Building engineering progress intelligent monitoring method

Abstract

The invention relates to a building engineering progress intelligent monitoring method. According to the method, a building space is divided into area units for fine management, a progress deviation analysis result is generated in combination with a construction plan and field data collected in real time, a deviation value is dynamically mapped to a three-dimensional building model to realize visual monitoring, and meanwhile, resource allocation data is associated to perform spatial clustering and optimization adjustment, so that the construction efficiency is improved. The problem that in a traditional method, progress monitoring and resource allocation are disjointed in the spatial dimension is solved, accurate correlation analysis and closed-loop optimization of the progress and resource dynamics of the constructional engineering are achieved, and the real-time performance and decision-making scientificity of construction management are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of construction project progress management, and in particular relates to an intelligent construction project progress monitoring method. Background Art

[0002] In the field of construction project progress management, traditional methods mainly rely on manual inspection records and two-dimensional charts to track progress, which makes it difficult to reflect the spatial distribution characteristics of the construction status in real time.

[0003] In existing technologies, the comparison between construction plans and actual on-site progress usually remains at the overall project level, and it is impossible to conduct detailed monitoring of different area units within the building. As a result, the root cause of progress deviations (such as material shortages in specific areas or equipment scheduling delays) is difficult to accurately locate.

[0004] Furthermore, progress data lacks effective correlation with 3D building models and resource allocation information. The spatial location of construction delays and imbalances in resource allocation cannot be visually represented, forcing managers to rely on empirical judgment to adjust resources, which can lead to delayed decisions and wasteful resources. As building scale and construction complexity increase, traditional 2D charts are no longer sufficient for the dynamic management of multi-task collaboration and multi-regional parallelism. This is especially true for spatially dependent processes like concrete pouring and steel structure installation. The lack of technical means to map progress deviations to 3D models makes it difficult to quantify the correlation between resource allocation and spatial progress.

[0005] Therefore, how to achieve spatial modeling of progress data, real-time deviation analysis, and closed-loop feedback for resource optimization has become a key challenge in improving the efficiency of construction project progress management. Summary of the Invention

[0006] Based on this, it is necessary to provide an intelligent monitoring method for construction project progress to address the above technical issues.

[0007] In a first aspect, the present application provides a method for intelligently monitoring the progress of a construction project, comprising:

[0008] S1. Based on the architectural design drawing data, the building space is segmented using a grid division algorithm to generate a regional unit management data set;

[0009] S2. Perform time series analysis on the process time series and regional unit management data sets in the construction plan to generate a regional progress plan data set;

[0010] S3. Based on the regional unit management data set, the construction status data is acquired through on-site data acquisition equipment and fused and processed to generate the actual progress data set;

[0011] S4. Calculate the deviation between the regional schedule data set and the actual schedule data set to generate a schedule deviation data set;

[0012] S5. Based on the progress deviation dataset and the BIM model, the 3D model is updated through the data mapping algorithm to generate a 3D visualization dataset;

[0013] S6. Based on the three-dimensional visualization data set and the preset resource allocation data, a resource allocation bottleneck data set is generated through a cluster analysis algorithm;

[0014] S7. Based on the resource allocation bottleneck dataset, perform resource optimization processing through a linear programming algorithm, generate an optimized resource allocation plan, and update the three-dimensional visualization dataset.

[0015] In a second aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements a method for intelligent monitoring of construction project progress as in the first aspect.

[0016] In a third aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for intelligent monitoring of construction project progress as in the first aspect.

[0017] The above-mentioned intelligent monitoring method for construction project progress generates a regional unit management data set by dividing the building space using a grid division algorithm based on architectural design drawings; generates a regional progress plan data set through time series analysis based on the data set and the construction plan; obtains construction status data based on the regional unit management data set and on-site data acquisition equipment and fuses them to generate an actual progress data set; compares the planned and actual progress data sets through a deviation calculation formula to generate a progress deviation data set; combines the deviation data with the BIM model to generate a three-dimensional visualization data set; generates a resource allocation bottleneck data set through cluster analysis based on the three-dimensional data set and resource allocation data; finally, generates a resource optimization plan through a linear programming algorithm and updates the three-dimensional model, forming a closed-loop process from space division, data acquisition, deviation analysis to resource optimization, realizing dynamic monitoring of construction project progress in the three-dimensional spatial dimension and real-time correlation optimization of resource allocation, and solving the systematic defect of the disconnection between progress data and resource management space in traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only 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.

[0019] Figure 1 A schematic diagram of a flow chart of a construction project progress intelligent monitoring method provided by the present invention;

[0020] Figure 2 A schematic diagram of a flow chart of generating a regional unit management data set in an optional embodiment of the present invention;

[0021] Figure 3 The figure is a flow chart of generating a resource allocation bottleneck data set in an optional embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0023] refer to Figure 1 , which presents a flow chart of a construction project progress intelligent monitoring method provided by the present application, the method comprising the following steps:

[0024] S1. Based on the architectural design drawing data, the building space is segmented through the grid division algorithm to generate the regional unit management data set.

[0025] Specifically, in construction projects, architectural design drawings detail key information such as the building's spatial layout, structural design, and the relative positions of various elements. These drawing data provide an accurate blueprint for subsequent construction.

