Intelligent building construction management method and system

Abstract

The invention relates to the field of intelligent management, and provides an intelligent building construction management method and system, and the method comprises the steps: obtaining construction process information based on a BIM model of a preset first region, sorting a plurality of construction sub-plans in the construction process information according to a construction sequence, and obtaining a first construction sequence; and updating the first construction sequence according to the historical climate data of the first region to obtain a second construction sequence, and finally carrying out construction work of the first region based on the second construction sequence. In this way, the intelligence and refinement level of building construction management can be improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent management, and more specifically, to a smart construction management method and system. Background Art

[0002] Smart construction management aims to significantly improve the level of refinement and intelligence of project management through advanced technologies and methods, thereby reducing costs and ensuring construction quality and safety. In existing technologies, civil engineering construction is susceptible to weather changes, especially outdoor construction, which often cannot proceed as planned due to adverse weather conditions, which will lead to confusion in the construction schedule, which not only increases labor costs but also reduces construction efficiency.

[0003] Patent CN118037027B proposes an intelligent civil engineering construction management method and system. The method first determines the construction process based on the 3D construction model and generates construction process information containing multiple construction sub-plans. Then, the first construction sequence is generated according to the construction order, and the sequence is predicted and updated using historical climate data to form a second construction sequence that is more in line with the actual weather. Finally, the construction is guided by this sequence to solve the problems of unreasonable construction schedules and low construction efficiency in the existing ones.

[0004] However, when the patent uses historical climate data to predict and update the first construction sequence, it mainly relies on the similarity between historical climate data and current climate data, ignoring long-term climate trends and cyclical changes, which may lead to inaccurate prediction results. For example, the climate in some areas may show obvious seasonal changes or long-term warming trends, which are easily ignored in prediction methods that only rely on similarity.

[0005] In addition, the complexity and dynamic changes between various climate parameters are also important factors affecting the accuracy of prediction. Although the deep learning model is used in the patent, it cannot effectively capture the interaction and time series dynamic changes between various climate data. This simplified processing method may not provide sufficient support when facing complex and changeable climate conditions, resulting in the scientificity and rationality of the construction plan being affected, which in turn affects the construction progress and cost control.

[0006] Therefore, an optimized smart construction management solution is needed. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present application provides a smart construction management method and system.

[0008] According to one aspect of the present application, a smart construction management method is provided, which includes: Based on a preset BIM model of the first area, construction process information is obtained; multiple construction sub-plans in the construction process information are sorted according to a construction order to obtain a first construction sequence; based on historical climate data of the first area, the first construction sequence is updated to obtain a second construction sequence; based on the second construction sequence, construction is performed on the first area; Wherein, updating the first construction sequence based on the historical climate data of the first area to obtain the second construction sequence includes: predicting the climate of the first area based on the historical climate data of the first area to obtain first climate information, and updating each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence; The step of predicting the climate of the first region based on the historical climate data of the first region to obtain first climate information includes: Acquire a time queue of historical climate data of the first area, and extract historical climate data within a construction period from the time queue of historical climate data to obtain a time queue of historical climate data during the construction period; Performing time series regularization and historical climate time series semantic feature extraction on the time series of the historical climate data and the time series of the historical climate data during the construction period respectively to obtain the time series correlation features of the historical climate multidimensional parameters and the time series correlation features of the historical climate multidimensional parameters during the construction period; Performing fine-grained feature cross-domain interactive encoding on the historical climate multidimensional parameter time series correlation features and the historical climate multidimensional parameter time series correlation features during the construction period to obtain the historical climate multidimensional parameter time series fine-grained semantic interactive fusion features; Based on the time series fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameters, a prediction result is obtained as the first climate information.

[0009] According to another aspect of the present application, a smart construction management system is provided, which includes: A construction process information data acquisition module, used to obtain construction process information based on a preset BIM model of the first area; a construction sub-plan sorting module, used to sort multiple construction sub-plans in the construction process information according to the construction sequence to obtain a first construction sequence; a construction sequence updating module, used to update the first construction sequence based on the historical climate data of the first area to obtain a second construction sequence; a construction implementation module, used to construct the first area based on the second construction sequence; The construction sequence updating module includes: a second construction sequence generating subunit, which is used to predict the climate of the first area based on the historical climate data of the first area to obtain first climate information, and to update each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence; Wherein, the second construction sequence generating subunit includes: A secondary subunit for collating historical climate data during the construction period, for obtaining a time queue of historical climate data of the first region, and extracting historical climate data within the construction period from the time queue of historical climate data to obtain a time queue of historical climate data during the construction period; A secondary sub-unit for extracting historical climate time series features during the historical climate construction period is used to respectively perform time series regularization and historical climate time series semantic feature extraction on the time queue of the historical climate data and the time queue of the historical climate data during the construction period to obtain the time series correlation features of the historical climate multidimensional parameters and the time series correlation features of the historical climate multidimensional parameters during the construction period; A secondary sub-unit is provided for generating fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter temporal series, which is used for performing fine-grained feature cross-domain interaction encoding on the historical climate multi-dimensional parameter temporal series correlation features and the historical climate multi-dimensional parameter temporal series correlation features during the construction period to obtain fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter temporal series; The first climate information prediction generates a secondary subunit, which is used to obtain a prediction result as the first climate information based on the fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter time series.

[0010] This application has significant technical effects due to the adoption of the above technical solutions: The smart construction management method and system provided by the present application extracts the historical climate data within the construction period from the time queue of the acquired historical climate data to obtain the time queue of the historical climate data during the construction period, and uses a data analysis and processing algorithm based on deep learning to perform temporal regularization and temporal association of the historical climate data and the historical climate data during the construction period, so as to automatically predict the climate data of the first area based on the interactive fusion representation between the temporal association characteristics of the historical climate multidimensional parameters and the temporal association characteristics of the historical climate multidimensional parameters during the construction period. In this way, the mutual influence between different climate factors and their temporal change trends can be excavated and fully reflected, thereby significantly improving the accuracy and reliability of climate forecasting, thereby providing strong support for the scientificity and rationality of the construction plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 It is a flow chart of the smart construction management method according to an embodiment of the present application.

[0013] Figure 2 This is a flowchart of predicting the climate of the first area based on the historical climate data of the first area to obtain first climate information in a smart construction management method according to an embodiment of the present application.

[0014] Figure 3 In the smart construction management method according to the embodiment of the present application, fine-grained feature cross-domain interactive encoding is performed on the historical climate multidimensional parameter time series correlation characteristics and the historical climate multidimensional parameter time series correlation characteristics of the construction period to obtain a flowchart of the fine-grained semantic interactive fusion characteristics of the historical climate multidimensional parameter time series.

[0015] Figure 4 In the smart construction management method according to the embodiment of the present application, based on the historical climate time series joint fine-grained core feature semantic clustering center vector, the set of historical climate time series joint fine-grained core feature vectors is subjected to multi-dimensional feature fine-grained fusion to obtain the flowchart of the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion features.

[0016] Figure 5 This is a system block diagram of a smart construction management system according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0018] Based on the problems in the above-mentioned background technology, the present application provides a smart construction management method. Figure 1 Flow chart of the smart construction management method according to the embodiment of the present application. Figure 1As shown, the smart construction management method according to the embodiment of the present application includes: S110, obtaining construction process information based on a preset BIM model of the first area; S120, sorting multiple construction sub-plans in the construction process information according to the construction order to obtain a first construction sequence; S130, based on the historical climate data of the first area, updating the first construction sequence to obtain a second construction sequence; S140, constructing the first area based on the second construction sequence.

[0019] In step S110, the construction process information is obtained based on the preset BIM model of the first area. Specifically, in an embodiment of the present application, the first area is a construction area to be constructed, the construction process includes multiple construction sub-plans, and the construction process information includes the construction content and ideal duration of each construction sub-plan. It should be understood that the BIM model (Building Information Model) can describe various aspects of a construction project in detail, including the overall layout, structure, and detailed information of each part of the construction area. By obtaining the construction process information of the construction area to be constructed based on the BIM model, the construction content can be specifically understood, which can provide clear guidance for the construction team. Specifically, the construction process information helps identify the dependencies between the various construction sub-plans, thereby ensuring that construction activities are carried out in the correct order, avoiding delays caused by improper planning, and at the same time, by understanding the ideal duration and requirements of each sub-plan, it helps to reasonably allocate human, material and financial resources and improve construction efficiency.

