Prefabricated building prefabricated part construction management system and method

Abstract

The invention discloses an assembly type building prefabricated part construction management system and method, and relates to the technical field of building construction management.The assembly type building prefabricated part construction management method comprises the steps that information data of various building prefabricated parts are collected, a complete information data set is formed, the information data set is classified into multiple subsets, and the subsets are stored in a database; the use scene and the scheduling requirement of the component can be understood; historical construction data and a marked data set are combined to train a prefabricated part management model, the scheduling requirements of different parts can be predicted, and the construction progress and quality guarantee are ensured. Through the model, the application demand of each component is identified, the construction demand of a target component is predicted, and adjustment of resources and a scheduling plan is facilitated. A construction scheduling mechanism is set according to a prediction result, information is fed back in real time to optimize scheduling tasks, target prefabricated part scheduling tasks are managed in order, resource waste and progress lag are avoided, and the prefabricated part supervision efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of construction project management, and particularly to a construction management system and method for prefabricated components of prefabricated buildings. Background Art

[0002] With the continuous improvement of the requirements for construction efficiency and quality in the modern construction industry, prefabricated buildings have gradually become a mainstream construction method. The construction process of prefabricated buildings usually requires a large number of prefabricated components (such as walls, floors, columns, etc.) to be assembled; currently, in the construction of prefabricated buildings, the management and scheduling of prefabricated components still need to be improved, and there is a lack of effective information communication and real-time feedback between the construction site, storage locations, and prefabrication factories; as a result, the transportation, storage, and installation of prefabricated components are often difficult to synchronize, causing waste or shortage of building materials, thus leading to frequent delays in the construction progress and making it difficult to ensure the construction quality and the completion acceptance time.

[0003] In summary, the present invention provides a construction management system and method for prefabricated components of prefabricated buildings to solve the problem that the unreasonable scheduling of prefabricated components leads to out-of-sync construction progress and makes it difficult to supervise the construction quality and completion time. Summary of the Invention

[0004] The present invention provides a construction management system and method for prefabricated components of prefabricated buildings, which solves the technical problems that the unreasonable scheduling of prefabricated components leads to out-of-sync construction progress and makes it difficult to supervise the construction quality and completion time.

[0005] To solve the above technical problems, the present invention provides a construction management system and method for prefabricated components of prefabricated buildings, and the specific technical solutions are as follows: In the first aspect, a construction management method for prefabricated components of prefabricated buildings includes: Collecting various information data of building prefabricated components to obtain an information data set; Classifying the information data set to divide it into multiple prefabricated component information subsets; respectively marking the multiple prefabricated component data subsets to obtain multiple marked data sets; Training and constructing a prefabricated component management model with the target prefabricated component data set to output an identification result representing the scheduling requirements of the target prefabricated component for the construction project; the target prefabricated component data set includes historical construction data, construction project requirements, construction stages, and the multiple marked data sets; Based on the prefabricated component management model, inputting at least one type of data in the target prefabricated component data set into the prefabricated component management model, and outputting an identification result representing the scheduling requirements of the current target prefabricated component for the construction project; Set a construction scheduling mechanism according to the recognition result of the precast component management model, and feed back scheduling information in real time through the set construction scheduling mechanism to continuously optimize the balanced scheduling and allocation of the target precast component.

[0006] As a further optimization scheme of the present invention, classify the information data set to divide it into multiple precast component information subsets, including: Scan and collect various building precast component information data to obtain an information data set; preprocess the information data set to obtain a preprocessed information data set; input the preprocessed information data set and perform hierarchical arrangement according to the preset range of the basic information of the precast component to determine the number of hierarchical columns K; the basic information includes the structural dimensions, shape, material and installation method of the precast component. Randomly select one of the hierarchical columns K from the number of hierarchical columns K i ; i Determine a category center in the column K as a feature vector, and through To obtain the distribution distance between each information data item in the information data set and the category centers of multiple columns K i ; Compare multiple said distribution distances to obtain the shortest distribution distance, and allocate the information data item to the column K according to the shortest distribution distance i ; In the formula, Represents the jth shortest distribution distance; x i Represents the ith information data item, and μ j Represents the jth category center. Repeatedly execute the allocation and update of the hierarchical arrangement of information data items until the category center no longer changes or reaches the preset iteration value. Each information data item is divided into multiple precast component information subsets according to the final category center to which it belongs; there are identical information data items in the precast component information subsets.

[0007] As a further optimization scheme of the present invention, mark multiple precast component data subsets respectively to obtain multiple marked data sets, including: Mark multiple precast component data subsets according to the hierarchical arrangement result of the precast component information data, and determine three clusters, and then we use the number of each cluster as a label for marking to obtain multiple marked data sets; The marked data set is marked with three cluster number labels of fast, medium and slow respectively according to the data items in the construction progress data according to the hierarchical arrangement result of each information data item; the construction progress data includes transportation progress, installation progress and quality inspection progress.

[0008] As a further optimization scheme of the present invention, the precast component management model includes: Generate structural data from historical construction data, construction project requirements, construction stages, the information dataset, and the multiple labeled datasets, and encode the structural data into sequence data to train the precast component management model; Input the sequence data into the precast component management model; the precast component management model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. Transmit the intermediate representation data of multiple hidden layers to the output layer, and the output layer outputs the recognition result representing the application requirements of precast components with different labels; Input at least one target precast component into the precast component management model, and the output layer of the precast component management model outputs the recognition result representing the scheduling requirements of the current target precast component for the construction project.

[0009] As a further optimization scheme of the present invention, according to the recognition result of the precast component management model; set a construction scheduling mechanism, and the construction scheduling mechanism evenly schedules and allocates the target precast components with each label in the multiple labeled datasets according to the scheduling path according to the precast component requirements of the construction project to obtain scheduling allocation information data; Real-time feedback the scheduling allocation information data to obtain a feedback result; according to the feedback result, synchronously schedule the input of the next batch of multiple target precast components into the construction project until the target precast components complete the current construction project.

[0010] As a further optimization scheme of the present invention, the construction scheduling mechanism includes: Assign demand consumption weights Ri to multiple different labeled datasets, where the demand consumption weight Ri represents the precast component resources consumed by a single data item in the labeled dataset due to demand in the construction project; and select the source node Ei and the target node si according to the demand consumption weight; Through Establish a labeled data consumption dependency relationship; in the formula, represents the consumption dependency weight, n represents the number of data items in the labeled dataset; b represents the resource additional consumption parameter, and the labeled data consumption dependency relationship represents the dependency relationship between the quantity consumed by the labeled target precast component according to the construction project requirements and the current total resources, so that the scheduling task of the target precast component progresses step by step.