[0026] In the present invention, this rich and accurate drawing data is first used as the basic input, and the entire building space is segmented using a grid partitioning algorithm. The grid partitioning algorithm is widely used in the fields of computer graphics and spatial analysis. Its core principle is to divide the continuous building space into multiple independent and interrelated regional units based on factors such as the building's geometric shape, functional zoning, and construction process. Each regional unit has its own unique attributes, including but not limited to spatial position coordinates, three-dimensional dimensions, building structure type, etc. These attribute information are organized through a specific data structure to generate a regional unit management data set. This data set not only contains the basic geometric features of each regional unit, but may also cover important information such as the functional positioning of the area in the construction, the spatial correlation with other areas, etc., laying the foundation for subsequent more refined construction progress management, allowing managers to implement customized monitoring and management strategies for each regional unit.

[0027] S2. Perform time series analysis on the process time series and regional unit management data sets in the construction plan to generate a regional progress plan data set.

[0028] Specifically, a construction plan plays a programmatic role in a construction project. It details each step in the construction process and its expected timing, forming a time sequence. This time sequence is a crucial reference for construction progress management, reflecting the temporal sequence and duration of each construction step.

[0029] In the present invention, the process time series in the construction plan is combined with the regional unit management dataset generated in step S1 to perform time series analysis. Time series analysis is a method based on statistics and mathematical models. By decomposing, correlating, and reorganizing the expected time schedules of each process in the construction plan in different regional units, and considering factors such as the construction difficulty, resource requirements, and logical dependencies between construction processes in different regional units, the construction progress of each regional unit is accurately planned. After this analysis process, a regional progress plan dataset is generated. This dataset records in detail information such as the expected completion time, key node times, and connection times of each process in different construction phases for each regional unit. This provides a precise target reference for subsequent comparative analysis of actual construction progress, making construction progress monitoring more targeted and operational, and can effectively avoid the ambiguity and lag problems of overall project-level progress monitoring in traditional methods.

[0030] S3. Based on the regional unit management dataset, the construction status data is acquired through on-site data acquisition equipment and fused to generate the actual progress dataset.

[0031] Specifically, various data collection devices are deployed in different areas of the construction site. These devices include, but are not limited to, IoT sensors, smart surveillance cameras, RFID tags and readers, and the data collection modules built into smart construction equipment. These devices can capture real-time construction status data during the construction process, covering aspects such as construction progress, personnel activities, material usage, and equipment operation.

[0032] Specifically, IoT sensors can monitor environmental parameters, the operating status of construction machinery, and changes in physical quantities during some construction processes. Smart surveillance cameras can capture images and video of the construction site and use image recognition to analyze worker behavior, material storage, and the spatial location of equipment. RFID technology can be used to track the flow of materials and personnel on the construction site. And the data acquisition modules built into smart construction equipment can accurately record key data such as equipment operating time and workload. These data, coming from different devices and data sources, may vary in format, accuracy, and update frequency. Therefore, they need to be fused and processed based on the regional attributes and data association rules defined by the regional unit management dataset.

[0033] The fusion process can include data cleaning, data format conversion, data alignment, and regional unit-based temporal and spatial correlation operations. Through these processing steps, dispersed, multi-source construction status data is integrated into a unified actual progress dataset. This dataset, based on regional units, records the actual construction status of each regional unit at different points in time in detail, including key information such as completed processes, ongoing processes, their progress ratios, and remaining construction quantities. This provides a real-time, accurate data foundation for subsequent comparative analysis with the planned progress, ensuring that construction progress monitoring closely matches actual on-site conditions and promptly reflects dynamic changes in construction.

[0034] S4. Calculate the deviation between the regional schedule plan dataset and the actual schedule dataset to generate a schedule deviation dataset.

[0035] Specifically, in the present invention, the regional progress plan data set generated in step S2 is compared and analyzed with the actual progress data set generated in step S3. The comparison analysis can be based on two key dimensions: regional unit and time. For each regional unit, the difference between its actual construction progress and planned construction progress is calculated at different time nodes. This difference can be reflected in many aspects, including the delay or advance of the process completion time, the achievement of key nodes, and the completion ratio of the project volume. The progress deviation of each regional unit can be accurately quantified by adopting an appropriate deviation calculation formula, such as the time-based deviation value calculation can use the difference between the actual completion time and the planned completion time, and the project volume-based deviation calculation can use the difference between the actual completed project volume and the planned completed project volume divided by the planned completed project volume.

[0036] The calculated deviation values are systematically organized and stored to form a schedule deviation dataset. This dataset not only contains the schedule deviation values for each regional unit but also includes a preliminary analysis of the causes of the deviations (such as a simple correlation analysis based on historical data and common construction interference factors) and an assessment of the potential impact of the deviations on subsequent construction processes and the overall project progress. This provides a key basis for subsequent construction schedule adjustments and resource optimization, allowing managers to quickly identify areas and key processes with lagging progress and take effective corrective measures to prevent further expansion of schedule deviations and ensure the project progresses as planned.

[0037] S5. Based on the progress deviation dataset and the BIM model, the 3D model is updated through the data mapping algorithm to generate a 3D visualization dataset.

[0038] Specifically, BIM (Building Information Modeling) is a digital model that integrates information on the entire life cycle of a construction project. It not only contains the geometric shape information of the building, but also covers rich semantic information, such as the properties of components, material characteristics, construction process requirements, etc.

[0039] In the present invention, based on the progress deviation dataset generated in step S4 and combined with the original BIM model, a pre-designed data mapping algorithm is used to update the 3D model. The core concept of the data mapping algorithm is to establish an association between the progress deviation data and the corresponding regional units and components in the BIM model.

[0040] Specifically, based on the correspondence between the areas defined in the regional unit management dataset and the spatial areas in the BIM model, the progress deviation data is accurately mapped to the corresponding parts of the BIM model. This mapping process can involve adjusting the display status of components in the model (such as color and transparency) to intuitively reflect the progress deviation; or updating and replacing some unfinished or completed components in the model to match the actual construction progress; at the same time, some visual annotation information can also be added, such as the time value of the progress delay and description of key issues.

