BIM model generation method, device, equipment, medium and program product

Abstract

The present invention discloses a BIM model generation method, device, equipment, medium and program product, belonging to the field of architectural design technology, the method comprising: obtaining at least one two-dimensional component sketch that meets the BIM model generation requirements; inputting the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; using a component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, inputting the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model; using a BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, model rendering is performed on the intermediate BIM model to obtain a target BIM model. The present invention improves the generation efficiency and accuracy of the BIM model.

Description

Technical Field

[0001] The present invention relates to the technical field of building design, and in particular to a BIM model generation method, device, equipment, medium and program product. Background Art

[0002] BIM (Building Information Modeling) is a new tool based on 3D modeling technology, which has been widely used in the field of construction engineering. Compared with the traditional CAD 2D drawing design method, generating BIM models can greatly reduce the various errors made by design team members in the early stage of design, and can also reduce the errors made by subsequent contractors.

[0003] However, the existing BIM generation method is mainly based on manual drawing, which not only has low generation efficiency but is also prone to errors, resulting in low accuracy of BIM generation and affecting actual production efficiency. Summary of the invention

[0004] The present invention provides a BIM model generation method, device, equipment, medium and program product to improve the generation efficiency and accuracy of the BIM model.

[0005] According to one aspect of the present invention, a BIM model generation method is provided, the method comprising:

[0006] Obtain at least one two-dimensional component sketch that meets the requirements for generating a BIM model;

[0007] Input the 2D component sketch into the component generation model to generate a 3D component drawing corresponding to the 2D component sketch;

[0008] The component evaluation model is used to evaluate the correctness of each 3D component drawing. When it is determined that each 3D component drawing is correct, the 2D BIM sketch and each 3D component drawing are input into the BIM generation model to obtain an intermediate BIM model.

[0009] The BIM evaluation model is used to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, the intermediate BIM model is rendered to obtain the target BIM model.

[0010] According to another aspect of the present invention, a BIM model generation device is provided, the device comprising:

[0011] A two-dimensional component sketch acquisition module is used to acquire at least one two-dimensional component sketch that meets the BIM model generation requirements;

[0012] A three-dimensional component drawing generation module is used to input a two-dimensional component sketch into a component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch;

[0013] The intermediate BIM model determination module is used to use the component evaluation model to evaluate the correctness of each 3D component drawing, and when it is determined that each 3D component drawing is correct, the 2D BIM sketch and each 3D component drawing are input into the BIM generation model to obtain the intermediate BIM model;

[0014] The target BIM model determination module is used to evaluate the correctness of the intermediate BIM model using the BIM evaluation model, and when it is determined that the intermediate BIM model is correct, the intermediate BIM model is rendered to obtain the target BIM model.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by at least one processor so that the at least one processor can execute the BIM model generation method of any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the BIM model generation method of any embodiment of the present invention when executed by a processor.

[0020] According to another aspect of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the BIM model generation method of any embodiment of the present invention is implemented.

[0021] The technical solution of the embodiment of the present invention is to obtain at least one two-dimensional component sketch that meets the BIM model generation requirements; input the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; use the component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, input the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model; use the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, render the intermediate BIM model to obtain the target BIM model. The above technical solution reduces manual operations in the BIM model generation process, thereby reducing human errors in the BIM model generation process, and further reduces the error rate of the BIM model, and improves the generation efficiency and accuracy of the BIM model.

[0022] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 is a flow chart of a BIM model generation method provided according to Embodiment 1 of the present invention;

[0025] Figure 2 is a flow chart of a BIM model generation method provided according to Embodiment 2 of the present invention;

[0026] Figure 3 is a structural schematic diagram of a BIM model generating device provided according to Embodiment 3 of the present invention;

[0027] Figure 4 It is a structural schematic diagram of an electronic device for implementing the BIM model generation method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "target", "intermediate", "first" and "second" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] In addition, it should be noted that in the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of the BIM model generation requirements, sample component sketch sets, three-dimensional sample component atlases, and sample image data composed of three-dimensional sample component drawings and two-dimensional sample BIM sketches, etc., all comply with the relevant laws and regulations and do not violate public order and good morals.

[0031] Embodiment 1

[0032] Figure 1 This is a flowchart of a BIM model generation method provided in the first embodiment of the present invention. This embodiment is applicable to the case of automatically generating a BIM model. The method can be executed by a BIM model generation device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0033] S101. Obtain at least one two-dimensional component sketch that meets the requirements for generating a BIM model.