[0011] As a further optimization scheme of the present invention, let the resource pool size be C r , the maximum available quantity of each resource is C rk , and the resources required for each target scheduling task m are R ik , through to obtain the resource constraint conditions of the consumption dependency relationship; At any moment, the resource requirements consumption of all target scheduling tasks does not exceed the resource pool size; where T represents the set of all ongoing tasks within the current moment. When h target scheduling tasks and f target scheduling tasks are carried out synchronously, it indicates that the i-th batch of target scheduling tasks is completed, which is the first target scheduling task; when the scheduling is carried out and completed after the i-th batch of target scheduling tasks and the previous batch of target scheduling tasks are completed, it is the second target scheduling task.

[0012] As a further optimization scheme of the present invention, based on the resource consumption constraint condition and the marked data consumption dependency relationship, the scheduling progress information is fed back in real time. When there is a scheduling deviation or resource tension, the scheduling strategy is automatically adjusted. The scheduling strategy includes adjusting production tasks, modifying transportation routes, and changing allocation batches. The recognized results and the scheduling scheme are adjusted according to the real-time feedback scheduling progress information to construct a closed-loop feedback, so as to iteratively optimize the construction scheduling mechanism in a cycle.

[0013] As a further optimization scheme of the present invention, according to the urgency of the project progress, the assembly duration of components, and the transportation distance, the transportation routes of target precast components are prioritized to obtain the preferred transportation routes of target precast components. According to the preferred transportation route of the target precast component, determine the route of the target precast component from production, transportation to the construction site, and transport the target precast component to the target location; the construction project progress has been completed. Preset multiple scheduling routes and assign a weight value to each route. According to the resource requirements at the construction site and the delivery timeliness information of precast components, the optimal transportation route is dynamically selected.

[0014] In a second aspect, the system is provided with an electronic device including a memory, a processor, and a precast component construction management method program for an assembled building stored on the memory and executable on the processor. When the precast component construction management method program for an assembled building is executed by the processor, the steps of a precast component construction management method for an assembled building are implemented. The system includes: An information collection module: which is used to collect various building precast component information data to obtain an information data set. A data processing module: which is used to classify the information data set into multiple precast component information subsets; and mark each of the multiple precast component data subsets to obtain multiple marked data sets. Prefabricated component scheduling module: It is used to train and construct a prefabricated component management model with a target prefabricated component data set to output an identification result representing the scheduling requirements of the target prefabricated component for the construction project; the target prefabricated component data set includes historical construction data, construction project requirements, construction stages, and the multiple labeled data sets; based on the prefabricated component management model, at least one type of data in the target prefabricated component data set is input into the prefabricated component management model to output an identification result representing the scheduling requirements of the current target prefabricated component for the construction project; Progress tracking and feedback module: It is used to set a construction scheduling mechanism according to the identification result of the prefabricated component management model, and to continuously optimize the balanced scheduling and allocation of the target prefabricated component by continuously feeding back scheduling information through the set construction scheduling mechanism.

[0015] The present invention has at least the following beneficial effects: By collecting various building prefabricated component information data, an information data set is obtained. By comprehensively collecting different types of prefabricated component information, including dimensions, types, materials, manufacturing processes, etc., a complete data set is formed. These data will provide a basis for subsequent analysis, classification, and modeling, and help to comprehensively understand the characteristics and status of the components.

[0016] The information data set is classified to be divided into multiple prefabricated component information subsets; according to the collected data, algorithms are used to classify the prefabricated components, such as dividing them according to component types, material characteristics, functional requirements, etc., which helps to understand the usage scenarios and scheduling requirements of different types of components and provides support for precise scheduling; the multiple prefabricated component data subsets are respectively labeled to obtain multiple labeled data sets; by labeling different categories of components, different labels can be assigned to each subset through historical construction data or expert experience, which will help the system identify the priorities and scheduling requirements of the components.

[0017] The historical construction data, construction project requirements, construction stages, and the multiple labeled data sets are used to train and construct a prefabricated component management model; by combining information such as historical construction data, project requirements, and construction stages with the prefabricated component data subsets and labeled data, a prefabricated component management model is constructed. Through training, the model can identify the relationships between construction progress, quality control, and construction requirements, predict the best scheduling methods for different components, and ensure the synchronization of construction progress and the guarantee of quality.

[0018] Based on the precast component management model, to output the recognition result indicating the scheduling requirements of the target precast component for the construction project; through the trained precast component management model, identify the requirements of different precast components and output the application requirements of each marked component. For example, the model can identify that certain components need to be installed preferentially, or certain components should be scheduled in a specific order. This step helps the construction team understand the scheduling requirements of each component in real time, avoiding schedule delays or resource waste caused by improper scheduling; input at least one target precast component into the precast component management model, and output the recognition result indicating the scheduling requirements of the current target precast component for the construction project; make specific predictions on the target precast component according to the actual construction situation. By inputting the real-time data of the target component, the model outputs the construction requirements of the component, such as whether it is necessary to accelerate production and whether it can be installed according to the plan. This result helps construction managers understand the specific requirements of each component in the current construction stage, so as to more effectively adjust resources and scheduling plans.

[0019] Set the construction scheduling mechanism according to the recognition result of the precast component management model; based on the recognition result of the model, set the construction scheduling mechanism. This mechanism can automatically or manually adjust the construction plan according to the demand priority of each component, ensuring that the precast components can arrive at the construction site on time and be installed according to the project progress. In this way, the synchronization of the construction progress and quality supervision are effectively guaranteed.

[0020] Through the set construction scheduling mechanism, real-time feedback scheduling information to continuously optimize the balanced scheduling and allocation of the target precast component. The construction scheduling mechanism will monitor the construction progress in real time and adjust the scheduling strategy through continuous feedback information. This real-time adjustment and feedback mechanism ensures that there will be no construction lag or over-concentration of resources caused by unreasonable scheduling of precast components during the construction process, so as to achieve balanced scheduling, improve construction efficiency and avoid quality problems. Brief Description of the Drawings

[0021] Figure 1 It is a schematic flow chart of a construction management method for precast components of an assembled building provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of a construction management system for precast components of an assembled building provided by an embodiment of the present invention. Detailed Embodiment

[0022] The following further describes the present application in detail with reference to the drawings. It is necessary to point out here that the following detailed embodiments are only used to further illustrate the present application and cannot be understood as limiting the protection scope of the present application. Those skilled in the art can make some non-essential improvements and adjustments to the present application according to the above application content.

[0023] A construction management system and method for prefabricated components of an assembled building provided in this embodiment are specifically implemented as follows: As Figure 1 shown, a construction management method for prefabricated components of an assembled building includes the following steps: Step 11: Collect information data of various building prefabricated components to obtain an information data set; Step 12: Classify the information data set to divide it into multiple prefabricated component information subsets; mark each of the multiple prefabricated component data subsets to obtain multiple marked data sets; Step 13: Train and construct a prefabricated component management model with the target prefabricated component data set to output an identification result indicating the scheduling requirements of the target prefabricated component for the construction project; the target prefabricated component data set includes historical construction data, construction project requirements, construction stages, and the multiple marked data sets; based on the prefabricated component management model, input at least one type of data in the target prefabricated component data set into the prefabricated component management model, and output an identification result indicating the scheduling requirements of the current target prefabricated component for the construction project; Step 14: Set a construction scheduling mechanism according to the identification result of the prefabricated component management model, and continuously feedback scheduling information through the set construction scheduling mechanism to continuously optimize the balanced scheduling and allocation of the target prefabricated component.

