Method and system for digital monitoring of building construction progress

Abstract

The application relates to the technical field of building engineering and provides a building construction progress digital monitoring method and system. The method comprises the following steps: collecting three-dimensional point data of a construction area, comparing the three-dimensional point data with a BIM model to extract a progress deviation, associating a construction log with a BIM component node to set a first evaluation index, associating a material record with the BIM component node to set a second evaluation index, combining the deviation and the two indexes to formulate a resource atlas of a construction process logic, accumulating influences based on the atlas according to a weight attenuation coefficient, taking efficiency as a characteristic to perform multi-scale evaluation, and combining dynamic threshold adjustment to perform resource compensation reminding. The application solves the technical problem that in traditional building construction progress monitoring, data updating is lagged, and a construction process logic is disengaged, so that a progress deviation is difficult to accurately identify, achieves the technical effect that through multi-source data fusion and intelligent comparison of a BIM model, real-time and accurate analysis of construction progress is realized, dynamic optimization of resource allocation is realized in combination with multi-dimensional evaluation indexes, and the technical effect of improving construction management efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of building engineering, in particular to a building construction progress digital monitoring method and system. BACKGROUND

[0002] In the field of building engineering, with the rapid development of prefabricated buildings and intelligent construction technology, the complexity and construction rhythm of projects have been significantly improved. Traditional construction progress management relies on manual inspection and paper log recording, which has problems such as data lag and information fragmentation. Although BIM technology has realized the digital modeling of building components, there is still a fault between the real-time dynamics of the construction site and the virtual model: managers cannot intuitively perceive the actual progress deviation, and resource scheduling relies on experience, resulting in frequent material accumulation or shortage. Especially in the multi-process cross-operation scene, environmental changes (such as extreme weather), process logic conflicts or sudden risk events often cause chain delays, and the existing system lacks the ability to integrate the analysis of construction logs, material consumption and environmental parameters, and cannot build a resource warning mechanism driven by process logic. For example, the lag of concrete pouring progress may not be timely associated with the change in resource demand of subsequent steel structure installation, or sudden rain and snow may not dynamically correct the priority of window construction, ultimately causing the project to lose control. Therefore, there is an urgent need for a progress monitoring method based on digital technology to realize real-time perception of progress deviation, dynamic optimization of resource allocation and proactive warning of potential risks, thereby improving engineering management efficiency and resource utilization. SUMMARY

[0003] The application provides a building construction progress digital monitoring method and system, which aims to solve the technical problems of data update lag and construction process logic disconnection in traditional building construction progress monitoring, which makes it difficult to accurately identify progress deviation.

[0004] The first aspect of the application provides a building construction progress digital monitoring method, which comprises: collecting three-dimensional point data of the construction area, comparing with the BIM building model, and extracting deviation information of the construction progress and the planned progress; associating the construction log with each building component node of the BIM building model, and setting a first progress evaluation index; associating the material consumption record with each building component node of the BIM building model, and setting a second progress evaluation index; through the deviation information, combining the first progress evaluation index and the second progress evaluation index, and formulating a building construction resource allocation graph conforming to the construction process logic relationship; based on the building construction resource allocation graph, according to the weight decay coefficient, taking the resource allocation efficiency as the correlation feature, performing multi-scale evaluation on the cumulative influence range, and combining the dynamic threshold adjustment rule to perform resource compensation reminding.

[0005] In another aspect of the present disclosure, a building construction progress digital monitoring system is provided, which comprises: a real-time comparison module configured to collect three-dimensional point data of a construction area, compare the three-dimensional point data with a BIM building model, and extract deviation information between a construction progress and a planned progress; a construction log association module configured to associate a construction log with each building component node of the BIM building model, and set a first progress evaluation index; a consumption record association module configured to associate a material consumption record with each building component node of the BIM building model, and set a second progress evaluation index; a resource allocation graph drafting module configured to draft a building construction resource allocation graph in accordance with a construction process logical relationship by using the deviation information, the first progress evaluation index, and the second progress evaluation index; and a resource compensation reminding module configured to perform multi-scale evaluation on a cumulative influence range based on the building construction resource allocation graph, the resource allocation efficiency, and a weight decay coefficient, and perform resource compensation reminding according to a dynamic threshold adjustment rule.

[0006] The one or more technical solutions provided in the present disclosure have at least the following technical effects or advantages:

[0007] The building construction progress digital monitoring method described above first extracts deviation information between a construction progress and a planned progress by collecting three-dimensional point data of a construction area and comparing the three-dimensional point data with a BIM building model. Then, a construction log is associated with building component nodes in the BIM model to set a first progress evaluation index, and a material consumption record is associated with each component node to set a second progress evaluation index. Subsequently, a resource allocation graph in accordance with a construction process logic is drafted by comprehensively analyzing the deviation information and the evaluation indexes. Finally, multi-scale evaluation is performed based on the graph, the resource allocation efficiency, and a weight decay coefficient, and resource compensation reminding is performed according to a dynamic threshold adjustment rule, so as to ensure that resource allocation and progress in the construction process reach an optimized state.