[0020] In smart construction management, obtaining construction process information based on the preset BIM model of the first area is a crucial basic work. This process not only involves the construction of the BIM model, but also includes the decomposition of construction tasks, the calculation of ideal duration, the integration and verification of construction process information, and other links. The following is a detailed description of this process: First, determine the specific location and scope of the construction project, that is, the "first area". The basic information of this area, such as the geographical coordinates, topography, and surrounding environment, needs to be recorded in detail. The accuracy of this information is crucial for the subsequent BIM model construction and construction plan formulation. After clarifying the construction area, it is necessary to collect all relevant design data such as the project's architectural design drawings, structural design drawings, and electromechanical design drawings. Next, use professional BIM modeling software (such as Revit, ArchiCAD, etc.) to create a detailed three-dimensional building information model (BIM) based on the design data. The BIM model not only contains the geometric shape of the building, but also includes various attribute information, such as material type, component size, construction process, etc. The construction of the BIM model is a complex process that requires professional technicians to gradually refine and improve it according to the design drawings and the actual situation on site. In this process, it is necessary not only to ensure the geometric accuracy of the model, but also to ensure that the attribute information of each component in the model is accurate. After the construction of the BIM model is completed, it can provide a solid foundation for the subsequent extraction of construction process information.

[0021] Based on the BIM model, the entire construction project needs to be decomposed into multiple specific construction tasks, namely construction sub-plans. Each construction sub-plan should contain detailed information such as specific construction content, required materials, equipment, human resources, etc. The decomposition of construction tasks needs to take into account the scale, complexity and construction specifications of the project. For example, a large-scale construction project may need to be decomposed into multiple sub-plans such as foundation construction, main structure construction, interior and exterior decoration, and mechanical and electrical installation. Each sub-plan can be further subdivided into smaller tasks, such as foundation construction can be subdivided into earth excavation, pile foundation construction, cushion layer laying, etc.

[0022] Then, for each construction sub-plan, its ideal construction duration needs to be estimated. This requires comprehensive consideration of factors such as construction difficulty, resource availability, and weather conditions. The calculation of the ideal duration can be based on historical data and experience, or it can be obtained through simulation. For example, based on the construction experience of similar projects in the past and the actual situation on site, the average duration of foundation construction can be estimated. The calculation of the ideal duration also needs to take into account uncertainties that may arise during the construction process, such as weather changes, equipment failures, etc., to ensure the rationality and feasibility of the construction plan.

[0023] Next, integrate all construction sub-plans and their related information into a complete construction process information. The construction process information should include the following: Construction sub-plan list: List the names, numbers, construction contents, etc. of all construction sub-plans. Ideal duration: The estimated completion time of each construction sub-plan. Resource requirements: The materials, equipment, human resources, etc. required for each construction sub-plan. Dependencies: Indicate which construction sub-plans can only start after other sub-plans are completed.

[0024] In the BIM model, each construction sub-plan also needs to be associated with the corresponding building components or areas. For example, a sub-plan may involve the steel bar binding of a certain floor. In this way, the sub-plan should be associated with the steel bar components of that floor. In this way, the construction process information can be seamlessly connected with the BIM model, providing support for subsequent construction plan formulation and resource scheduling. And using the visualization function of BIM software, the construction process information can be displayed in a graphical way. Project managers and construction personnel can intuitively understand the location, content and progress of each construction sub-plan through the BIM model, improving the project management level and construction efficiency. Finally, the construction process is simulated in the BIM model to check the rationality and feasibility of the construction process information.

[0025] Through the above steps, based on the preset BIM model of the first area, construction process information can be systematically and comprehensively obtained. This information can provide a basis for the subsequent construction plan sequencing and provide important support for the management and coordination of the overall construction project.

[0026] In step S120, the multiple construction sub-plans in the construction process information are sorted according to the construction order to obtain a first construction sequence. It should be understood that the construction process is usually a complex system, and there are often dependencies between the various sub-plans. For example, some construction tasks must be carried out after other tasks are completed (for example, superstructure construction can only be carried out after the foundation construction is completed). In order to help identify and maintain these dependencies, avoid construction delays caused by improper sequence, reduce conflicts between different construction tasks, and ensure efficient use of resources, it is necessary to sort the multiple construction sub-plans in the construction process information according to the construction order in this application. The first construction sequence obtained by sorting is more in line with the actual construction situation and can better guide construction activities. This helps to enhance the feasibility of the construction plan and thereby reduce uncertainty and risks in the construction process.

[0027] In order to ensure that construction activities proceed in an orderly manner, it is necessary to sort the multiple construction sub-plans in the construction process information according to the construction sequence. This process needs to comprehensively consider the logical relationship between construction tasks, resource availability, construction specifications, project goals and other factors. The following is a detailed description of this process: First, the logical relationship between construction tasks needs to be analyzed. The logical relationship between construction tasks mainly includes predecessor relationship and parallel relationship. The predecessor relationship means that some construction sub-plans must be started after other sub-plans are completed. For example, the foundation construction must be completed before the main structure construction. The parallel relationship means that some construction sub-plans can be carried out at the same time in the same time period. For example, different floors of the main structure construction can be carried out at the same time. By analyzing the logical relationship between construction tasks, the dependency relationship of each construction sub-plan can be determined, providing a basis for subsequent sorting. For example, if a sub-plan needs to be started after another sub-plan is completed, then there is a predecessor relationship between the two sub-plans, which needs to be reflected in the sorting.

[0028] Next, the availability of construction resources needs to be considered. Construction resources include human resources, machinery and equipment, materials, etc. When determining the construction sequence, the availability and scheduling of resources need to be considered. For example, if there is a shortage of machinery and equipment for a period of time, the construction sequence may need to be adjusted to give priority to those construction sub-plans that do not require a large amount of machinery and equipment. Similarly, if the supply of a certain material is unstable, the construction sequence may need to be adjusted to give priority to those construction sub-plans that are less dependent on the material. By analyzing the availability of construction resources, it is possible to ensure that each construction sub-plan is carried out when there are sufficient resources, avoiding construction delays caused by resource shortages. For example, project managers can view the available time and quantity of each resource through resource calendars and resource demand plans, so as to arrange the construction sequence reasonably.

[0029] Construction specifications and project goals are also important bases for determining the construction sequence. Construction specifications usually include local building standards, safety specifications, environmental protection requirements, etc. When determining the construction sequence, it is necessary to ensure that each construction sub-plan complies with relevant specifications and requirements to avoid safety accidents and quality problems caused by illegal operations. Project goals include the project's duration, cost, quality, etc. When determining the construction sequence, it is necessary to comprehensively consider the various goals of the project to ensure that construction activities can achieve cost control and quality assurance while meeting the duration requirements. For example, if the project duration is very tight, it may be necessary to prioritize those construction sub-plans that have a greater impact on the duration to ensure that tasks on the critical path are completed on time.

[0030] In order to sort the construction sequence more efficiently, project management tools such as Microsoft Project and Primavera P6 can be used. These tools provide powerful project management functions that can help project managers quickly generate construction sequences. The specific steps are as follows: First, enter all construction sub-plans and their related information into the project management tool, including the name, number, construction content, required resources, ideal duration, etc. of the sub-plan. Then, define the dependencies between each construction sub-plan in the project management tool. For example, by setting predecessor tasks and successor tasks, clarify the predecessor relationship and parallel relationship of each sub-plan. The project management tool will automatically generate a preliminary construction sequence based on the defined dependencies. The project manager can view the generated sequence to check whether there are omissions or errors. Adjust and optimize the generated construction sequence according to the actual situation of the project and resource availability. For example, if resources are tight during a period of time, the construction sequence can be adjusted to give priority to those construction sub-plans with lower resource requirements. After multiple adjustments and optimizations, the first construction sequence is finally generated.