[0024] In the implementation of the present invention, in Step 11, by collecting information data (such as type, size, weight, material, shape, transportation method, assembly process, etc.) of different types of building prefabricated components, a comprehensive information data set is constructed; the data collection comes from different sources, such as actual data at the construction site, production data of the production factory, design drawings, and construction requirements, thus providing comprehensive raw data support, which is the basis for subsequent analysis, classification, modeling, and prediction; through the collection of the information data set, the characteristics of various components can be comprehensively understood, laying a foundation for subsequent management and scheduling optimization.

[0025] In Step 12, the collected information data set is classified. The classification may be carried out according to different component types (such as beams, columns, walls, slabs, etc.), functions (load-bearing, decorative, etc.), usage scenarios (indoor, outdoor, etc.); each classified subset will be marked, and the marked content may be information such as the usage stage, assembly stage, and installation location of the component; the goal of classification and marking is to clarify the data characteristics and application scenarios of each component, providing clear label information for subsequent model training and demand prediction; classification and marking help to efficiently organize and manage prefabricated component information; it can provide a more accurate data set for model training in subsequent steps, avoid information mixing, and improve prediction accuracy.

[0026] Step 13 trains a machine learning model by utilizing historical construction data, construction project requirements, construction stages, as well as the previously collected information dataset and labeled dataset; through model training, the precast component management model can learn the application requirements of different components under different construction stages and demand changes; the model can output the recognition results of the application requirements of each precast component, and can predict its future construction application requirements (such as whether it is necessary to transport in advance, whether it is necessary to prepare in advance, etc.) according to the specific characteristics of the input target component; the management model constructed through training can accurately identify the construction requirements of different precast components, which helps with real-time decision-making at the construction site, thereby improving the accuracy of the construction process and reducing unnecessary waste, such as avoiding premature production, excessive inventory, or insufficient preparation; the prediction function enables the engineering project to plan in advance, make material preparations and construction plans in advance, thereby improving construction efficiency and shortening the construction period.

[0027] Step 14 depends on the previous recognition results and uses the prediction information of the precast component management model to adjust the construction scheduling mechanism; the construction scheduling mechanism can provide real-time feedback on the actual information during the construction process (for example, the arrival time of components, changes in construction progress, etc.), and adjust the scheduling plan according to this feedback information; the goal is to ensure that each precast component is allocated and scheduled in an optimized manner, avoiding over-concentration or resource waste; through real-time feedback and the scheduling mechanism, the construction arrangement can be flexibly adjusted according to the actual situation to maintain the dynamic balance of component scheduling; optimize the construction progress, ensure the maximization of resource utilization rate, and reduce the risks of project delay and cost waste; continuous optimization means that the system can continuously self-adjust according to past data and predictions, gradually improving the accuracy and efficiency of construction scheduling.

[0028] The above steps cooperate with each other, combining the ideas of data collection, machine learning modeling, and dynamic scheduling optimization, and conduct full-process management of precast components in an intelligent way; improve the accuracy of construction management, reduce unnecessary waste; strengthen the predictability during the construction process, identify and address potential problems in advance; through the dynamic feedback mechanism, optimize the scheduling and allocation of construction resources, and reduce the risks and costs of the project; the core of the entire process lies in combining the intelligent management and scheduling of building data, and using data-driven and model prediction to continuously optimize the construction process.

[0029] In another preferred embodiment of the present invention, in step 12, the information dataset is classified into multiple precast component information subsets, including: Step 121, scan and collect information data of various building precast components to obtain an information data set; preprocess the information data set to obtain a preprocessed information data set; input the preprocessed information data set and perform hierarchical arrangement according to the preset range of the basic information of the precast components to determine the number of hierarchical columns K; the basic information includes the structural dimensions, shape, material and installation method of the precast components. Step 122, randomly select one of the hierarchical columns K from the number of hierarchical columns K i ; Determine a category center in the column K i as a feature vector, and through to obtain the distribution distances between each information data item in the information data set and the category centers of multiple columns K i ; Compare the multiple distribution distances to obtain the shortest distribution distance, and allocate the information data item to the column K according to the shortest distribution distance i ; Wherein, represents the j-th shortest distribution distance; x i represents the i-th information data item, and μ j represents the j-th category center. Step 123, repeatedly perform the allocation and update of the hierarchical arrangement of the information data items until the category center no longer changes or reaches the preset iteration value, and each information data item is divided into multiple precast component information subsets according to the final category center it belongs to; there are identical information data items in the precast component information subsets.

[0030] In the implementation of the present invention, in Step 121, by scanning and collecting the information data of various building precast components, a complete data set is obtained, constituting the original information data set; by obtaining a large amount of precast component data, a comprehensive data foundation is established, covering multiple features of the components. This helps with subsequent preprocessing and classification.

[0031] Step 122 preprocesses the collected original data, including operations such as removing noise data, filling in missing data, data standardization or normalization, etc., aiming to eliminate unnecessary interference and improve data quality; based on the preprocessed data set, a "hierarchical range" is set according to the basic information of the precast components (such as structural dimensions, shape, material, etc.), and hierarchical arrangement is performed according to this range. Specifically, the hierarchical arrangement can be based on different features, such as size, material, installation method; data preprocessing can improve data quality and ensure the accuracy of subsequent analysis; hierarchical arrangement helps to reduce the complexity during classification and makes subsequent classification more efficient.

[0032] Step 123 randomly selects one column K from the K hierarchical columns obtained in Step 122 i as the starting point; determine this column K iThe category center - can be understood as the average eigenvalue or representative feature point of all data items within the sub-column; then, by calculating the assignment distance between each information data item and the category centers of each sub-column, it is determined to which sub-column the information data item should belong; through the calculation of the assignment distance, different precast component information can be classified into the most suitable sub-columns, improving the accuracy of classification; randomly selecting a sub-column can avoid being overly restricted to a certain category and promote diversity and robustness; repeating the assignment and update operations until the conditions are met; the category center no longer changes: this means that the current classification is stable and all data items are accurately classified; reaching the preset number of iterations: even if the category center has not fully converged, the termination of the algorithm can be ensured by setting a maximum number of iterations; during each iteration process, the assignment strategy is updated based on the current category center, thereby continuously optimizing the classification result; through repeated iterations, the classification result is continuously optimized, and finally each information data item can be accurately classified into the most suitable precast component subset; the iterative mechanism can improve the classification accuracy of the system and avoid the influence of early classification biases on the final result.