[0008] The above description is only a summary of the technical solutions of the present disclosure. In order to enable one of ordinary skill in the art to better understand the technical means of the present disclosure and implement the same in accordance with the contents of the description, and in order to enable the above and other purposes, features and advantages of the present disclosure to be more apparent and understandable, the following specific embodiments of the present disclosure are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present disclosure, and other drawings can also be obtained by those of ordinary skill in the art without any creative effort.

[0010] Figure 1A flowchart of a building construction progress digital monitoring method in an embodiment.

[0011] Figure 2 A building construction progress digital monitoring system architecture diagram in an embodiment.

[0012] Label explanation: real-time comparison module 11, construction log association module 12, consumption record association module 13, resource configuration atlas formulation module 14, resource compensation reminding module 15. DETAILED DESCRIPTION

[0013] The embodiments of the present application provide a building construction progress digital monitoring method and system, and solve the technical problem that in traditional building construction progress monitoring, data updating is lagging behind, and the logical disconnection of construction processes leads to difficulty in accurately identifying progress deviation.

[0014] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0015] It should be noted that the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0016] Embodiment one, as shown in the present application provides a building construction progress digital monitoring method, which comprises: Figure 1

[0017] Collecting three-dimensional point data of the construction area, comparing with the BIM building model, and extracting deviation information of the construction progress and the planned progress.

[0018] ​In the embodiments of the present application, in the building construction process, in order to realize accurate progress monitoring, first, a laser scanner or a sensor carried by a drone is used to periodically scan the construction area, and three-dimensional point cloud data containing spatial coordinates and intensity information is obtained, then the obtained three-dimensional point data is normalized. The purpose of normalization is to adjust point data of different sources and different accuracies to a unified scale, so that these data have consistency in subsequent analysis. This process also applies a statistical filtering algorithm (Statistical Outlier Removal) to remove outliers, ensuring the accuracy and reliability of the data. Subsequently, the ICP (Iterative Closest Point) algorithm is used to align the processed three-dimensional point data with the coordinate system of the BIM model, ensuring the consistency of the spatial reference, and then the aligned three-dimensional point data is input into a three-dimensional modeling software to construct a real-time building model of the current construction area. Then, the processed point cloud data is matched with the geometric information of the corresponding components in the BIM model, that is, the Euclidean distance is used to calculate the deviation of the actual construction coordinates of each component in the real-time building model and the planned coordinates of each component in the BIM model, then the mean value of the deviation of all points is calculated to obtain the spatial position deviation information of the construction progress and the planned progress, and then the actual completion time is subtracted from the planned completion time to obtain the time deviation information of the construction progress and the planned progress. Finally, the spatial position deviation information and the time deviation information are summarized to form the deviation information of the construction progress and the planned progress, helping construction managers to discover problems in time and make adjustments, thereby reducing the risk of project delay.

[0019] The construction construction log is associated with each building component node of the BIM building model, and a first progress evaluation index is set.

[0020] In one embodiment, a connection is established with an electronic log database from which construction logs are obtained, the construction logs recording the progress of construction each day, usually containing the working hours of construction personnel, the completed processes, problems encountered during construction, and the actual progress of construction, etc. In order to ensure accurate tracking of construction progress, the data in the construction logs will be sorted and classified according to the building components, thereby obtaining work information related to each building component. Then, the work information of each building component is associated with the nodes in the BIM model representing the corresponding building component, which usually includes the location information, size, material, process requirements, etc. of the component. After the records in the construction logs are associated with these nodes, the system can obtain the specific information of the component corresponding to the node by matching with the nodes in the BIM model, helping to set subsequent progress evaluation indicators. Then, according to the information associated with each node, the first progress evaluation indicators are set, which are used to measure the completion of construction tasks, usually including the quantity completion rate (the ratio of the actual installation volume of the component to the planned installation volume), the time efficiency (the ratio of the planned construction time of the component to the actual construction time), the team efficiency (the ratio of the average completion time of the same construction team on different component nodes to the planned team benchmark time), etc. Through these evaluation indicators, the actual construction status of each building component can be clearly understood, thereby having a more comprehensive understanding of the overall progress to ensure that the project is completed on time.

[0021] The material consumption records are associated with the nodes of each building component of the BIM building model, and the second progress evaluation indicators are set.

