Construction monitoring method and device based on Internet of Things and BIM and electronic equipment

Abstract

The invention discloses a construction monitoring method and device based on the Internet of Things and BIM and electronic equipment, and relates to the field of data processing. In the method, a target engineering project is acquired; obtaining a first shot image corresponding to the first sub-engineering project and a second shot image corresponding to the second sub-engineering project; inputting the first shot image into a preset progress recognition model to obtain a corresponding first project progress, and inputting the second shot image into the preset progress recognition model to obtain a corresponding second project progress; integrating the first project progress and the second project progress into a preset BIM model to obtain a target BIM model; judging whether the target engineering project has an overdue risk or not; if it is determined that the target engineering project has the overdue risk, determining a risk level corresponding to the overdue risk; and matching a risk processing mode corresponding to the risk level. According to the technical scheme, whether the project has the delay risk or not can be judged in time, and then the delay risk is managed, controlled and processed in time.

Description

Technical Field

[0001] The present application relates to the field of data processing, and specifically to a construction monitoring method, device and electronic equipment based on the Internet of Things and BIM. Background Art

[0002] As the global economy continues to grow and technology continues to advance, engineering projects have become larger and more complex. These projects not only involve a large amount of money and resources, but also need to deal with complex technical issues and multi-party coordination issues. In this environment, it is particularly important to monitor the progress of the project in real time and determine whether the project will be delayed in a timely manner. Delays will not only lead to increased costs, but may also affect the return on investment of the entire project and the reputation of the relevant parties.

[0003] At present, relevant technologies rely on regular manual inspections and reports when managing projects, which leads to untimely information updates and makes it difficult for managers to make timely judgments on whether a project is at risk of delay, and thus unable to deal with the delay risk in a timely manner.

[0004] Therefore, there is an urgent need for a construction monitoring method, device and electronic equipment based on the Internet of Things and BIM. Summary of the invention

[0005] The present application provides a construction monitoring method, device and electronic equipment based on the Internet of Things and BIM, so as to make timely judgments on whether a project has a risk of delay, and then timely manage and handle the risk of delay.

[0006] In a first aspect of the present application, a construction monitoring method based on the Internet of Things and BIM is provided, the method comprising: obtaining a target project, the target project comprising a plurality of sub-projects; obtaining a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, the first sub-project being any one of the plurality of sub-projects, and the second sub-project being any one of the plurality of sub-projects except the first sub-project; inputting the first captured image into a preset progress recognition model to obtain a corresponding first project progress, and inputting the second captured image into a preset progress recognition model to obtain a corresponding second project progress; integrating the first project progress and the second project progress into a preset BIM model to obtain a target BIM model; judging whether the target project has a risk of overdue according to the target BIM model; if it is determined that the target project has a risk of overdue, determining a risk level corresponding to the risk of overdue; matching a risk handling method corresponding to the risk level in a preset risk handling database, the preset risk handling database including a correspondence between risk levels and risk handling methods.

[0007] By adopting the above technical solution, real-time images of engineering projects can be obtained through IoT devices, and the preset progress recognition model can be used to identify the progress of each sub-project in real time, thereby helping supervisors understand the actual progress of the project. Integrating the progress information of each sub-project into the BIM model can form a more comprehensive and accurate target BIM model, which is helpful for the overall management and planning of the project. Based on the target BIM model, the risk of overdue projects can be evaluated, potential progress delays can be discovered in time, and the risk level can be determined. According to the preset risk handling database, the corresponding risk handling methods are matched for different levels of overdue risks, which helps to deal with possible risk events in advance.

[0008] Optionally, before acquiring the target engineering project, the method further includes: acquiring a historical engineering image and a progress annotation corresponding to the historical engineering image, the progress annotation being an actual progress value annotation pre-marked on the historical engineering image by a user; inputting the historical engineering image and the progress annotation corresponding to the historical engineering image as training data into a preset convolutional neural network model for training; determining whether the accuracy of the preset convolutional neural network model is greater than a preset accuracy threshold; if it is determined that the accuracy is greater than the preset accuracy threshold, stopping training to obtain the preset progress recognition model.

[0009] By adopting the above technical solution, the accuracy of the progress recognition model can be improved by using historical project images and corresponding progress annotations to train the neural network model. During the training process, the model learns the patterns and features in the historical data to more accurately identify the actual progress value in the new project progress image.

[0010] Optionally, the first captured image is input into a preset progress recognition model to obtain the corresponding first project progress, specifically including: inputting the first captured image into a feature extraction network of the preset progress recognition model to extract engineering features of the first captured image; inputting the engineering features into a progress regression network of the preset progress recognition model to map out a progress percentage value corresponding to the engineering features; and outputting the progress percentage value as the first project progress.