[0033] The above steps cooperate with each other. Through multi-dimensional acquisition, preprocessing, grading, distance calculation, and iterative update of building precast component data, efficient and accurate precast component classification is finally achieved; noise is removed through preprocessing to ensure the accuracy of the data; the calculation of the assignment distance and the iterative mechanism ensure that each data item can find the most suitable category; through operations such as iterative update and random selection of sub-columns, local optimal solutions are avoided, ensuring the robustness of the system; thereby significantly improving work efficiency and classification accuracy.

[0034] In a preferred embodiment of the present invention, in step 12, multiple precast component data subsets are respectively marked to obtain multiple marked data sets, including: Step 124, the multiple precast component data subsets are marked according to the grading arrangement result of the precast component information data, and three clusters are determined, and then the number of each cluster is used as a label for marking to obtain multiple marked data sets; Step 125, the marked data sets are respectively labeled as fast, medium, and slow, which are the three cluster number labels, according to the grading arrangement result of each information data item according to the data items in the construction progress data; the construction progress data includes transportation progress, installation progress, and quality inspection progress.

[0035] In the implementation of the present invention, in step 124, the hierarchical arrangement and classification of precast components have been completed in step 123. Now, multiple subsets of precast component data will be marked according to these classification results. The specific operation is to determine three main clusters (or categories), and each cluster represents a group of precast component data with similar attributes. Each cluster will be assigned a number as a label. Through this marking, the belonging and characteristics of each subset of precast components can be clarified. The marking process systematically classifies different precast components according to their characteristics, facilitating subsequent management and invocation. By organizing and marking the data subsets into clusters, more effective resource allocation and progress control can be achieved, especially in large-scale construction projects.

[0036] Based on the marked data set, step 125 further classifies each data item in combination with the construction progress data. Here, the construction progress includes transportation progress, installation progress, and quality inspection progress, which are all key factors affecting construction efficiency. According to the specific situation of the construction progress data, the precast components are divided into three speed categories: fast, medium, and slow. This classification reflects the processing speed and priority of each component during the construction process. Each speed category will be assigned a corresponding cluster number label to further refine the management of the precast components. By combining the construction progress with the attributes of the precast components, resources can be scheduled and managed more precisely. For example, for components with a fast progress, resources and personnel can be arranged preferentially to maintain the continuity and efficiency of construction. It helps to identify components that may cause construction delays, thereby taking preventive measures. It improves the transparency and predictability of project management, enabling the construction team to better meet the project schedule and quality standards.

[0037] Through the above two steps, the data analysis is effectively combined with the actual construction progress. By detailed marking and classification of the precast components, the refinement level of construction management is improved. In this way, the managers of construction projects can carry out more targeted scheduling and resource allocation according to the specific construction progress and the characteristics of the precast components, greatly improving the efficiency and response speed of engineering projects. This not only optimizes the use of resources but also reduces potential construction delays, thus playing a positive role in the successful implementation of the entire construction project.

[0038] In a preferred implementation of the present invention, the precast component management model in step 13 includes: Step 131, generating structural data from historical construction data, construction project requirements, construction stages, the information data set, and the multiple marked data sets, and encoding the structural data into sequence data to train the precast component management model; Step 132: Input the sequence data into the precast component management model; the precast component management model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer. Transmit the intermediate representation data of multiple hidden layers to the output layer, and the output layer outputs the recognition result representing the application requirements of different marked precast components. Step 133: Input at least one target precast component into the precast component management model, and the output layer of the precast component management model outputs the recognition result representing the scheduling requirements of the current target precast component for the construction project.

[0039] In the implementation of the present invention, Step 131 collects and integrates historical construction data, construction project requirements, construction stage information, information data sets (such as component characteristics, progress, quality control, etc.), and multiple marked data sets (such as precast component data graded according to progress). After processing and integrating these data, a structured data set is formed, which contains multi-faceted information of the project; then, these structured data will be encoded into "sequence data". Sequence data is input data in the form of a time series, commonly found in deep learning models, which can capture the evolution of data at different time points. In this step, structured data (such as the markings of precast components, construction progress, etc.) is converted into a sequence format, enabling the deep learning model to identify the temporal relationships of these data; by integrating different types of data into a structured data set and converting it into sequence data, the dynamic changes of the construction project can be more comprehensively reflected; it provides an efficient source of input data for the training of the precast component management model, helping the model better capture the correlations between various types of data; by encoding the data into sequence data, the powerful temporal data processing ability of the deep learning model can be utilized to further improve the prediction accuracy.

[0040] Step 132 inputs the sequence data generated in Step 131 into the precast component management model for training. The precast component management model usually adopts a deep neural network, which includes multiple hidden layers; this model includes an input layer and multiple hidden layers (the first, second, and third hidden layers), and finally an output layer.

[0041] Input layer: Receives the sequence data as input, and this data contains historical construction data, requirements, marked data, etc.

[0042] Multiple hidden layers: These layers gradually extract the features in the data through different activation functions, and process the non-linear relationships and complex patterns in the data. The intermediate representation (intermediate data result) of each layer will be passed to the next layer until the output layer.

[0043] Output layer: Based on the data processing results of the hidden layer, the output layer predicts the recognition results of the application requirements for precast components with different tags. This result represents the actual requirements of precast components during the construction process (such as whether priority transportation, installation, or quality inspection is required, etc.).

[0044] The multi-layer neural network structure enables the model to extract complex and non-linear relationships from the data, and can better predict the application requirements of precast components at different construction stages; the multiple data processing and intermediate representation transmission in the hidden layer enable the model to capture different levels of information in the data more carefully, enhancing the accuracy of prediction; the output layer can provide accurate recognition results of application requirements based on the input data, thus providing reliable support for subsequent construction decisions.

[0045] In step 133, the target precast component is input into the trained precast component management model for prediction. The target precast component refers to the specific component for which the application requirements need to be predicted currently; after the target component is input, through the multi-layer processing of the model, the output layer gives the recognition result of the application requirements of this target precast component during construction. For example, it may predict the transportation progress, installation requirements, quality inspection requirements, etc. of this component.

[0046] By inputting a specific target precast component, the model can accurately predict the specific requirements of this component during construction, which helps to perform precise scheduling and resource allocation during the construction process; it improves the efficiency and flexibility of construction because decisions can be made in advance based on the model's prediction, avoiding delays or resource waste caused by the failure to identify requirements in advance; this predictive management can respond to possible problems during construction in real time and make adjustments in advance, thus ensuring the smooth progress of the construction process.

[0047] The above three steps constitute a complete precast component management system; By converting historical construction data, requirements, stages, etc. into structured sequence data, the usability of the data and the processing ability of the system are enhanced; using the multi-layer architecture of the deep neural network for data processing can effectively capture the complex relationships between different factors in the construction project, thereby improving the prediction accuracy; by inputting the target precast component, the model can output accurate predictions of construction application requirements, which helps to optimize the construction progress and resource management.

