Method and device for assisting simulation calculation of construction progress plan

Abstract

The invention provides a method and device for assisting construction progress plan simulation calculation, and relates to the technical field of data processing, construction data of historical projects is collected, and the construction data comprises one or more of task information, process information, resource information and construction progress information; training a constructed prediction model by using the collected construction data to obtain a trained prediction model; and performing simulation calculation on the construction progress plan of the current project based on the trained prediction model, and judging whether delay occurs or not. Therefore, feature vectors of task information, process information, resource information, construction progress information and the like are extracted from the input actual construction progress data by using the deep learning model so as to predict a construction progress plan in real time and adjust the construction progress plan in time, and the effects of better allocating resources, reducing construction cost and improving benefits are achieved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for assisting construction schedule simulation calculation. Background Art

[0002] In the construction industry, accurate construction schedules are crucial to the success of a project. However, in the actual construction process, the construction schedule is often affected by various reasons, such as changes in the construction environment, adjustments to on-site conditions, and resource supply. If the construction schedule cannot be adjusted in time, it may lead to increased costs, delays in construction, and may even affect the safety of the project. At present, there is a lack of real-time control of the construction schedule. Summary of the invention

[0003] In view of this, the purpose of this application is to provide a method and device for assisting construction schedule simulation calculation, which can, based on a deep learning model, predict in real time whether the construction schedule will be completed on time according to the actual construction progress of the current project.

[0004] In a first aspect, an embodiment of the present application provides a method for assisting construction schedule simulation calculation, the method comprising the following steps:

[0005] Collecting construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information;

[0006] Using the collected construction data to train the constructed prediction model to obtain a trained prediction model;

[0007] Based on the trained prediction model, the construction schedule of the current project is simulated and calculated to determine whether it will be delayed.

[0008] In some embodiments, the construction data of the historical project comprises the following steps:

[0009] Collecting construction data of historical projects from multiple sources; the sources include one or more of construction drawings, construction plans, and bills of quantities;

[0010] Classifying the collected construction data, and marking the construction data of each category;

[0011] The annotated construction data is preprocessed to use the preprocessed construction data as input of a prediction model.

[0012] In some embodiments, the preprocessing of the annotated construction data comprises the following steps:

[0013] Data cleaning to check and correct errors, missing or duplicate data in the construction data;

[0014] Data standardization is to convert the images and texts in the construction data into a unified digital format.

[0015] In some embodiments, the prediction model is constructed based on a neural network, including an input end, a backbone network layer, a NECK layer and an output end, wherein the input end is used to input the construction data of the project's construction schedule; the backbone network layer includes a Focus structure and a CSP simplified structure, which are used to extract features from the construction data; the NECK layer includes an FPN structure and a PAN structure, which are used to fuse the features extracted from the construction data; the output end includes a GIOU_Loss function, which is used to output the prediction results of the project's construction schedule.

[0016] In some embodiments, the prediction model is trained in the following manner:

[0017] Acquire construction data of several historical projects, and convert task information, process information, resource information, and construction progress information in the construction data into feature vectors of the same dimension;

[0018] All eigenvectors are normalized, and the normalized eigenvectors are multiplied by the corresponding eigenweights to form a eigenmatrix.

[0019] According to the construction data of each historical project, set the corresponding prediction result label;

[0020] Model training is performed according to the feature matrix and the corresponding prediction result labels; wherein, the original weight file of the pre-built prediction model is loaded, and the prediction accuracy of the pre-built prediction model is continuously regressed and adjusted by comparing the labels with the labeled construction data until the loss function exceeds the set threshold, thereby obtaining a trained prediction model; wherein, the calculation formula of the loss function is:

[0021]

[0022] y' is the actual result obtained through the network, y is the actual label, n is the number of iterations, y1, y2, y3, and y4 represent the feature vectors of task information, process information, resource information, and construction progress information, respectively.

[0023] In some embodiments, the simulation calculation of the construction schedule of the current project based on the trained prediction model to determine whether it is delayed includes the following steps:

[0024] According to the established BIM model, obtain the actual construction progress of the current project;

[0025] Inputting the actual construction progress and construction schedule of the current project into the trained prediction model to obtain a prediction result of whether the construction schedule of the current project can be completed on time based on the trained prediction model;

[0026] Based on the forecast results obtained, a new construction schedule is re-arranged.

[0027] In some embodiments, the method further comprises the following steps:

[0028] Based on the actual construction progress of the current project and the forecast results of each construction progress plan, a construction progress status chart is established to provide risk warning.