[0041] After data mapping and updating the BIM model, a three-dimensional visualization data set is generated. This data set presents the construction progress status of the entire building in an intuitive three-dimensional form, allowing managers and construction personnel to view the construction progress of each regional unit in an immersive way, identify the spatial distribution of progress deviations, and understand the impact of deviations on the overall structure of the building. This greatly improves the readability and comprehensibility of construction progress information, provides more intuitive and efficient auxiliary support for subsequent construction decisions, and helps all parties to communicate and collaborate efficiently in a visual environment and quickly formulate reasonable construction adjustment strategies.

[0042] S6. Based on the three-dimensional visualization data set and the preset resource allocation data, a resource allocation bottleneck data set is generated through a cluster analysis algorithm.

[0043] Specifically, the three-dimensional visualization data set generated in step S5 not only intuitively presents the spatial information of the construction progress, but also implicitly contains the consumption and demand of various resources (such as manpower, materials, equipment, etc.) during the construction process.

[0044] In this invention, a cluster analysis algorithm is used to deeply explore the resource allocation situation, combining pre-set resource allocation data (covering information such as the expected demand for various resources for each regional unit and each process in the construction plan, the timing of resource supply, and available resource inventory). The cluster analysis algorithm analyzes the construction progress, resource consumption rate, and associated information related to resource allocation for different regional units in the three-dimensional visualization dataset over different periods of time, and classifies and groups regional units or processes with similar resource allocation characteristics. For example, based on indicators such as the degree of match between resource consumption and supply and the urgency of resource demand, it can identify groups of regions or processes with potential problems or bottlenecks in resource allocation. Through this cluster analysis process, a resource allocation bottleneck dataset is generated, which records in detail the characteristic information of different types of resource allocation bottlenecks, including the specific area where the bottleneck occurs, the construction process involved, the resource type, and the severity of the bottleneck. At the same time, the causes of bottlenecks can be further analyzed, such as insufficient resource supply, untimely resource allocation, and resource competition between different processes. The development trends of these bottlenecks in time and space dimensions can be predicted to provide precise target orientation and decision-making basis for subsequent resource optimization and allocation, helping managers to take measures in advance, optimize resource allocation plans, ensure smooth resource supply during the construction process, and avoid construction delays and cost increases due to resource problems.

[0045] S7. Based on the resource allocation bottleneck dataset, perform resource optimization processing through a linear programming algorithm, generate an optimized resource allocation plan, and update the three-dimensional visualization dataset.

[0046] Specifically, after obtaining the resource allocation bottleneck dataset generated in step S6, the present invention uses a linear programming algorithm to perform resource optimization processing for the various resource allocation bottlenecks identified therein. Linear programming is a mathematical optimization method suitable for solving optimal decision-making problems on how to reasonably allocate resources to achieve specific goals under limited resource conditions.

[0047] In the application scenario of this invention, the optimization objectives are to maximize construction schedule efficiency, minimize resource waste, or balance resource allocation fairness. A corresponding linear programming model is constructed based on the actual resource constraints of the construction site (such as material inventory limits, equipment quantity limits, and personnel skill matching), as well as the constraints formed by the construction process and engineering logic. By solving this model, an optimized resource allocation plan is obtained, which details key information such as the quantity of various resources to be allocated to each regional unit and each construction process within different time periods, as well as the resource deployment time and deployment path.

[0048] Compared with traditional empirical resource adjustment methods, this optimization process based on linear programming algorithms can more scientifically and accurately determine resource allocation plans, fully tap the potential of resource utilization, effectively solve resource allocation bottlenecks, and improve the resource utilization efficiency and progress assurance capabilities of the entire construction project. At the same time, after generating the optimized resource allocation plan, the three-dimensional visualization data set in step S5 is synchronously updated, and the new resource allocation information is integrated into the corresponding areas and components of the three-dimensional model to intuitively display the optimized resource allocation status. For example, the display identification of resources can be dynamically adjusted in the three-dimensional model to reflect the changes after resource allocation, allowing construction personnel and managers to clearly understand the construction layout after resource optimization, facilitating resource allocation and scheduling operations according to the optimized plan at the construction site, ensuring that the optimization measures can be effectively implemented, thereby forming a complete closed loop from problem identification and analysis to solution formulation and visual feedback, and continuously improving the progress management level and resource utilization efficiency of the construction project.

[0049] The above-mentioned intelligent monitoring method for construction project progress generates a regional unit management data set by dividing the building space using a grid division algorithm based on architectural design drawings; generates a regional progress plan data set through time series analysis based on the data set and the construction plan; obtains construction status data based on the regional unit management data set and on-site data acquisition equipment and fuses them to generate an actual progress data set; compares the planned and actual progress data sets through a deviation calculation formula to generate a progress deviation data set; combines the deviation data with the BIM model to generate a three-dimensional visualization data set; generates a resource allocation bottleneck data set through cluster analysis based on the three-dimensional data set and resource allocation data; finally, generates a resource optimization plan through a linear programming algorithm and updates the three-dimensional model, forming a closed-loop process from space division, data acquisition, deviation analysis to resource optimization, realizing dynamic monitoring of construction project progress in the three-dimensional spatial dimension and real-time correlation optimization of resource allocation, and solving the systematic defect of the disconnection between progress data and resource management space in traditional methods.

[0050] refer to Figure 2 In an optional embodiment, S1 includes the following steps:

[0051] S11. Extract spatial geometric data from the architectural design drawing data, segment the architectural space using a quadtree meshing algorithm, and obtain multiple area units.