[0048] This method not only improves the intelligent level of construction management, but also effectively improves the construction efficiency and accuracy, reduces unnecessary delays and cost waste, and finally realizes the refined management of construction projects.

[0049] In a preferred embodiment of the present invention, it further includes: Step 15: According to the recognition result of the precast component management model, set a construction scheduling mechanism. The construction scheduling mechanism evenly schedules and allocates the target precast components of each mark in multiple said marked data sets according to the scheduling path according to the demand situation of precast components in the construction project, so as to obtain scheduling allocation information data. Step 16: Real-time feedback the scheduling allocation information data to obtain a feedback result; according to the feedback result, synchronously schedule the input of multiple said target precast components in the next batch into the construction project until the target precast components complete the current construction project.

[0050] In the implementation of the present invention, in Step 15, the construction scheduling is first set according to the recognition result of the precast component management model. These recognition results provide the specific requirements of each precast component in the construction project, such as when to transport, installation requirements, priorities, etc.; based on the data provided by the model, the construction scheduling mechanism will be set or adjusted to cope with different requirements and resource states. The scheduling mechanism will consider the overall requirements of the project and reasonably arrange the transportation and usage timeline of precast components; the scheduling mechanism is responsible for evenly scheduling and allocating the target precast components of each mark in multiple marked data sets according to the scheduling path. This means that the scheduling not only considers the requirements of each component, but also considers the efficiency of the entire construction site, how to balance different tasks and resources to minimize waiting time and costs.

[0051] Through an accurate scheduling mechanism, it is possible to ensure the optimal use of resources, prevent resource waste, and improve construction efficiency; the balanced scheduling allocation ensures that the work of each part can proceed smoothly, reduces waiting and idle time, and speeds up the construction progress; effective scheduling can reduce unnecessary transportation and delays, thereby reducing costs.

[0052] In Step 16, the scheduling allocation information is real-time fed back to the construction site and the management system. This real-time nature allows project managers to timely understand the implementation situation of the scheduling and possible deviations; the real-time fed-back data is used to evaluate the effectiveness of the current scheduling plan, monitor the usage status of precast components and the construction progress; based on the feedback result, the management system will optimize or adjust the scheduling of the target precast components in the next batch. This dynamic adjustment ensures that the construction project can flexibly adjust the plan according to the actual situation.

[0053] Through real-time feedback and synchronous scheduling, construction management can respond more quickly to on-site changes and challenges, ensuring that the construction is not interrupted due to delays or incorrect scheduling of precast components; the utilization of real-time data allows for more accurate adjustment of the construction plan and better prediction and preparation for future construction batches; the feedback mechanism provides an opportunity for continuous improvement and optimization of the construction process, and each feedback is a verification of the scheduling strategy and possible improvement points.

[0054] Step 15 and Step 16 together constitute a cyclic and self-optimizing construction scheduling system. The recognition results of the deep learning model are used to set and adjust the construction scheduling to ensure that each precast component can reach the usage location in a timely manner according to requirements. By monitoring the execution of the scheduling and the actual construction requirements in real time, the subsequent construction scheduling plan is adjusted and optimized to ensure the continuity and efficiency of the construction.

[0055] In a preferred embodiment of the present invention, the construction scheduling mechanism in Step 15 includes: Step 151: Assign demand consumption weights Ri to multiple different said marked data sets. The demand consumption weight Ri represents the precast component resources consumed by a single data item in the marked data set due to the requirements in the construction project. And select the source node Ei and the target node Si according to the demand consumption weight. Step 152: Through Establish a marked data consumption dependency relationship; in the formula, G represents the marked data consumption dependency relationship function, represents the consumption dependency weight, n represents the number of data items in the marked data set; b represents the resource additional consumption parameter. The marked data consumption dependency relationship represents the dependency relationship between the quantity consumed by the marked target precast component according to the construction project requirements and the current total resources, so that the scheduling task of the target precast component progresses step by step.

[0056] In the implementation of the present invention, each data item in each marked data set is assigned a demand consumption weight; this weight represents the consumption of precast component resources by each data item in the construction project. For example, a data item may represent a specific construction task, and this task may require different quantities of precast components. The demand consumption weight reflects the specific resource requirements of this task and helps the scheduling system evaluate the resource consumption situation; Select the source node and the target node: According to the demand consumption weight, the system will select the source node and the target node of the construction scheduling. The source node represents the starting position of the task or operation, and the target node represents the final execution position or result of this task. The basis for selecting these nodes is the amount of resources required by each node and how to optimize the construction scheduling by reasonably allocating resources through a path.

[0057] By specifying a consumption weight for each task, the system can accurately calculate the resource requirements of each task, so as to give priority to those tasks that consume less resources or have intensive resource requirements in the scheduling; Efficient scheduling path planning: The selection of the resource node and the target node is based on the influence of the demand consumption weight, making the resource allocation more in line with the actual needs of the project, avoiding waste of resources, and improving the accuracy and flexibility of resource scheduling.

[0058] Step 152 further refines the management of construction scheduling by establishing consumption dependencies of marked data. The consumption dependency weight describes the relationship between the consumption pattern of a marked data set and other tasks or resources. For example, the completion of certain tasks depends on the quantity of prefabricated components consumed in the previous stage, or the resource requirements of certain tasks affect the scheduling of subsequent tasks. This dependency weight describes the dependency relationship between the consumption quantity of the target prefabricated component and the current total resources by establishing a mathematical model. Specifically, the completion of a certain task may depend on the quantity of resources consumed in the early stage, the efficiency of resource allocation, and the remaining status of resources; ensure that the scheduling tasks of the target prefabricated component are executed in a proper step and sequence. Through step-by-step scheduling, the system can ensure reasonable resource allocation, avoid excessive resource consumption or shortage, and ensure the smooth progress of each task; establishing consumption dependencies helps prevent delays or resource waste caused by resource scheduling conflicts between different construction tasks. The mutual dependencies between tasks and resources are clearly defined, enabling the scheduling to proceed step by step; through the consumption dependency weight, the system can accurately evaluate the impact of each task on the overall resources and perform reasonable scheduling and allocation. This precise dependency relationship model can greatly improve the efficiency of resource use and the accuracy of scheduling; the dependency relationship model helps ensure that each task can be completed step by step, avoiding delays or cost increases caused by resource shortages or scheduling errors. The sequence and dependency relationships between tasks can be optimized, thus accelerating the construction progress.

[0059] Through the above two steps, by introducing the demand consumption weight and consumption dependencies, the management of construction scheduling is further refined; the demand consumption weight enables the scheduling tasks to be prioritized according to the resource requirements of each target prefabricated component, optimizing the resource allocation and scheduling path during the construction process; the establishment of consumption dependencies provides a more precise dependency structure for the scheduling tasks, ensuring that the task scheduling does not conflict, the dependency relationships are clear, and can be reasonably adjusted according to the progress of resource consumption; Overall, adopting this model of dependency relationships and demand consumption weights can greatly improve the accuracy, flexibility, and efficiency of construction project scheduling, and at the same time ensure the project is completed on time and efficiently, avoiding resource waste and unnecessary delays.