[0029] In a second aspect, an embodiment of the present application provides a device for assisting in simulation calculation of a construction schedule, the device comprising:

[0030] A collection module, used to collect construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information;

[0031] A training module, used to train the constructed prediction model using the collected construction data to obtain a trained prediction model;

[0032] The simulation calculation module is used to simulate the construction schedule of the current project based on the trained prediction model to determine whether it will be delayed.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory through the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for assisting construction schedule simulation calculation described in any one of the first aspects are performed.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for assisting construction schedule simulation calculation as described in any one of the first aspects above are executed.

[0035] The method and device for assisting the simulation calculation of the construction schedule described in the present application collects the construction data of historical projects; uses the collected construction data to train the constructed prediction model to obtain a trained prediction model; and simulates the construction schedule of the current project based on the trained prediction model to determine whether it is delayed. Thus, by using the deep learning model, the construction schedule can be predicted in real time according to the actual construction progress of the current project, so as to make timely adjustments to the construction schedule, better allocate resources, reduce construction costs and improve efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flowchart showing the method for assisting construction schedule simulation calculation according to an embodiment of the present application is shown;

[0038] Figure 2 A schematic diagram showing the summary of construction data of historical projects collected by an embodiment of the present application is shown;

[0039] Figure 3 A schematic diagram showing a simulation calculation of a construction schedule of a current project based on the trained prediction model according to an embodiment of the present application is shown;

[0040] Figure 4 A schematic diagram of the structure of the device for assisting construction schedule simulation calculation according to an embodiment of the present application is shown;

[0041] Figure 5 A structural block diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0042] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0043] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0044] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0045] In view of the technical problems eliminated by the background technology, the present application provides a method and device for assisting the simulation calculation of the construction schedule, which can predict in real time whether the construction schedule will be completed on time based on the actual construction progress of the current project based on a deep learning model.

[0046] See the instruction manual Figure 1 The present application provides a method for assisting construction schedule simulation calculation, the method comprising the following steps:

[0047] S1. Collecting construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information;

[0048] S2. Training the constructed prediction model using the collected construction data to obtain a trained prediction model;

[0049] S3. Based on the trained prediction model, simulate and calculate the construction schedule of the current project to determine whether it will be delayed.

[0050] In an embodiment of the present application, the method for assisting the simulation calculation of the construction schedule can be run on a terminal device or a server; wherein the terminal device can be a local application software, and when the method for assisting the simulation calculation of the construction schedule is run on the server, the method for assisting the simulation calculation of the construction schedule can be implemented and executed based on a cloud interaction system, wherein the cloud interaction system at least includes a server and a client device (i.e., application software). Specifically, taking application to a server as an example, when the method for assisting the simulation calculation of the construction schedule is run on the server, it can be based on a deep learning model and predict in real time whether the construction schedule will be completed on time according to the actual construction progress of the current project.

[0051] For details, see the attached manual. Figure 2 In step S1, the construction data of historical projects are collected from multiple sources to ensure the integrity and accuracy of the data, including engineering quantities, manpower, materials, equipment, etc. The sources may include construction drawings, construction plans, and bills of quantities. In addition, in the present application, the construction data also needs to be preprocessed before it can be used as input for the prediction model. In one embodiment, the construction data may be classified and labeled first to facilitate subsequent simulation calculations and analysis. For example, the construction data is divided into task information, process information, resource information, milestone information, construction progress information, and environmental factors. Among them, for task information, the task name, start time, end time, duration, etc. are marked. Different symbols or colors can be used to mark different types of tasks so that they can be distinguished in subsequent simulation calculations. This information can help the neural network understand the relationship and time arrangement between different tasks; for process information, the dependencies between processes, the resources required for processes, the sequence of processes, etc. are marked. Arrows or other symbols can be used to indicate the sequence and dependencies between processes. This information can help the neural network understand the association between processes and resource allocation; for resource information, the demand and usage time of resources such as manpower, materials, and equipment are marked. Different symbols or icons can be used to indicate different types of resources. This information can help the neural network understand the allocation and utilization of resources; for milestone information, the time arrangement and completion status of important nodes and milestones are marked. This information can help the neural network understand the key nodes and important events of project progress; for construction progress information, the actual completion time, delays, etc. are marked. This information can help the neural network learn the past construction progress and predict the future progress; for environmental factors, external factors that may affect the construction progress, such as weather and supply chain conditions, are marked. This information can help the neural network understand the impact of the external environment on the construction progress.