[0022] In one embodiment, a connection material management system is connected to obtain material consumption records, which can reflect the actual resource consumption of each stage in the project, usually containing the name, specification, consumption, use time and other information of various building materials (such as cement, steel bars, concrete, etc.). In order to ensure accurate tracking of material consumption, the data in the material consumption records will be sorted and classified according to the building components, so as to obtain the material information related to each building component. Then, the material information of each building component is associated with the node representing the corresponding building component in the BIM model. After association, the system can obtain the specific information of the component corresponding to the node by matching with the node in the BIM model, helping to set subsequent progress evaluation indicators. Then, according to the information associated with each node, the second progress evaluation indicator is set, which is used to evaluate the construction degree of the building component, usually including material usage deviation rate (ratio of actual material usage to planned usage), supply timeliness rate (ratio of planned delivery time to actual delivery time), loss deviation rate (absolute difference between actual material usage and planned usage and planned usage), etc. Through these evaluation indicators, the material consumption of each component in the building project can be accurately mastered, so as to ensure the efficient and timely completion of the project.

[0023] By means of the deviation information, in combination with the first progress evaluation indicator and the second progress evaluation indicator, an architectural construction resource allocation map conforming to the logical relationship of the construction process is drafted.

[0024] In one embodiment, after obtaining the deviation information, the first progress evaluation indicator and the second progress evaluation indicator, a directed graph is constructed based on the pre-defined process logical relationship in the BIM model (such as "foundation construction → main structure → decoration and renovation"). The nodes in this directed graph represent the construction processes (such as "steel bar binding" and "concrete pouring"), and the edges represent the dependency relationship between the processes (such as "steel bar binding completion is a prerequisite for concrete pouring"). In the directed graph, the obtained deviation information, the first progress evaluation indicator and the second progress evaluation are assigned to the corresponding process nodes, and then the sliding time window is used to dynamically update the weights between the construction processes, and the calculated weights are assigned to the corresponding edges. After completing the configuration of edges and nodes, an architectural construction resource allocation map based on the BIM model is drafted, which can guide the resource scheduling and management in the construction process, ensure the timely completion of the construction task, avoid resource waste, and improve the construction efficiency. Through real-time monitoring and adjustment of the map, the management personnel can flexibly respond to various changes in the construction process, ensuring the efficient and smooth progress of the construction project.

[0025] Further, the application provides that the building construction resource configuration graph is determined by a sliding time window, and each construction process is connected by a directed edge corresponding to the building construction resource configuration graph; meanwhile, a preceding constraint relationship, a time dependency parameter and resource association information between each construction process are labeled.

[0026] Preferably, the sliding time window is a time period-based data processing method for capturing real-time progress information and dynamically updating construction processes. The size of the sliding window is usually set according to the construction period or project requirements, for example, the window can be a daily, weekly or monthly time period. When building or updating the construction resource allocation graph, the time window will continuously move forward on the deviation information, the first progress evaluation index and the second progress evaluation index. After each move, new data enters the window, and old data is excluded. For the data in the time window, a pre-trained long short-term memory network (LSTM) is used for analysis to calculate the connection strength between each construction process in the time window, and the calculated connection strength is used as the weight of the edge between the corresponding construction processes. This long short-term memory network is obtained by forward propagation, loss calculation (mean square error), back propagation, and parameter optimization (Adam optimizer) iterative training using sample deviation information, sample progress evaluation index and sample influence weight. After setting or updating the weight of the edge, the construction processes are connected again to form a new construction resource allocation graph. In each node of the construction resource allocation graph, in addition to the allocated deviation information, the first progress evaluation index and the second progress evaluation index, the pre-constraint relationship, the time dependency parameter and the resource association information between each construction process are also labeled. The pre-constraint relationship is determined by the logical relationship and order of the construction processes. Because some processes may be limited by the previous processes, for example, the concrete pouring process must be carried out after the foundation construction is completed; the steel structure installation must be carried out after the concrete hardens. The pre-constraint relationship can clearly show the pre-process of each process. Only when the pre-process is completed and the resources are ready, the process of the node can be started. The time dependency parameter is determined by the time required for each construction process and the completion of the pre-process. Because the execution time of some processes depends on the completion time of the pre-process and the complexity of the process itself, for example, the time of the concrete pouring process depends on the completion of the foundation construction, and the time of the steel structure installation depends on the hardening time of the concrete. The time dependency parameter can clearly show the time requirement of each process. Only when the pre-process is completed and the time dependency relationship is satisfied, the subsequent process can be carried out according to the plan. The resource association information is determined by the type and quantity of resources required by each process. Because each construction process requires specific resources (such as manpower, equipment, materials, etc.), for example, a process may require a large amount of concrete, while another process may require specific construction equipment or labor. The resource association information can clearly show the type and quantity of resources required by each process. Only when the pre-process is completed and the required resources are ready, the process can be started.In summary, by dynamically updating the directed edges in the building construction resource allocation graph and labeling the pre-requisite constraint relationships, time-dependent parameters, and resource association information for each process, the construction progress can be timely reflected in the actual situation, thereby optimizing resource allocation, avoiding delays, and ensuring the smooth progress of the construction project.