[0031] After the first construction sequence is generated, it needs to be verified and optimized to ensure its rationality and feasibility. The specific steps are as follows: Simulate the construction process in the project management tool to check the rationality and feasibility of the construction sequence. Through simulation, potential problems such as resource conflicts and construction sequence errors can be discovered. According to the simulation results, the construction sequence is adjusted and optimized as necessary.

[0032] In summary, by sorting the multiple construction sub-plans in the construction process information according to the construction order, a first construction sequence can be generated.

[0033] In step S130, based on the historical climate data of the first area, the first construction sequence is updated to obtain a second construction sequence. Specifically, in an embodiment of the present application, based on the historical climate data of the first area, the first construction sequence is updated to obtain a second construction sequence, including: predicting the climate of the first area based on the historical climate data of the first area to obtain first climate information, and updating each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence.

[0034] It should be understood that the importance of climatic conditions to construction activities cannot be ignored. It directly affects the safety, efficiency, quality and cost of construction. For example, high temperature weather can cause excessive physical exertion of workers, reduce work efficiency, and even cause heat stroke. At the same time, high temperature will also affect building materials. For example, the water in concrete evaporates quickly at high temperature, so the amount of water needs to be increased. When it exceeds 30℃, it may be necessary to add retarders to prevent the tensile strength of concrete from decreasing and cracks from appearing. Low temperature weather will make some construction processes impossible, such as paint application and concrete pouring. Low temperature may also cause materials to become brittle and affect the quality of construction. The amount of precipitation directly affects the progress of construction, especially in open-air operations such as earthwork and electric welding. Rainfall will cause the operation to be suspended, affecting the progress of construction. In addition, precipitation may also cause construction materials to become damp and damaged, affecting the quality of construction. When the wind reaches a certain intensity, it will threaten the safety of the construction site. For example, when the wind reaches level 3 or above, some operations should take protective measures or stop to ensure construction safety. Excessive wind may also increase the risk of high-altitude operations, and equipment needs to be reinforced to prevent wind. High humidity will increase the evaporation time of water, slowing down the drying of construction materials and thus extending the construction period.

[0035] A humid environment can also easily cause building materials to become damp and moldy, further extending the construction period.

[0036] Accordingly, in predicting the climate of the first region based on the historical climate data of the first region, the technical concept of the present application is to obtain the time queue of the historical climate data of the first region, and extract the historical climate data within the construction period from the time queue of the historical climate data (temperature value, humidity value, precipitation and wind speed value) to obtain the time queue of the historical climate data of the construction period, and use the data analysis and processing algorithm based on deep learning to perform the time series regularization and time series association of the historical climate data and the historical climate data within the construction period, so as to automatically predict the climate data of the first region according to the interactive fusion representation between the time series association characteristics of the historical climate multidimensional parameters and the time series association characteristics of the historical climate multidimensional parameters of the construction period. In this way, the mutual influence between different climate factors and their time series change trends can be excavated and fully reflected, thereby significantly improving the accuracy and reliability of climate prediction, and providing strong support for the scientificity and rationality of the construction plan.

[0037] Figure 2 The present invention is a flowchart of predicting the climate of the first area based on the historical climate data of the first area to obtain the first climate information in the smart construction management method according to the embodiment of the present application. Figure 2As shown, based on the historical climate data of the first area, the climate of the first area is predicted to obtain the first climate information, including: S131, obtaining the time queue of the historical climate data of the first area, and extracting the historical climate data within the construction time period from the time queue of the historical climate data to obtain the time queue of the historical climate data during the construction period; S132, respectively performing time series regularization and historical climate time series semantic feature extraction on the time queue of the historical climate data and the time queue of the historical climate data during the construction period to obtain the historical climate multi-dimensional parameter time series correlation feature and the historical climate multi-dimensional parameter time series correlation feature of the construction period; S133, performing fine-grained feature cross-domain interactive encoding on the historical climate multi-dimensional parameter time series correlation feature and the historical climate multi-dimensional parameter time series correlation feature of the construction period to obtain the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion feature; S134, based on the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion feature, obtaining the prediction result as the first climate information.

[0038] In step S131, the time queue of the historical climate data of the first area is obtained, and the historical climate data in the construction time period is extracted from the time queue of the historical climate data to obtain the time queue of the historical climate data of the construction period. Specifically, in the embodiment of the present application, the historical climate data includes temperature value, humidity value, precipitation and wind speed value. It should be understood that climate conditions are one of the important factors affecting construction activities. Climate factors such as temperature, humidity, precipitation and wind speed will directly affect the construction process, such as high temperature may cause workers to work less efficiently, excessive humidity may affect the performance of materials, and excessive precipitation may cause construction to be suspended. In order to understand the basic information of climate change in the construction area and help understand and analyze the climate conditions that may be encountered during construction, it is necessary to obtain the historical climate data of the first area and extract the historical climate data in the construction time period from the time queue of the historical climate data to obtain the time queue of the historical climate data of the construction period. The time queue of the historical climate data of the construction period obtained provides sufficient data support for the climate prediction model. By analyzing the historical climate data, the climate characteristics of the construction area can be more accurately understood, so as to formulate scientific construction plans and measures. This helps improve construction efficiency and quality and reduce construction delays and rework due to climate factors.

[0039] As an important step in climate prediction and construction plan optimization, this application needs to obtain historical climate data and extract historical climate data during the construction period. This process requires accurate collection and processing of a large amount of climate data to ensure the integrity and accuracy of the data. The following is a detailed description of this process: First, it is necessary to obtain historical climate data for the first area. This data can usually be obtained from meteorological stations, meteorological service providers and other channels. Historical climate data includes the following aspects: temperature value, humidity value, precipitation, wind speed value. The collected historical climate data should cover a longer period of time, usually including at least the data of the past year, and longer data can also be selected to improve the accuracy of the prediction. For example, historical climate data of the past five years can be selected to better capture the long-term trends and cyclical changes of the climate.

[0040] After collecting historical climate data, it is necessary to process these data and construct a time queue of historical climate data. A time queue is a structure that stores data in chronological order, which can be easily analyzed and processed in time series. The specific steps are as follows: First, clean the collected historical climate data to remove invalid data and outliers. For example, if the temperature value on a certain day is obviously abnormal (such as beyond the normal range), it needs to be corrected or deleted. Data cleaning is an important step to ensure data quality, and any outliers may affect the subsequent analysis results. Next, standardize the data from different sources to ensure that the data format is consistent. For example, unify all temperature values ​​into degrees Celsius and all precipitation into millimeters. Data standardization can eliminate differences between different data sources and make data easier to process and analyze. Then, align all climate parameters in chronological order to form a time series of multidimensional parameters. For example, parameters such as temperature, humidity, precipitation, and wind speed should correspond to the same time point every day. Through time alignment, it can be ensured that the data at each time point is complete, which is convenient for subsequent time series analysis. In the process of building a time queue, the data at each time point can be represented as a vector containing all climate parameters for that day. For example, the data for January 1, 2023 can be expressed as [20°C, 60%, 0mm, 5m / s], which respectively represent the temperature, humidity, precipitation, and wind speed of that day.

[0041] After constructing the time queue of historical climate data, it is necessary to extract the historical climate data within the construction period. The construction period refers to the specific time range of the planned construction of the project, for example, from March 1, 2024 to December 31, 2024. The specific steps are as follows: First, clarify the construction start date and end date of the project to form the construction period. For example, the construction period is from March 1, 2024 to December 31, 2024. Then, from the time queue of historical climate data, filter out the data within the construction period. For example, the climate data for each day from March 1, 2024 to December 31, 2024. When filtering data, it is necessary to ensure that the data at each time point is complete and there are no missing values. If missing values ​​are found, interpolation methods can be used to fill them. For example, if the precipitation data for a certain day is missing, the data of the previous and next few days can be used for interpolation to ensure the continuity and integrity of the data.

