Project progress detection method and system in construction project collaborative supervision process

Abstract

The invention provides a project progress detection method and system in a construction project collaborative supervision process, and relates to the field of construction project supervision, and the method comprises the steps: obtaining a target image of a construction surface and corresponding construction log data; segmenting the target image, and generating mask regions of different construction materials based on an image recognition algorithm; according to the variable quantity of the coverage area corresponding to the multiple target images in the preset time period, the change rate of the different materials is obtained through calculation; and according to the construction log data and the change rates of the different materials, calculating the weight value and the actual completion progress of each sub-project, further determining the overall progress of the main sub-project and the target project of the current construction surface, and outputting a progress analysis report. By implementing the method, the probability of misjudgment caused by simultaneous change of various construction materials in the prior art is reduced, the main sub-project which is being executed on the current construction surface can be identified more accurately, and the precision and reliability of project progress detection are improved.

Description

Technical Field

[0001] This application relates to the field of construction project supervision, and particularly to a method and system for detecting the project progress during the collaborative supervision of construction projects. Background Art

[0002] In modern construction projects, the detection of project progress is an important link in project management. With the expansion of project scale and the increase in construction complexity, traditional manual measurement and recording methods have gradually been replaced by more efficient digital and intelligent technologies. By collecting and analyzing data on the construction site, project managers can grasp the project progress in real time, optimize the construction process, thereby improving project quality and reducing management costs. Among them, using image processing technology to monitor the construction site has become an important application direction in the field of project progress detection.

[0003] In the related art, a target image of the construction surface is obtained through a camera, and image segmentation technology is used to generate mask regions (Mask) of different construction materials, and the sub-projects being executed on the construction surface are judged based on the changes in the areas covered by the Mask. Through the engineering quantity information and construction sequence relationship recorded in the construction log data, the overall progress of the target project is further calculated. This method reduces the dependence on manual measurement through automatic image recognition and improves the monitoring efficiency of the construction site.

[0004] However, when there are multiple construction materials (such as steel bars, formwork, concrete, etc.) on the construction surface, the covered areas of various materials may change simultaneously, resulting in misjudgment of the sub-projects being executed in the related art. For example, in the transition stage when the steel bar project is approaching completion and the formwork project has just started, the Mask areas of the steel bars and formwork may increase simultaneously, making it difficult to accurately distinguish the specific sub-projects being executed on the current construction surface. Summary of the Invention

[0005] This application provides a method and system for detecting the project progress during the collaborative supervision of construction projects, which is used to solve the problem of how to accurately determine the first sub-project being executed on the current construction surface in the case of multiple construction materials on the construction surface, so as to improve the accuracy and reliability of project progress detection.

[0006] In a first aspect, this application provides a method for detecting the project progress during the collaborative supervision of construction projects, which is applied to an engineering supervision system. The method includes: Obtain a target image of the construction surface and the construction log data corresponding to the target image. The construction log data records the total engineering quantity of the construction plan and the sub-engineering quantities of each sub-project; Segment the target image and generate mask regions for different construction materials based on an image recognition algorithm. The mask regions are used to identify the covering positions and areas of each material in the target image. Calculate the change rates of different materials based on the change amounts of the covering areas corresponding to multiple target images within a preset time period. Calculate the weight values and actual completion progress of each sub-project based on the construction log data and the change rates of different materials. Determine the main sub-projects of the current construction surface based on the weight values and actual completion progress of each sub-project. Calculate the overall progress of the target project based on the actual completion progress of the main sub-projects and the construction log data, and output a progress analysis report. The progress analysis report includes the construction status of the main sub-projects, the completion ratios of each sub-project on the construction surface, and the corresponding estimated completion times.

[0007] Through the above embodiments, the system segments the target image of the construction surface, generates mask regions for different construction materials, calculates the weight values and actual completion progress of each sub-project in combination with the construction log data, and finally determines the main sub-projects of the current construction surface and outputs a progress analysis report. This method reduces the probability of misjudgment problems caused by the simultaneous changes of multiple construction materials in the traditional technology, can more accurately identify the main sub-projects being executed on the current construction surface, avoids progress evaluation deviations caused by improper data processing, and thus improves the accuracy and reliability of project progress detection.

[0008] In some embodiments, after the step of segmenting the target image and generating mask regions for different construction materials based on an image recognition algorithm, where the mask regions are used to identify the covering positions and areas of each material in the target image, it further includes: Input the change amounts of the covering areas corresponding to multiple target images within a preset time period into a time series model, and output the change trends of each material in a future time period. Determine the main sub-projects based on the change trends.

[0009] Through the above embodiments, the system can more accurately predict the change trends of each construction material in a future time period through the input and modeling of the change amounts of the covering areas of multiple target images within a preset time period, and determine the main sub-projects based on the trend judgment. This method improves the recognition accuracy of the main sub-projects on the current construction surface, thus better planning construction resources and reducing progress deviations.

[0010] In some embodiments, after the step of inputting the change amounts of the covering areas corresponding to multiple target images within a preset time period into a time series model and outputting the change trends of each material in a future time period, it further includes: Calculate the estimated completion time of each sub-project according to the change trend.