[0060] In a preferred embodiment of the present invention, step 15 further includes: Set the resource pool size as C r , the maximum available quantity of each resource is C rk , the resources required for each target scheduling task m are R ik , through to obtain the resource constraint conditions of consumption dependencies; At any moment, the resource requirements of all target scheduling tasks do not exceed the size of the resource pool; where T represents the set of all ongoing tasks at the current moment. When h target scheduling tasks and f target scheduling tasks are carried out synchronously, it means that the i-th batch of target scheduling tasks is completed, which is the first target scheduling task; when the target scheduling task is carried out and completed after the previous batch of the i-th batch of target scheduling tasks, it is the second target scheduling task.

[0061] In the implementation of the present invention, let the size of the resource pool be C r , and the maximum available amount of each resource be C rk ; the size of the resource pool (C r ) and the maximum available amount of the resource (C rk ): These two parameters define the total amount of available resources in the entire system and the maximum allocable amount of each resource. The size of the resource pool C r represents the maximum number of resources that the system can carry, while the maximum available amount of each resource C rk stipulates the upper limit of the allocation of each resource; by setting the size of the resource pool and the maximum available amount of each resource, the system can control the total amount and allocation of resources at any moment, avoiding resource overload or unnecessary waste; the resources required for each target scheduling task m are R ik , and the resource constraint conditions are obtained through the consumption dependency relationship. The resource requirements of the target scheduling task (R ik ): Each target scheduling task m has specific resource requirements R ik , and these requirements may include different types of resources, such as manpower, materials or equipment; this refers to restricting the resource requirements of each scheduling task within the scope of the available resource pool based on the aforementioned consumption dependency relationship model. These constraint conditions ensure that at any moment, the total resource requirements of all scheduling tasks do not exceed the size of the resource pool; through the consumption dependency relationship resource constraint conditions, the system can dynamically adjust the resource allocation to ensure that each task obtains the required resources without exceeding the limit that the system can carry. This can improve resource utilization, avoid resource shortages or surpluses, and thus optimize the execution efficiency of the project.

[0062] At any moment, the resource requirements of all target scheduling tasks do not exceed the size of the resource pool. This principle states that when the system processes scheduling tasks at any moment, it must ensure that the cumulative resource requirements of all tasks do not exceed the set size Cr of the resource pool. This can be achieved by dynamically adjusting the scheduling of tasks and resource allocation; such constraint conditions ensure that the system can effectively manage resources under both high-load and low-load conditions, avoiding excessive consumption or waste of resources. This can improve the execution efficiency and resource utilization of the project, while reducing the operating cost.

[0063] Completion definitions of the first target scheduling task and the second target scheduling task; task batches and completion definitions describe the progress and completion order of scheduling tasks in terms of time. The completion of the first target scheduling task and the second target scheduling task defines the sequence and dependency relationships between tasks, affecting the scheduling process and resource allocation of the entire project; thus, determining the completion order of each scheduling task helps the system to reasonably arrange resources and work processes, ensuring that the project can proceed in the expected order and schedule. Such a clear definition of task batches can optimize the overall scheduling arrangement and improve the execution efficiency and quality of the project.

[0064] The above steps construct an effective scheduling management system by defining the resource pool size, the maximum available resources, and the specific scheduling task requirements and constraints; thus ensuring the stability and controllability of scheduling tasks in terms of resources, avoiding waste and shortage of resources; optimizing the order of scheduling tasks and resource allocation through constraints and task completion definitions, improving the execution efficiency and cost-effectiveness of the project; being able to effectively cope with complex construction environments and resource management challenges, ensuring that the project can be completed on time and meet the expected quality standards.

[0065] In a preferred embodiment of the present invention, step 15 further includes: Based on the resource consumption constraint conditions and the marked data consumption dependency relationships, real-time feedback of scheduling progress information is provided. When scheduling deviations or resource shortages occur, the scheduling strategy is automatically adjusted. The scheduling strategy includes adjusting production tasks, modifying transportation routes, and changing allocation batches; The real-time feedback scheduling progress information is used to adjust the recognition results and scheduling plans to construct a closed-loop feedback for iteratively optimizing the construction scheduling mechanism.

[0066] In the implementation of the present invention, resource consumption constraint conditions and data consumption dependency relationships: The system uses the previously set resource pool size, the maximum available resources, and the resource requirements of each task (R ik ), to track and record in real time the resource consumption of each task. At the same time, the data consumption dependency relationships guide the execution order and resource usage between tasks; by collecting and analyzing the resource consumption of tasks in real time, the system can immediately feedback scheduling progress information. Such real-time monitoring helps to promptly detect scheduling deviations or resource shortages, providing data support for subsequent adjustments.

[0067] Automatically adjusting the scheduling strategy, including adjusting production tasks, modifying transportation routes, and changing allocation batches; when the system detects scheduling deviations or resource shortages, it automatically triggers adjustment measures for the scheduling strategy. These measures may include: Adjusting the priority or quantity of production tasks.

[0068] Modify the transportation route to optimize the use of resources and time costs.

[0069] Change the allocation batches to adjust the execution order of tasks or resource allocation.

[0070] By automatically adjusting the scheduling strategy, it can quickly respond to real-time feedback information, optimize the use of resources and the execution order of tasks. This can reduce scheduling deviations and resource waste, and improve the overall efficiency and cost control ability of the construction process; adjust the recognition results and scheduling plan according to the real-time feedback of the scheduling progress information; dynamically adjust the previous recognition results and scheduling plan according to the real-time feedback of the scheduling progress information. This includes re-evaluating the task completion time, changes in resource requirements, and possible bottlenecks.

[0071] Through the feedback and adjustment of real-time data, the system can more accurately predict the task completion time and resource requirements, thereby optimizing the overall construction scheduling plan. This closed-loop feedback mechanism ensures the continuous improvement and optimization of the scheduling process; build a closed-loop feedback and iteratively optimize the construction scheduling mechanism By continuously collecting, analyzing, and applying real-time feedback information, a closed-loop feedback mechanism is formed. This mechanism supports the system to continuously optimize and improve during the real-time scheduling process; through iterative cycles, the system can continuously learn and adapt to the changing construction environment and resource conditions. This can improve the flexibility and response ability of the scheduling mechanism, ensuring that the construction project can be completed on time and within budget.

[0072] The above steps cooperate with each other. Through real-time data collection and analysis, timely understand the scheduling progress and resource usage; automatically adjust task priorities and resource allocation according to real-time feedback to cope with changes and bottlenecks; through the closed-loop feedback mechanism, continuously improve the prediction accuracy and scheduling efficiency, and improve the quality and efficiency of overall construction management.