[0027] Based on the building construction resource allocation graph, the cumulative influence range is evaluated at multiple scales according to the weight decay coefficient, with resource allocation efficiency as the associated feature, and resource compensation reminders are provided in combination with dynamic threshold adjustment rules.

[0028] In one embodiment, after the building construction resource allocation graph is constructed, an LSTM time series perception model is used to analyze the building construction resource allocation graph to determine the weight decay coefficient of the building construction resource allocation graph. Then, the resource allocation efficiency of each process node in the building construction resource allocation graph is used as an associated feature to measure the actual use effect of resources in the construction process. Subsequently, the influence range of lagging processes on subsequent processes is measured through multi-scale evaluation. Specifically, in micro-scale evaluation, the weights of all edges of each node are added, and the sum is multiplied by the weight decay coefficient to obtain the cumulative influence value of each node. In meso-scale evaluation, the cumulative influence values of all nodes in each construction partition (such as floor, bid section) are added, and then divided by the number of nodes in the construction partition to obtain the aggregated node influence value. In macro-scale evaluation, the mean value of the resource allocation efficiency of all nodes is calculated to obtain the macro-node influence value. Then, according to the preset weights of each scale, the normalized results of the three influence values are weighted to obtain the multi-scale evaluation result. The multi-scale evaluation result is compared with the dynamic threshold, which is dynamically set according to actual business needs to adapt to the construction needs at different stages. When the multi-scale evaluation result exceeds the dynamic threshold, resource compensation reminders are triggered. These reminders help managers adjust resource allocation in a timely manner, supplement resources such as materials, labor, or equipment arrangements for key nodes and potential risk nodes, thereby avoiding resource waste and maintaining smooth progress of the construction schedule. Through this step, resource allocation can be optimized in real time to ensure that the construction project is completed on time and with quality, reducing delays and resource waste in construction.

[0029] Further, the present application provides a method for evaluating the cumulative influence range according to the weight decay coefficient, with resource allocation efficiency as the associated feature, the method further comprising:

[0030] dynamically assigning weights to the directed edges of the building construction resource allocation graph, and based on the LSTM time series perception, the pre-requisite constraint relationships, time-dependent parameters, and resource association information between the construction processes are fused to obtain the weight decay coefficient.

[0031] Optionally, in order to ensure that the construction progress and resource allocation can reflect the changes in the construction site in real time, the directed edges in the building construction resource allocation graph are dynamically weighted according to the data in the sliding time window. In this process, the deviation information, the first progress evaluation index and the second progress evaluation index in the sliding time window are input into the long short-term memory network to map the weight of each edge. Subsequently, based on the LSTM time sequence perception model, the pre-construction constraint relationship, the time dependence parameter and the resource association information between each construction process in the building construction resource allocation graph are fused to calculate a weight decay coefficient to cope with changes in the construction process, ensure the smooth progress of each process, and adjust the resource allocation in time when needed, thereby optimizing the efficiency and quality of the overall building construction process.

[0032] Further, the present application provides a building construction resource allocation graph that meets the logical relationship of the construction process by combining the first progress evaluation index and the second progress evaluation index. The method comprises:

[0033] A dynamic environmental parameter perception network is constructed by integrating a temperature and humidity sensing unit, a wind speed monitoring unit and a light intensity detection unit to obtain construction environment data. Based on the process sub-interval associated with the construction efficiency influence coefficient, an environmental progress correlation matrix is constructed in combination with the construction environment data to dynamically correct the weight decay coefficient of the building construction resource allocation graph.

[0034] Preferably, in order to make the weight decay coefficient more consistent with the current working conditions, an environmental parameter perception network is used to collect construction environment data, wherein the environmental parameter perception network is composed of a temperature and humidity sensor, a wind speed monitoring device, and an illumination intensity detection unit. The temperature and humidity sensor unit is used to monitor the temperature and humidity changes of the construction site in real time, the wind speed monitoring unit is used to capture the wind speed data of the construction area, and the illumination intensity detection unit is used to detect the sunshine intensity. During the construction process, environmental factors have a significant impact on the execution efficiency of each process. For example, excessive temperature or humidity may cause the performance of certain building materials (such as concrete, paint, etc.) to decline, thereby affecting the construction quality and efficiency, excessive wind speed may affect the normal operation of hoisting equipment, and illumination intensity may affect the working environment of outdoor construction. In order to take environmental factors into account, a construction efficiency influence coefficient is set for each process according to the characteristics of the construction process. The construction efficiency influence coefficient is obtained by weighting the ratio of all environmental data to ideal environmental data, reflecting the influence of the construction environment on the process efficiency. These process efficiency influence coefficients are associated with process sub-intervals. For example, concrete pouring may need to be carried out under suitable temperature and humidity conditions, while steel structure installation may be limited by wind speed. Then, the construction environment data and the process sub-interval corresponding to the process efficiency influence coefficient are integrated to construct an environmental progress correlation matrix. This environmental progress correlation matrix directly reflects the mutual influence between each construction process and environmental factors. Then, the average value of the process efficiency influence coefficients in the same row of the environmental progress correlation matrix is taken as a dynamic correction factor, which is multiplied by the weight decay coefficient calculated according to the building construction resource allocation map, to complete the correction of the weight decay coefficient. Thus, the weight decay coefficient can reflect environmental changes in real time, avoid resource waste or time delay caused by environmental factors, and optimize overall construction efficiency.

