Method and system for building construction progress analysis based on CIM data
By combining CIM data with graphics and image algorithms, construction progress can be automatically identified, solving the problems of heavy manual reporting workload and limitations of traditional image recognition scenarios, and achieving accuracy and efficiency in construction progress.
Patent Information
- Application Number
- CN202510642286.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-19
- Publication Date
- 2025-10-17
AI Technical Summary
In the existing construction progress management system, manual filling is a large workload and there are deviations or omissions. Traditional image recognition solutions are limited in usage scenarios and cannot meet the needs of large-scale construction.
By utilizing CIM data, graphics, and image algorithms, combined with BIM models and OSGB models, construction progress can be automatically identified through coordinate conversion, OpenGL rendering, and Unet model training, reducing manual reporting workload and improving data accuracy.
In large-scale construction, the workload of filling in construction progress is reduced, data accuracy is ensured, omissions or errors in manual filling are avoided, and the needs of various algorithm recognition scenarios are adapted.
Smart Images
Figure CN120807866A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of BIM, and particularly relates to a method and system for analyzing construction progress based on CIM data. BACKGROUND
[0002] The demand for application of digital technology in management of urban regional construction progress control is becoming more and more intense. The city information model (CIM) mainly includes building information model (BIM), geographic information system (GIS), Internet of Things (IoT) and other data.
[0003] Building information model (BIM) is a digital building design and construction management tool, which is widely used in the fields of architecture, engineering and civil engineering. The BIM model contains building design information, such as the target floor height to be constructed, the installation position of tower crane and construction elevator, the distribution of each process on the outer wall surface, etc., which can be used for auxiliary calculation of construction progress.
[0004] Oblique photography OSGB (Open Scene Graph Binary) can provide large-scale image data with elevation information, which can capture detailed information of ground features such as buildings, terrain, roads and vegetation. Through oblique photography of OSGB, high-resolution image data can be obtained. Oblique photography technology is usually used for making digital maps, three-dimensional building models, studying ground changes and other applications. The image information of OSGB contains the state information of the construction of the outer surface of the building.
[0005] OpenGL (Open Graphics Library) is a cross-language and cross-platform application programming interface (API) for rendering 2D and 3D vector graphics. It can render three-dimensional model objects such as OSGB into graphics images.
[0006] Unet model is a deep learning model widely used in image segmentation field, and its structure presents U type, hence the name. Unet model exhibits excellent performance in image segmentation tasks through its unique U-shaped structure and effective feature fusion strategy, and becomes an important milestone in semantic segmentation field.
[0007] In the existing construction progress plan management system, manual mobile phone APP reporting is often used, which has large workload and may have deviation or omission. The problem is more prominent in the scene with large construction area. The traditional image recognition scheme needs to install a camera in the construction site, which cannot output the required image according to different scenes, and has limitations in use scenarios. SUMMARY
[0008] In order to solve the problems of large workload and possible deviation or omission in manual filling, and the scene limitation in traditional image recognition, the application provides a method for analyzing construction progress based on CIM data, which uses CIM data and graphics and image algorithms to identify and analyze specific stages in the construction process, thereby reducing the workload of manual filling of construction progress and ensuring the accuracy of data.
[0009] According to an aspect of the application, a method for analyzing construction progress based on CIM data is provided, comprising:
[0010] obtaining project information of the construction building from the BIM model;
[0011] confirming the CIM data collection range based on the project red line range and collecting CIM data, and making an OSGB model based on the collected CIM data;
[0012] extracting the shape change of the target area from the OSGB model, combining the coordinate conversion relationship between the OSGB data and the BIM data, obtaining the shape change value of the target area in the OSGB model, and obtaining the shape change progress of the target area;
[0013] extracting image information of the target area from the OSGB model and performing OpenGL rendering, combining the trained semantic segmentation model to extract the target area, and obtaining the texture change progress of the target area;
[0014] updating the progress information of the project according to the shape change progress and the texture change progress of the target area.