[0042] The filtered data are arranged in chronological order to form a time queue of historical climate data during the construction period. The data at each time point is still represented as a vector, containing all climate parameters of the day. In this way, a complete and continuous time queue of historical climate data during the construction period can be obtained, providing important support for subsequent climate prediction and construction plan optimization.

[0043] Finally, in order to ensure the accuracy and completeness of the historical climate data extracted during the construction period, data verification and quality control are required. The specific steps are as follows: First, check whether there is missing data at each time point during the construction period. If there is missing data, interpolation or filling is required. For example, if the data of a certain day is missing, the data of the previous and next few days can be used for interpolation. Data integrity check is a key step to ensure data continuity, and any missing values ​​may affect subsequent analysis results. Next, check whether the data during the construction period is consistent. For example, check whether the changes in parameters such as temperature, humidity, precipitation, and wind speed are logical. If abnormal data is found, it needs to be corrected or deleted. Data consistency check can ensure the reliability and accuracy of the data, and any abnormal values ​​may affect subsequent analysis results.

[0044] Through the above steps, the accuracy and completeness of the extracted historical climate data during the construction period can be ensured, providing reliable data support for subsequent climate forecasting and construction plan optimization.

[0045] In step S132, the time queue of the historical climate data and the time queue of the historical climate data during the construction period are respectively time-ordered and historical climate time-order semantic features are extracted to obtain the time-order correlation features of the historical climate multidimensional parameters and the time-order correlation features of the historical climate multidimensional parameters during the construction period. Specifically, in an embodiment of the present application, the step S132 includes: arranging the time queue of the historical climate data and the time queue of the historical climate data during the construction period according to the climate sample dimension and time to obtain the time-order matrix of the historical climate multidimensional parameters and the time-order matrix of the historical climate multidimensional parameters during the construction period; passing the time-order matrix of the historical climate multidimensional parameters and the time-order matrix of the historical climate multidimensional parameters during the construction period through a historical climate time-order semantic feature extractor based on a void convolutional neural network model to obtain a time-order correlation feature graph of the historical climate multidimensional parameters as the time-order correlation features of the historical climate multidimensional parameters and the time-order correlation feature graph of the historical climate multidimensional parameters during the construction period as the time-order correlation features of the historical climate multidimensional parameters during the construction period.

[0046] It should be understood that the historical climate data of the first area and the historical climate data of the construction period contain information on multiple climate parameters, and these parameters have time series characteristics in the time dimension, and there is a mutual correlation between these parameters in the time scale. Based on this, in the technical solution of the present application, the time queue of the historical climate data and the time queue of the historical climate data of the construction period are arranged according to the climate sample dimension and time to obtain the time series matrix of the historical climate multidimensional parameters and the time series matrix of the historical climate multidimensional parameters of the construction period. In particular, at least historical data within the past year is included here, and data for a longer period of time can also be selected to improve the accuracy of the prediction.

[0047] Then, considering that the historical climate multidimensional parameter time series matrix and the construction period historical climate multidimensional parameter time series matrix both contain the deep temporal characteristics and semantic information of their respective parameters, and considering that the atrous convolutional neural network model can increase the receptive field without losing spatial resolution and without introducing additional parameters, this means that the model can capture a wider range of climate data characteristics, thereby more comprehensively understanding the laws and trends of climate change. Therefore, in the technical solution of the present application, the historical climate multidimensional parameter time series matrix and the construction period historical climate multidimensional parameter time series matrix are extracted through a historical climate time series semantic feature extractor based on a atrous convolutional neural network model to utilize the characteristics of atrous convolution to effectively capture the long-term trends in the historical climate data and the intrinsic structure and semantic patterns of the data, thereby obtaining a historical climate multidimensional parameter time series correlation feature map and a construction period historical climate multidimensional parameter time series correlation feature map.

[0048] In step S133, fine-grained feature cross-domain interactive coding is performed on the historical climate multidimensional parameter time series correlation features and the historical climate multidimensional parameter time series correlation features of the construction period to obtain the historical climate multidimensional parameter time series fine-grained semantic interactive fusion features. Specifically, Figure 3 In the smart construction management method according to the embodiment of the present application, the fine-grained feature cross-domain interactive encoding is performed on the historical climate multidimensional parameter time series correlation feature and the historical climate multidimensional parameter time series correlation feature of the construction period to obtain the flow chart of the historical climate multidimensional parameter time series fine-grained semantic interactive fusion feature. Figure 3 As shown, the step S133 includes: S1331, performing feature fine-grained decoupling on the historical climate multidimensional parameter time series correlation feature graph and the historical climate multidimensional parameter time series correlation feature graph of the construction period to obtain a set of historical climate multidimensional parameter time series correlation local fine-grained feature vectors and a set of historical climate multidimensional parameter time series correlation local fine-grained feature vectors of the construction period; S1332, decoupling each corresponding group of historical climate multidimensional parameter time series correlation local fine-grained feature vectors and the set of historical climate multidimensional parameter time series correlation local fine-grained feature vectors of the construction period; The local fine-grained feature vectors associated with the historical climate multi-dimensional parameter time series during the construction period are input into the fine-grained common feature extraction network to obtain a set of historical climate time series joint fine-grained core feature vectors; S1333, the set of historical climate time series joint fine-grained core feature vectors is input into the clustering network to obtain the historical climate time series joint fine-grained core feature semantic clustering center vector; S1334, based on the historical climate time series joint fine-grained core feature semantic clustering center vector, the set of historical climate time series joint fine-grained core feature vectors is subjected to multi-dimensional feature fine-grained fusion to obtain the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion features.

[0049] It should be understood that although the historical climate multidimensional parameter time series correlation features and the construction period historical climate multidimensional parameter time series correlation features belong to different time domains, there is indeed a complex interaction between them. For example, if historical data shows that a certain area often experiences high temperatures in the summer, then in future summer construction, special attention should be paid to the impact of high temperatures on construction. Therefore, in order to capture the correlation and mutual influence between the two time domains and to achieve a deeper level of feature fusion and interaction, in the technical solution of the present application, the historical climate multidimensional parameter time series correlation feature map and the construction period historical climate multidimensional parameter time series correlation feature map are subjected to fine-grained feature cross-domain interactive encoding to obtain a historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature map as a historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature.

[0050] Specifically, in the embodiment of the present application, the step S1331 includes: expanding each characteristic matrix along the channel dimension of the historical climate multidimensional parameter time series correlation feature map into a characteristic vector to obtain a set of local fine-grained characteristic vectors of the historical climate multidimensional parameter time series correlation; expanding each characteristic matrix along the channel dimension of the construction period historical climate multidimensional parameter time series correlation feature map into a characteristic vector to obtain a set of local fine-grained characteristic vectors of the construction period historical climate multidimensional parameter time series correlation. This process can be expressed by the formula: ;in, and They are respectively the time series correlation characteristic diagram of the historical climate multi-dimensional parameters and the time series correlation characteristic diagram of the historical climate multi-dimensional parameters during the construction period, In order to perform fine-grained feature decoupling operations on feature maps, , , and They are the first, second, and third local fine-grained feature vectors in the set of historical climate multidimensional parameter time series correlation. and The local fine-grained feature vectors of the historical climate multidimensional parameter time series association, , , and They are the first, second, and third local fine-grained feature vectors of the historical climate multidimensional parameter temporal association during the construction period. and The local fine-grained feature vectors of the historical climate multidimensional parameters time series association during the construction period.

[0051] That is, in order to be able to analyze local patterns in climate data in a more fine-grained manner, such as temperature fluctuations and humidity changes in a short period of time, the historical climate multidimensional parameter time series correlation feature map and the historical climate multidimensional parameter time series correlation feature map of the construction period are subjected to feature fine-grained decoupling to decompose the feature map into multiple local feature vectors. Each vector represents the climate characteristics within a small time window. The sets of local fine-grained feature vectors of historical climate multidimensional parameter time series correlation and the sets of local fine-grained feature vectors of historical climate multidimensional parameter time series correlation during the construction period are obtained, so as to capture more subtle historical climate changes and patterns.