[0035] Further, the present application provides a method for constructing an environmental progress correlation matrix and dynamically correcting the weight decay coefficient of a building construction resource allocation map, comprising:

[0036] The row dimension of the environmental progress correlation matrix is the construction environment data; the column dimension of the environmental progress correlation matrix includes a concrete engineering sub-interval, a steel structure installation sub-interval, and a door and window installation sub-interval; and the matrix element quantization and dynamic updating of the environmental progress correlation matrix are performed.

[0037] Optionally, first, an environment progress correlation matrix is established according to different construction environment parameters and process intervals, the row dimension of the matrix represents construction environment data, that is, environmental factors such as temperature, humidity, wind speed, and light intensity monitored in real time, the column dimension represents different construction process sub-intervals, such as concrete engineering sub-interval, steel structure installation sub-interval, and door and window installation sub-interval, and each element in the matrix represents the influence degree of a certain environmental factor on the construction progress of a specific process sub-interval. Subsequently, the set construction efficiency influence coefficient is assigned to the corresponding position of the environment progress correlation matrix to complete the quantization of the environment progress correlation matrix, and then the same weight decay coefficient correction process is performed according to the data in the environment progress correlation matrix, so as to complete the dynamic update of the weight decay coefficient and ensure that the construction progress and resource use efficiency are maximized.

[0038] Further, the application provides that when the construction environment data does not meet the safe construction environment limit, the matrix element value of the environment progress correlation matrix is set to 0.

[0039] Optionally, when it is detected that there is data exceeding the safe construction environment limit range in the construction environment data, an alarm mechanism is triggered to remind the project management personnel to pay attention to the environmental abnormality. At the same time, the progress influence value of the construction process related to these abnormal environmental conditions is adjusted, that is, the related matrix element value in the environment progress correlation matrix is set to 0. For example, if the temperature of the construction site is too high and exceeds the safe range of the concrete pouring process, the system will detect this abnormality and set the matrix element value between the temperature and the concrete engineering sub-interval to 0, which means that the construction progress of the concrete engineering sub-interval will be considered as unable to proceed under such unsafe environmental conditions. In this way, it can be ensured that each process in the construction process is carried out under safe and suitable conditions, and the safety of construction personnel and the quality of the project are maximized.

[0040] Further, the application provides resource compensation reminders combined with dynamic threshold adjustment rules, and the method comprises:

[0041] The start symbol and the end symbol are used for timing feature analysis, and the start symbol and the end symbol are used to mark the basic construction stage, the main structure construction stage, and the decoration stage. The dynamic threshold adjustment rule is configured through the timing relationship corresponding to the start symbol and the end symbol.

[0042] Optionally, in the construction process, different stages of the project have different construction characteristics and requirements, therefore, in order to effectively manage the construction progress, the start symbol and the end symbol are used for time sequence feature analysis to mark and distinguish different construction stages. Specifically, the start symbol and the end symbol are key nodes that identify the beginning and end of the construction stage, and each construction stage (such as the foundation construction stage, the main structure construction stage and the decoration stage) has a clear start and end time. These symbols mark the beginning and end of a stage and can help the system accurately locate the current construction progress to the stage. In the time sequence feature analysis of the start symbol and the end symbol, different stages are first divided according to the overall time framework of the construction project, ensuring that the start symbol and the end symbol of each stage are accurately corresponded, and then by monitoring the progress of each stage, the time between the start symbol and the end symbol is subtracted from the planned time consumption, and then the difference is divided by the planned time consumption to obtain the time flexibility coefficient. This time flexibility coefficient is greater than 0, indicating that the progress is lagging behind, and less than 0, indicating that the progress is ahead of schedule. Subsequently, the time flexibility coefficient is combined with the hard constraint to form the time sequence relationship between different stages, wherein the hard constraint is that a certain stage must be earlier than another stage, for example, after the foundation construction stage is completed, the main structure construction stage can start, and the decoration stage needs to start after the main structure construction is completed. Then, according to the determined time sequence relationship, the resource type, the historical accident case are combined to configure the risk early warning knowledge graph, and the configured risk early warning knowledge graph is embedded in the dynamic threshold adjustment rule, which is used to ensure that the construction stages are sequentially advanced, thereby optimizing the resource allocation in real time, improving the construction efficiency, and avoiding the delay of the construction period caused by the lagging progress.