[0015] As a further technical solution, the CIM data collection range is confirmed based on the project red line range and the CIM data is collected, and the OSGB model is made based on the collected CIM data, comprising:
[0016] confirming the region range of CIM data collection through the project red line range in the BIM model or CAD drawing;
[0017] obtaining a series of images with different tilt angles by taking oblique photographs of the confirmed CIM data collection area;
[0018] performing image preprocessing, registration and correction on the photographed image data, converting the registered image data into an OSGB model and a digital surface model, and extracting ground features and terrain information.
[0019] As a further technical solution, the shape change value of the target area in the OSGB model is obtained, comprising:
[0020] The control coordinate point position adopts a seven-parameter conversion formula or a four-parameter conversion formula to perform coordinate system conversion of a three-dimensional BIM model or a two-dimensional CAD drawing and three-dimensional OSGB data.
[0021] Based on the conversion coordinate relationship between the BIM data and the OSGB data, the shape change value of the target region in the OSGB model is obtained through the shape information of the target region in the BIM.
[0022] As a further technical solution, when obtaining the building main body progress, further comprising:
[0023] The ray intersection algorithm is used to obtain the building height in the building area.
[0024] As a further technical solution, the ray intersection algorithm is used to obtain the building height in the building area, comprising:
[0025] Random sampling or equidistant sampling is performed on the building contour range to obtain a sampling point, and a ray is established along the Z axis downward from the coordinate point O.
[0026] When the ray direction d is not coplanar with the plane of the triangular face, it is assumed that the intersection point of the ray and the triangular face ABC is P, and the proportion of AP in the direction of vector AB and the proportion of AP in the direction of vector AC are calculated.
[0027] According to the proportions, it is determined whether the ray intersects the triangular face, and when the ray intersects the triangular face, the length of |OP| is calculated, and the intersection point coordinate P is calculated.
[0028] A plurality of intersection point coordinates P are obtained, and the main body height of the building at the current time is obtained according to the plurality of intersection point coordinates P.
[0029] As a further technical solution, when the ray direction d is coplanar with the plane of the triangular face, the two-dimensional case is returned for judgment.
[0030] As a further technical solution, when determining whether the ray intersects the triangular face according to the proportions, comprising:
[0031] If v<0 or v>1, the ray does not intersect the triangular face; if v>0 or u+v>1, the ray intersects the triangular face, wherein u represents the proportion of AP in the direction of vector AB, and v represents the proportion of AP in the direction of vector AC.
[0032] As a further technical solution, the image information of the target region is extracted from the OSGB model and rendered by OpenGL, comprising:
[0033] An OBB bounding box of the BIM model is used to construct a clipping plane required for OpenGL rendering;
[0034] For the clipped model, an orthogonal view of OpenGL is used for rendering to obtain image information at a specific viewing angle.
[0035] As a further technical solution, the method further comprises:
[0036] Collecting photos of each construction stage to form an image training set;
[0037] Using the image training set, performing model training on the Unet model for a specific scene, and outputting a trained semantic segmentation model.
[0038] According to an aspect of the present application, a system for analyzing construction progress based on CIM data is provided, comprising:
[0039] A project information import module is configured to obtain project information of a construction building from a BIM model;
[0040] A CIM data acquisition module is configured to confirm a CIM data acquisition range based on a project red line range, acquire CIM data, and produce an OSGB model based on the acquired CIM data;
[0041] A shape change processing module is configured to extract shape changes of a target region from the OSGB model, obtain shape change values of the target region in the OSGB model in combination with a coordinate conversion relationship between the OSGB data and the BIM data, and obtain a shape change progress of the target region;
[0042] A texture change processing module is configured to extract image information of the target region from the OSGB model and perform OpenGL rendering, extract the target region in combination with a trained semantic segmentation model, and obtain a texture change progress of the target region;
[0043] A progress acquisition module is configured to update progress information of a project according to the shape change progress and the texture change progress of the target region.
[0044] Compared with the prior art, the present application has the following advantages:
[0045] 1. In the scenario of large-area construction, the construction progress report related to the outer surface of the building is saved;
[0046] 2. The present application generates data sources required by an image algorithm based on an OSGB model, performs shape cutting using BIM contour information, and can meet the needs of various algorithm recognition scenarios;
[0047] 3. The present application identifies construction progress through an algorithm, avoiding missing or incorrect filling caused by manual filling. BRIEF DESCRIPTION OF DRAWINGS
[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.