[0011] By adopting the above technical solution, the input first captured image can be converted into engineering features through the feature extraction network and the progress regression network of the progress recognition model, and the corresponding progress percentage value can be mapped. This feature extraction and mapping process can better capture the engineering progress information in the image and improve the accuracy of progress recognition.

[0012] Optionally, the progress of the first project and the progress of the second project are integrated into a preset BIM model to obtain a target BIM model, specifically including: obtaining a first component corresponding to the first sub-project in the preset BIM model, and obtaining a second component corresponding to the second sub-project in the preset BIM model; converting the progress of the first project into a first standard format, and converting the progress of the second project into a second standard format; mapping the first standard format to the first component, and mapping the second standard format to the second component to obtain the target BIM model.

[0013] By adopting the above technical solution, the progress information and the model are integrated by mapping the progress of the first project and the progress of the second project to the corresponding components in the preset BIM model. In this way, the progress information of the engineering project will be combined with the BIM model, providing more comprehensive data support for subsequent project management and decision-making. Converting the progress of the first project and the second project into a standard format and mapping them to the corresponding components will help unify and standardize the data processing process.

[0014] Optionally, judging whether the target project has a risk of being overdue based on the target BIM model, specifically includes: determining a first weight corresponding to the first sub-project and a second weight corresponding to the second sub-project in a preset weight database; taking a weighted sum of the progress of the first project and the progress of the second project based on the first weight and the second weight to obtain a target progress; judging whether the target progress is within a preset progress threshold; if it is determined that the target progress is within the preset progress threshold, then judging that there is no risk of being overdue for the target project; if it is determined that the target progress is not within the preset progress threshold, then judging that there is a risk of being overdue for the target project.

[0015] By adopting the above technical solution, the importance of each sub-project in the overall project progress can be determined by presetting the weight database. The comprehensiveness of this weight takes into account the different contribution levels of each sub-project, so as to more accurately evaluate the progress of the entire project. According to the determined weight, the progress of the first project and the progress of the second project are weighted and summed. This processing method can comprehensively consider the progress of different sub-projects and obtain a more comprehensive and accurate target progress. By comparing the target progress with the preset progress threshold, it can be determined whether the project is at risk of overdue. This judgment mechanism provides timely early warning for project management, helping relevant parties to take necessary adjustments and measures as soon as possible to avoid possible progress delays.

[0016] Optionally, after the first project progress and the second project progress are integrated into a preset BIM model to obtain a target BIM model, the method further includes: determining the size relationship between the first project progress and the preset progress; if it is determined that the first project progress is greater than or equal to the preset progress, then in the preset BIM model, rendering the first component corresponding to the first sub-project green.

[0017] By adopting the above technical solution, by comparing the progress of the first project with the preset progress, real-time monitoring of the project progress can be achieved. If the progress of the first project is greater than or equal to the preset progress, it means that the project is progressing smoothly and can proceed as planned. By rendering the components corresponding to the first sub-project green in the preset BIM model, it can be intuitively displayed that the sub-project has been completed or completed ahead of schedule. This real-time progress monitoring helps project managers to discover the progress in a timely manner and make corresponding adjustments and decisions.

[0018] Optionally, after determining whether the progress of the first project is greater than a preset progress, the method further includes: if it is determined that the progress of the first project is less than the preset progress, rendering the first construction corresponding to the first sub-project in red in the preset BIM model.

[0019] By adopting the above technical solution, by rendering the components corresponding to the first sub-project in red, the possible overdue risk of the sub-project is intuitively conveyed. Such a warning method can attract the attention of project managers and remind them to take timely measures.

[0020] In a second aspect of the present application, there is provided a construction monitoring device based on the Internet of Things and BIM, the device comprising an acquisition module and a processing module, wherein: the acquisition module is used to acquire a target project, the target project comprises a plurality of sub-projects; the acquisition module is also used to acquire a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, the first sub-project being any one of the plurality of sub-projects, the second sub-project being any one of the plurality of sub-projects except the first sub-project; the processing module is used to input the first captured image into a preset progress recognition model to obtain to the corresponding first project progress, and input the second captured image into a preset progress recognition model to obtain the corresponding second project progress; the processing module is also used to integrate the first project progress and the second project progress into a preset BIM model to obtain a target BIM model; the processing module is also used to determine whether the target engineering project has a risk of overdue according to the target BIM model; the processing module is also used to determine the risk level corresponding to the overdue risk if it is determined that the target engineering project has a risk of overdue; the processing module is also used to match the risk handling method corresponding to the risk level in a preset risk handling database, and the preset risk handling database includes a corresponding relationship between risk levels and risk handling methods.