[0052] S12. Assign a unique unit ID to each of the multiple area units, and record the spatial coordinates and geometric boundary parameters of the unit.

[0053] S13. Store the unit IDs, spatial coordinates, and geometric boundary parameters of the multiple regional units as a structured data table to obtain a regional unit management data set.

[0054] Specifically, spatial geometry data is extracted from the architectural design drawings to provide a foundation for subsequent segmentation. The building space is segmented using a quadtree meshing algorithm, resulting in multiple regional units. The quadtree meshing algorithm is an efficient spatial segmentation method that adaptively divides the building space into multiple regional units of appropriate size, tailored to the building's complexity and detail requirements. The size and shape of each regional unit can be adjusted based on actual construction requirements to ensure manageability and operability during construction.

[0055] Each generated area unit is then identified and its parameters recorded. Specifically, a unique unit ID is assigned to each area unit so that it can be accurately identified and located during subsequent construction management. At the same time, the spatial coordinates and geometric boundary parameters of each area unit are recorded. These parameters describe the location and shape of the area unit in the building space. Spatial coordinates can be represented using a three-dimensional coordinate system to accurately define the center position of the area unit or the location of a reference point; geometric boundary parameters include dimensional information such as the length, width, and height of the area unit, as well as the definition of the boundary line.

[0056] Finally, the unit ID, spatial coordinates, and geometric boundary parameters of all regional units are structured and stored as a structured data table. A structured data table is a way to organize and store data, making it easy to query, update, and manage it. By storing this information as a structured data table, a regional unit management dataset is formed, providing basic data support for subsequent intelligent monitoring of construction progress. This dataset not only contains basic spatial information for each regional unit but can also be further expanded to include additional attribute information, such as the unit's functional purpose and construction difficulty coefficient, to meet the diverse needs of construction management.

[0057] In an optional embodiment, S2 includes the following steps:

[0058] S21. Extract the process time series corresponding to the unit ID in the regional unit management data set from the construction plan.

[0059] S22. Based on the process time series, a time series prediction model is used to perform prediction processing to generate a planned progress prediction curve for each regional unit, and a planned progress cumulative value for each regional unit is obtained according to the planned progress prediction curve.

[0060] S23. Bind the planned progress cumulative value to the unit ID to generate a regional progress plan data set including a timestamp, a unit ID, and the planned progress cumulative value.

[0061] Specifically, the process time series are extracted from the construction plan and mapped to the unit IDs in the regional unit management dataset. The construction plan details the entire project's construction process, including the start and end times of each process. By parsing the construction plan, the time series information for each process can be obtained. Using a specific algorithm, the process time series are precisely matched and categorized based on the unit IDs in the regional unit management dataset, clearly identifying the process time series corresponding to each unit ID.

[0062] A time series prediction model is introduced to forecast process time series. Based on historical data and specific algorithms, the time series prediction model can predict values at future points in time. By inputting the extracted process time series into the model and comprehensively considering the impact of multiple factors on construction progress, such as resource allocation, personnel scheduling, and equipment operation, a planned progress forecast curve for each regional unit can be generated. This curve intuitively presents the expected progress of each regional unit at different times, reflecting the overall trends and fluctuations in construction. By integrating the prediction curve or using other statistical methods, the cumulative planned progress value of each regional unit is derived, thereby quantifying the expected workload completion of each regional unit within a specific time period.

[0063] The planned progress cumulative values are bound to the corresponding unit IDs to construct a regional progress data set. To ensure data integrity and traceability, timestamps are introduced to record the specific time when the data was generated or updated. The resulting regional progress data set is presented in a structured table format, containing key information such as timestamps, unit IDs, and planned progress cumulative values. This structure facilitates subsequent comparison and analysis with actual progress data, accurately identifying areas of progress deviation and providing strong support for dynamic management of the construction progress.

[0064] In an optional embodiment, S3 includes the following steps:

[0065] S31. Use the panoramic photography equipment in the on-site data acquisition equipment to collect images of the construction area, use the YOLOv5 algorithm to perform target recognition processing on the images of the construction area, and extract the number of component installations and completion features.

[0066] Specifically, panoramic photography equipment within the on-site data acquisition equipment is used to collect image information of the construction area in all directions. Panoramic photography equipment can capture the complete scene of the construction area, providing rich visual data for subsequent target recognition. The collected images of the construction area are input into the YOLOv5 target recognition algorithm based on deep learning. The YOLOv5 algorithm excels in the field of target detection due to its high efficiency and accuracy. It can quickly identify various components in the image and accurately calculate the number of components installed and the completion characteristics. The completion characteristics can be quantitatively evaluated by analyzing the installation status of the components (such as whether they are in place, whether they are fixed, etc.).

[0067] S32. Obtain material arrival time and equipment operation status data through sensors in the on-site data acquisition equipment, and match the material arrival time and equipment operation status data with the unit ID in the regional unit management data set.

[0068] Specifically, with the help of sensors in on-site data acquisition equipment, the material arrival time and equipment operating status data can be obtained in real time. Material arrival time data can be recorded by sensors installed on material transport vehicles or material storage locations. Equipment operating status data can be obtained through sensors on the equipment (such as vibration sensors, current sensors, etc.), which can monitor key status information such as the start, stop, and operating speed of the equipment. The above data is matched with the unit ID in the regional unit management data set. Through spatial positioning technology and data association algorithms, it is ensured that each data can be accurately mapped to a specific regional unit, providing accurate spatiotemporal correlation information for subsequent actual progress analysis.