[0011] Through the above embodiments, the system calculates the estimated completion time of each sub-project by combining the change trend of construction materials, solving the problem in the related art that it is difficult to accurately predict the project progress in terms of time. This method can quantitatively analyze the completion situation of each sub-project by using the trend prediction results and construction log data, identify in advance the possible risks of schedule delays, and facilitate the subsequent optimization of the construction plan arrangement.

[0012] In some embodiments, the step of calculating the weight value and the actual completion progress of each sub-project according to the construction log data and the change rate of different materials specifically includes: Obtain the sub-quantity of each current sub-project and the total quantity of the construction plan. Calculate the proportion of the sub-quantity of each in the total quantity of the total project quantity. Determine the initial importance weight of each sub-project according to the priority of each sub-project set by the user. Calculate the weight value of each sub-project based on the proportion of the project quantity and the initial importance weight. Calculate the actual completion progress of each sub-project according to the change amount of the mask area and the total project quantity.

[0013] Through the above embodiments, the system proposes a method for dynamically calculating the weight value and the actual completion progress of each sub-project through comprehensive calculations based on construction log data, the proportion of project quantity, and priority weights. Specifically, by calculating the proportion of the project quantity of each sub-project and dynamically adjusting the importance weight of each sub-project in combination with the initial weight value set by the user, it can more comprehensively reflect the actual situation of the construction site. At the same time, by combining the change amount of the mask area with the construction plan data, it ensures that the calculation of the actual completion progress is more accurate. This method reduces the probability of the occurrence of the problem of schedule evaluation deviation caused by unreasonable weight allocation in the related art. It helps project managers to more scientifically evaluate the progress of each sub-project, optimize resource allocation, and ensure the smooth progress of the construction plan.

[0014] In some embodiments, the step of determining the main sub-project of the current construction surface according to the weight value and the actual completion progress of each sub-project specifically includes: Calculate the comprehensive score of each sub-project according to the actual completion progress, weight value of each sub-project, and the change rate of the mask area corresponding to each sub-project. Determine the sub-project with the highest comprehensive score as the main sub-project of the current construction surface.

[0015] Through the above embodiments, the system comprehensively evaluates each sub-project by combining multi-dimensional data such as the actual completion progress, weight value, and change rate of the mask area, ensuring that the judgment results of the main sub-projects are more accurate. Compared with traditional methods, this technology avoids the inaccuracy of single-factor judgment through the calculation of comprehensive scores. Especially in complex scenarios where multiple construction materials change simultaneously, it can effectively improve the reliability of identifying the main sub-projects on the construction surface, thereby providing a scientific basis for the dynamic regulation of the construction progress.

[0016] In some embodiments, the step of determining the sub-project with the highest comprehensive score as the main sub-project of the current construction surface specifically includes: If it is detected that the comprehensive scores of multiple sub-projects are the same, the main sub-project is determined according to the priority relationship among the actual completion progress, weight value of each sub-project, and the change rate of the mask area corresponding to each sub-project; The priority of the change rate of the mask area corresponding to each sub-project is higher than that of the weight value, and the priority of the weight value is higher than the actual completion progress of each sub-project.

[0017] Through the above embodiments, the system can quickly and accurately determine the main sub-projects in complex construction scenarios by setting the priority relationship among the change rate of the mask area, weight value, and actual completion progress. Especially when the comprehensive scores of multiple sub-projects are the same, the rationality of the judgment results can be ensured according to the priority relationship. Among them, the high-priority setting of the change rate of the mask area in the priority mechanism can better reflect the actual situation of dynamic changes on the construction surface, thereby further improving the accuracy and adaptability of identifying the main sub-projects.

[0018] In some embodiments, after the step of calculating the change rates of different materials based on the change amounts of the coverage areas corresponding to multiple target images within a preset time period, it specifically includes: Receiving the monitoring data uploaded by the sensors on the construction surface; Adjusting the coverage position and coverage area of each material according to the monitoring data.

[0019] Through the above embodiments, the system can dynamically correct the coverage range of the mask area through the fusion of sensor data and image data, ensuring that the detection results are more accurate and reliable. Especially in cases where the construction site environment is complex or the light conditions change greatly, the introduction of sensor data significantly improves the robustness and adaptability of the detection. At the same time, by dynamically adjusting the material coverage range, the monitoring ability of the project progress can be further optimized, providing more comprehensive support for the judgment of the main sub-projects on the construction surface, thereby providing a more accurate technical means for project management.

[0020] Second aspect, the present application provides a project supervision system, and the project supervision system includes: one or more processors and a memory; The memory is coupled to the one or more processors. The memory is used to store computer program code, and the computer program code includes computer instructions. The one or more processors call the computer instructions so that the project supervision system can implement a method for detecting the project progress during the collaborative supervision of a construction project provided in the above embodiment, which will not be elaborated here.

[0021] Third aspect, the present application provides a computer-readable storage medium, including instructions. When the instructions run on the project supervision system, the project supervision system can implement a method for detecting the project progress during the collaborative supervision of a construction project provided in the above embodiment, which will not be elaborated here.