[0021] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes any one of the methods described above.

[0022] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions, and when the instructions are executed, any of the methods described above is executed.

[0023] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. By obtaining real-time images of the project through IoT devices and using the preset progress recognition model, the progress of each sub-project can be identified in real time, thereby helping supervisors understand the actual progress of the project. Integrating the progress information of each sub-project into the BIM model can form a more comprehensive and accurate target BIM model, which is helpful for the overall management and planning of the project. Based on the target BIM model, the risk of overdue projects can be assessed, potential progress delays can be discovered in a timely manner, and the risk level can be determined. According to the preset risk handling database, the corresponding risk handling methods are matched for different levels of overdue risks, which helps to deal with possible risk events in advance.

[0024] 2. The accuracy of the progress recognition model can be improved by training the neural network model using historical project images and corresponding progress annotations. During the training process, the model learns the patterns and features in the historical data to more accurately identify the actual progress values ​​in new project progress images.

[0025] 3. Through the preset weight database, the importance of each sub-project in the overall project progress can be determined. The comprehensiveness of this weight takes into account the different contributions of each sub-project, so as to more accurately evaluate the progress of the entire project. According to the determined weight, the progress of the first project and the progress of the second project are weighted and summed. This processing method can comprehensively consider the progress of different sub-projects and obtain a more comprehensive and accurate target progress. By comparing the target progress with the preset progress threshold, it can be determined whether the project is at risk of overdue. This judgment mechanism provides timely early warning for project management, helping relevant parties to take necessary adjustments and measures as soon as possible to avoid possible progress delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flowchart of a construction monitoring method based on the Internet of Things and BIM disclosed in an embodiment of the present application; Figure 2 It is a module schematic diagram of a construction monitoring device based on the Internet of Things and BIM disclosed in an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present application.

[0027] Explanation of the reference numerals: 201, acquisition module; 202, processing module; 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0028] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0029] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0030] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0031] This application provides a construction monitoring method based on the Internet of Things and BIM, referring to Figure 1 , Figure 1 1 is a flow chart of a construction monitoring method based on the Internet of Things and BIM provided in an embodiment of the present application. The method is applied to a server and includes steps S101 to S107, which are as follows: Step S101: Acquire a target project, where the target project includes multiple sub-projects.

[0032] Before step S101, the method also includes: obtaining historical engineering images and progress annotations corresponding to the historical engineering images, where the progress annotations are actual progress value annotations made by users on the historical engineering images in advance; inputting the historical engineering images and the progress annotations corresponding to the historical engineering images as training data into a preset convolutional neural network model for training; determining whether the accuracy of the preset convolutional neural network model is greater than a preset accuracy threshold; if it is determined that the accuracy is greater than the preset accuracy threshold, stopping the training to obtain a preset progress recognition model.

[0033] Specifically, the server pre-acquires the historical engineering images and the progress annotations corresponding to the historical engineering images. The historical engineering images can come from multiple completed or under-construction engineering projects, covering different construction stages and scenes. The historical engineering images can be obtained from the project image archives. Each historical engineering image needs to be equipped with an accurate progress annotation, that is, the actual progress value reflected by the image. These progress annotations need to be completed in advance by professionals (such as project managers, on-site supervisors, etc.) to ensure the quality of the annotations. After obtaining a sufficient amount of historical engineering images and progress annotations, the server needs to divide them into training data and verification data. Preferably, 80% of the historical engineering images will be divided into training data, and 20% will be divided into verification data, and input into a preset convolutional neural network (CNN) model for training. Before inputting the historical engineering images into the preset convolutional neural network model, the server will perform necessary preprocessing on the historical engineering images. The preprocessing steps include scaling to a uniform size, normalizing pixel values, data enhancement (such as rotation, flipping, cropping, etc.), etc. The purpose of the preprocessing operation is to improve the generalization ability and robustness of the model. After the preprocessing operation is completed, the server begins to iteratively train the preset convolutional neural network model. During the training process, the server needs to evaluate the accuracy of the preset convolutional neural network model on the verification data in real time, and compare the accuracy with the preset accuracy threshold. Accuracy can include multiple indicators, such as classification accuracy. The preset accuracy threshold is a performance indicator pre-set by the user according to actual needs, such as 90% classification accuracy. The server will calculate the accuracy after each iteration. If it is determined that the accuracy is greater than the preset accuracy threshold, the server stops training and saves the current model as the final preset progress recognition model.