[0049] Figure 1 A schematic diagram of a method for analyzing construction progress based on CIM data according to an embodiment of the present application.
[0050] Figure 2 A schematic diagram of floor information according to an embodiment of the present application.
[0051] Figure 3 A schematic diagram of construction plan import information according to an embodiment of the present application, wherein (a) is a main construction plan, and (b) is a soil excavation and soil backfill plan.
[0052] Figure 4 A schematic diagram of contour information in a site layout according to an embodiment of the present application.
[0053] Figure 5 A schematic diagram of control points for coordinate conversion in drawings and OSGB according to an embodiment of the present application.
[0054] Figure 6 A schematic diagram of sampling points within a certain building contour range according to an embodiment of the present application.
[0055] Figure 7 A schematic diagram of a ray intersection algorithm according to an embodiment of the present application.
[0056] Figure 8 A schematic diagram of building exterior surface construction according to an embodiment of the present application.
[0057] Figure 9 A schematic diagram of target area clipping according to an embodiment of the present application.
[0058] Figure 10 A schematic diagram of building image information obtained at a specific viewing angle according to an embodiment of the present application.
[0059] Figure 11 A schematic diagram of target area extraction according to an embodiment of the present application.
[0060] Figure 12 A schematic diagram of building facade painting construction progress according to an embodiment of the present application. DETAILED DESCRIPTION
[0061] In the existing construction progress plan management system, manual APP filling is often used, which has large workload and deviation or omission, and the problem is more prominent in the scene with large construction area, and the traditional image recognition scheme has the problem of scene limitation, the present application uses CIM data and graphics, image algorithm, and identifies and analyzes the specific stage in the construction process, which can reduce the workload of manual filling of construction progress, and ensure the accuracy of data, and through the specific scene training in the construction process, the progress of the construction can be effectively judged.
[0062] The present application uses OSGB as an image data carrier, and uses the image rendering capability of OpenGL to obtain arbitrary view image information of the construction site.
[0063] In some of the processes described in the specification and claims and the above description, a plurality of operations appear in a specific order, but it should be clear that these operations can be executed or in parallel with the order in which they appear in this text, for example, steps 1, steps 2, etc., are only used to distinguish different operations, and the serial number itself does not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel.
[0064] The technical solutions of the embodiments of the present application will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.
[0065] The main data preparation of the method described in the embodiments of the present application includes project information of the construction building, progress plan information, Unet training model for specific scene recognition, and GIS aerial data of the corresponding time when the progress needs to be monitored. As shown in Figure 1 The processing flow of the method described in the embodiments of the present application is as follows:
[0066] Step 1, input of project information.
[0067] The overall profile information of the project can be obtained from the BIM data, which extracts the building number, floor information, ± zero value elevation, building contour range, GIS coordinate system information, etc. for the subsequent process.
[0068] The input project information is as follows:
[0069] Building name number: In order to accurately identify the construction progress of the building in a large area, the building name number is used as the identification of the progress data attribution. Common arrangement rules are, for example, 1#-20#, 1#-20#, C1#-C20# and the like.
[0070] Floor information: The input of floor information mainly includes the floor name corresponding to the node of the progress plan, floor height and the like, as shown in Figure 2
[0071] Building construction plan import: Taking the housing construction plan as an example, the construction progress identified by the method mainly includes earth excavation, earth backfill, cushion construction, main body progress construction, external facade external insulation layer, external facade surface paint, tower crane installation and removal, construction elevator installation and removal and the like, as shown in Figure 3 (a) and (b).
[0072] ±0 elevation confirmation: Here, the elevation information corresponding to the zero value of the elevation of each building is extracted, which is mainly used for the identification of the floor main machine construction progress and the calculation of the earthwork related construction progress.
[0073] Building contour range: The building contour can adopt the OBB (Oriented Bounding Box) bounding box of the building or extract the corresponding building outer contour information from the BIM model or CAD site layout and the like, as shown in Figure 4
[0074] Step 2, CIM data collection.