[0043] Further, the method comprises:

[0044] The resource type, the historical accident case, the start symbol and the end symbol are associated, and the risk early warning knowledge graph is set. Based on the risk early warning knowledge graph, potential risk nodes are identified, and resource transfer optimization is performed.

[0045] Optionally, first, various types of resources (such as labor, materials, equipment, etc.) in the project are associated with the tasks of each construction stage, and each process and construction stage has specific requirements for different types of resources. By analyzing resource requirements, it can be assessed which resources are critical at a particular stage, and which resources may cause problems in construction progress due to lag or shortage. Then, historical accident cases are associated with different construction stages and processes, and historical accident cases usually include common problems in construction, construction delays, equipment failures, material supply problems, etc. By analyzing historical accident cases, potential risks of specific stages or specific resources can be identified, for example, some stages may be delayed due to extreme weather, and some resources (such as steel bars and concrete) may be out of stock due to supply chain problems. Then, according to the time sequence relationship between the start symbol and the end symbol of the construction stage and various types of resources and historical accident cases, a risk warning knowledge graph is constructed based on a graph convolution network with an attention mechanism, in which each node represents a different risk type or factor, and the relationship between the nodes reflects their interaction and influence in the construction process. Once the risk warning knowledge graph is constructed, potential risk nodes can be identified in real time based on these data. Specifically, the latest data of each construction stage will be input into the risk warning knowledge graph in real time, which will be matched with each node in the risk warning knowledge graph to assess whether there is a potential risk in the current construction site. Thus, the potential risk node, i.e. the construction stage with potential risk, is determined. Once the potential risk node is identified, the resource loan optimization mechanism will be triggered to perform the same resource compensation as described above, so as to reasonably adjust the resource allocation and ensure that the construction progress and quality are not affected.

[0046] Further, the present application provides a method for identifying potential risk nodes based on the risk warning knowledge graph, comprising:

[0047] setting a graph convolution network based on an attention mechanism, inputting node features including historical accident frequency and resource availability, and obtaining risk propagation weights between each construction process; determining key nodes of risk diffusion and risk propagation paths based on the risk propagation weights between each construction process; simulating a chain reaction process using the risk propagation paths based on the risk warning knowledge graph and the key nodes of risk diffusion to determine the potential risk nodes.

[0048] Optionally, in order to effectively identify and predict potential risks in building construction, a graph convolution network based on attention mechanism is set up to analyze the risk propagation weight between construction processes. The graph convolution network is a deep learning model for processing graph data, which can perform information transmission and feature updating in the graph structure. In order to more accurately simulate the spread of risks in construction projects, the feature data of each construction process (such as historical accident frequency, resource availability, etc.) is input into the graph convolution network. The historical accident frequency reflects the potential risks that a specific process may face due to historical reasons, while the resource availability represents the sufficiency of resources, which directly affects the execution progress and quality of the process. In the graph convolution network, through the propagation mechanism of the adjacency matrix, each node shares information with its neighbor nodes and updates the features. Combined with the attention mechanism, the information flow between neighbor nodes can be dynamically adjusted according to the feature values of each node. In this way, the relationship between construction processes can be modeled in a more intelligent way, so as to calculate the risk propagation weight between processes. These risk propagation weights represent the degree of risk impact that a process may have on its adjacent processes during the progress. For example, if a process has a high historical accident frequency and insufficient resource availability, the risk propagation weight of this process will be larger, which may cause a chain reaction to multiple subsequent processes. Subsequently, according to the risk propagation weight of each process and the risk propagation weight threshold, it is determined which processes are key nodes. By analyzing the connection relationship of these key nodes, the risk propagation path is drawn, which represents how the risk of a process gradually affects the subsequent processes. These paths may span multiple construction stages or even different resource demand areas. Based on the determined risk propagation path, the risk warning knowledge graph is used to simulate the changes of different construction stages and processes, and to predict which nodes may trigger a series of risk diffusion under certain conditions. If a process has a delay or resource allocation problem, it may not only affect the current process, but also cause the progress of multiple subsequent processes to lag behind. For example, in the construction stage, the delay of concrete pouring progress may affect the subsequent progress of steel structure installation and door and window installation. Through the simulation of this chain reaction process, potential risk nodes can be identified in advance to ensure that warning measures are taken at these nodes, and resource transfer optimization is performed according to the risk propagation path. Through these steps, not only can potential risk nodes in the building construction process be identified, but also these risks can be prevented by optimizing resource allocation, so as to ensure the smooth progress of construction.