[0069] S33. Perform weighted fusion processing on the component installation quantity, completion characteristics, material arrival time, and equipment operation status data to generate the actual progress cumulative value of each regional unit.

[0070] Specifically, the collected data on the number of component installations, completion characteristics, material arrival time, and equipment operating status are weighted and fused. The core of weighted fusion processing lies in assigning corresponding weight coefficients based on the degree of influence of different data types on the construction progress. The weight coefficients can be determined through a combination of methods such as statistical analysis of historical data, expert experience judgment, and machine learning algorithm training. For example, the number of component installations and completion characteristics may have a greater direct impact on the progress and have a relatively high weight; while the material arrival time and equipment operating status data are indirect influencing factors and have relatively low weights. Through weighted fusion calculation, various types of data are integrated into a single value that can comprehensively reflect the actual progress of construction, namely the cumulative actual progress value of each regional unit. This fusion processing method fully considers the importance and relevance of different data, effectively avoiding the progress assessment deviation that may be caused by a single data indicator, and improving the accuracy and reliability of the actual progress assessment.

[0071] S34. Bind the actual progress accumulated value to the unit ID to generate an actual progress data set.

[0072] Specifically, the calculated actual progress cumulative values are bound to the corresponding unit IDs to construct an actual progress dataset. A timestamp is also introduced to record the time of data generation to ensure data timeliness and traceability. The generated actual progress dataset is presented in a structured table format, containing key information such as timestamp, unit ID, and actual progress cumulative values. This dataset is structurally consistent with the regional schedule dataset, facilitating subsequent comparative analysis between the two, accurately identifying construction progress deviations and providing timely and accurate data support for refined construction progress management.

[0073] In an optional embodiment, S4 includes the following steps:

[0074] S41. According to the formula D(t)=P(t)-A(t), calculate P(t) in the regional progress plan data set and A(t) in the actual progress data set to obtain the progress deviation value D(t) of each regional unit; where P(t) is the cumulative value of the planned progress, A(t) is the cumulative value of the actual progress, and t is time.

[0075] Specifically, the progress deviation value D(t) for each regional unit is calculated according to the formula D(t) = P(t) - A(t). P(t) represents the cumulative planned progress, derived from the regional progress dataset, reflecting the total amount of progress expected to be completed by each regional unit at time t according to the construction plan. A(t) represents the cumulative actual progress, derived from the actual progress dataset, reflecting the total amount of progress actually completed by each regional unit at the same time point t. Subtracting the two yields the progress deviation value D(t), which intuitively quantifies the gap between the actual construction progress and the planned progress. A positive value for D(t) indicates that the actual progress lags behind the planned progress; a negative value for D(t) indicates that the actual progress is ahead of the planned progress. The calculation process strictly matches the time series and regional units, ensuring that the progress deviation for each regional unit at different time points can be accurately calculated.

[0076] S42. Associating the progress deviation value D(t) with the spatial coordinates in the regional unit management data set through a hash index algorithm.

[0077] Specifically, a hash index algorithm is used to associate the progress deviation value D(t) with the spatial coordinates in the regional unit management dataset. The hash index algorithm is an efficient association method that can quickly establish a correspondence between different datasets.

[0078] In this embodiment, by performing hash mapping between the progress deviation value D(t) and the spatial coordinates recorded in the regional unit management data set, each progress deviation value can be accurately corresponded to a specific location in the building space. Specifically, the hash index algorithm generates a unique hash key value based on the unit ID or spatial coordinates of the regional unit, and then uses this key value to quickly store the progress deviation value D(t) to the corresponding location. This association method not only improves the speed of data query and matching, but also ensures the consistency and accuracy of the progress deviation data and the building space location information, laying the foundation for the subsequent intuitive display of the spatial distribution of progress deviations in the three-dimensional BIM model, allowing construction management personnel to quickly locate areas with large progress deviations and take effective corrective measures in a timely manner.

[0079] S43. Write the associated progress deviation value into the IFC attribute field of the BIM model to generate a progress deviation data set.

[0080] Specifically, the associated progress deviation values are written into the IFC attribute fields of the BIM model to generate a progress deviation dataset. The IFC (Industry Foundation Classes) standard is an internationally recognized building information modeling data standard used to define data models and information exchange formats throughout the lifecycle of a construction project. Each component and area unit in the BIM model has corresponding IFC attribute fields, which can store a wealth of information, such as geometric attributes, physical properties, and construction progress.

[0081] In this embodiment, by developing a special data interface and conversion tool, the progress deviation value D(t) associated by the hash index algorithm can be written into the IFC attribute field of the corresponding regional unit of the BIM model in accordance with the IFC standard format. In this way, the progress deviation data is organically integrated with other information of the BIM model (such as geometric model, component attributes, etc.) to form a complete progress deviation data set. This data set not only contains the progress deviation value of each regional unit at different time points, but also retains information related to the building space position, component type, etc., so that construction management personnel can intuitively view and analyze the progress deviation situation in the visual environment of the BIM model, providing strong support for the refined management and decision-making of the construction progress, but also providing an accurate data source for subsequent data mapping and three-dimensional model updates.

[0082] refer to Figure 3 In an optional embodiment, S6 includes the following steps:

[0083] S61 : Based on the progress deviation value in the three-dimensional visualization data set, a visualization rendering process is performed according to a preset color coding rule to generate a color-mapped three-dimensional model.