[0075] In the embodiment of the application, the unmanned aerial vehicle aerial photography is adopted to collect and use software to make OSGB and DSM, wherein the data of the DSM can be converted into the OSGB format for extraction of ground features and terrain information. The specific process is as follows:
[0076] 1. Flight plan and preparation: The project red line range is confirmed through the BIM model or CAD drawing, the flight plan of aerial photography or unmanned aerial vehicle is arranged, and the aerial photography equipment and related software are prepared.
[0077] 2. Field flight shooting: The flight plan is executed, oblique photography is performed, a series of images at different angles are shot, and the ground coverage rate and overlap degree of the shooting are ensured to meet the requirements.
[0078] 3. Data processing and registration: The shot image data is transmitted to the computer for post-processing, including image preprocessing, registration and correction, so as to ensure the consistency and accuracy between the images.
[0079] 4. OSGB model making: The registered image data is converted into point OSGB model and digital surface model through the ContextCapture image processing software, and the ground features and terrain information are extracted.
[0080] Step 3, shape change progress calculation.
[0081] The construction progress information of the main body of the building, earth excavation, earth backfilling, etc. can be calculated by recognizing the shape feature change of the building through a geometric algorithm. This process mainly processes the coordinate system registration between the CIM data and obtains the shape change value of the target area.
[0082] 1. BIM data and OSGB coordinate system registration
[0083] The coordinate system conversion of the three-dimensional BIM model or two-dimensional CAD drawing and three-dimensional OSGB data can be realized by using the seven-parameter conversion formula or four-parameter conversion formula by controlling the coordinate points. The control points for coordinate conversion in the drawing and OSGB are shown in FIG. 1. Figure 5
[0084] The seven-parameter conversion formula of the coordinate system is as follows:
[0085]
[0086] wherein m represents the scale change parameter, ΔX0, ΔY0 and ΔZ0 represent the translation change parameters, and εx, εy and εz represent the rotation parameters. X ε Y ε Z .
[0087] 2. Shape change value acquisition of the target area
[0088] Taking the building main body progress calculation as an example, after the coordinate conversion between the BIM data and the OSGB data, the coordinate value of a building in the OSGB corresponding to the building contour in the BIM can be obtained.
[0089] The vertex of the Mesh triangular grid of the OSGB contains elevation information, but directly using the vertex coordinates of the triangular grid within the building contour range will affect the calculation accuracy due to the precision of the OSGB model. Here, the ray intersection algorithm is used to obtain the building height in the building area, and the specific algorithm is as follows.
[0090] As shown in FIG. 2, first, random sampling or equidistant sampling is performed within the building contour range to obtain a sampling point On. A ray is established along the Z axis from the coordinate point O downward, as shown in FIG. 3. Figure 6 Figure 7 The process is as follows:
[0091] a. Determine whether the ray direction d (unit vector) is coplanar with the plane where the triangular face is located. If not, proceed to the subsequent steps, otherwise, return to the two-dimensional case for judgment. The way to return to the two-dimensional case for judgment can be realized by using the prior art, which is not described herein.
[0092] b. Assuming the intersection of the ray and the triangular face ABC is P, then calculate the proportion u of AP in the direction of vector AB and the proportion v of AP in the direction of vector AC.
[0093] c. If u < 0 or u > 1, then there is no intersection.
[0094] d. If v < 0 or u + v > 1, then there is no intersection (if u + v > 1, then the intersection falls within the triangular face BCD).
[0095] e. Calculate the length t of |OP|, and then calculate the intersection point P from P = O + t * d.
[0096] Repeat the above process to obtain the array P, and then calculate the average value of the Z-axis values of the three-dimensional coordinates P after removing the extreme values to obtain the current building height H.
[0097] The current construction floor can be obtained by the following formula: L = (H - zero value elevation) / average floor height.
[0098] Step 4, texture class change progress calculation.
[0099] 1. Unet model training
[0100] Semantic segmentation is a problem in computer vision, and our goal is to convert the OSGB containing construction site information into an image data carrier model, and use the image rendering capability of OpenGL to assign a class to each pixel in the image, thereby confirming the current construction progress, as shown in Figure 8 The Unet model training method is not described here.