[0034] In step S101, the server first needs to determine the target project, which is the object of subsequent progress identification and management. The target project is usually a large and complex construction project, such as a high-rise building, municipal infrastructure, industrial plant, etc. The server can obtain information about the target project through various channels, such as: receiving the project information provided by the project owner or general contractor, such as construction contracts, design drawings, schedules, etc.; the server can also import the project data of the approved or under-construction project from the public engineering platform of the government department or the enterprise's own project management system; the target project information obtained by the server should include the basic attributes of the project, such as project name, project type and project scale. Furthermore, the server also needs to obtain the sub-project information of the target project. The target project is often decomposed into multiple sub-projects according to standards such as profession, region, and construction steps. These sub-projects together constitute the task structure and progress network of the entire project.

[0035] For example, suppose a construction engineering company undertakes a large commercial complex project, which includes two 50-story twin towers, a 3-story podium, a two-story underground garage and other sub-projects.

[0036] Step S102: obtaining a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, wherein the first sub-project is any one of a plurality of sub-projects, and the second sub-project is any one of the plurality of sub-projects except the first sub-project.

[0037] In step S102, after clarifying the target project and its sub-projects, the server needs to further obtain the captured images of each sub-project. The purpose of this step is to collect a certain number of on-site photos or videos for each sub-project as input data for subsequent progress identification. The server randomly selects a sub-project from the multiple sub-projects contained in the target project. The channels for image acquisition may include: the server sends an image acquisition task to the person in charge or on-site manager of the first sub-project, requiring him to use the mobile terminal APP to shoot and upload the latest progress pictures of the sub-project; the server automatically captures the real-time image or video clip of the relevant area of ​​the first sub-project from the project monitoring system or the fixed camera at the construction site; the server can also trigger automated shooting equipment such as drones or robots to perform fixed-point aerial photography or patrol photography of the area where the first sub-project is located. For any sub-project in the target project, the server takes the same operation to obtain its corresponding captured images and obtains the captured images corresponding to each sub-project; wherein, the first sub-project and the second sub-project are used as examples in the embodiment of the present application, and the first sub-project corresponds to the first captured image, and the second sub-project corresponds to the second captured image.

[0038] Step S103: input the first captured image into a preset progress recognition model to obtain a corresponding first project progress, and input the second captured image into a preset progress recognition model to obtain a corresponding second project progress.

[0039] In step S103, the first captured image is input into the feature extraction network of the preset progress recognition model to extract the engineering features of the first captured image; the engineering features are input into the progress regression network of the preset progress recognition model to map the progress percentage values ​​corresponding to the engineering features; and the progress percentage values ​​are output as the first project progress.

[0040] Specifically, the server preprocesses the first captured image to improve the accuracy of progress recognition. The preprocessing includes: image scaling, image normalization and image enhancement; wherein the server scales the image to a preset size (such as 224x224 pixels) through an image scaling operation to adapt to the input requirements of the progress recognition model. The server normalizes the image pixel values ​​to the range of [0, 1] or [-1, 1] through an image normalization operation to eliminate the brightness and contrast differences under different shooting conditions. The server performs random transformations such as rotation, flipping, and cropping on the image through an image enhancement operation to increase the diversity and robustness of the sample. After the server completes the preprocessing steps, the feature extraction part in the preset progress recognition model is used to extract engineering features from the preprocessed first captured image. The server inputs the preprocessed image into the feature extraction network of the preset progress recognition model, and the feature extraction network automatically learns and extracts high-level semantic features of the image through multi-layer convolution, pooling, activation and other operations. The server outputs the extracted engineering feature vector as a compact representation of the image. Next, the server uses the progress regression part of the preset progress recognition model to predict the progress value of the first project based on the extracted engineering features. The server inputs the image feature vector into a progress regression network (such as a fully connected neural network). The progress regression network maps the high-dimensional engineering features to a progress percentage value between 0 and 100 through multiple layers of nonlinear transformation. The server outputs the predicted progress percentage value as the first project progress of the first sub-project.

[0041] Step S104: Integrate the progress of the first project and the progress of the second project into a preset BIM model to obtain a target BIM model.

[0042] In step S104, a first component corresponding to the first sub-project in the preset BIM model is obtained, and a second component corresponding to the second sub-project in the preset BIM model is obtained; the progress of the first project is converted into a first standard format, and the progress of the second project is converted into a second standard format; the first standard format is mapped to the first component, and the second standard format is mapped to the second component, so as to obtain a target BIM model.