[0049] In summary, the embodiments of the present application have at least the following technical effects:

[0050] This application first collects three-dimensional point data of the construction area and compares it with the BIM building model to extract deviation information between the construction progress and the planned progress. Then, it associates the construction log with each building component node of the BIM building model and sets a first progress evaluation index. Next, it associates material consumption records with each building component node of the BIM building model and sets a second progress evaluation index. Then, based on the deviation information and the first and second progress evaluation indices, it formulates a building construction resource allocation map that conforms to the logical relationship of the construction procedures. Finally, based on the building construction resource allocation map, and according to the weight attenuation coefficient, with resource allocation efficiency as the correlation feature, it performs a multi-scale evaluation of the cumulative impact range and provides resource compensation reminders based on dynamic threshold adjustment rules. These technical effects collectively solve the technical problems of data update lag and logical disconnection in construction procedures in traditional building construction progress monitoring, making it difficult to accurately identify progress deviations. It achieves the technical effect of real-time and accurate analysis of construction progress through multi-source data fusion and intelligent comparison with the BIM model, and dynamically optimizes resource allocation by combining multi-dimensional evaluation indices, thereby improving construction management efficiency.

[0051] Example 2, based on the same inventive concept as the digital monitoring method for building construction progress in the foregoing examples, such as... Figure 2 As shown, this application provides a digital monitoring system for building construction progress. The system includes: a real-time comparison module 11: collecting three-dimensional point data of the construction area, comparing it with the BIM building model, and extracting deviation information between the construction progress and the planned progress; a construction log association module 12: associating the construction log with each building component node of the BIM building model and setting a first progress evaluation index; a consumption record association module 13: associating material consumption records with each building component node of the BIM building model and setting a second progress evaluation index; a resource allocation map formulation module 14: using the deviation information, combined with the first progress evaluation index and the second progress evaluation index, to formulate a building construction resource allocation map that conforms to the logical relationship of the construction process; and a resource compensation reminder module 15: based on the building construction resource allocation map, according to the weight attenuation coefficient, using resource allocation efficiency as the correlation feature, performing multi-scale evaluation of the cumulative impact range, and combining dynamic threshold adjustment rules to provide resource compensation reminders.

[0052] Furthermore, the resource allocation map formulation module 14 is also used to perform the following method:

[0053] By using a sliding time window, the directed edges corresponding to the building construction resource allocation map are determined, connecting each construction process; at the same time, the preconditions, time dependencies, and resource association information between each construction process are marked.

[0054] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0055] The directed edges of the building construction resource configuration graph are dynamically weighted, the pre-requirement relationship, time dependence parameter and resource association information between the construction procedures are fused based on LSTM time sequence perception, and a weight decay coefficient is obtained.

[0056] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0057] A dynamic environmental parameter perception network is constructed by integrating a temperature and humidity sensing unit, a wind speed monitoring unit and a light intensity detection unit to obtain construction environment data; an environmental progress correlation matrix is constructed based on a procedure sub-interval associated with a construction efficiency influence coefficient and in combination with the construction environment data, and the weight decay coefficient of the building construction resource configuration graph is dynamically corrected.

[0058] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0059] The row dimension of the environmental progress correlation matrix is the construction environment data; the column dimension of the environmental progress correlation matrix includes a concrete engineering sub-interval, a steel structure installation sub-interval and a door and window installation sub-interval; and the matrix element of the environmental progress correlation matrix is quantified and dynamically updated.

[0060] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0061] When the construction environment data does not meet the safety construction environment limit, the matrix element value of the environmental progress correlation matrix is set to 0.

[0062] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0063] Time sequence feature analysis is performed on a start symbol and an end symbol, the start symbol and the end symbol are used to mark a basic construction stage, a main structure construction stage and a decoration stage; and the dynamic threshold adjustment rule is configured through the time sequence relationship corresponding to the start symbol and the end symbol.

[0064] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0065] A risk early warning knowledge graph is set by associating resource types, historical accident cases, start symbols and end symbols; potential risk nodes are identified based on the risk early warning knowledge graph, and resource borrowing optimization is performed.

[0066] Further, the resource compensation reminding module 15 is further used to execute the following method:

[0067] The attention mechanism-based graph convolution network is set, input node features include historical accident frequency and resource availability, and risk propagation weights between each construction process are obtained; based on the risk propagation weights between each construction process, a key node of risk diffusion and a risk propagation path are determined; based on the risk early warning knowledge graph and the key node of risk diffusion, a cascading reaction process is simulated using the risk propagation path, and the potential risk node is determined.