[0101] 2. Identification area confirmation and picture cropping
[0102] The information contained in the OSGB model is the full building exterior surface information of the construction site, and it is necessary to confirm how to obtain the exterior surface picture information of a certain building in the OSGB. In order to remove the pixel interference of non-identification areas, the OBB bounding box of the BIM model can be used to construct the cropping plane required for OpenGL rendering, as shown in Figure 9 .
[0103] By cropping the model, the orthogonal view rendering of OpenGL can be used to obtain the building image information under a specific viewing angle, as shown in Figure 10 .
[0104] 3. Target extraction and percentage calculation
[0105] Here, taking the yellow finish of the building facade as an example, the trained Unet model can be used to extract and calculate the percentage of the finish area, as shown in Figure 11 .
[0106] The planned finish coating construction information can be obtained from the information designed in the BIM model or CAD drawing, and the finish coating construction progress of the facade can be obtained by comparison, as shown in Figure 12 .
[0107] The current finish coating construction progress percentage L is: L = Unet extraction area / CAD drawing extraction area.
[0108] The implementation basis of each embodiment of the present application is realized by programmed processing of a device with processor function. Therefore, in engineering practice, the technical solutions and functions of each embodiment of the present application are packaged into various modules. Based on this actual situation, on the basis of the above-mentioned embodiments, the embodiments of the present application provide a system for analyzing construction progress based on CIM data, which is used to execute the method for analyzing construction progress based on CIM data in the above-mentioned method embodiments.
[0109] The system comprises: a project information import module, configured to obtain project information of a construction building from a BIM model; a CIM data acquisition module, configured to confirm a CIM data acquisition range based on a project red line range and perform CIM data acquisition, and make an OSGB model based on the acquired CIM data; a shape change processing module, configured to extract shape changes of a target area from the OSGB model, obtain shape change values of the target area in the OSGB model in combination with a coordinate conversion relationship between the OSGB data and the BIM data, and obtain a shape change progress of the target area; a texture change processing module, configured to extract image information of the target area from the OSGB model and perform OpenGL rendering, extract the target area in combination with a trained semantic segmentation model, and obtain a texture change progress of the target area; and a progress acquisition module, configured to update progress information of the project according to the shape change progress and the texture change progress of the target area.
[0110] The system for analyzing construction progress based on CIM data provided by the embodiments of the present application is aimed at the problems that manual reporting work is large and may have deviations or omissions, and traditional image recognition has the problem of scene limitation, adopts the foregoing several modules, uses CIM data and graphics and image algorithms, and performs identification and analysis for specific stages in the construction process, so that the workload of manual reporting of construction progress can be reduced, and the accuracy of data can be ensured.
[0111] It should be noted that the system embodiments provided by the present application are used to implement the methods in the above method embodiments, and are also used to implement the methods in other method embodiments provided by the present application, the difference is only that the corresponding function modules are set, the principle is basically the same as that of the above system embodiments provided by the present application, as long as the person skilled in the art improves the modules in the above system embodiments on the basis of the above system embodiments, refers to the specific technical solutions in other method embodiments, obtains the corresponding technical means by combining technical features, and the technical solutions composed of these technical means, on the premise of ensuring the practicability of the technical solutions, the corresponding system class embodiments are obtained, which are used to implement the methods in other method class embodiments.
[0112] In summary of the above embodiments, the key technical point of the present application is:
[0113] 1. In the scene of large-area building construction, the construction progress report related to the outer surface of the building is saved.
[0114] 2. The present application generates data sources required by the image algorithm based on the OSGB model, uses BIM contour messages for shape cutting, and can meet the scene requirements of various algorithm identification.
[0115] 3. The present application identifies the construction progress through an algorithm, avoiding the omission or miswriting caused by manual reporting.
[0116] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the above embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solution deviate from the technical solutions of the present application embodiments.
Claims
1. A method for analyzing construction progress based on CIM data, characterized in that: include: Get project information of the constructed building from the BIM model; Confirm the CIM data collection scope based on the project red line scope and conduct CIM data collection, and create OSGB model based on the collected CIM data; Extract the shape change of the target area from the OSGB model, combine the coordinate conversion relationship between OSGB data and BIM data, obtain the shape change value of the target area in the OSGB model, and obtain the shape change progress of the target area; Extract the image information of the target area from the OSGB model and perform OpenGL rendering. Combined with the trained semantic segmentation model, the target area is extracted to obtain the texture change progress of the target area. Update the project progress information based on the shape change progress and texture change progress of the target area.