[0022] Fourth aspect, the present application provides a computer program product. When the computer program product runs on the project supervision system, the project supervision system can implement a method for detecting the project progress during the collaborative supervision of a construction project provided in the above embodiment, which will not be elaborated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. The system performs segmentation processing on the target image of the construction surface to generate mask regions of different construction materials, calculates the weight values and actual completion progress of each sub-project in combination with the construction log data, and finally determines the main sub-project of the current construction surface and outputs a progress analysis report. This method reduces the probability of misjudgment problems caused by the simultaneous change of multiple construction materials in the traditional technology, can more accurately identify the main sub-project being executed on the current construction surface, avoids progress evaluation deviations caused by improper data processing, and thus improves the accuracy and reliability of project progress detection.

[0024] 2. By introducing a time series model and a priority mechanism, the limitations of the prior art in predicting construction trends and making dynamic judgments are overcome. Among them, the time series model can predict the change trend of future construction materials and calculate the estimated completion time of sub-projects, helping managers identify progress risks in advance and optimize the allocation of construction resources. At the same time, the priority mechanism solves the problem of judgment confusion during parallel operation of multiple sub-projects in complex construction scenarios through comprehensive scores and dynamic adjustment of priority relationships, ensuring more accurate and efficient identification of main sub-projects, and providing reliable technical support for the dynamic adjustment of construction plans.

[0025] 3. By combining sensor data with image recognition technology, a technical means for dynamically adjusting the coverage range and completion progress of construction materials is proposed, which solves the problem of detection errors caused by insufficient image recognition accuracy in traditional methods. Among them, the introduction of sensor data enhances the accuracy and adaptability of construction status monitoring. Especially in complex environments or under large changes in light conditions, it can dynamically correct the mask area and coverage area to ensure the accuracy of progress assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 is a schematic flowchart of a method for detecting project progress in the process of collaborative supervision of a construction project in an embodiment of the present application; Figure 2 is another schematic flowchart of a method for detecting project progress in the process of collaborative supervision of a construction project in an embodiment of the present application; Figure 3 is a schematic structural diagram of an entity device of an engineering supervision system in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of the present application, the singular forms "a", "an", "the", "above", "said", "this" are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations including one or more of the listed items.

[0028] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as implying or indicating relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0029] For ease of understanding, the method provided in this embodiment is described in terms of a process below. Please refer to Figure 1 , which is a schematic flowchart of a method for detecting project progress in the process of collaborative supervision of a construction project in an embodiment of the present application.

[0030] S101. Obtain the target image of the construction surface and the construction log data corresponding to the target image.

[0031] The project supervision system collects image data of the construction surface in real time through a high-definition camera array deployed at the construction site. Among them, the camera array usually includes multiple fixed cameras at different angles and several pan-tilt cameras that can rotate 360 degrees to ensure full coverage of the construction surface without dead angles. The system can adopt a time-division acquisition method, performing image acquisition every 30 minutes during the day, and starting the infrared imaging mode to continue acquisition when the light is insufficient. The collected image data is preprocessed to generate a standardized target image. This preprocessing process includes, but is not limited to, operations such as image denoising, illumination compensation, and perspective correction, ensuring that the image quality meets the requirements of subsequent analysis.

[0032] Optionally, the system synchronously obtains construction log data corresponding to the time stamp of the target image through the data interface with the project management platform. Among them, the construction log data includes information such as the total engineering quantity of the construction plan, the sub-engineering quantities of each sub-project, the construction progress plan, and the construction process arrangement. These data are stored in the system database in a structured form for subsequent calculation and analysis. For example, for a concrete frame structure project, the construction log data will record specific values such as a total building area of 10,000 square meters, including 3,000 tons of steel works, 8,000 square meters of formwork works, and 2,000 cubic meters of concrete pouring, as well as information such as the construction sequence and planned construction period of each sub-project.

[0033] S102. Perform segmentation processing on the target image and generate mask regions of different construction materials based on the image recognition algorithm.

[0034] The project supervision system processes the target image using a semantic segmentation network under the deep learning framework. Specifically, an improved U-Net network structure can be used. This network uses ResNet50 as the backbone network in the encoder part and adopts a multi-scale feature fusion mechanism in the decoder part, which can effectively extract the feature information of different construction materials. The system pre-trains the U-Net network using a large number of pre-labeled construction site images to enable it to accurately identify common construction materials such as steel bars, formwork, and concrete.

[0035] In practical applications, the system performs normalization processing on the input target image, scaling the image to a standard size (such as 512×512 pixels). After being processed by the trained semantic segmentation network, the system can generate a binary mask image corresponding to each construction material. These mask images identify the position distribution of various materials in the original image with pixel-level accuracy. For example, the system can generate a mask for the steel bar area, a mask for the formwork area, a mask for the concrete area, etc. The pixel value 1 in each mask indicates the presence of the corresponding material at that position, and 0 indicates the absence. The system also calculates the total number of pixels in each mask region and converts it into an actual area unit (square meters) as a quantitative indicator of the material coverage area.