[0068] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above describes a specific embodiment of the present application. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0069] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0070] The present application is only an exemplary description of the present application, and should be considered as covering any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A method for digitally monitoring building construction progress, characterized in that, The method includes: Collect three-dimensional point data of the construction area, compare it with the BIM building model, and extract the deviation information between the construction progress and the planned progress. Associate the construction log with each building component node of the BIM building model and set the first progress evaluation index; Associate the material consumption records with each building component node of the BIM building model and set a second progress evaluation index. Based on the deviation information, and combined with the first progress evaluation index and the second progress evaluation index, a building construction resource allocation map that conforms to the logical relationship of construction procedures is formulated. Based on the building construction resource allocation map, according to the weight attenuation coefficient and with resource allocation efficiency as the correlation feature, the cumulative impact range is evaluated on a multi-scale basis, and resource compensation reminders are given in combination with dynamic threshold adjustment rules. According to the preset weights for each scale, the normalized results of the three influence values ​​are weighted and calculated to obtain the multi-scale evaluation result. The multi-scale evaluation result is then compared with a dynamic threshold. This dynamic threshold is used to determine whether the current construction needs compensation. It is dynamically set according to actual business needs to adapt to the construction needs at different stages. When the multi-scale evaluation result exceeds the dynamic threshold, a resource compensation reminder is triggered. The reminder helps managers adjust resource allocation in a timely manner to supplement resources for key nodes and potential risk nodes, including increasing materials, allocating labor, or adjusting equipment arrangements, thereby avoiding resource waste and maintaining the smooth progress of construction. By using a sliding time window, the directed edges corresponding to the building construction resource allocation map are determined, and each construction process is connected. At the same time, the preconditions, time dependencies, and resource association information between each construction process are marked. Based on the weight decay coefficient and with resource allocation efficiency as the correlation feature, the method further includes: Dynamic weights are assigned to the directed edges of the building construction resource allocation graph. Based on LSTM time-series perception, the pre-constraint relationships, time dependency parameters, and resource association information between various construction procedures are fused to obtain the weight decay coefficient.

2. The digital monitoring method for building construction progress as described in claim 1, characterized in that, The method for providing resource compensation reminders by combining dynamic threshold adjustment rules includes: Temporal feature analysis is performed using start and end symbols, which are used to mark the foundation construction stage, the main structure construction stage, and the decoration and finishing stage. The dynamic threshold adjustment rule is configured based on the temporal relationship between the start symbol and the end symbol.

3. The digital monitoring method for building construction progress as described in claim 2, characterized in that, The method includes: Link resource types, historical accident cases, start symbols, and end symbols to create a risk warning knowledge graph; Based on the aforementioned risk warning knowledge graph, potential risk nodes are identified, and resource allocation is optimized.

4. The digital monitoring method for building construction progress as described in claim 3, characterized in that, Based on the aforementioned risk warning knowledge graph, potential risk nodes are identified, and the method includes: Set up an attention-based graph convolutional network, with input node features including historical accident frequency and resource availability, and obtain risk propagation weights between various construction procedures; Based on the risk propagation weights among the various construction procedures, the key nodes and risk propagation paths for risk diffusion are determined. Based on the aforementioned risk warning knowledge graph and key nodes of risk diffusion, the risk propagation path is used to simulate the chain reaction process and identify the potential risk nodes.

5. The digital monitoring method for building construction progress as described in claim 1, characterized in that, Combining the first progress assessment indicator and the second progress assessment indicator, a building construction resource allocation map conforming to the logical relationship of construction procedures is formulated. The method includes: A dynamic environmental parameter sensing network is constructed by integrating temperature and humidity sensing units, wind speed monitoring units, and light intensity detection units to acquire construction environment data. Based on the process sub-intervals associated with the construction efficiency impact coefficient, and combined with the construction environment data, an environmental progress correlation matrix is ​​constructed, and the weight attenuation coefficient of the building construction resource allocation map is dynamically corrected.

6. The digital monitoring method for building construction progress as described in claim 5, characterized in that, Constructing an environmental progress correlation matrix and dynamically adjusting the weight decay coefficient of the building construction resource allocation map, the method includes: The row dimension of the environmental progress correlation matrix is ​​the construction environment data; The column dimensions of the environmental progress correlation matrix include the concrete engineering sub-interval, the steel structure installation sub-interval, and the door and window installation sub-interval; The environmental progress correlation matrix is ​​quantized and dynamically updated.

7. The digital monitoring method for building construction progress as described in claim 6, characterized in that, When the construction environment data does not meet the safety construction environment restrictions, the matrix element values ​​of the environmental progress correlation matrix are set to 0.

8. A digital monitoring system for building construction progress, characterized in that: The system is used to execute the digital monitoring method for building construction progress according to any one of claims 1-7, and the system includes: Real-time comparison module: Collects three-dimensional point data of the construction area, compares it with the BIM building model, and extracts information on the deviation between the construction progress and the planned progress; Construction log association module: Associates the construction log with each building component node of the BIM building model and sets the first progress evaluation index; Consumption record association module: associates material consumption records with each building component node of the BIM building model and sets a second progress evaluation index; Resource allocation map formulation module: Based on the deviation information and combined with the first progress evaluation index and the second progress evaluation index, formulate a building construction resource allocation map that conforms to the logical relationship of construction procedures; Resource compensation reminder module: Based on the building construction resource allocation map, according to the weight attenuation coefficient, with resource allocation efficiency as the correlation feature, the cumulative impact range is evaluated at multiple scales, and resource compensation reminders are given in combination with dynamic threshold adjustment rules.

Images