[0043] Specifically, the server needs to find the components corresponding to the first sub-project and the second sub-project in the preset BIM model. The preset BIM model is established by the user based on the target project. The preset BIM model is a digital expression of the project. The preset BIM model describes the form, position, relationship and attributes of each physical and functional component in the project through multi-dimensional data such as three-dimensional geometry and attribute information. For the BIM model of a building, it contains three-dimensional models and attribute information of various components such as foundations, columns, beams, walls, doors and windows. In order to associate the project progress with the BIM model, the server first needs to clarify the component range corresponding to each sub-project in the BIM model. The server establishes a mapping relationship between the two based on the WBS (work breakdown structure) of the project and the component classification system of the BIM model. After establishing the mapping relationship between each sub-project and the component, the server quickly locates and obtains one or more components corresponding to the sub-project in the BIM model, and marks them as the first component (corresponding to the first sub-project) and the second component (corresponding to the second sub-project). At the same time, the server needs to convert the progress of the first project and the progress of the second project into a standard format that can be applied to the preset BIM model. Since the progress indicators and metrics of different sub-projects may be different (for example, the progress of the main structure may be expressed in pouring volume, and the progress of the exterior wall decoration may be expressed in completed area), the server needs to convert them into a common and calculable progress representation, such as percentage completion, the ratio of actual workload to planned workload, etc. The conversion process needs to adopt different calculation formulas or mapping rules according to the characteristics and conventions of the sub-projects. For example, for the first sub-project, the server may need to convert the estimated progress percentage value (such as 60%) into the completed construction quantity (such as 6,000 cubic meters of concrete pouring), and compare it with the total planned construction quantity of the sub-project (such as 10,000 cubic meters) to obtain a standardized completion percentage (60%). Regardless of the conversion rule used, the server will eventually obtain the first standard format of the first sub-project (such as 60%) and the second standard format of the second sub-project (such as 30%), which are both quantitative indicators that can be directly used in the preset BIM model. At the same time, the server needs to determine the progress data format supported by the preset BIM model. Different BIM software may use different data structures and attribute fields to represent the progress information of components. For example, some BIM systems may use a floating-point attribute called "percentage of completion" to represent the progress of a component, with a value range of 0 to 1.

[0044] The server needs to map the first standard format to the first component, and the second standard format to the second component. The mapping process is essentially to update the attribute information of the relevant components in the preset BIM model so that it reflects the current actual progress status. Specifically, the server will add or update a "completion progress" field in the attribute table of the first component (such as the main body of the factory building in Area A), and set its value to the first standard format (such as 60%); similarly, in the attribute table of the second component (such as the exterior wall of the factory building in Area A), add or update the "completion progress" field, and set its value to the second standard format (such as 30%). The target BIM model is the model after the preset BIM model is mapped.

[0045] After step S104, the method further includes: determining the size relationship between the progress of the first project and the preset progress; if it is determined that the progress of the first project is greater than or equal to the preset progress, rendering the first component corresponding to the first sub-project in green in the preset BIM model.

[0046] Specifically, the server needs to obtain two values, the progress of the first project and the preset progress, and compare them. The progress of the first project is obtained through the previous image analysis step, representing the actual completion percentage of the first sub-project at the current time point; while the preset progress is a threshold value pre-set according to the project plan or progress control target, representing the completion percentage that the first sub-project should achieve at the current time point.

[0047] For example, if the current date is June 30, 2023, the progress of the first project of the first sub-project is 70%, and according to the project progress plan, the first sub-project should reach the preset progress of 60% on June 30, then the server needs to compare the size relationship between the two values ​​70% and 60%.

[0048] The server can use simple numerical comparison operations to make this judgment, such as using the greater than (>) or greater than or equal to (>=) operator to determine whether the progress of the first project exceeds or reaches the preset progress. In the above example, since 70% is greater than 60%, the server will conclude that the progress of the first project has reached the preset progress. Based on the comparison results, the server will adjust the visualization style of the first component in the preset BIM model accordingly. If the progress of the first project is greater than or equal to the preset progress, indicating that the actual progress of the first sub-project meets or exceeds the planned schedule, the server will render the first component representing the first sub-project in the preset BIM model as green to indicate that the progress of the sub-project is normal or ahead. The rendering operation here refers to modifying the color properties of the components in the BIM model so that it presents a specified color effect when displayed visually.

[0049] In a possible implementation, after determining whether the progress of the first project is greater than the preset progress, the method further includes: if it is determined that the progress of the first project is less than the preset progress, rendering the first construction corresponding to the first sub-project in red in the preset BIM model.

[0050] Specifically, if the server determines that the progress of the first project is less than the preset progress, the server will render the first component in red in the BIM model, indicating that the sub-project is at risk of delay and measures need to be taken to speed up the progress. The specific operation of rendering red is similar to rendering green, except that a different color ID or color constant needs to be specified.