[0036] S103. Calculate the change rates of different materials based on the change amounts of the coverage areas corresponding to multiple target images within a preset time period.

[0037] The project supervision system can set a sliding time window (such as the most recent 24 hours), collect all target images and the corresponding mask area data within this time period, and calculate the change rate of the coverage area of various construction materials over time using the numerical differentiation method. Specifically in the calculation, the area data of the mask area can be smoothed, and the moving average filter is used to eliminate the influence of short-term fluctuations. Then calculate the area difference between adjacent time points and divide it by the time interval to obtain the instantaneous change rate.

[0038] Optionally, the system can also consider the continuity characteristics of the construction operations, combine the change rates of different time periods in an exponentially weighted manner to obtain a more stable rate index. For example, for the concrete pouring process, the system can monitor the continuous growth process of the concrete coverage area: if it is detected that the area increases by 100 square meters per hour, the current change rate of the concrete material is recorded as +100 square meters per hour. At the same time, the system can also monitor the corresponding reduction in the formwork coverage area, and this relationship of one increasing while the other decreasing can help judge the construction progress. The system can also compare the calculated change rate with the preset standard construction rate to evaluate the construction efficiency and progress deviation.

[0039] S104. Calculate the weight values and actual completion progress of each sub-project based on the construction log data and the change rates of different materials.

[0040] The project supervision system extracts the sub-quantity and total quantity data of each sub-project from the construction log database. Taking the concrete frame structure project as an example, the system obtains specific values such as 3000 tons of steel bar project, 8000 square meters of formwork project, and 2000 cubic meters of concrete pouring. By calculating the percentage of each sub-quantity in the total quantity, the quantity occupancy ratio is obtained. At the same time, the system will determine the initial importance weight of each sub-project according to the sub-project priority preset by the project management personnel. For example, the steel bar project in the main structure construction stage may be given a weight of 0.4, the formwork project 0.3, and the concrete pouring 0.3.

[0041] Furthermore, the system calculates the weighted sum of the engineering quantity proportion and the initial importance weight to obtain the final weight value of each sub-project. Subsequently, based on the change rate of different materials and the change amount of the mask area, combined with the total engineering quantity data, the actual completion progress of each sub-project is calculated. For example, if it is detected that the covered area of steel bars has reached 75% of the designed area, the actual completion progress of the steel bar project is 75%. The system adopts a dynamic weighting algorithm, using the material change rate as a correction factor to calibrate the completion progress in real time, ensuring that the calculation results can more accurately reflect the actual situation at the construction site.

[0042] S105. Determine the main sub-projects of the current construction surface based on the weight values and actual completion progress of each sub-project.

[0043] The project supervision system uses a multi-dimensional evaluation method to determine the main sub-projects. Specifically, the system inputs the actual completion progress, weight value, and change rate of the corresponding mask area of each sub-project into the scoring model to calculate the comprehensive score. Among them, the scoring model uses the method of weighted summation, with the highest weight coefficient for the change rate of the mask area, followed by the weight value, and the lowest weight coefficient for the actual completion progress. This priority setting can better reflect the dynamic characteristics of the construction site.

[0044] Furthermore, when there are multiple sub-projects with the same comprehensive score, the system will make a judgment according to the preset priority relationship. For example, if the comprehensive scores of the steel bar project and the formwork project are the same, but the change rate of the mask area of the steel bar project is higher, the system will determine the steel bar project as the main sub-project.

[0045] S106. Calculate the overall progress of the target project based on the actual completion progress of the main sub-projects and the construction log data, and output a progress analysis report.

[0046] The project supervision system takes the actual completion progress of the main sub-projects as a key indicator, combines the information such as the planned progress and construction period requirements recorded in the construction log data, and uses the critical path method (CPM) of project management to calculate the overall progress of the target project and generate a progress analysis report.

[0047] Among them, the progress analysis report generated by the system contains multiple key information modules: the construction status of the main sub-projects shows the current most active construction projects and their specific situations; the completion ratios of each sub-project are presented in numerical and chart forms to show the overall construction progress; the estimated completion time is calculated through a time series prediction model based on the current progress and historical data. The report can also mark progress anomalies and risk warning information. For example, when the deviation between the actual progress and the planned progress of a certain sub-project exceeds the threshold, the system automatically generates a warning prompt and gives optimization suggestions, etc., which are not limited here.

[0048] In the above embodiments, the system generates mask regions of different construction materials by segmenting the target image of the construction surface, calculates the weight values and actual completion progress of each sub-project in combination with the construction log data, and finally determines the main sub-project of the current construction surface and outputs a progress analysis report. This method reduces the probability of misjudgment problems caused by the simultaneous changes of multiple construction materials in the traditional technology, can more accurately identify the main sub-project being executed on the current construction surface, avoids the progress evaluation deviation caused by improper data processing, and thus improves the accuracy and reliability of project progress detection.

[0049] The following further describes the more specific process for determining the main sub-project in this embodiment. Please refer to Figure 2 , which is another process schematic diagram of a project progress detection method in the collaborative supervision process of a construction project according to an embodiment of the present application.