[0052] Next, each corresponding set of the historical climate multidimensional parameter time series associated local fine-grained feature vectors and the historical climate multidimensional parameter time series associated local fine-grained feature vectors in the set of the historical climate multidimensional parameter time series associated local fine-grained feature vectors during the construction period is input into the fine-grained common feature extraction network to obtain a set of historical climate time series joint fine-grained core feature vectors. This process can be expressed by the formula: ;in, is the set of local fine-grained feature vectors associated with the historical climate multidimensional parameter time series. The local fine-grained feature vectors of the historical climate multidimensional parameter time series association, is the number of local fine-grained feature vectors in the set of historical climate multi-dimensional parameter time series associations during the construction period. The local fine-grained feature vector of the historical climate multi-dimensional parameters time series association during the construction period, , and They are point-by-point addition, point-by-point multiplication, and point-by-point subtraction. and are the weight matrix and bias vector respectively, for function, It is the first in the set of joint fine-grained core feature vectors of historical climate time series. The fine-grained core feature vector of historical climate time series is combined.

[0053] That is, through the fine-grained common feature extraction network, the common features are extracted from each group of corresponding historical climate multidimensional parameter time series associated local fine-grained feature vectors and construction period historical climate multidimensional parameter time series associated local fine-grained feature vectors to reflect the similarity and consistency of historical climate data in different time periods. In this way, a more representative and generalizable set of historical climate time series joint fine-grained core feature vectors can be generated. That is, the core feature not only contains the characteristics of each historical climate and construction period climate time domain, but also contains the interactive information between them, thereby improving the accuracy of climate prediction.

[0054] Specifically, in the embodiment of the present application, the step S1333 includes: calculating the position mean vector of the set of the historical climate time series joint fine-grained core feature vectors to obtain the semantic clustering center vector of the historical climate time series joint fine-grained core feature. This process can be expressed by the formula: ;in, It is the first in the set of joint fine-grained core feature vectors of historical climate time series. The historical climate time series are combined with fine-grained core feature vectors, is the number of vectors in the set of the historical climate time series joint fine-grained core feature vectors, It is the central vector of semantic clustering of the joint fine-grained core features of historical climate time series.

[0055] That is, each core feature vector is input into the clustering network to represent the semantic commonalities between the temporal correlation characteristics of the historical climate multidimensional parameters and the temporal correlation characteristics of the historical climate multidimensional parameters during the construction period in the entire time domain, and the semantic clustering center vector of the joint fine-grained core features of the historical climate time series is obtained to discover the hidden patterns and structures in the climate data.

[0056] Specifically, Figure 4 In the smart construction management method according to the embodiment of the present application, based on the historical climate time series joint fine-grained core feature semantic clustering center vector, the set of the historical climate time series joint fine-grained core feature vectors is subjected to multi-dimensional feature fine-grained fusion to obtain the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion feature. Figure 4 As shown, the step S1334 includes: S13341, constructing a historical climate time series query vector and a historical climate time series value vector based on each historical climate time series joint fine-grained core feature vector in the set of the historical climate time series joint fine-grained core feature vectors and constructing a historical climate time series key vector based on the historical climate time series joint fine-grained core feature semantic clustering center vector, and inputting the historical climate time series query vector, the historical climate time series value vector and the historical climate time series key vector of each historical climate time series joint fine-grained core feature vector into a global semantic interaction encoder based on a converter structure to obtain a set of historical climate time series context joint fine-grained core feature vectors; S13342, reshaping the feature shape of each historical climate time series context joint fine-grained core feature vector in the set of the historical climate time series context joint fine-grained core feature vector to obtain a historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map as the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature. More specifically, in the embodiment of the present application, the step S13341 includes: multiplying the query embedding matrix with the historical climate time series joint fine-grained core feature vector to obtain the historical climate time series query vector; multiplying the value embedding matrix with the historical climate time series joint fine-grained core feature vector to obtain the historical climate time series value vector; multiplying the key embedding matrix with the historical climate time series joint fine-grained core feature semantic clustering center vector to obtain the historical climate time series key vector; inputting the historical climate time series query vector, the historical climate time series value vector and the historical climate time series key vector into the global semantic interaction encoder based on the converter structure to obtain the historical climate time series context joint fine-grained core feature vector. The above process can be expressed as follows: ;in, It is the first in the set of joint fine-grained core feature vectors of historical climate time series. The historical climate time series are combined with fine-grained core feature vectors, is the query embedding matrix, yes The corresponding historical climate time series query vector, is the value embedding matrix, yes The corresponding historical climate time series value vector, is the key embedding matrix, is the historical climate time series key vector, for The transposed vector of for Length, yes function, is the matrix-vector multiplication, , , and They are the first, second, and third in the set of historical climate time series context joint fine-grained core feature vectors. and The historical climate time series context is combined with the fine-grained core feature vector, It is a collection of fine-grained core feature vectors of the historical climate time series context.

[0057] That is, the value vector and the query vector are constructed based on the joint fine-grained core feature vectors of each historical climate time series, and the key vector is constructed based on the cluster center vector. These vectors are input into the global semantic interaction encoder based on the converter structure to utilize the self-attention mechanism of the converter to capture the global dependencies between the joint features of historical climate and the correlation influence between the contexts, so as to generate a set of joint fine-grained core feature vectors that more semantically represent the context of historical climate time series.

[0058] Specifically, each historical climate time series context joint fine-grained core feature vector in the set of the historical climate time series context joint fine-grained core feature vectors is feature reshaped to obtain a historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map.

[0059] The process can be expressed as follows: ;in, is the set of joint fine-grained core feature vectors of the historical climate time series context, To perform a feature reshape operation, It is the time series fine-grained semantic interactive fusion feature map of the historical climate multi-dimensional parameters.

[0060] In step S134, based on the historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature, a prediction result is obtained as the first climate information. Specifically, in an embodiment of the present application, based on the historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature, a prediction result is obtained, including: passing the historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature map through a decoder-based climate predictor to obtain the prediction result, and the prediction result is used to represent the decoded value of the climate prediction data of the first area. In particular, the decoded value represents the predicted climate conditions during the execution of the first construction sequence, that is, the first climate information. That is, the historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature obtained by fine-grained cross-domain interaction using the historical climate multidimensional parameter time series association feature map and the historical climate multidimensional parameter time series association feature map of the construction period is decoded and processed to automatically predict the climate data of the first area. In this way, the mutual influence between different climate factors and their temporal change trends can be excavated and fully reflected, thereby significantly improving the accuracy and reliability of climate prediction, thereby providing strong support for the scientificity and rationality of the construction plan.

[0061] In particular, when the historical climate multidimensional parameter time series correlation feature map and the construction period historical climate multidimensional parameter time series correlation feature map represent the sample-time series dimension cross-correlation features of the historical climate data and the construction period historical climate data respectively, when performing cross-domain fine-grained feature global interaction encoding, the fine-grained interaction coding representation of the historical climate multidimensional parameter time series fine-grained semantic interaction fusion feature map in different time domain spaces will also have a selective time domain feature interaction state space representation in the distribution field due to the differences in fine-grained interaction coding in different time domains, resulting in an imbalance in the regression understanding of the feature representation relative to the source time domain semantics, affecting the accuracy of the decoding results.

