model, extracting the status information and resource distribution of the construction site, and generating a construction status snapshot based on the extracted status information and resource distribution, wherein the status information includes the current progress of the building, the location and status of the equipment, and the stacking location of the materials; and the resource distribution includes the availability of equipment and the working hours of the workers; Acquire and analyze weather data for a period of time in the future, evaluate the impact of different weather conditions on the construction efficiency of the construction site in the analysis results, and generate a meteorological impact assessment report; Based on the actual constraints in the meteorological impact assessment report and the construction status snapshot, construct an optimization problem model including multiple variables to form a set of constraint conditions, wherein the actual constraints include equipment availability and worker working hours, and the multiple variables include time, location, and resource type; Solving the optimization problem model, and generating a preliminary construction guidance plan on the premise that all constraints in the constraint condition set are satisfied; Performing multi-objective optimization on the preliminary construction guidance plan to obtain an optimized construction guidance plan; In combination with preset personalized needs, the optimized construction guidance scheme is adjusted to generate a personalized construction guidance plan.

4. The method according to claim 3, characterized in that Solve the optimization problem model and generate a preliminary construction guidance plan on the premise that all constraints in the constraint set are satisfied, including: Constructing an objective function according to the constraint condition set and the plurality of variables, and constructing a mixed integer linear programming mathematical model including decision variable expressions according to the objective function; Based on the actual constraints in the meteorological impact assessment report and the construction status snapshot, adding constraints in a constraint set to the mixed integer linear programming mathematical model to generate a mixed integer linear programming model with constraints; Using a solver to iteratively calculate and solve the mixed integer linear programming model with constraints, and on the basis of satisfying all constraints in the constraint set, confirming the optimal solution that satisfies the needs of improving construction progress and resource utilization; Using the optimal solution, conduct feasibility verification to check whether it meets construction safety standards, quality control and other key performance indicators, and generate a verified solution. The other key performance indicators include resource utilization, environmental protection and cost control; Based on the verified solution, a preliminary construction guidance plan is generated, which includes a timetable, location arrangement and resource allocation plan for specific construction tasks.

5. The method according to claim 4, characterized in that The mixed integer linear programming model with constraints is iteratively calculated and solved by a solver, and the optimal solution that satisfies the requirements of improving the construction progress and resource utilization is determined on the basis of satisfying all constraints in the constraint set, including: Initialize the solver and set the initial parameters and solution strategy to obtain the solution environment; According to the solution environment, starting a solver to perform iterative calculations on a mixed integer linear programming model with constraints, generating a preliminary solution, and recording an objective function value of the preliminary solution; Based on the objective function value, a solution path in the solution environment is iteratively optimized using a heuristic algorithm until an intermediate solution that satisfies all constraints and has an objective function value better than an existing objective function value is confirmed, and the intermediate solution and the corresponding objective function value are saved as a candidate solution; An optimal solution is determined based on the candidate solutions.

6. The method according to claim 1, characterized in that The personalized construction guidance plan is optimized, and each operation step in the optimized personalized construction guidance plan is recorded, and operation instructions are generated and synchronized to the mobile devices of the relevant parties on site, including: Optimizing the construction tasks of the construction site by using the personalized construction guidance plan and actual constraints and preset priority requirements in the construction status snapshot to obtain an optimized personalized construction guidance plan, wherein the actual constraints include equipment availability and worker working hours, and the priority requirements are based on the urgency and critical path of the project; Assigning a unique identifier to each construction task in the optimized personalized construction guidance plan, and generating an operation instruction set according to the assignment result, wherein the unique identifier is used to track and manage each construction task; The operation instruction set is sent to the mobile devices of all relevant parties at the construction site through a mobile application platform.

7. A data processing system for intelligent building construction, characterized in that: include: Aggregation and filtering module, used to perform preliminary aggregation and filtering of multi-source heterogeneous data streams at the construction site to obtain current construction data; A construction module is used to construct a three-dimensional digital twin model according to the current construction data, wherein the three-dimensional digital twin model generates a basic model through multi-source data fusion and spatial mapping, and is formed after a spatial relationship network of physical elements is established through dynamic grid optimization and continuous data iteration; A prediction module is used to use the three-dimensional digital twin model to predict the optimal path and resource allocation plan of the construction activities at the construction site according to the meteorological trend in the future, and generate a personalized construction guidance plan according to the prediction results; A synchronization module is used to optimize the personalized construction guidance plan, record each operation step in the optimized personalized construction guidance plan, generate operation instructions and synchronize them to the mobile devices of all relevant parties on site; Wherein, the building block is also used for: parse structured data and unstructured data from the current construction data using augmented reality technology, and map the structured data and the unstructured data to the physical space of the construction site to obtain a preliminary three-dimensional environment representation; Based on the preliminary three-dimensional environment representation, spatially locate and annotate the attributes of various physical elements in the construction site, establish a spatial relationship network between the various physical elements, and generate a three-dimensional environment representation with position information; Dynamically adjusting the grid density of each area in the three-dimensional environment representation with position information according to a preset threshold value to obtain an optimal three-dimensional environment representation; The entity features in the optimal three-dimensional environment representation are extracted, an initial three-dimensional digital twin model is constructed according to the entity features, and the three-dimensional digital twin model is updated in combination with the historical construction data and the current construction data to generate an enhanced three-dimensional digital twin model.

8. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a data processing method for intelligent building construction as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a data processing method for intelligent building construction as described in any one of claims 1 to 6 is implemented.

Images