[0050] S201. Segment the target image and generate mask regions of different construction materials based on an image recognition algorithm.

[0051] This step is the same as step S102 and will not be described in detail here.

[0052] S202. Calculate the change rates of different materials based on the change amounts of the coverage areas corresponding to multiple target images within a preset time period.

[0053] This step is the same as step S103 and will not be described in detail here.

[0054] S203. Adjust the coverage position and coverage area of each material according to the monitoring data uploaded by the sensors on the construction surface.

[0055] The project supervision system realizes the accurate measurement and dynamic correction of the coverage range of construction materials by deploying multiple types of sensor networks at the construction site. Specifically, the system can integrate multiple hardware devices such as laser range sensors, ultrasonic sensors, and infrared thermal imaging sensors to form a multi-modal perception network for collecting real-time data of the construction site.

[0056] Furthermore, the system performs spatio-temporal alignment and standardization processing on the original data collected by different sensors. The optimal estimation of the measurement results of multiple sensors is performed through a Kalman filter to reduce the measurement error of a single sensor. Subsequently, the system uses a Bayesian fusion algorithm to integrate the sensor data with the image recognition results to obtain a more accurate estimation of the material coverage range.

[0057] In addition, to handle possible outliers and missing values in sensor data, the system can also adopt an anomaly detection algorithm based on time series, identifying and removing abnormal data points by establishing a statistical model. For cases of missing data, the system can use an interpolation algorithm for supplementation to ensure data continuity and reliability.

[0058] In a specific embodiment, when monitoring the steel reinforcement project, the laser distance sensor can accurately measure the height and width of the steel reinforcement cage, while the ultrasonic sensor is used to detect the spacing and density of the steel bars. If the steel bar coverage area calculated by the image recognition algorithm is 100 square meters and the sensor measurement result is 98 square meters, the system can perform a weighted average of these two values through a data fusion algorithm to obtain a more accurate estimate of the coverage area.

[0059] In the above embodiment, through the fusion of sensor data and image data, the system can dynamically correct the coverage range of the mask area, ensuring that the detection results are more accurate and reliable. Especially in cases where the construction site environment is complex or the lighting conditions change greatly, the introduction of sensor data significantly improves the robustness and adaptability of the detection. At the same time, by dynamically adjusting the material coverage range, the monitoring ability of the project progress can be further optimized, providing more comprehensive support for the judgment of the main sub-projects of the construction surface, thus providing a more accurate technical means for project management.

[0060] S204. Calculate the proportion of the engineering quantity of each current sub-project in the total engineering quantity of the construction plan respectively.

[0061] The project supervision system extracts the data of the total engineering quantity of the construction plan and the data of the engineering quantity of each sub-project from the construction log database. Then, the system calculates the proportion of the engineering quantity of each sub-project in the total engineering quantity, that is, the engineering quantity proportion. The purpose of this step is to quantify the relative scale and importance of each sub-project in the entire construction project.

[0062] Optionally, the formula for the engineering quantity proportion of each sub-project is: Engineering quantity proportion i = Sub - engineering quantity i / Total engineering quantity, where i represents the i-th sub-project.

[0063] S205. Determine the initial importance weight of each sub-project according to the priority of each sub-project set by the user.

[0064] Based on the calculation of the engineering quantity proportion, the project supervision system further considers the construction priority of each sub-project to reflect its importance in the construction sequence arrangement. Optionally, the priority is usually set by project management personnel according to construction experience and specific requirements, and the system numerically converts the priority set by the user to generate the initial importance weight.

[0065] Optionally, the system can determine the initial importance weights using the following method: First, the user assigns priorities to each sub-project in the construction sequence, such as 1, 2, 3, etc. The smaller the number, the higher the priority. Then, based on the priority ranking, the system generates an initial weight value between 0 and 1 for each sub-project. The sub-project with the highest priority has a weight value of 1, and the weight values of the remaining sub-projects decrease successively, showing an arithmetic progression distribution.

[0066] S206. Calculate the weight values of each sub-project based on the proportion of the project quantity and the initial importance weights.

[0067] After obtaining the proportion of the project quantity and the initial importance weights, the project supervision system further comprehensively considers these two factors and calculates the final weight values of each sub-project. Specifically, the system uses the weighted average method to linearly combine the proportion of the project quantity and the initial importance weights to obtain the weight values. The formula for calculating the weight values is as follows: Weight value i = a * Proportion of project quantity i + b * Initial importance weight i; Where i represents the i-th sub-project, and a and b are two weight factors, and a + b = 1. The values of a and b can be adjusted according to the specific project characteristics and management requirements to balance the impacts of the two dimensions of the project quantity and the priority, which are not limited here.

[0068] S207. Calculate the actual completion progress of each sub-project based on the change amount of the mask area and the total project quantity.