[0062] Preferably, the process of passing the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature graph through a decoder-based climate predictor to obtain a prediction result includes: determining the number of zero eigenvalues ​​in the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature graph, and respectively calculating the reciprocal of the logarithm of the number of zero eigenvalues ​​with base two and the exponential value of the reciprocal of the number of zero eigenvalues ​​with base natural constants to obtain a first historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion representation value and a second historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion representation value; expanding the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature graph into a historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature vector; calculating the power function of each eigenvalue of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature vector with the reciprocal of the number of zero eigenvalues ​​as the exponent to obtain a historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion structural state vector; and converting the historical climate The multidimensional parameter temporal fine-grained semantic interaction fusion structure state vector is point-multiplied with the first historical climate multidimensional parameter temporal fine-grained semantic interaction fusion representation value to obtain the historical climate multidimensional parameter temporal fine-grained semantic interaction fusion information representation vector; the autocorrelation matrix of the historical climate multidimensional parameter temporal fine-grained semantic interaction fusion structure state vector is point-multiplied with the second historical climate multidimensional parameter temporal fine-grained semantic interaction fusion representation value and the weight hyperparameter to obtain the historical climate multidimensional parameter temporal fine-grained semantic interaction fusion regression understanding matrix; the historical climate multidimensional parameter temporal fine-grained semantic interaction fusion information representation vector is matrix-multiplied with the historical climate multidimensional parameter temporal fine-grained semantic interaction fusion regression understanding matrix to obtain the optimized historical climate multidimensional parameter temporal fine-grained semantic interaction fusion feature vector; the optimized historical climate multidimensional parameter temporal fine-grained semantic interaction fusion feature vector is passed through the decoder-based climate predictor to obtain the prediction result.

[0063] Here, the first historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion representation value and the second historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion representation value are expressed as: ;in, is the number of zero eigenvalues ​​in the fine-grained semantic interaction fusion feature map of the historical climate multi-dimensional parameter time series, represents the logarithmic function with base 2, represents the natural exponential function, is the time series fine-grained semantic interaction fusion representation value of the first historical climate multi-dimensional parameter, The second historical climate multi-dimensional parameter temporal fine-grained semantic interactive fusion representation value.

[0064] And the optimized historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature vector is expressed as: ;in, is the fine-grained semantic interaction fusion feature vector of the historical climate multi-dimensional parameter time series, and is a row vector, is the time series fine-grained semantic interaction fusion representation value of the first historical climate multi-dimensional parameter, is the number of zero eigenvalues ​​in the fine-grained semantic interaction fusion feature map of the historical climate multi-dimensional parameter time series, represents a power function that calculates each eigenvalue of the fine-grained semantic interactive fusion eigenvector of the historical climate multi-dimensional parameter time series with the inverse of the number of zero eigenvalues ​​as the exponent, It means point multiplication by position. is the historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion information representation vector, express The transposed vector of represents matrix multiplication, represents the weight hyperparameter, is the second historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion representation value, is the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion regression understanding matrix, The optimized historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion feature vector is provided.

[0065] That is, in the above preferred example, by modeling the vector field zero dimension of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature vector after the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map is expanded as the global field redundant dependency, the effective long-range modeling of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map under the field linear complexity is realized, so that in the feature regression process of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map, the structured correlation self-distillation between information representation and decoding regression understanding is performed in the selective feature enhancement state space based on feature distribution, so as to maintain the overall information complexity of the feature distribution of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map while promoting the long-range dynamic regression understanding balance of its feature convergence, so as to improve the regression understanding consistency between the feature regression and feature extraction processes, and improve the accuracy of the prediction results obtained by the decoder-based climate predictor of the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map. In this way, the mutual influence of different climate factors and their temporal change trends can be explored and fully reflected, thereby significantly improving the accuracy and reliability of climate forecasts, and providing strong support for the scientificity and rationality of construction plans.

[0066] In an embodiment of the present application, each construction sub-plan in the construction process information is updated based on the first climate information to obtain the second construction sequence. It should be understood that in practical applications, by introducing historical climate data to update the construction plan, that is, updating the first construction sequence, so that the construction plan can match the actual weather conditions, the rationality and scientificity of the construction plan can be improved, and the impact of external weather conditions on the construction progress can be reduced, thereby improving the construction efficiency of the construction site. And considering that the weather factors associated with each construction stage in the construction process are different, and the correlation with different weather factors is different, therefore, in order to improve the rationality and scientificity of the updated construction sequence, each construction sub-plan can be treated as an independent individual, and each construction sub-plan in the first construction sequence can be updated in sequence according to the climate information. In particular, a specific implementation method for updating each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence can be: starting from the first construction sub-plan in the first construction sequence, for each construction sub-plan, based on the first climate information, determine the weather conditions of the construction sub-plan to obtain the second climate information; based on the second climate information, judge the matching degree between the construction sub-plan and the corresponding weather conditions, and when the matching degree is lower than a preset threshold, update the construction of the construction sub-plan and subsequent construction sub-plans in the first construction sequence; based on the updated construction sub-plan, obtain the second construction sequence.

[0067] Therefore, step S130 is explained clearly, which extracts the historical climate data within the construction period from the time queue of the acquired historical climate data to obtain the time queue of the historical climate data during the construction period, and uses a data analysis and processing algorithm based on deep learning to perform time series regularization and time series association of the historical climate data and the historical climate data during the construction period, so as to automatically predict the climate data of the first area according to the interactive fusion representation between the time series association characteristics of the historical climate multidimensional parameters and the time series association characteristics of the historical climate multidimensional parameters during the construction period. In this way, the mutual influence between different climate factors and their time series change trends can be excavated and fully reflected, thereby significantly improving the accuracy and reliability of climate forecasting, thereby providing strong support for the scientificity and rationality of the construction plan.

[0068] In step S140, the first area is constructed based on the second construction sequence. The second construction sequence is an optimized and sorted construction plan that fully considers the impact of climate factors on construction. According to the arrangement of the second construction sequence, project managers can accurately allocate manpower and equipment to ensure sufficient resource support at each construction stage, and avoid idleness or waste of resources due to weather changes, thereby improving resource utilization efficiency. In this way, the construction progress and quality can be more effectively controlled, and the controllability and transparency of project management can be improved.

[0069] It should be understood that constructing the first area based on the second construction sequence is a complex and delicate process. This process requires ensuring that construction activities are carried out strictly according to the plan while responding to various emergencies that may arise. The following is a detailed description of this process: Before the formal construction, a series of preparations need to be carried out to ensure that the construction activities can proceed smoothly. First, ensure that all necessary construction permits and approval procedures have been completed. These approval procedures are the basis for the legality and compliance of the construction, and any negligence may lead to construction obstruction. Secondly, conduct a comprehensive on-site survey of the construction area to understand the topography, geological conditions, surrounding environment, etc., to ensure the feasibility of the construction plan. The results of the on-site survey will directly affect the formulation of the construction plan and the allocation of resources.

[0070] Next, prepare all necessary construction resources, including human resources, machinery and equipment, building materials, etc. Ensure that the quantity and quality of resources meet the construction requirements. The preparation of human resources includes not only the formation of the construction team, but also the technical training and safety education of construction personnel. The preparation of machinery and equipment needs to ensure that all equipment has good performance and is reasonably deployed according to the needs of the construction plan. The preparation of building materials needs to ensure that the quality and quantity of the materials meet the construction needs and have stable supply chain support.

[0071] Technical disclosure is an important part of the preparation work. The construction team should be organized to conduct technical disclosure to ensure that all construction personnel have a full understanding of the construction plan, technical requirements and safety regulations. The content of the technical disclosure should include construction methods, construction sequence, quality standards, safety measures, etc., to ensure that each construction personnel can clearly understand their responsibilities and tasks. In addition, a detailed emergency plan needs to be formulated, including measures to deal with various emergencies such as weather changes, equipment failures, and material shortages. The emergency plan should be operational to ensure that it can respond quickly in emergencies and reduce the impact on the construction progress.

[0072] Based on the second construction sequence, a detailed construction plan should be developed. The construction plan should include the specific content, construction methods, required resources, ideal duration, etc. of each construction sub-plan. The detailed description of each construction sub-plan should cover the construction content, construction methods, required resources, ideal duration, etc., to ensure that construction personnel have clear operating guidelines. The construction sequence should be carried out strictly in accordance with the second construction sequence, clarifying the order of each construction sub-plan to ensure that construction activities are carried out as planned. Resource allocation should list in detail the resources required for each construction sub-plan, including human resources, machinery and equipment, building materials, etc., to ensure the rational allocation of resources. The time node should set the start and end time of each construction sub-plan to ensure that construction activities are completed on schedule. Quality control should formulate quality control standards and inspection methods to ensure that the construction quality meets the requirements. Safety management should formulate safety management measures to ensure the safety of personnel and equipment during the construction process.