2. The method for analyzing construction progress based on CIM data according to claim 1, characterized in that: Confirm the CIM data collection scope based on the project redline scope and conduct CIM data collection. Create an OSGB model based on the collected CIM data, including: Confirm the area scope of CIM data collection through the project red line scope in the BIM model or CAD drawing; Oblique photography is performed on the confirmed CIM data collection area to obtain a series of images at oblique angles; The captured image data is preprocessed, registered and corrected, and the registered image data is converted into OSGB model and digital surface model to extract ground features and terrain information.
3. The method for analyzing construction progress based on CIM data according to claim 1, characterized in that: Get the shape change value of the target area in the OSGB model, including: The control coordinate points use the seven-parameter conversion formula or the four-parameter conversion formula to convert the coordinate system between the 3D BIM model or 2D CAD drawing and the 3D OSGB data; Based on the conversion coordinate relationship between BIM data and OSGB data, the shape change value of the target area in the corresponding OSGB model is obtained through the shape information of the target area in BIM.
4. The method for analyzing construction progress based on CIM data according to claim 3, characterized in that: When obtaining the progress of the main building, it also includes: The ray intersection algorithm is used to obtain the building heights within the building area.
5. The method for analyzing construction progress based on CIM data according to claim 4, characterized in that: The ray intersection algorithm is used to obtain the building heights within the building area, including: Perform random sampling or equidistant sampling within the building outline to obtain sampling points, and establish a ray downward along the Z axis at coordinate point O; When the ray direction d is not coplanar with the plane where the triangle is located, assume that the intersection of the ray and the triangle ABC is P, and calculate the proportion of AP in the direction of vector AB and the proportion in the direction of vector AC; Determine whether the ray intersects the triangle face according to the ratio, and when they do intersect, calculate the length of |OP|, and then calculate the intersection point coordinates P; Obtain multiple sets of intersection coordinates P, and obtain the main height of the building at the current moment based on the multiple sets of intersection coordinates P.
6. The method for analyzing construction progress based on CIM data according to claim 5, characterized in that: When the ray direction d is coplanar with the plane where the triangle face is located, return to the two-dimensional situation for judgment.
7. The method for analyzing construction progress based on CIM data according to claim 5, characterized in that: When judging whether the ray intersects the triangle face according to the ratio, it includes: If u < 0 or u > 1, then they do not intersect; if v < 0 or u + v > 1, then they do not intersect, where u represents the proportion of AP in the direction of vector AB, and v represents the proportion of AP in the direction of vector AC.
8. The method for analyzing construction progress based on CIM data according to claim 1, characterized in that: Extract the image information of the target area from the OSGB model and perform OpenGL rendering, including: Use the OBB bounding box of the BIM model to construct the clipping plane required for OpenGL rendering; The cropped model is rendered using OpenGL's orthographic view to obtain image information at a specific perspective.
9. The method for analyzing construction progress based on CIM data according to claim 8, characterized in that: The method further comprises: Collect photos of each construction stage to form an image training set; The image training set is used to perform model training on the Unet model for a specific scenario, and a trained semantic segmentation model is output.
10. A system for analyzing construction progress based on CIM data, characterized in that: include: Project information import module, used to obtain project information of construction buildings from BIM models; The CIM data collection module is used to confirm the CIM data collection scope based on the project red line scope and perform CIM data collection, and to create an OSGB model based on the collected CIM data; The shape change processing module is used to extract the shape change of the target area from the OSGB model, combine the coordinate conversion relationship between OSGB data and BIM data, obtain the shape change value of the target area in the OSGB model, and obtain the shape change progress of the target area; The texture change processing module is used to extract the image information of the target area from the OSGB model and perform OpenGL rendering. It is combined with the trained semantic segmentation model to extract the target area and obtain the texture change progress of the target area. The progress acquisition module is used to update the project progress information according to the shape change progress and texture change progress of the target area.