[0034] Among them, the BIM model generation demand refers to the design demand of the construction project demander for the construction building. For example, the BIM model generation demand can be the house BIM model generation demand. The two-dimensional component sketch refers to the component sketch manually drawn by the BIM designer.

[0035] Specifically, according to the BIM model generation requirements, at least one two-dimensional component sketch that meets the BIM model generation requirements can be obtained from the BIM designer.

[0036] For example, if the BIM model generation requirement is a housing BIM model generation requirement, then according to the housing BIM model generation requirement, the two-dimensional component sketches obtained from the BIM designer include but are not limited to structural component sketches, building component sketches, and electromechanical component sketches. Among them, the structural component sketches include but are not limited to wall sketches, beam sketches, column sketches, and floor sketches; the building component sketches include but are not limited to door and window sketches, staircase sketches, and roof sketches; the electromechanical component sketches include but are not limited to electrical system sketches, water supply and drainage system sketches, and HVAC system sketches.

[0037] S102, inputting the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch.

[0038] The component generation model can be obtained by training the first neural network model through the sample component sketch set. The specific training process is as follows: obtain the sample component sketch set, and adjust the image size of the sample component sketch in the sample component sketch set. For example, adjust the image size of all the sample component sketches in the sample component sketch set to pixel format, and obtain an adjusted sample component sketch set; use the adjusted sample component sketch set to train the first neural network model until the model training loss of the first neural network model drops to a preset loss range, and use the first neural network model when the training stops as the component generation model.

[0039] Optionally, the component generation model includes a feature extraction layer, a feature flattening layer, a fully connected layer and a deconvolution layer; wherein the feature extraction layer is connected to the feature flattening layer, the feature flattening layer is connected to the fully connected layer, and the fully connected layer is connected to the deconvolution layer.

[0040] Specifically, after the two-dimensional component sketch is input into the component generation model, the feature extraction layer in the component generation model is used to extract features from the two-dimensional component sketch to obtain two-dimensional component features; the feature flattening layer in the component generation model is used to flatten the two-dimensional component features to obtain one-dimensional component flattened features; the fully connected layer in the component generation model is used to feature map the one-dimensional component flattened features to obtain three-dimensional component features; the deconvolution layer in the component generation model is used to reconstruct the three-dimensional component features to obtain a three-dimensional component diagram.

[0041] Among them, the feature extraction layer in the component generation model includes a two-dimensional convolution sublayer, a normalization sublayer and a ReLU activation function sublayer. Accordingly, through the feature extraction layer in the component generation model, the two-dimensional component sketch is feature extracted to obtain the two-dimensional component feature, which can be specifically: the two-dimensional convolution sublayer in the feature extraction layer is used to extract the feature of the two-dimensional component sketch to obtain the first intermediate feature; then, the first intermediate feature is normalized through the normalization sublayer in the feature extraction layer to obtain the second intermediate feature; then, the second intermediate feature is nonlinearly transformed through the ReLU activation function sublayer in the feature extraction layer to obtain the two-dimensional component feature.

[0042] Among them, the deconvolution layer in the component generation model includes a three-dimensional transposed convolution sublayer, a normalization sublayer and a ReLU activation function sublayer. Accordingly, through the deconvolution layer in the component generation model, the three-dimensional component features are reconstructed to obtain a three-dimensional component diagram, which can be specifically: the three-dimensional component features are reconstructed through the three-dimensional transposed convolution sublayer in the deconvolution layer to obtain reconstructed features; then, the reconstructed features are normalized through the normalization sublayer in the deconvolution layer to obtain normalized features; and then, the normalized features are nonlinearly transformed through the ReLU activation function sublayer in the deconvolution layer to obtain a three-dimensional component diagram.

[0043] It can be understood that, compared with manually drawing a three-dimensional component drawing, the component generation model automatically generates a three-dimensional component drawing corresponding to the two-dimensional component sketch based on the input two-dimensional component sketch, thereby improving the generation efficiency of the three-dimensional component drawing.

[0044] S103, using the component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, inputting the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model.

[0045] The component evaluation model can be obtained by training the second neural network model through a three-dimensional sample component atlas that is pre-labeled with correct or incorrect image labels. The correct image label can be , the image error label can be ; imagel is used to represent the image identifier of the three-dimensional sample component diagram, for example, imagel is used to represent the name of the three-dimensional sample component diagram. Optionally, the component evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; wherein the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer.