[0073] During the construction process, the second construction sequence and detailed construction plan are strictly followed. First, start the construction activities. After confirming that all preparatory work is completed, the construction activities are officially started. In accordance with the sequence of the construction plan, each construction sub-plan is started in turn. Construction supervision is a key link to ensure that construction activities are carried out as planned. A special construction supervision team is set up to supervise various activities during the construction process to ensure that construction activities are carried out strictly according to the plan. Resource scheduling should be based on the construction plan, and various resources should be reasonably scheduled to ensure that each construction sub-plan is carried out with sufficient resources. For example, if a sub-plan requires specific mechanical equipment, the time for the equipment to enter the site should be arranged in advance. Quality inspection is carried out after the completion of each construction sub-plan to ensure that the construction quality meets the requirements. If problems are found, they should be rectified in time. Safety management strictly implements the safety management system to ensure the safety of personnel and equipment during the construction process. Regular safety training and safety inspections are carried out to promptly discover and eliminate safety hazards. Progress tracking tracks the construction progress in real time to ensure that each construction sub-plan is completed on schedule. If the progress is found to be lagging behind, the construction plan should be adjusted in time and measures should be taken to speed up the construction progress.

[0074] During the construction process, you may encounter various emergencies, such as weather changes, equipment failures, and material shortages. A detailed emergency plan needs to be formulated to ensure that construction activities can proceed smoothly. In response to weather changes, take countermeasures in advance according to weather forecasts. For example, if heavy rain is forecast, the construction sequence can be adjusted to give priority to construction sub-plans that are not affected by the weather. In response to equipment failures, establish an equipment maintenance and repair mechanism to ensure that the equipment can be repaired in time when problems occur. Have spare equipment available to deal with emergencies. In response to material shortages, establish a stable supply chain system to ensure the timely supply of materials. If there is a shortage of materials, contact the supplier in time to ensure that the materials are in place as soon as possible. In response to personnel changes, establish a flexible human resource allocation mechanism to ensure that manpower can be quickly replenished when personnel changes occur without affecting the construction progress.

[0075] During the construction process, it is necessary to record the progress of each construction sub-plan in detail, including construction time, construction content, resource usage, quality inspection results, etc. These records will provide an important basis for subsequent construction management and project summary. The construction team records the construction situation of the day every day, including construction content, resource usage, problems encountered and solutions, etc. Prepare construction progress reports every week and month to summarize the construction progress, existing problems and improvement measures. These reports will be submitted to the project manager and relevant management personnel. Record the quality inspection results of each construction sub-plan in detail, including inspection time, inspection content, inspection results, etc. Record the safety situation during the construction process in detail, including safety inspection results, safety hazards and rectification measures, etc.

[0076] After the construction is completed, the project acceptance and summary are carried out to ensure that the construction quality meets the requirements. Organize a professional team to conduct a comprehensive acceptance of the construction project to check whether the construction quality, safety status, functional performance and other aspects meet the requirements. If problems are found, they should be rectified in a timely manner. Prepare a project summary report to summarize the lessons learned during the construction process and put forward suggestions for improvement. The project summary report should include the implementation of the construction plan, existing problems and solutions, achievements and experience, etc. Archive all documents and records generated during the construction process, including construction plans, construction records, quality inspection reports, safety records, etc. These documents will provide important references for subsequent project management and maintenance.

[0077] In summary, construction of the first area based on the second construction sequence is a systematic work that requires comprehensive consideration of multiple factors to ensure that construction activities are carried out strictly according to plan. This process includes the preparation stage, detailed formulation of the construction plan, execution of the construction process, response to emergencies, construction records and reports, and project acceptance and summary. Through scientific management and meticulous operation, we can ensure the smooth progress of the construction project, improve construction efficiency and quality, and achieve successful project delivery.

[0078] In summary, the intelligent construction management method based on the embodiment of the present application is explained, which obtains construction process information based on the preset BIM model of the first area, and then sorts the multiple construction sub-plans in the construction process information according to the construction order, thereby obtaining the first construction sequence, and then updates the first construction sequence based on the historical climate data of the first area, thereby obtaining the second construction sequence, and finally carrying out the construction work in the first area based on the second construction sequence. This is conducive to improving the intelligence and refinement level of construction management. Figure 5 : is a system block diagram of a smart construction management system according to an embodiment of the present application. Figure 5 As shown, according to the embodiment of the present application, the smart construction management system 100 includes: a construction process information data acquisition module 110, which is used to obtain construction process information based on a preset BIM model of the first area; a construction sub-plan sorting module 120, which is used to sort multiple construction sub-plans in the construction process information according to the construction sequence to obtain a first construction sequence; a construction sequence updating module 130, which is used to update the first construction sequence based on the historical climate data of the first area to obtain a second construction sequence; a construction implementation module 140, which is used to construct the first area based on the second construction sequence; wherein the construction sequence updating module includes: a second construction sequence generating subunit, which is used to predict the climate of the first area based on the historical climate data of the first area to obtain the first climate information, and update each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence; wherein the second construction sequence generating subunit includes: a secondary construction period historical climate data sorting module; A subunit is used to obtain a time queue of historical climate data of the first area, and extract historical climate data within the construction time period from the time queue of historical climate data to obtain a time queue of historical climate data during the construction period; a secondary subunit for extracting historical climate time series features during the construction period is used to respectively perform time series regularization and historical climate time series semantic feature extraction on the time queue of historical climate data and the time queue of historical climate data during the construction period to obtain historical climate multi-dimensional parameter time series correlation features and construction period historical climate multi-dimensional parameter time series correlation features; a secondary subunit for generating historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion features is used to perform fine-grained feature cross-domain interactive encoding on the historical climate multi-dimensional parameter time series correlation features and the construction period historical climate multi-dimensional parameter time series correlation features to obtain historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion features; a secondary subunit for generating first climate information prediction is used to obtain a prediction result as the first climate information based on the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion features.

[0079] Here, those skilled in the art will appreciate that the specific functions and operations of each unit and module in the above-mentioned smart construction management system 100 have been described in detail above. Figures 1 to 4 The invention has been introduced in detail in the description of the smart construction management method, and therefore, its repeated description will be omitted.

Claims

1. A smart construction management method, characterized in that: include: Based on a preset BIM model of the first area, construction process information is obtained; multiple construction sub-plans in the construction process information are sorted according to a construction order to obtain a first construction sequence; based on historical climate data of the first area, the first construction sequence is updated to obtain a second construction sequence; based on the second construction sequence, construction is performed on the first area; Wherein, updating the first construction sequence based on the historical climate data of the first area to obtain the second construction sequence includes: predicting the climate of the first area based on the historical climate data of the first area to obtain first climate information, and updating each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence; The step of predicting the climate of the first region based on the historical climate data of the first region to obtain first climate information includes: Acquire a time queue of historical climate data of the first area, and extract historical climate data within a construction period from the time queue of historical climate data to obtain a time queue of historical climate data during the construction period; Performing time series regularization and historical climate time series semantic feature extraction on the time series of the historical climate data and the time series of the historical climate data during the construction period respectively to obtain the time series correlation features of the historical climate multidimensional parameters and the time series correlation features of the historical climate multidimensional parameters during the construction period; Performing fine-grained feature cross-domain interactive encoding on the historical climate multidimensional parameter time series correlation features and the historical climate multidimensional parameter time series correlation features during the construction period to obtain the historical climate multidimensional parameter time series fine-grained semantic interactive fusion features; Based on the time series fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameters, a prediction result is obtained as the first climate information.

2. The smart construction management method according to claim 1, characterized in that: The historical climate data includes temperature values, humidity values, precipitation and wind speed values.