[0084] Specifically, based on the progress deviation value in the three-dimensional visualization data set, a color coding rule is used to perform visualization rendering on the three-dimensional model. The color coding rule can divide the deviation into multiple intervals according to the size of the progress deviation value, and each interval corresponds to a unique color. For example, when the progress deviation value is negative (indicating that the progress is ahead of schedule), the green color system can be used, and the color deepens as the absolute value of the deviation increases; when the deviation is zero (the progress is in line with the plan), blue is used; and when the deviation is positive (the progress is lagging behind), the red color system is used, and the color depth also deepens as the degree of lag increases. Through this intuitive color coding method, construction management personnel can clearly identify the progress status of different areas on the three-dimensional model without in-depth analysis of complex data tables, so as to quickly focus on the key areas where the progress is lagging behind and take targeted measures in a timely manner.

[0085] At the same time, the geometric characteristics of the architectural space and the hierarchical relationship of the components are fully considered during the rendering process. In a three-dimensional model, different types of components (such as beams, columns, plates, etc.) may have different sensitivities to progress deviations. Therefore, when rendering colors, they can be classified according to the type and function of the components. For key components that have a greater impact on the overall progress, such as core load-bearing structures, even if their progress deviation values are small, they will be marked with relatively eye-catching colors to highlight their importance. In addition, to ensure the visual clarity and readability of the rendered three-dimensional model, graphic processing technologies such as transparency adjustment and edge enhancement can be used to make areas of different colors clearly distinguishable in complex spatial models, avoiding mutual interference and confusion between colors.

[0086] S62: Extract spatial resource allocation records of manpower, equipment, and materials from the resource scheduling system, and align the spatial resource allocation records with the unit ID in the regional unit management data set.

[0087] Specifically, spatial resource allocation records for manpower, equipment, and materials are extracted from the resource scheduling system and precisely aligned with the unit IDs in the regional unit management dataset. The resource scheduling system records in detail the allocation of various resources over time and space during the construction process, including information such as each construction worker's work area and tasks, the operating location and operating hours of each piece of equipment, and the storage and use locations of various materials. When extracting this data, appropriate data parsing and conversion techniques can be used based on the data structure and storage format of the resource scheduling system to convert it into a format compatible with the regional unit management dataset.

[0088] The alignment process is a critical step in ensuring accurate association between resource allocation data and schedule deviation data. Because resource allocation records and area unit management data may originate from different data sources, their temporal and spatial granularity may differ. To address this issue, temporal interpolation and spatial mapping techniques can be employed. Temporal interpolation supplements and refines resource allocation data temporally based on the timestamps of resource allocation records and the update frequency of schedule deviation data, ensuring temporal consistency between the two. Spatial mapping, on the other hand, accurately maps resource allocation data to corresponding unit IDs by analyzing the correspondence between location information (such as latitude and longitude, construction area ID, etc.) in resource allocation records and the spatial coordinates and geometric boundary parameters in the area unit management dataset. This alignment not only improves data accuracy but also provides a reliable data foundation for subsequent spatial correlation analysis, enabling construction managers to clearly understand the allocation of each resource across various area units and the relationship between these resource allocations and the construction progress.

[0089] S63. Based on the aligned spatial resource allocation records and progress deviation values, a spatial correlation analysis is performed using the DBSCAN clustering algorithm to identify the overlapping relationship between the resource allocation intensive area and the lagging area.

[0090] Specifically, the DBSCAN clustering algorithm is used to perform spatial correlation analysis and processing in combination with the aligned spatial resource allocation records and progress deviation values to identify the overlapping relationship between resource allocation intensive areas and progress lagging areas. The DBSCAN clustering algorithm is a density-based spatial clustering algorithm that can automatically discover clustering areas with similar characteristics in complex spatial data sets, while effectively identifying noise data. In this embodiment, the resource density (such as the number of manpower, equipment and materials per unit area) and progress deviation values in the spatial resource allocation records are used as the main features to construct a multidimensional feature space. By performing cluster analysis in this feature space using the DBSCAN algorithm, it is possible to identify resource allocation intensive areas (i.e., areas with higher resource density) and progress lagging areas (areas with larger progress deviation values).

[0091] Furthermore, by analyzing the spatial distribution and overlap of these regions, potential correlations between resource allocation and construction progress can be uncovered. For example, if a region is densely resourced but progress is still lagging, this may indicate problems such as inefficient resource utilization and irrational construction organization. Conversely, if resource allocation is low but progress is normal or ahead of schedule, this may indicate high construction efficiency or relatively reasonable resource allocation. This cluster analysis can help construction managers quickly identify areas where resource allocation and progress are poorly matched, providing a strong basis for subsequent resource optimization and adjustment, improving resource utilization efficiency and reducing progress delays caused by irrational resource allocation.

[0092] S64: Bind the overlapping relationship with the unit ID to generate a resource allocation bottleneck data set.

[0093] Specifically, the identified overlapping relationships are bound to the unit ID to construct a resource allocation bottleneck dataset. After completing the spatial association analysis, each overlapping relationship (i.e., the overlap between the resource-intensive area and the delayed progress area) is associated with the corresponding unit ID to ensure that the overlapping relationship information associated with each unit ID is accurate. Simultaneously, this information is integrated into the resource allocation bottleneck dataset, which is stored in a structured table and contains the unit ID, the spatial extent of the overlapping area, the resource type (manpower, equipment, materials, etc.), the resource density, the progress deviation value, and a preliminary assessment of the possible bottleneck cause.

[0094] Furthermore, to facilitate subsequent analysis and decision-making, the information in the dataset can be further statistically analyzed. For example, the correlation coefficient between the intensity of resource allocation and the degree of schedule delay corresponding to each unit ID can be calculated, and the impact of resource allocation on the construction progress can be assessed. This dataset provides construction managers with a comprehensive and systematic view of resource allocation bottlenecks, enabling them to gain a deeper understanding of the complex relationship between resource allocation and construction progress, thereby developing more precise and effective resource optimization strategies, eliminating resource allocation bottlenecks, and improving overall construction efficiency.