[0052] After completing the data annotation, the next step is to preprocess the data to ensure the accuracy and applicability of the data. First, check whether the collected construction data is wrong, missing or repeated, and correct or supplement the wrong or incomplete data; for duplicate data, remove duplicates; secondly, perform data format conversion to convert the construction data into a format that can be recognized by the computer, such as unifying the date and time format, converting text data into digital format, etc., for subsequent simulation calculations and analysis.

[0053] In other embodiments, further, the preprocessing method also includes data screening, which is to screen and eliminate the construction data according to the needs of the simulation calculation, remove unnecessary data or aggregate the data to simplify the calculation process; data verification, which is to verify and check the construction data to ensure the accuracy and completeness of the data and eliminate possible errors or abnormal data; data conversion, which is to convert and process the construction data according to the needs of the simulation calculation, such as converting time data into duration, converting resource requirements into computable values, etc.

[0054] In step S2, that is, after the preprocessing of the collected historical project construction data is completed, the prediction model constructed based on deep learning can be trained. In one embodiment, the constructed prediction model includes: an input end, for inputting the construction data of the construction schedule of the project; a backbone network layer, including a Focus structure and a CSP simplified structure, for extracting features from the construction data; a NECK layer, including an FPN structure and a PAN structure, for fusing the features extracted from the construction data; an output end, including a GIOU_Loss function, for outputting the prediction result of the construction schedule of the project. In addition, the pre-built prediction model is trained in the following manner: the construction data of several historical projects are obtained, and the task information, process information, resource information, and construction progress information in the construction data are converted into feature vectors of the same dimension; all feature vectors are normalized, and the normalized feature vectors are multiplied by the corresponding feature weights to form a feature matrix; the corresponding prediction result labels are set according to the construction data of each historical project; the model is trained according to the feature matrix and the corresponding prediction result labels; wherein, the original weight file of the pre-built prediction model is loaded, and the prediction accuracy of the pre-built prediction model is continuously regressed and adjusted by comparing with the labels of the annotated construction data until the loss function exceeds the set threshold, and a trained prediction model is obtained; wherein the calculation formula of the loss function is:

[0055]

[0056] y' is the actual result obtained through the network, y is the actual label, n is the number of iterations, y1, y2, y3, and y4 represent the feature vectors of task information, process information, resource information, and construction progress information, respectively.

[0057] In step S3, after the prediction model is trained using the construction data of the historical project, the actual construction progress and construction schedule of the current project are input into the trained prediction model, and the trained prediction model can output the prediction result of whether the construction schedule can be completed on time. In one embodiment, after the construction schedule of the current project is input, the map of each engineering node of the project can be constructed according to the construction schedule, and then after the actual construction progress of the current project is input, the prediction result of whether the construction schedule is smooth can be immediately generated in the map. Among them, the BIM model can be used to obtain the actual construction progress of the current project in real time. The BIM (Building Information Modeling, Building Information Modeling) is based on the relevant information data of the construction project as the basis of the model, and the building model is established. The real information model of the building is simulated by digital information simulation. It is now widely used in engineering management platform, and will not be repeated here.

[0058] Therefore, in the architectural design and planning stage, this prediction model can be used to predict the construction schedule of new projects and provide reference for decision makers; during the construction process, this prediction model can be used to monitor the construction progress in real time, discover and solve problems in time, and ensure that the project is completed on time. Figure 3 When predicting for the project named site leveling, the preset planned start date is 2023-10-10 and the planned end time is 2023-11-08. According to the actual construction progress of the current site leveling, the predicted result obtained by the prediction model simulation calculation is 41 days behind. The decision maker can make timely adjustments based on the prediction result and reset the planned end time, that is, the adjusted date.

[0059] Furthermore, according to the actual construction progress of the current project and the forecast results of each construction schedule, a construction progress status diagram can be established on the basis of the map of each engineering node to provide intuitive visual risk warning. For example, the completed construction schedule is represented in green, the delayed construction schedule is represented in red, the unstarted construction schedule is represented in white, the normal construction schedule is represented in blue, and the warning construction schedule is represented in yellow.

[0060] It can be seen that the method provided by the present application is to assist in the simulation calculation of the construction schedule, by collecting a large amount of construction data of historical projects to train the constructed prediction model to obtain a trained prediction model, and through the trained prediction model, extract the task information, process information, resource information, construction progress information and other feature vectors from the actual construction progress of the input current project, so as to predict in real time whether the construction schedule is progressing smoothly and make adjustments, thereby improving the efficiency and accuracy of decision-making and better adapting to the rapidly changing environment.