[0051] Step S105: Determine whether the target project has a risk of being overdue based on the target BIM model.

[0052] In step S105, in the preset weight database, the first weight corresponding to the first sub-project and the second weight corresponding to the second sub-project are determined; according to the first weight and the second weight, the progress of the first project and the progress of the second project are weighted and summed to obtain the target progress; it is determined whether the target progress is within the preset progress threshold; if it is determined that the target progress is within the preset progress threshold, it is determined that there is no risk of overdue for the target project; if it is determined that the target progress is not within the preset progress threshold, it is determined that there is a risk of overdue for the target project.

[0053] Specifically, the server needs to obtain the weight data of the first sub-project and the second sub-project. These weight data are usually stored in a preset weight database, which is used to quantify the contribution or influence of different sub-projects on the progress of the entire project. The weight data can be pre-set according to factors such as the scale, complexity, and criticality of the sub-project, or dynamically adjusted according to historical project data and expert experience. For example, if the first sub-project is the critical path of the entire project and the duration accounts for a large proportion, then the corresponding first weight should be set relatively high; and if the second sub-project is a non-critical path and the duration accounts for a small proportion, then the corresponding second weight should be set relatively low. The server obtains the first weight (such as 0.6) corresponding to the first sub-project and the second weight (such as 0.4) corresponding to the second sub-project by querying the weight database. These weights are usually expressed as decimals between 0 and 1, and the sum of the weights of all sub-projects is equal to 1. The server needs to perform weighted summation of the progress completion percentage of the first sub-project (i.e., the progress of the first project) and the progress completion percentage of the second sub-project (i.e., the progress of the second project) according to the first weight and the second weight to obtain the comprehensive progress of the entire project (i.e., the target progress). The server multiplies the progress of the first project by the first weight to obtain the weighted progress of the first sub-project; multiplies the progress of the second project by the second weight to obtain the weighted progress of the second sub-project; then adds the weighted progress of the two sub-projects to obtain the target progress of the entire target project. At the same time, in order to determine whether the target progress has a risk of overdue, the server needs to compare it with a preset progress threshold. The preset progress threshold is usually set according to the project's planned progress and risk tolerance, indicating the minimum progress completion percentage that the target project should achieve at the current time point, such as 70%. The server compares the target progress with the preset progress threshold and draws a conclusion on whether there is a risk of overdue based on the comparison result. If the target progress is greater than or equal to the preset progress threshold, it indicates that the overall progress of the project has reached or exceeded expectations, and the server will determine that the project does not have a risk of overdue; conversely, if the target progress is less than the preset progress threshold, it indicates that the overall progress of the project lags behind expectations, and the server will determine that the project has a risk of overdue.

[0054] Step S106: If it is determined that the target project has a risk of being overdue, then the risk level corresponding to the risk of being overdue is determined.

[0055] In step S106, if it is determined that the target project has a risk of overdue, the difference between the target progress and the planned progress is calculated, and the difference is used as the delay duration. The server determines the corresponding risk level according to the delay duration, and the risk level includes low risk, medium risk and high risk. Low risk, medium risk and high risk each correspond to a delay duration range, such as a delay of less than 1 week is low risk, 1-2 weeks is medium risk, and more than 2 weeks is high risk.

[0056] Step S107: matching the risk handling methods corresponding to the risk levels in a preset risk handling database, wherein the preset risk handling database includes a correspondence between the risk levels and the risk handling methods.

[0057] In step S107, in order to achieve automatic matching between risk levels and risk handling methods, the server usually maintains a preset risk handling database, which defines risk handling methods corresponding to different risk levels. Risk handling methods are usually designed and optimized by project management experts based on industry best practices, historical lessons, etc., covering risk avoidance, risk transfer, and risk mitigation. For example, the risk handling database can define the following matching rules: If the risk level is low risk, track and monitor risk factors and adjust resource allocation. If the risk level is medium risk, adjust task priority. If the risk level is high risk, perform personnel transfer management.