[0095] In an optional embodiment, S7 includes the following steps:

[0096] S71. Based on the bottleneck types and impact weights in the resource allocation bottleneck dataset, a linear programming function is constructed with the goal of minimizing the total progress deviation.

[0097] Specifically, based on the bottleneck types and impact weights in the resource allocation bottleneck dataset, a linear programming function is constructed with the goal of minimizing the total schedule deviation. The resource allocation bottleneck dataset records in detail the resource allocation bottleneck types (such as manpower shortages, material supply delays, equipment failures, etc.) of each regional unit and their impact weights on the construction progress. These impact weights can be obtained through statistical analysis of historical data, expert experience judgment, or machine learning algorithm training, reflecting the relative impact of different bottleneck types on the construction progress. The construction of the linear programming function aims to minimize the total schedule deviation by adjusting the resource allocation strategy. Specifically, the function uses the schedule deviation of each regional unit as the target variable, combines it with the corresponding resource allocation amount and bottleneck impact weight, and forms a mathematical expression. This expression takes into account both resource availability and the logical constraints of the construction process, ensuring that the optimal resource allocation plan can be found to minimize the schedule deviation when resources are limited.

[0098] S72. Solve the linear programming function using the simplex method to generate a unit-level resource adjustment plan as an optimized resource allocation plan.

[0099] Specifically, the simplex method is a classic linear programming solution algorithm that can find a solution that makes the objective function reach the optimal value through iterative optimization within the feasible domain. In this embodiment, by inputting the linear programming function into the simplex method solver, combined with constraints such as the resource requirements, resource supply constraints, and construction progress priorities of each regional unit, the amount of resources (including manpower, equipment, materials, etc.) to be allocated to each regional unit and the time schedule for resource allocation are calculated. This solution process fully considers the dynamic nature of resources and the real-time changes in the construction progress, and can generate a detailed unit-level resource adjustment plan, clearly indicating the type and quantity of resources that need to be increased or decreased in each regional unit during different time periods, as well as the specific resource allocation path and method. This refined resource adjustment plan provides direct decision-making support for construction management personnel, helping them to efficiently optimize resource allocation in a complex construction site environment and ensure the smooth progress of construction progress.

[0100] S73. Write the unit-level resource adjustment plan into the corresponding unit attribute field in the three-dimensional visualization dataset through the BIM model API, update the resource distribution layer, and generate a three-dimensional visualization dataset after the resources are updated.

[0101] Specifically, the BIM model API provides a programming interface for data interaction with the BIM model, so that the resource adjustment plan can be accurately mapped to the three-dimensional visualization data set. Specifically, according to the unit ID, the various data in the resource adjustment plan (such as the number of manpower, equipment type and operating time, material consumption, etc.) are written into the attribute field of the corresponding regional unit, and the relevant information of the resource distribution layer is updated at the same time. The resource distribution layer displays the distribution of various resources in the building space in an intuitive graphical manner in the three-dimensional visualization data set, including the location, quantity and status of the resources. Through this update operation, construction management personnel can view the distribution status of resources after adjustment in real time in the three-dimensional model, intuitively understand the distribution of resources in each regional unit and its relationship with the construction progress, and provide more intuitive and efficient auxiliary decision support for on-site resource allocation and construction organization, ensuring that the resource optimization plan can be effectively implemented.

[0102] S74. Based on the updated three-dimensional visualization dataset of resources, recalculate the plan progress prediction curve through the time series prediction model, and write the prediction curve into the updated three-dimensional visualization dataset of resources to generate a closed-loop optimized three-dimensional visualization dataset.

[0103] Specifically, the time series prediction model, already used in step S22 to generate the initial planned progress prediction curve, is reused here, but based on updated resource allocation and construction status information. By inputting relevant data from the updated 3D visualization dataset (such as the adjusted resource allocation amount, actual progress accumulation value, etc.), the time series prediction model can re-evaluate the construction progress trend of each regional unit and generate a new planned progress prediction curve. This prediction curve reflects the expected construction progress after resource optimization and adjustment, providing construction management personnel with a basis for predicting future progress. After writing the new prediction curve into the 3D visualization dataset, the generated closed-loop optimized 3D visualization dataset not only contains the latest resource allocation information and actual progress data, but also incorporates predictions for future progress, forming a complete closed-loop construction progress management loop. This closed-loop optimization mechanism enables the construction progress monitoring system to respond to changes on the construction site in real time, dynamically adjust resource allocation strategies, and continuously optimize the construction progress, providing a strong guarantee for the efficient and orderly implementation of construction projects. It also provides construction management personnel with an integrated, dynamically updated progress management visualization platform, facilitating their comprehensive construction progress monitoring and decision-making analysis.

[0104] The above-mentioned intelligent construction project progress monitoring method first uses a gridding algorithm based on architectural design drawings to divide the building space into multiple regional units with unique unit IDs and spatial coordinates, thereby constructing a structured regional unit data set. Then, based on the process time series in the construction plan, a time series analysis model is used to generate a planned progress curve for each regional unit. This is then weighted and fused with real-time on-site construction data to generate an actual progress curve. The progress difference of each regional unit is further quantified using a deviation calculation formula, and the deviation value is mapped to the corresponding spatial coordinates of the BIM model to construct a dynamically updated three-dimensional visual twin model. The deviation value is also visualized based on color coding rules to intuitively present the spatial distribution of areas with advanced and lagging progress. A cluster analysis algorithm is then used to identify the overlap between areas with intensive resource allocation and areas with lagging progress, thereby locating resource bottlenecks. Finally, a linear programming algorithm is used to generate a resource optimization plan, and adjustment instructions are fed back to the three-dimensional model in real time, forming a closed-loop control process of "data collection-deviation analysis-resource allocation-model update". This achieves dynamic correlation optimization between construction progress and resource allocation in the three-dimensional space dimension, solving the problems of disconnection between progress monitoring and resource management and delayed decision-making in traditional methods.