[0061] Based on the same inventive concept, a device for assisting in the simulation calculation of a construction schedule is also provided in an embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the method for assisting in the simulation calculation of a construction schedule in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0062] As the instruction manual Figure 4 As shown, the present application also provides a device for assisting construction schedule simulation calculation, the device comprising:

[0063] The collection module 401 is used to collect the construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information;

[0064] A training module 402 is used to train the constructed prediction model using the collected construction data to obtain a trained prediction model;

[0065] The simulation calculation module 403 is used to perform simulation calculation on the construction schedule of the current project based on the trained prediction model to determine whether it will be delayed.

[0066] In some embodiments, the acquisition module 401 acquires construction data of historical projects, including: collecting construction data of historical projects from multiple sources; the sources include one or more of construction drawings, construction plans, and bills of quantities; classifying the collected construction data, and labeling the construction data of each category separately; and preprocessing the labeled construction data to use the preprocessed construction data as input of a prediction model.

[0067] In some embodiments, the acquisition module 401 pre-processes the annotated construction data, including: data cleaning to check and correct errors, missing or duplicate data in the construction data; data standardization to convert images and texts in the construction data into a unified digital format.

[0068] In some embodiments, the prediction model is constructed based on the YOLOv5 network structure, including an input end, a backbone network layer, a NECK layer and an output end, wherein the input end is used to input the construction data of the project's construction schedule; the backbone network layer includes a Focus structure and a CSP simplified structure, which are used to extract features from the construction data; the NECK layer includes an FPN structure and a PAN structure, which are used to fuse the features extracted from the construction data; the output end includes a GIOU_Loss function, which is used to output the prediction results of the project's construction schedule.

[0069] In some embodiments, the training module 402 trains the prediction model, including: obtaining construction data of several historical projects, and converting the task information, process information, resource information, and construction progress information in the construction data into feature vectors of the same dimension; normalizing all feature vectors, and multiplying the normalized feature vectors by corresponding feature weights to form a feature matrix; setting corresponding prediction result labels according to the construction data of each historical project; training the model according to the feature matrix and the corresponding prediction result labels; wherein, the original weight file of the pre-built prediction model is loaded, and the prediction accuracy of the pre-built prediction model is continuously regressed and adjusted by comparing with the labels of the annotated construction data until the loss function exceeds the set threshold, thereby obtaining a trained prediction model; wherein the calculation formula of the loss function is:

[0070]

[0071] y' is the actual result obtained through the network, y is the actual label, n is the number of iterations, y1, y2, y3, and y4 represent the feature vectors of task information, process information, resource information, and construction progress information, respectively.

[0072] In some embodiments, the simulation calculation module 403 performs simulation calculations on the construction schedule of the current project based on the trained prediction model to determine whether it will be delayed, including: obtaining the actual construction progress of the current project based on the established BIM model; inputting the actual construction progress and construction schedule of the current project into the trained prediction model to obtain a prediction result of whether the construction schedule of the current project can be completed on time based on the trained prediction model; and re-arranging a new construction schedule based on the obtained prediction result.

[0073] In some embodiments, the device further includes an early warning module for establishing a construction progress status diagram based on the actual construction progress of the current project and the forecast results of each construction progress plan to provide risk early warning.

[0074] The present application provides a device for assisting in simulation calculation of construction schedule, which collects construction data of historical projects through a collection module; uses the collected construction data to train the constructed prediction model through a training module to obtain a trained prediction model; and uses the simulation calculation module to simulate the construction schedule of the current project based on the trained prediction model to determine whether it is delayed. Thus, by using a deep learning model, the construction schedule can be predicted in real time according to the actual construction progress of the current project, so as to make timely adjustments to the construction schedule, better allocate resources, reduce construction costs and improve efficiency.

[0075] Based on the same concept of the present invention, the specification is attached Figure 5 As shown, the structure of an electronic device 500 provided in an embodiment of the present application includes: at least one processor 501, at least one network interface 504 or other user interface 503, a memory 505, and at least one communication bus 502. The communication bus 502 is used to realize the connection and communication between these components. The electronic device 500 optionally includes a user interface 503, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, a trackball (trackball), a touch pad or a touch screen, etc.).

[0076] The memory 505 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A portion of the memory 505 may also include a non-volatile random access memory (NVRAM).