[0058] Reference Figure 2 The present application also provides a construction monitoring device based on the Internet of Things and BIM. The device is a server, and the server includes an acquisition module 201 and a processing module 202; the acquisition module 201 is used to acquire a target project, and the target project includes multiple sub-projects; the acquisition module 201 is also used to acquire a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, the first sub-project is any one of the multiple sub-projects, and the second sub-project is any one of the multiple sub-projects except the first sub-project; the processing module 202 is used to input the first captured image into a preset progress recognition model to obtain the corresponding The first project progress is obtained by inputting the second captured image into a preset progress recognition model to obtain the corresponding second project progress; the processing module 202 is also used to integrate the first project progress and the second project progress into the preset BIM model to obtain the target BIM model; the processing module 202 is also used to determine whether the target engineering project has a risk of overdue according to the target BIM model; the processing module 202 is also used to determine the risk level corresponding to the overdue risk if it is determined that the target engineering project has a risk of overdue; the processing module 202 is also used to match the risk handling method corresponding to the risk level in the preset risk handling database, and the preset risk handling database includes the corresponding relationship between the risk level and the risk handling method.

[0059] In a possible implementation, before the acquisition module 201 acquires the target engineering project, the method further includes: the acquisition module 201 acquires the historical engineering image and the progress annotation corresponding to the historical engineering image, where the progress annotation is the actual progress value annotation pre-made by the user on the historical engineering image; the processing module 202 inputs the historical engineering image and the progress annotation corresponding to the historical engineering image as training data into a preset convolutional neural network model for training; the processing module 202 determines whether the accuracy of the preset convolutional neural network model is greater than a preset accuracy threshold; if it is determined that the accuracy is greater than the preset accuracy threshold, the processing module 202 stops training to obtain a preset progress recognition model.

[0060] In a possible implementation, the processing module 202 inputs the first captured image into a preset progress recognition model to obtain the corresponding first project progress, specifically including: the processing module 202 inputs the first captured image into a feature extraction network of the preset progress recognition model to extract the engineering features of the first captured image; the processing module 202 inputs the engineering features into a progress regression network of the preset progress recognition model to map the progress percentage values ​​corresponding to the engineering features; the processing module 202 outputs the progress percentage values ​​as the first project progress.

[0061] In a possible implementation, the processing module 202 integrates the progress of the first project and the progress of the second project into a preset BIM model to obtain a target BIM model, specifically including: the acquisition module 201 acquires the first component corresponding to the first sub-project in the preset BIM model, and acquires the second component corresponding to the second sub-project in the preset BIM model; the processing module 202 converts the progress of the first project into a first standard format, and converts the progress of the second project into a second standard format; the processing module 202 maps the first standard format to the first component, and maps the second standard format to the second component to obtain the target BIM model.

[0062] In a possible implementation, the processing module 202 determines whether the target project has a risk of being overdue based on the target BIM model, specifically including: the processing module 202 determines the first weight corresponding to the first sub-project and the second weight corresponding to the second sub-project in the preset weight database; the processing module 202 performs weighted summation of the progress of the first project and the progress of the second project based on the first weight and the second weight to obtain the target progress; the processing module 202 determines whether the target progress is within the preset progress threshold; if it is determined that the target progress is within the preset progress threshold, the processing module 202 determines that the target project does not have a risk of being overdue; if it is determined that the target progress is not within the preset progress threshold, the processing module 202 determines that the target project has a risk of being overdue.

[0063] In a possible implementation, the processing module 202 integrates the progress of the first project and the progress of the second project into a preset BIM model. After obtaining the target BIM model, the method further includes: the processing module 202 determines the size relationship between the progress of the first project and the preset progress; if it is determined that the progress of the first project is greater than or equal to the preset progress, the processing module 202 renders the first component corresponding to the first sub-project in green in the preset BIM model.

[0064] In a possible implementation, after the processing module 202 determines whether the progress of the first project is greater than the preset progress, the method further includes: if it is determined that the progress of the first project is less than the preset progress, the processing module 202 renders the first construction corresponding to the first sub-project in red in the preset BIM model.

[0065] It should be noted that: when the device provided in the above embodiment realizes its function, only the division of the above functional modules is used as an example. In actual application, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0066] The present application also provides an electronic device. Figure 3 , Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0067] The communication bus 302 is used to realize the connection and communication between these components.

[0068] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0069] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0070] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0071] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally also be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program of a construction monitoring method based on the Internet of Things and BIM.

[0072] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of a construction monitoring method based on the Internet of Things and BIM stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0073] The present application also provides a computer-readable storage medium, which stores instructions. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments.

[0074] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0075] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0076] 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.