[0046] Among them, the two-dimensional BIM sketch refers to the BIM sketch manually drawn by the BIM designer. The BIM generation model can be obtained by training the third neural network model with sample image data composed of the three-dimensional sample component drawing and the two-dimensional sample BIM sketch. The intermediate BIM model refers to the BIM model generated in the process of determining the target BIM model. The target BIM model refers to the final BIM model.

[0047] Specifically, for each 3D component drawing, the 3D component drawing is input into the component evaluation model, and the correctness of the 3D component drawing is evaluated through the component evaluation model, so as to determine whether the 3D component drawing is correct; similarly, it can be determined whether each 3D component drawing is correct; when it is determined that each 3D component drawing is correct, the 2D BIM sketch and each 3D component drawing are input into the BIM generation model, and the intermediate BIM model is automatically generated through the BIM generation model.

[0048] Optionally, for an erroneous three-dimensional component drawing, the BIM designer shall redraw the two-dimensional component sketch corresponding to the erroneous three-dimensional component drawing, and input the redrawn two-dimensional component sketch into the component generation model, and regenerate the correct three-dimensional component drawing through the component generation model to ensure the correctness of each three-dimensional component drawing.

[0049] It can be understood that by evaluating the correctness of the three-dimensional component drawings, erroneous three-dimensional component drawings can be detected in time, and thus erroneous two-dimensional component sketches can be detected in time, which can help BIM designers to modify erroneous two-dimensional component sketches in time, effectively ensuring the accuracy of the two-dimensional component sketches.

[0050] S104: Use the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, render the intermediate BIM model to obtain a target BIM model.

[0051] Among them, the BIM evaluation model can be obtained by training the fourth neural network model through a sample BIM model set that is pre-labeled with model correct or model error labels.

[0052] Specifically, the intermediate BIM model is input into the BIM evaluation model, and the correctness of the intermediate BIM model is evaluated through the BIM evaluation model, so as to determine whether the intermediate BIM model is correct; when it is determined that the intermediate BIM model is correct, the intermediate BIM model is fed back to the user interface, and the intermediate BIM model is rendered on the user interface with the help of a model rendering tool to obtain a target BIM model.

[0053] Optionally, when it is determined that the intermediate BIM model is wrong, the cause of the error causing the intermediate BIM model error is determined; the error in the intermediate BIM model generation process is corrected according to the cause of the error, and steps S101 to S104 are re-executed to regenerate the correct intermediate BIM model to obtain the target BIM model.

[0054] It is understandable that rendering the intermediate BIM model to obtain the target BIM model can make the target BIM model more vivid and realistic, which will help relevant personnel better understand the design intent and more intuitively see the building effect, providing a clear visual reference for the construction of subsequent construction projects, thereby improving the accuracy and efficiency of the construction of construction projects.

[0055] The technical solution of the embodiment of the present invention is to obtain at least one two-dimensional component sketch that meets the BIM model generation requirements; input the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; use the component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, input the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model; use the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, perform model rendering on the intermediate BIM model to obtain the target BIM model. The above technical solution reduces manual operations in the BIM model generation process, thereby reducing human errors in the BIM model generation process, thereby improving the generation efficiency of the BIM model, reducing the error rate of the BIM model, and improving the accuracy of the BIM model.

[0056] Embodiment 2

[0057] Figure 2 This is a flowchart of a BIM model generation method provided in Example 2 of the present invention. Based on the above example, this example further optimizes "using a component evaluation model to evaluate the correctness of each three-dimensional component drawing" and provides an optional implementation plan. It should be noted that for the parts not described in detail in the example of the present invention, reference can be made to the relevant descriptions of other examples. Figure 2 As shown, the method includes:

[0058] S201. Obtain at least one two-dimensional component sketch that meets the requirements for generating a BIM model.

[0059] S202: Input the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch.

[0060] S203 . Extract features of corresponding three-dimensional component drawings through the feature extraction layer in the component evaluation model to obtain three-dimensional image features corresponding to each three-dimensional component drawing.

[0061] The feature extraction layer in the component evaluation model includes a three-dimensional convolution sublayer, a normalization sublayer, and a ReLU activation function sublayer. The corresponding three-dimensional component graph refers to each three-dimensional component graph in all three-dimensional component graphs.

[0062] Specifically, for each three-dimensional component diagram, the three-dimensional convolution sublayer in the feature extraction layer in the component evaluation model is used to extract features of the three-dimensional component diagram to obtain candidate three-dimensional image features; then, the candidate three-dimensional image features are normalized by the normalization sublayer in the feature extraction layer in the component evaluation model to obtain three-dimensional normalized features; and then, the three-dimensional normalized features are nonlinearly transformed by the ReLU activation function sublayer in the feature extraction layer in the component evaluation model to obtain the three-dimensional image features corresponding to the three-dimensional component diagram. Similarly, the three-dimensional image features corresponding to each three-dimensional component diagram can be obtained.