[0077] In some embodiments, the memory 505 stores the following elements, which may be protected modules or data structures, or subsets thereof, or extended sets thereof:

[0078] Operating system 5051, including various system programs, used to implement various basic services and process hardware-based tasks;

[0079] The application module 5052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0080] In an embodiment of the present application, by calling the program or instructions stored in the memory 505, the processor 501 is used to execute steps in a method for assisting in the simulation calculation of a construction schedule, and to predict the construction schedule in real time based on the actual construction progress of the current project, so as to make timely adjustments to the construction schedule, better allocate resources, reduce construction costs and improve efficiency.

[0081] The present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the method for assisting construction schedule simulation calculation are executed.

[0082] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned method for auxiliary construction schedule simulation calculation can be executed.

[0083] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0084] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0086] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0087] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for assisting construction schedule simulation calculation, characterized in that: The method comprises the following steps: Collecting construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information; Using the collected construction data to train the constructed prediction model to obtain a trained prediction model; Based on the trained prediction model, the construction schedule of the current project is simulated and calculated to determine whether it will be delayed.

2. A method for assisting construction schedule simulation calculation according to claim 1, characterized in that: The construction data of the historical project includes the following steps: Collecting construction data of historical projects from multiple sources; the sources include one or more of construction drawings, construction plans, and bills of quantities; Classifying the collected construction data, and marking the construction data of each category; The annotated construction data is preprocessed to use the preprocessed construction data as input of a prediction model.

3. A method for assisting construction schedule simulation calculation according to claim 1, characterized in that: The preprocessing of the annotated construction data comprises the following steps: Data cleaning to check and correct errors, missing or duplicate data in the construction data; Data standardization is to convert the images and texts in the construction data into a unified digital format.

4. A method for assisting construction schedule simulation calculation according to claim 3, characterized in that: The prediction model is based on a neural network, and includes an input end, a backbone network layer, a NECK layer and an output end. The input end is used to input the construction data of the project's construction schedule; the backbone network layer includes a Focus structure and a CSP simplified structure, which are used to extract features from the construction data; the NECK layer includes an FPN structure and a PAN structure, which are used to fuse the features extracted from the construction data; the output end includes a GIOU_Loss function, which is used to output the prediction results of the project's construction schedule.

5. A method for assisting construction schedule simulation calculation according to claim 4, characterized in that: The prediction model is trained in the following way: Acquire construction data of several historical projects, and convert task information, process information, resource information, and construction progress information in the construction data into feature vectors of the same dimension; All eigenvectors are normalized, and the normalized eigenvectors are multiplied by the corresponding feature weights to form a feature matrix; According to the construction data of each historical project, set the corresponding prediction result label; Model training is performed according to the feature matrix and the corresponding prediction result labels; wherein, the original weight file of the pre-built prediction model is loaded, and the prediction accuracy of the pre-built prediction model is continuously regressed and adjusted by comparing the labels with the labeled construction data until the loss function exceeds the set threshold, thereby obtaining a trained prediction model; wherein, the calculation formula of the loss function is: y' is the actual result obtained through the network, y is the actual label, n is the number of iterations, y1, y2, y3, and y4 represent the feature vectors of task information, process information, resource information, and construction progress information, respectively.

6. A method for assisting construction schedule simulation calculation according to claim 5, characterized in that: The method of simulating and calculating the construction schedule of the current project based on the trained prediction model to determine whether it is delayed includes the following steps: According to the established BIM model, obtain the actual construction progress of the current project; Inputting the actual construction progress and construction schedule of the current project into the trained prediction model to obtain a prediction result of whether the construction schedule of the current project can be completed on time based on the trained prediction model; Based on the forecast results obtained, a new construction schedule is re-arranged.

7. A method for assisting construction schedule simulation calculation according to claim 6, characterized in that: The method further comprises the following steps: Based on the actual construction progress of the current project and the forecast results of each construction progress plan, a construction progress status chart is established to provide risk warning.

8. A device for assisting construction schedule simulation calculation, characterized in that: The device comprises: A collection module, used to collect construction data of historical projects; the construction data includes one or more of task information, process information, resource information, and construction progress information; A training module, used to train the constructed prediction model using the collected construction data to obtain a trained prediction model; The simulation calculation module is used to simulate the construction schedule of the current project based on the trained prediction model to determine whether it will be delayed.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for auxiliary construction schedule simulation calculation as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for assisting construction schedule simulation calculation as described in any one of claims 1 to 7.

Images