[0069] After obtaining the weight values of each sub-project, the project supervision system also needs to accurately evaluate its actual completion progress to grasp the real dynamics of the construction site. Specifically, the system uses the semantic segmentation algorithm to process the images of the construction surface, generates mask areas for different material categories (such as steel bars, formworks, concrete, etc.), and uses binary images to represent the coverage ranges of each material. By tracking the change in the number of pixel points in the mask area, the laying area of each material can be statistically calculated in real time. Then, the system combines the project quantity information recorded in the construction log, such as the amount of steel bars used, the area of formworks, the volume of concrete, etc., calculates the completion percentage of each material, and further estimates the overall completion progress of the sub-project.

[0070] For example, in a specific embodiment, at a certain moment, the image recognition result shows that the mask area of the steel bars laid on the construction surface is 800 square meters, and the concrete pouring area is 200 square meters. The construction log records that the designed amount of steel bar project is 1000 tons, and the designed volume of concrete project is 1000 cubic meters. Assuming that each ton of steel bars corresponds to a laying area of 10 square meters and each cubic meter of concrete corresponds to a pouring area of 1 square meter, the system calculates: The actual completion progress of the steel bar project = 800 / (1000 * 10) = 8%; The actual completion progress of the concrete project = 200 / (1000 * 1) = 20%.

[0071] Then, the system combines the weight values of each sub-project and uses the weighted average method to estimate the comprehensive completion progress of the entire construction surface.

[0072] In the above embodiment, the system proposes a method for dynamically calculating the weight values and actual completion progress of each sub-project through comprehensive calculations based on construction log data, engineering quantity ratio, and priority weights. Specifically, by calculating the ratio of the engineering quantity of each sub-project and dynamically adjusting the importance weights of each sub-project in combination with the initial weight values set by the user, the actual situation of the construction site can be more comprehensively reflected. At the same time, by combining the change amount of the mask area and the construction plan data, the calculation of the actual completion progress is ensured to be more accurate. This method reduces the probability of occurrence of progress evaluation deviation problems caused by unreasonable weight distribution in related technologies. It helps project managers to more scientifically evaluate the progress of each sub-project, optimize resource allocation, and ensure the smooth progress of the construction plan.

[0073] S208. Calculate the comprehensive score of each sub-project according to the actual completion progress, weight value of each sub-project, and the change rate of the corresponding mask area of each sub-project.

[0074] After obtaining the key indicators such as the actual completion progress, weight value, and corresponding mask area change rate of each sub-project, the project supervision system further comprehensively evaluates these indicators to fully consider the influence of different factors on the judgment of the main sub-projects. Specifically, the system uses a weighted summation mathematical model, multiplies the three indicators by the preset weight coefficients respectively, and then adds them to obtain the comprehensive score of each sub-project. Among them, the weight coefficient of the mask area change rate is set the highest, the weight value is the second, and the actual completion progress is the lowest.

[0075] For example, in a specific embodiment, assume that a construction surface includes three sub-projects: steel bars, formwork, and concrete. Through the calculation in the foregoing steps, it can be known that: the actual completion progress of the steel bar project is 60%, the weight value is 0.4, and the corresponding mask area change rate is 5% / day; the actual completion progress of the formwork project is 80%, the weight value is 0.3, and the corresponding mask area change rate is 3% / day; the actual completion progress of the concrete project is 30%, the weight value is 0.3, and the corresponding mask area change rate is 8% / day. Set the weight coefficients of the three indicators of the mask area change rate, actual completion progress, and weight value to 0.6, 0.3, and 0.1 respectively. Then the comprehensive scores of the three sub-projects are calculated as follows: Comprehensive score of steel bar work = 0.6 × 5% + 0.3 × 60% + 0.1 × 0.4 = 21.4%; Comprehensive score of formwork work = 0.6 × 3% + 0.3 × 80% + 0.1 × 0.3 = 25.8%; Comprehensive score of concrete work = 0.6 × 8% + 0.3 × 30% + 0.1 × 0.3 = 13.8%.

[0076] S209. Determine the main sub - project of the current construction surface as the sub - project with the highest comprehensive score.

[0077] After calculating the comprehensive scores of each sub - project, the project supervision system determines the sub - project with the highest score as the main sub - project of the construction surface. Taking the above case as an example, through comprehensive evaluation, it is found that the comprehensive score of the formwork work is 25.8%, higher than 21.4% of the steel bar work and 13.8% of the concrete work. Therefore, the system determines the formwork work as the main sub - project of the current construction surface.

[0078] In the above - mentioned embodiment, the system conducts a comprehensive evaluation of each sub - project by combining multi - dimensional data such as the actual completion progress, weight value, and change rate of the mask area, ensuring that the judgment result of the main sub - project is more accurate. Compared with the traditional method, this technology avoids the inaccuracy of single - factor judgment through the calculation of comprehensive scores. Especially in complex scenarios where multiple construction materials change simultaneously, it can effectively improve the reliability of identifying the main sub - project of the construction surface, thus providing a scientific basis for the dynamic regulation of the construction progress.

[0079] S210. If it is detected that the comprehensive scores of multiple sub - projects are the same, then determine the main sub - project according to the priority relationship among the actual completion progress, weight value, and change rate of the corresponding mask area of each sub - project.