[0073] In a preferred embodiment of the present invention, step 15 further includes: According to the urgency of the project progress, the assembly duration of the components, and the transportation distance, prioritize the transportation route of the target precast component to obtain the preferred transportation route of the target precast component; According to the preferred transportation route of the target precast component, determine the path of the target precast component from production, transportation to the construction site, and transport the target precast component to the target location; the construction project progress has been completed; Preset multiple scheduling paths and assign a weight value to each path. According to the resource requirements at the construction site and the delivery timeliness information of the precast components, dynamically select the optimal transportation route.

[0074] In the implementation of the present invention, according to the urgency of the project progress, the assembly duration of components, and the transportation distance, the priority planning of the transportation routes for target precast components is carried out; according to the overall progress of the construction project, the time limit of the project, and the priorities of various tasks, it is decided which components need to be transported first. For example, some precast components may be components of key nodes and need to arrive at the construction site as early as possible to ensure the project progress.

[0075] The assembly duration of precast components is also a factor to be considered when planning transportation routes. Components with a long assembly time need to be transported to the construction site earlier to ensure that they can be put into use in time during construction.

[0076] According to the length of the transportation route, road conditions, traffic conditions, etc., the transportation time and cost of each route are evaluated, and then the priorities are planned for different precast components.

[0077] By comprehensively considering the urgency, assembly duration, and transportation distance, the transportation resources and time can be effectively allocated to ensure that the most urgent components arrive first, avoiding delays during the construction process; reasonably planning the priority of transportation routes to avoid unnecessary repeated transportation or idle time and improve transportation efficiency.

[0078] According to the preferred transportation route of the target precast component, determine the route from production, transportation to the construction site, transport the target precast component to the target location, and complete the construction project progress; according to the priority planning in the previous step, select the most suitable transportation route to transport the target precast component from the production place to the construction site. This includes selecting the shortest and most unobstructed transportation route, considering factors such as transportation time, traffic conditions, and route safety; this step needs to comprehensively consider the transportation route, the scheduling of logistics vehicles, and possible emergencies to ensure that the precast component can arrive at the construction site on time and as required; ensure that through the optimization of the transportation route, all precast components can arrive at the construction site within the specified time to support the smooth progress of the construction; through efficient transportation route selection and scheduling, the precast component can be delivered to the construction site on time, avoiding affecting the overall construction progress due to the delay of the component arrival; the preferred route not only ensures the timeliness of transportation but also reduces unnecessary detours or roundabouts, thereby reducing the transportation cost.

[0079] Preset multiple scheduling paths and assign a weight value to each path. Before planning the transportation route, the system will preset multiple possible transportation routes according to conditions such as geographical location and road network. Each path will have different characteristics (for example, distance, traffic flow, road conditions, etc.), and each preset path will be assigned a weight value according to its impact on the project schedule and cost. The weight value can be dynamically adjusted according to the actual situation, such as traffic congestion, weather factors, etc.; By presetting multiple paths and assigning weights, the best path can be flexibly selected under different conditions. For example, when a certain path is blocked by traffic or impassable, the system can quickly adjust to an alternative path with a higher weight; The weight assignment of the path enables the system to make quick decisions for different real-time situations, improving the flexibility and adaptability of transportation.

[0080] Dynamically select the optimal transportation route according to the resource requirements at the construction site and the delivery timeliness information of precast components; Dynamically evaluate which paths can most effectively meet the on-site requirements according to the actual resource requirements at the construction site (such as the number of workers, equipment availability, etc.). For example, if the resources at the construction site are tight at a certain time point, a path that can complete the transportation in a shorter time can be selected; Track the delivery timeliness of each precast component in real time to ensure that the components arrive at the established time nodes. If the transportation time of a certain path is too long, the system will automatically adjust and select a shorter and more efficient path.

[0081] By dynamically selecting the optimal path in real time, the system can ensure the flexibility during the transportation process and can cope with the changes in on-site requirements and external factors; The matching of dynamic path selection and on-site resource requirements enables the construction site to receive precast components at the best time, avoiding construction delays caused by over-allocation or insufficient resources.

[0082] The above steps work together. By comprehensively considering the project urgency, assembly duration, and transportation distance, the transportation tasks can be accurately planned to ensure that urgent components can arrive at the construction site first, avoiding schedule delays; The presetting and dynamic selection of multiple scheduling paths can quickly respond to changes in different construction environments, ensuring the timely delivery of precast components during the construction process; Optimizing the transportation route can reduce unnecessary transportation time and costs, improve the utilization efficiency of resources, and maximize the reduction of the overall transportation cost of the project; By dynamically selecting the transportation route in combination with the resource requirements at the construction site, ensure that each component can arrive at the construction site at the right time, thereby improving the utilization efficiency of on-site resources and construction quality.

[0083] The overall scheduling mechanism will help reduce the impact caused by delays in transportation, assembly and other links, ensuring that the construction project can be completed on time, within budget and with high quality.

[0084] Such as Figure 2As shown in the figure, a construction management system for prefabricated components of an assembled building includes: An information collection module: It is used to collect various building prefabricated component information data to obtain an information data set; A data processing module: It is used to classify the information data set into multiple prefabricated component information subsets; mark the multiple prefabricated component data subsets respectively to obtain multiple marked data sets; A prefabricated component scheduling module: It is used to train and construct a prefabricated component management model with a target prefabricated component data set to output an identification result representing the scheduling requirements of the target prefabricated component for the construction project; the target prefabricated component data set includes historical construction data, construction project requirements, construction stages, and the multiple marked data sets; based on the prefabricated component management model, at least one type of data in the target prefabricated component data set is input into the prefabricated component management model, and an identification result representing the scheduling requirements of the current target prefabricated component for the construction project is output; A progress tracking and feedback module: It is used to set a construction scheduling mechanism according to the identification result of the prefabricated component management model, and continuously feedback scheduling information through the set construction scheduling mechanism to continuously optimize the balanced scheduling and allocation of the target prefabricated component.

[0085] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a well-known general intelligent device. Therefore, the object of the present invention can also be achieved only by providing a program product containing program code for implementing the method or system. It should also be pointed out that in the device and method of the present invention, obviously, each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present invention. And, the steps of performing the above series of processes can naturally be executed in chronological order according to the described order, but it is not necessary to execute them in chronological order. Some steps can be executed in parallel or independently of each other.

Claims

1. A construction management method for prefabricated components of prefabricated buildings, characterized in that, include: Collect information data of various building prefabricated components to obtain information data sets; Classifying the information data set to divide it into a plurality of prefabricated component information subsets; Labeling the plurality of prefabricated component data subsets respectively to obtain a plurality of labeled data sets; The target prefabricated component data set is trained to construct a prefabricated component management model to output an identification result representing the target prefabricated component's scheduling requirements for the construction project; the target prefabricated component data set includes historical construction data, construction project requirements, construction stages, and the multiple labeled data sets; Based on the prefabricated component management model, at least one data in the target prefabricated component data set is input into the prefabricated component management model, and an identification result representing the current target prefabricated component's scheduling demand for the construction project is output; A construction scheduling mechanism is set according to the identification results of the prefabricated component management model, and scheduling information is fed back in real time through the set construction scheduling mechanism to continuously optimize the balanced scheduling and allocation of the target prefabricated components.