[0105] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0106] An embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0107] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0108] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to the partial description of the method embodiments. The device embodiments described above are merely illustrative, wherein the components described as separate parts may or may not be physically separated, and the parts 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 can be selected according to actual needs to achieve the purpose of the disclosed solution. A person of ordinary skill in the art can understand and implement it without expending creative work.

[0109] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. A construction project progress intelligent monitoring method, characterized in that: The method comprises: S1. Based on the architectural design drawing data, the building space is segmented using a grid division algorithm to generate a regional unit management data set; S2. Performing time series analysis on the process time series in the construction plan and the regional unit management data set to generate a regional progress plan data set; S3. Based on the regional unit management data set, obtain construction status data through on-site data acquisition equipment and perform fusion processing to generate an actual progress data set; S4. Calculate the deviation between the regional schedule data set and the actual schedule data set to generate a schedule deviation data set; S5. Based on the progress deviation dataset and the BIM model, update the three-dimensional model through a data mapping algorithm to generate a three-dimensional visualization dataset; S6. Based on the three-dimensional visualization data set and the preset resource allocation data, a resource allocation bottleneck data set is generated by a cluster analysis algorithm; S7. Based on the resource allocation bottleneck dataset, perform resource optimization processing using a linear programming algorithm to generate an optimized resource allocation plan and update the three-dimensional visualization dataset.

2. The method according to claim 1, characterized in that Said S1 comprises: S11, extracting spatial geometric data from the architectural design drawing data, and segmenting the architectural space using a quadtree meshing algorithm to obtain a plurality of area units; S12, assigning a unique unit ID to each of the plurality of area units, and recording the spatial coordinates and geometric boundary parameters of the unit; S13: Store the unit IDs, the spatial coordinates, and the geometric boundary parameters of the multiple area units as a structured data table to obtain the area unit management data set.

3. The method according to claim 2, characterized in that The S2 includes: S21, extracting the process time series corresponding to the unit ID in the regional unit management data set from the construction plan; S22. Based on the process time series, a time series prediction model is used to perform prediction processing to generate a planned progress prediction curve for each of the regional units, and a planned progress cumulative value for each of the regional units is obtained according to the planned progress prediction curve; S23: Bind the planned progress cumulative value to the unit ID to generate the regional progress plan data set including a timestamp, the unit ID and the planned progress cumulative value.

4. The method according to claim 3, characterized in that The S3 includes: S31, using the panoramic photography equipment in the on-site data acquisition equipment to collect images of the construction area, using the YOLOv5 algorithm to perform target recognition processing on the images of the construction area, and extracting the number of component installations and completion features; S32. Acquire material arrival time and equipment operating status data through sensors in the field data acquisition device, and match the material arrival time and equipment operating status data with the unit ID in the regional unit management data set; S33, performing weighted fusion processing on the component installation quantity, completion characteristics, material arrival time, and equipment operation status data to generate an actual progress cumulative value for each of the regional units; S34: Bind the actual progress accumulated value with the unit ID to generate the actual progress data set.

5. The method according to claim 4, characterized in that The S4 includes: S41. Calculate P(t) in the regional progress plan data set and A(t) in the actual progress data set according to the formula D(t)=P(t)-A(t) to obtain a progress deviation value D(t) for each regional unit; wherein P(t) is the cumulative value of the planned progress, A(t) is the cumulative value of the actual progress, and t is time; S42. Associating the progress deviation value D(t) with the spatial coordinates in the regional unit management data set through a hash index algorithm; S43: Writing the associated progress deviation value into the IFC attribute field of the BIM model to generate the progress deviation data set.

6. The method according to claim 5, characterized in that The S6 includes: S61: Based on the progress deviation value in the three-dimensional visualization data set, a visualization rendering process is performed according to a preset color coding rule to generate a color-mapped three-dimensional model; S62: Extracting spatial resource allocation records of manpower, equipment, and materials from the resource scheduling system, and aligning the spatial resource allocation records with the unit ID in the regional unit management dataset; S63: Based on the aligned spatial resource allocation records and the progress deviation values, perform spatial association analysis using a DBSCAN clustering algorithm to identify overlapping relationships between resource allocation intensive areas and lagging areas. S64: Bind the overlapping relationship with the unit ID to generate the resource allocation bottleneck data set.

7. The method according to any one of claims 3 to 6, characterized in that The S7 includes: S71. Based on the bottleneck types and impact weights in the resource allocation bottleneck dataset, construct a linear programming function with the goal of minimizing the total progress deviation; S72, solving the linear programming function by the simplex method to generate a unit-level resource adjustment plan as the optimized resource allocation plan; S73. Writing the unit-level resource adjustment plan into the corresponding unit attribute field in the three-dimensional visualization dataset through the BIM model API, updating the resource distribution layer, and generating a three-dimensional visualization dataset after resource update; S74. Based on the updated three-dimensional visualization dataset of the resources, recalculate the planned progress prediction curve through the time series prediction model, and write the prediction curve into the updated three-dimensional visualization dataset of the resources to generate a closed-loop optimized three-dimensional visualization dataset.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images