3. The smart construction management method according to claim 2 is characterized in that: The time queue of the historical climate data and the time queue of the historical climate data during the construction period are respectively subjected to time series regularization and historical climate time series semantic feature extraction to obtain the time series correlation features of the historical climate multidimensional parameters and the time series correlation features of the historical climate multidimensional parameters during the construction period, including: Arranging the time queue of the historical climate data and the time queue of the historical climate data during the construction period according to the climate sample dimension and time to obtain a time series matrix of the historical climate multidimensional parameters and a time series matrix of the historical climate multidimensional parameters during the construction period; The historical climate multidimensional parameter time series matrix and the historical climate multidimensional parameter time series matrix of the construction period are passed through a historical climate time series semantic feature extractor based on a void convolutional neural network model to obtain a historical climate multidimensional parameter time series association feature graph as the historical climate multidimensional parameter time series association feature and a construction period historical climate multidimensional parameter time series association feature graph as the construction period historical climate multidimensional parameter time series association feature.

4. The smart construction management method according to claim 3 is characterized in that: Fine-grained feature cross-domain interactive encoding is performed on the historical climate multidimensional parameter time series correlation features and the historical climate multidimensional parameter time series correlation features during the construction period to obtain the historical climate multidimensional parameter time series fine-grained semantic interactive fusion features, including: Performing feature fine-grained decoupling on the historical climate multidimensional parameter time series correlation feature graph and the historical climate multidimensional parameter time series correlation feature graph during the construction period to obtain a set of local fine-grained feature vectors of historical climate multidimensional parameter time series correlation and a set of local fine-grained feature vectors of historical climate multidimensional parameter time series correlation during the construction period; Input each corresponding group of the set of the historical climate multi-dimensional parameter time series associated local fine-grained feature vectors and the set of the historical climate multi-dimensional parameter time series associated local fine-grained feature vectors during the construction period into a fine-grained common feature extraction network to obtain a set of historical climate time series joint fine-grained core feature vectors; Inputting the set of the historical climate time series joint fine-grained core feature vectors into a clustering network to obtain a historical climate time series joint fine-grained core feature semantic clustering center vector; Based on the historical climate time series joint fine-grained core feature semantic clustering center vector, the set of the historical climate time series joint fine-grained core feature vectors is subjected to multidimensional feature fine-grained fusion to obtain the historical climate multidimensional parameter time series fine-grained semantic interactive fusion feature.

5. The smart construction management method according to claim 4 is characterized in that: The historical climate multidimensional parameter time series correlation feature graph and the construction period historical climate multidimensional parameter time series correlation feature graph are subjected to feature fine-grained decoupling to obtain a set of historical climate multidimensional parameter time series correlation local fine-grained feature vectors and a set of historical climate multidimensional parameter time series correlation local fine-grained feature vectors during the construction period, including: Expanding each characteristic matrix along the channel dimension of the historical climate multi-dimensional parameter time series correlation characteristic graph into a characteristic vector to obtain a set of local fine-grained characteristic vectors of the historical climate multi-dimensional parameter time series correlation; Each characteristic matrix along the channel dimension of the historical climate multi-dimensional parameter time series correlation feature map during the construction period is expanded into a characteristic vector to obtain a set of local fine-grained characteristic vectors of the historical climate multi-dimensional parameter time series correlation during the construction period.

6. The smart construction management method according to claim 5 is characterized in that: Based on the historical climate time series joint fine-grained core feature semantic clustering center vector, a set of the historical climate time series joint fine-grained core feature vectors is subjected to multi-dimensional feature fine-grained fusion to obtain the historical climate multi-dimensional parameter time series fine-grained semantic interactive fusion feature, including: Based on each historical climate time series joint fine-grained core feature vector in the set of the historical climate time series joint fine-grained core feature vectors, a historical climate time series query vector and a historical climate time series value vector are constructed, and based on the historical climate time series joint fine-grained core feature semantic clustering center vector, a historical climate time series key vector is constructed, and the historical climate time series query vector, the historical climate time series value vector and the historical climate time series key vector of each historical climate time series joint fine-grained core feature vector are input into a global semantic interaction encoder based on a converter structure to obtain a set of historical climate time series context joint fine-grained core feature vectors; The feature shape of each historical climate time series context joint fine-grained core feature vector in the set of the historical climate time series context joint fine-grained core feature vector is reshaped to obtain a historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature map as the historical climate multi-dimensional parameter time series fine-grained semantic interaction fusion feature.

7. The smart construction management method according to claim 6, characterized in that: Based on each historical climate time series joint fine-grained core feature vector in the set of the historical climate time series joint fine-grained core feature vectors, a historical climate time series query vector and a historical climate time series value vector are constructed, and based on the historical climate time series joint fine-grained core feature semantic clustering center vector, a historical climate time series key vector is constructed, and the historical climate time series query vector, the historical climate time series value vector and the historical climate time series key vector of each historical climate time series joint fine-grained core feature vector are input into a global semantic interaction encoder based on a converter structure to obtain a set of historical climate time series context joint fine-grained core feature vectors, including: Multiplying the query embedding matrix and the historical climate time series joint fine-grained core feature vector to obtain the historical climate time series query vector; Multiplying the value embedding matrix and the historical climate time series joint fine-grained core feature vector to obtain the historical climate time series value vector; Multiplying the key embedding matrix with the historical climate time series joint fine-grained core feature semantic clustering center vector to obtain the historical climate time series key vector; The historical climate time series query vector, the historical climate time series value vector and the historical climate time series key vector are input into the global semantic interaction encoder based on the converter structure to obtain the historical climate time series context joint fine-grained core feature vector.

8. The smart construction management method according to claim 7, characterized in that: Based on the historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion features, a prediction result is obtained, including: passing the historical climate multi-dimensional parameter temporal fine-grained semantic interaction fusion feature map through a decoder-based climate predictor to obtain the prediction result, and the prediction result is used to represent the decoded value of the climate prediction data of the first area.

9. A smart construction management system, characterized in that: include: A construction process information data acquisition module, used to obtain construction process information based on a preset BIM model of the first area; a construction sub-plan sorting module, used to sort multiple construction sub-plans in the construction process information according to the construction sequence to obtain a first construction sequence; a construction sequence updating module, used to update the first construction sequence based on the historical climate data of the first area to obtain a second construction sequence; a construction implementation module, used to construct the first area based on the second construction sequence; The construction sequence updating module includes: a second construction sequence generating subunit, which is used to predict the climate of the first area based on the historical climate data of the first area to obtain first climate information, and to update each construction sub-plan in the construction process information based on the first climate information to obtain the second construction sequence; Wherein, the second construction sequence generating subunit includes: A secondary subunit for collating historical climate data during the construction period, for obtaining a time queue of historical climate data of the first region, and extracting historical climate data within the construction period from the time queue of historical climate data to obtain a time queue of historical climate data during the construction period; A secondary sub-unit for extracting historical climate time series features during the historical climate construction period is used to respectively perform time series regularization and historical climate time series semantic feature extraction on the time queue of the historical climate data and the time queue of the historical climate data during the construction period to obtain the time series correlation features of the historical climate multidimensional parameters and the time series correlation features of the historical climate multidimensional parameters during the construction period; A secondary sub-unit is provided for generating fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter temporal series, which is used for performing fine-grained feature cross-domain interaction encoding on the historical climate multi-dimensional parameter temporal series correlation features and the historical climate multi-dimensional parameter temporal series correlation features during the construction period to obtain fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter temporal series; The first climate information prediction generates a secondary subunit, which is used to obtain a prediction result as the first climate information based on the fine-grained semantic interaction fusion features of the historical climate multi-dimensional parameter time series.

10. The smart construction management system according to claim 9, characterized in that: The historical climate construction period historical climate time series feature extraction secondary sub-unit is used for: Arranging the time queue of the historical climate data and the time queue of the historical climate data during the construction period according to the climate sample dimension and time to obtain a time series matrix of the historical climate multidimensional parameters and a time series matrix of the historical climate multidimensional parameters during the construction period; The historical climate multidimensional parameter time series matrix and the historical climate multidimensional parameter time series matrix of the construction period are passed through a historical climate time series semantic feature extractor based on a void convolutional neural network model to obtain a historical climate multidimensional parameter time series association feature graph as the historical climate multidimensional parameter time series association feature and a construction period historical climate multidimensional parameter time series association feature graph as the construction period historical climate multidimensional parameter time series association feature.

Images