[0080] In actual projects, there may be a situation where the comprehensive scores of two or more sub - projects are the same. At this time, the main sub - project cannot be determined only by the comprehensive score. To solve this problem, the project supervision system further adopts a priority sorting method to distinguish and judge the sub - projects with the same score. Specifically, the system presets the priority relationship of three indicators: the change rate of the mask area, the weight value, and the actual completion progress. When the comprehensive scores are tied, the indicator with the highest priority is compared first, and the sub - project corresponding to the larger value is determined as the main sub - project; if this indicator is still the same, then the indicators with the second - highest priority are compared in turn until the main sub - project is judged.

[0081] In the above embodiments, by setting the priority relationships among the mask area change rate, the weight value, and the actual completion progress, the system can quickly and accurately determine the main sub-projects in complex construction scenarios. Especially when the comprehensive scores of multiple sub-projects are the same, the rationality of the judgment results can be ensured based on the priority relationships. Among them, the high-priority setting of the mask area change rate in the priority mechanism can better reflect the actual situation of the dynamic changes on the construction surface, thereby further improving the accuracy and adaptability of the identification of the main sub-projects.

[0082] S211. Input the change amount of the coverage areas corresponding to multiple target images within a preset time period into a time series model, and output the change trends of various materials in a future time period.

[0083] The project supervision system not only needs to accurately judge the current main sub-projects, but also needs to predict the development trends of each sub-project within a future period of time to provide decision-making references for optimizing the progress plan. Specifically, the system introduces a time series analysis model. By modeling the change data of the material coverage areas in the past period of time, it predicts the future change trends. When specifically implemented, the system can select the target images within a preset time period (such as the past 1 week), extract the number of pixel points in the mask areas of each material category (such as steel bars, formwork, concrete), and generate corresponding time series data. Then, input the time series data into a pre-trained time series model (such as an LSTM neural network), and output the change curves of the coverage areas of various materials within a future period of time (such as the next 3 days) through model inference.

[0084] For example, in a specific embodiment, one target image is taken every day on a certain construction surface in the past 5 days. The number of pixel points in the mask area of the concrete material obtained through image segmentation are: 12,000 on the first day, 14,000 on the second day, 18,000 on the third day, 21,000 on the fourth day, and 22,000 on the fifth day. The system inputs this data sequence into the LSTM model for training. By learning the historical change features, the model predicts that the number of pixel points in the mask area of the concrete in the next 3 days are: 24,000 on the sixth day, 27,000 on the seventh day, and 30,000 on the eighth day. This result shows that the concrete pouring project shows a trend of accelerating development in the next 3 days, the daily average coverage area increment is higher than that in the past, and the construction intensity continues to increase. After receiving the prediction information, the management personnel can adjust the configuration of the concrete supply and pouring machinery accordingly to meet the construction requirements. At the same time, attention should also be paid to the connection and coordination with the previous processes such as steel bars and formwork to avoid problems such as idling caused by too fast concrete pouring.

[0085] S212. Determine the main sub-projects based on the change trends, and calculate the estimated completion times of each sub-project.

[0086] The project supervision system further optimizes and improves the judgment results of the main sub-projects based on the material change trend information predicted by the time series model. Optionally, the system determines the sub-project corresponding to the material category with the fastest change (growth) in a future period as the trend main sub-project. By comparing with the current main sub-project obtained in the previous step, if the two are consistent, it indicates that the construction progress is in line with the plan and no major adjustments are required; if the two are inconsistent, it indicates that the original construction plan may deviate from the actual situation, and the management needs to attach great importance to the trend main sub-project and appropriately allocate resources to ensure its smooth implementation.

[0087] Optionally, the system uses the predicted material change curve to estimate the completion time of each sub-project. Specifically, the prediction curve is extended to the time point when the material coverage area reaches the designed quantity (such as the total concrete pouring area), and this time point is the estimated completion time of the sub-project. It can be further compared with the planned construction period to calculate the construction period deviation and risk level, which will not be elaborated here.

[0088] In the above embodiment, the system can more accurately predict the change trends of each construction material in a future period by inputting and modeling the change amounts of the coverage areas of multiple target images within a preset time period, and determine the main sub-projects based on trend judgment. This method improves the recognition accuracy of the main sub-projects on the current construction surface, thereby better planning construction resources and reducing schedule deviations.

[0089] The project supervision system of the embodiment of the present invention is an electronic device. Figure 3 The schematic diagram of the architecture of the electronic device suitable for implementing the embodiment of the present invention is shown.

[0090] It should be noted that Figure 3 The shown electronic device is only an example and should not bring any limitations to the functions and usage scopes of the embodiments of the present invention.

[0091] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions (computer programs), or the relevant hardware can be controlled by instructions (computer programs). These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor. The electronic device of this embodiment includes a storage medium and a processor. Among them, multiple instructions are stored in the storage medium, and these instructions can be loaded by the processor to execute any step of the method provided by the embodiments of the present invention.