2. The construction management method for prefabricated components of an assembled building according to claim 1, characterized in that The information data set is classified to be divided into a plurality of prefabricated component information subsets, including: Scan and collect information data of various prefabricated building components into an information data set; preprocess the information data set, and arrange the preprocessed information data set in a hierarchical manner to determine the number of hierarchical columns K; Randomly select a sub-column K from the number K of the hierarchical columns i ; Determine a category center in the sub-column K i as a feature vector, and obtain the shortest allocation distance of the information data set through ; Allocate the information data items according to the shortest allocation distance; where represents the j-th shortest allocation distance; x i represents the i-th information data item, and μ j represents the j-th category center; Each information data item is divided into a plurality of prefabricated component information subsets according to the final category center to which it belongs; the same information data items exist in the prefabricated component information subsets.

3. A construction management method for prefabricated components of an assembled building according to claim 2, characterized in that Multiple prefabricated component data subsets are labeled respectively to obtain multiple labeled data sets, including: Labeling multiple prefabricated component data subsets according to the hierarchical arrangement results of the prefabricated component information data, and determining three clusters, and then labeling each cluster number as a label to obtain multiple labeled data sets; The labeled data set is arranged according to each information data item in a hierarchical manner, and is divided into three types, namely, fast, medium and slow, according to the data items in the construction progress data, which are three cluster number labels; the construction progress data includes transportation progress, installation progress and quality inspection progress.

4. A construction management method for prefabricated components of an assembled building according to claim 3, characterized in that The prefabricated component management model includes: Generating structure data from a target prefabricated component data set, and encoding the structure data into sequence data to train the prefabricated component management model; The sequence data is input into the prefabricated component management model; the prefabricated component management model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, and the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer outputs the recognition result representing the scheduling demand of the target prefabricated component for the construction project; At least one target prefabricated component is input into the prefabricated component management model, and an output layer of the prefabricated component management model outputs an identification result representing a scheduling requirement of the current target prefabricated component for the construction project.

5. A construction management method for prefabricated components of an assembled building according to claim 4, characterized in that, According to the recognition result of the prefabricated component management model; a construction scheduling mechanism is set, and the construction scheduling mechanism evenly schedules and allocates the target prefabricated components marked in the multiple marked data sets according to the demand for prefabricated components in the construction project according to the scheduling path, so as to obtain scheduling allocation information data; The scheduling allocation information data is fed back in real time to obtain a feedback result; according to the feedback result, synchronous scheduling is performed on the input of multiple target precast components in the next batch for the construction project until the target precast components complete the current construction project.

6. The construction management method for prefabricated components of an assembled building according to claim 5, characterized in that, The construction scheduling mechanism includes: Demand consumption weights Ri are assigned to multiple different tag data sets respectively, where the demand consumption weight Ri represents the precast component resources consumed by a single data item in the tag data set due to demand in the construction project; and source nodes Ei and target nodes Si are selected according to the demand consumption weights. Step 152, by establishing a marked data consumption dependency relationship; where G represents a marked data consumption dependency relationship function, represents the consumption dependency weight, n represents the number of data items in the marked dataset; b represents a resource additional consumption parameter, and the marked data consumption dependency relationship represents the dependency relationship between the quantity consumed by the marked target prefabricated component according to the construction project requirements and the current total resources, so as to make the scheduling task of the target prefabricated component proceed step by step.

7. A construction management method for prefabricated components of an assembled building according to claim 6, characterized in that, Let the resource pool size be C r , and the maximum available amount of each resource is C rk . Each target scheduling task m requires resources R ik . By to obtain the resource constraint conditions of consumption dependency relationships; At any time, the demand consumption of all target scheduling tasks for resources does not exceed the size of the resource pool; where T represents the set of all ongoing tasks at the current time. When h target scheduling tasks and f target scheduling tasks are carried out synchronously, it means that the target scheduling tasks of the i-th batch are completed, which is the first target scheduling task; when the target scheduling tasks of the i-th batch of target scheduling tasks are carried out and completed after the previous batch of target scheduling tasks are completed, it is the second target scheduling task.

8. A construction management method for prefabricated components of an assembled building according to claim 7, characterized in that, Based on the resource consumption constraint conditions and the tag data consumption dependency relationship, the scheduling progress information is fed back in real time. When scheduling deviation or resource tension occurs, the scheduling strategy is automatically adjusted, and the scheduling strategy includes adjusting production tasks, modifying transportation routes, and changing the allocation batch. The scheduling progress information fed back in real time is used to adjust the recognition result and the scheduling plan to construct a closed-loop feedback, so as to iteratively optimize the construction scheduling mechanism.

9. A construction management method for prefabricated components of an assembled building according to claim 8, characterized in that, According to the urgency of the project progress, the assembly duration of the components, and the transportation distance, the transportation route of the target precast components is prioritized to obtain the preferred transportation route of the target precast components. According to the preferred transportation route of the target precast components, the route of the target precast components from production, transportation to the construction site is determined, and the target precast components are transported to the target location. The construction project progress has been completed. Multiple scheduling routes are preset and a weight value is assigned to each route. According to the resource requirements at the construction site and the delivery timeliness information of the precast components, the optimal transportation route is dynamically selected.

10. An assembled building precast component construction management system, characterized in that, The system is provided with an electronic device including a memory, a processor, and a program of a construction management method for precast components of an assembled building stored on the memory and executable on the processor. When the program of the construction management method for precast components of an assembled building is executed by the processor, the steps of the construction management method for precast components of an assembled building as described in any one of claims 1-9 are implemented. The system includes: An information collection module: It is used to collect various building precast component information data to obtain an information data set. A data processing module: It is used to classify the information data set into multiple precast component information subsets; and to label multiple precast component data subsets respectively to obtain multiple tag data sets. Prefabricated component scheduling module: It is used to train and construct a prefabricated component management model with a target prefabricated component dataset to output an identification result indicating the scheduling requirements of the target prefabricated component for the construction project; the target prefabricated component dataset includes historical construction data, construction project requirements, construction stages, and the multiple labeled datasets; based on the prefabricated component management model, at least one type of data in the target prefabricated component dataset is input into the prefabricated component management model to output an identification result indicating the scheduling requirements of the current target prefabricated component for the construction project; Progress tracking and feedback module: It is used to set a construction scheduling mechanism according to the identification result of the prefabricated component management model, and continuously feedback scheduling information through the set construction scheduling mechanism to continuously optimize the balanced scheduling and allocation of the target prefabricated component.

Images