[0077] In addition, each functional unit in each embodiment of 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0078] If the integrated unit 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 memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0079] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0080] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A construction monitoring method based on the Internet of Things and BIM, characterized in that: The method comprises: Acquire a target project, wherein the target project includes a plurality of sub-projects; Acquire a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, wherein the first sub-project is any one of the plurality of sub-projects, and the second sub-project is any one of the plurality of sub-projects except the first sub-project; Inputting the first photographed image into a preset progress recognition model to obtain a corresponding first project progress, and inputting the second photographed image into a preset progress recognition model to obtain a corresponding second project progress; Integrate the first project progress and the second project progress into a preset BIM model to obtain a target BIM model; According to the target BIM model, determine whether the target project has a risk of overdue; If it is determined that the target project has a risk of being overdue, then determining the risk level corresponding to the risk of being overdue; In a preset risk processing database, the risk processing method corresponding to the risk level is matched, and the preset risk processing database includes a corresponding relationship between the risk level and the risk processing method.

2. The method according to claim 1, characterized in that Before acquiring the target engineering project, the method further includes: Acquire historical engineering data, wherein the historical engineering data includes historical engineering projects and corresponding historical progress; Inputting the historical engineering data as training data into a preset machine learning model for training; Determining whether the accuracy of the preset machine learning model is greater than a preset accuracy threshold; If the accuracy is greater than the preset accuracy threshold, the training is stopped to obtain the preset progress recognition model.

3. The method according to claim 1, characterized in that The step of inputting the first captured image into a preset progress recognition model to obtain the corresponding first project progress specifically includes: Inputting the first captured image into a feature extraction network of the preset progress recognition model to extract engineering features of the first captured image; Inputting the engineering feature into the progress regression network of the preset progress recognition model to map out the progress percentage value corresponding to the engineering feature; The progress percentage value is output as the first project progress.

4. The method according to claim 1, characterized in that: The step of integrating the first project progress and the second project progress into a preset BIM model to obtain a target BIM model specifically includes: Obtain a first component corresponding to the first sub-project in the preset BIM model, and obtain a second component corresponding to the second sub-project in the preset BIM model; Converting the first project progress into a first standard format, and converting the second project progress into a second standard format, wherein the first standard format is a floating point format, and the second standard format is a floating point format; The first standard format is mapped to the first component, and the second standard format is mapped to the second component to obtain the target BIM model.

5. The method according to claim 1, characterized in that The determining, based on the target BIM model, whether the target engineering project has a risk of overdue includes: Determining, in a preset weight database, a first weight corresponding to the first sub-project and a second weight corresponding to the second sub-project; According to the first weight and the second weight, weighted sum of the first project progress and the second project progress is performed to obtain a target progress; Determining whether the target progress is within a preset progress threshold; If it is determined that the target progress is within the preset progress threshold, it is determined that there is no risk of overdue for the target project; If it is determined that the target progress is not within the preset progress threshold, it is determined that the target engineering project has a risk of being overdue.

6. The method according to claim 4, characterized in that After integrating the first project progress and the second project progress into a preset BIM model to obtain a target BIM model, the method further includes: Determine the magnitude relationship between the progress of the first project and the preset progress; If it is determined that the progress of the first project is greater than or equal to the preset progress, the first component corresponding to the first sub-project is rendered green in the preset BIM model.

7. The method according to claim 6, characterized in that After determining whether the progress of the first project is greater than a preset progress, the method further includes: If it is determined that the progress of the first project is less than the preset progress, the first construction corresponding to the first sub-project is rendered in red in the preset BIM model.

8. A construction monitoring device based on the Internet of Things and BIM, characterized in that: The device comprises an acquisition module (201) and a processing module (202), wherein: The acquisition module (201) is used to acquire a target engineering project, wherein the target engineering project includes a plurality of sub-engineering projects; The acquisition module (201) is further used to acquire a first captured image corresponding to a first sub-project and a second captured image corresponding to a second sub-project, wherein the first sub-project is any one of the plurality of sub-projects, and the second sub-project is any one of the plurality of sub-projects except the first sub-project; The processing module (202) is used to input the first captured image into a preset progress recognition model to obtain a corresponding first project progress, and input the second captured image into a preset progress recognition model to obtain a corresponding second project progress; The processing module (202) is further used to integrate the first project progress and the second project progress into a preset BIM model to obtain a target BIM model; The processing module (202) is further used to determine whether the target engineering project has a risk of overdue according to the target BIM model; The processing module (202) is further configured to determine a risk level corresponding to the overdue risk if it is determined that the target engineering project has an overdue risk; The processing module (202) is further used to match the risk processing method corresponding to the risk level in a preset risk processing database, wherein the preset risk processing database includes a correspondence between the risk level and the risk processing method.

9. An electronic device, characterized in that: The electronic device (300) comprises a processor (301), a memory (305), a user interface (303) and a network interface (304), wherein the memory (305) is used to store instructions, the user interface (303) and the network interface (304) are used to communicate with other devices, and the processor (301) is used to execute the instructions stored in the memory (305) so that the electronic device (300) executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images