[0092] Specifically, the storage medium and the processor are electrically connected directly or indirectly to achieve data transmission or interaction. For example, these components can be electrically connected to each other through one or more signal lines. The storage medium stores computer-executable instructions for implementing the data access control method, including at least one software function module that can be stored in the storage medium in the form of software or firmware. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium. The storage medium can be, but is not limited to, a random access memory (Random Access Memory, referred to as RAM), a read-only memory (Read Only Memory, referred to as ROM), a programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), an erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), an electrically erasable programmable read-only memory (Electric Erasable Programmable Read-Only Memory, referred to as EEPROM), etc. Among them, the storage medium is used to store programs, and the processor executes the programs after receiving the execution instructions.

[0093] Further, the software programs and modules in the above storage medium may further include an operating system, which may include various software components and / or drivers for managing system tasks (such as memory management, storage device control, power management, etc.), and can communicate with various hardware or software components to provide a running environment for other software components. The processor can be an integrated circuit chip with signal processing capabilities. The above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc., which can implement or execute the various methods, steps, and logic flow block diagrams disclosed in this embodiment. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0094] Since the instructions stored in the storage medium can execute the steps in any of the methods provided in the embodiments of the present invention, the beneficial effects of any of the methods provided in the embodiments of the present invention can be achieved. For details, see the previous embodiments and will not be elaborated here.

[0095] As described above, it is only the preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for detecting project progress during the collaborative supervision of construction projects, which is applied to an engineering supervision system, characterized in that, The method includes: Obtaining a target image of a construction surface and construction log data corresponding to the target image, where the construction log data records the total amount of work in the construction plan and the sub - amounts of work for each sub - project; Performing segmentation processing on the target image and generating mask regions for different construction materials based on an image recognition algorithm, where the mask regions are used to identify the covering positions and covering areas of each material in the target image; Calculating the change rates of different materials based on the change amounts of the covering areas corresponding to multiple target images within a preset time period; Calculating the weight values and actual completion progress of each sub - project based on the construction log data and the change rates of different materials; Determining the main sub - projects of the current construction surface based on the weight values and actual completion progress of each sub - project; Calculating the overall progress of the target project based on the actual completion progress of the main sub - projects and the construction log data, and outputting a progress analysis report, where the progress analysis report includes the construction status of the main sub - projects, the completion ratios of each sub - project on the construction surface, and the corresponding estimated completion times.

2. The method according to claim 1, wherein After the step of performing segmentation processing on the target image and generating mask regions for different construction materials based on an image recognition algorithm, where the mask regions are used to identify the covering positions and covering areas of each material in the target image, it further includes: Inputting the change amounts of the covering areas corresponding to multiple target images within a preset time period into a time - series model, and outputting the change trends of each material in a future time period; Determining the main sub - projects based on the change trends; 3. The method according to claim 2, wherein After the step of inputting the change amounts of the covering areas corresponding to multiple target images within a preset time period into a time - series model and outputting the change trends of each material in a future time period, it further includes: Calculating the estimated completion times of each sub - project based on the change trends; 4. The method according to claim 1, wherein The step of calculating the weight values and actual completion progress of each sub - project based on the construction log data and the change rates of different materials specifically includes: Obtaining the sub - amounts of work for each current sub - project and the total amount of work in the construction plan; Calculating the proportion of the amount of work of each sub - amount of work in the total amount of work; Determining the initial importance weight of each sub - project according to the priority levels of each sub - project set by the user; Calculating the weight values of each sub - project based on the proportion of the amount of work and the initial importance weight; Calculating the actual completion progress of each sub - project based on the change amount of the mask region and the total amount of work; 5. The method according to claim 1, characterized in that, The step of determining the main sub - projects of the current construction surface based on the weight values and actual completion progress of each sub - project specifically includes: Calculating the comprehensive scores of each sub - project based on the actual completion progress, weight values of each sub - project, and the change rates of the mask regions corresponding to each sub - project; Determining the sub - project with the highest comprehensive score as the main sub - project of the current construction surface; 6. The method according to claim 5, characterized in that, The step of determining the sub - project with the highest comprehensive score as the main sub - project of the current construction surface specifically includes: If it is detected that the comprehensive scores of multiple sub - projects are the same, then determining the main sub - project according to the priority relationship among the actual completion progress, weight values of each sub - project, and the change rates of the mask regions corresponding to each sub - project; The change rate priority of the mask area corresponding to each sub-project is higher than the weight value, and the weight value priority is higher than the actual completion progress of each sub-project.

7. The method according to claim 1, wherein After the step of calculating the change rates of different materials based on the change amount of the coverage area corresponding to multiple target images within a preset time period, it specifically includes: Receiving the monitoring data uploaded by the sensors on the construction surface; Adjusting the coverage position and coverage area of each material according to the monitoring data.

8. An engineering supervision system, characterized in that The project supervision system includes: one or more processors and a memory; The memory is coupled to the one or more processors, and the memory is used to store computer program code. The computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the project supervision system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium, comprising instructions, characterized in that, When the instruction runs on the project supervision system, it causes the project supervision system to execute the method described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product runs on the project supervision system, it causes the project supervision system to execute the method described in any one of claims 1-7.

Images