[0063] S204, performing feature merging processing on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings through the feature merging layer in the component evaluation model, and obtaining merged feature values ​​corresponding to each three-dimensional component drawing.

[0064] The merged feature value refers to the feature value obtained after the feature merging process of multiple three-dimensional image features. It should be noted that the number of three-dimensional image features corresponding to each three-dimensional component drawing is multiple.

[0065] Specifically, the feature weights corresponding to the three-dimensional image features corresponding to the corresponding three-dimensional component drawing may be determined; according to the feature weights corresponding to the three-dimensional image features, the three-dimensional image features corresponding to the corresponding three-dimensional component drawing are weighted summed to obtain a weighted summation result; according to the weighted summation result, the combined feature value corresponding to the corresponding three-dimensional component drawing is determined by the following formula:

[0066] ;

[0067] in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the kth 3D image feature corresponding to the corresponding 3D component diagram, represents the feature weight corresponding to the k-th 3D image feature, represents the weighted summation result, and b represents the preset constant term.

[0068] It can be understood that by performing feature merging processing on multiple three-dimensional image features corresponding to each three-dimensional component drawing through the feature merging layer in the component evaluation model, the possible hidden relationship between the three-dimensional image features corresponding to each three-dimensional component drawing can be revealed, thereby improving the accuracy of the merged feature value corresponding to each three-dimensional component drawing.

[0069] S205. Classify the merged feature values ​​corresponding to the corresponding three-dimensional component drawings through the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to each three-dimensional component drawing.

[0070] Specifically, the combined feature values ​​corresponding to the corresponding three-dimensional component drawings can be classified by the following probability distribution function in the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to the corresponding three-dimensional component drawings:

[0071] ;

[0072] in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the probability distribution function.

[0073] It should be noted that for each three-dimensional component drawing, if , then the correctness evaluation result corresponding to the three-dimensional component drawing is wrong; if , then the correctness assessment result corresponding to the three-dimensional component drawing is correct.

[0074] S206. When the correctness assessment results corresponding to the three-dimensional component drawings are all correct, the two-dimensional BIM sketch and the three-dimensional component drawings are input into the BIM generation model to obtain an intermediate BIM model.

[0075] Among them, the BIM generation model includes a first feature extraction layer, a second feature extraction layer, a first feature flattening layer, a second feature flattening layer, a feature fusion layer and a deconvolution layer; the first feature extraction layer is connected to the feature fusion layer through the first feature flattening layer, the second feature extraction layer is connected to the feature fusion layer through the second feature flattening layer, and the feature fusion layer is connected to the deconvolution layer.

[0076] Specifically, when the correctness evaluation results corresponding to each three-dimensional component drawing are correct, the first feature extraction layer in the BIM generation model is used to extract features from the two-dimensional BIM sketch to obtain the first image feature; the second feature extraction layer in the BIM generation model is used to extract features from each three-dimensional component drawing to obtain the second image feature; the first feature flattening layer in the BIM generation model is used to flatten the first image feature to obtain the first flattened feature; the second feature flattening layer in the BIM generation model is used to flatten the second image feature to obtain the second flattened feature; the feature fusion layer in the BIM generation model is used to fuse the first flattened feature and the second flattened feature to obtain the fused feature; the deconvolution layer in the BIM generation model is used to reconstruct the fused feature to obtain the intermediate BIM model.

[0077] The first feature extraction layer includes a two-dimensional convolution sublayer, a normalization sublayer, and a ReLU activation function sublayer. The second feature extraction layer includes a three-dimensional convolution sublayer, a normalization sublayer, and a ReLU activation function sublayer. The deconvolution layer in the BIM generation model includes a three-dimensional transposed convolution sublayer, a normalization sublayer, and a ReLU activation function sublayer.

[0078] It can be understood that, when it is determined that all three-dimensional component drawings are correct, the two-dimensional BIM sketch and each three-dimensional component drawing are input into the BIM generation model, and the intermediate BIM model is automatically generated through the BIM generation model, thereby improving the generation efficiency of the intermediate BIM model.

[0079] S207, using the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, rendering the intermediate BIM model to obtain a target BIM model.

[0080] Among them, the BIM evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; among them, the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer.

[0081] Specifically, feature extraction is performed on the intermediate BIM model through a three-dimensional convolution sublayer in a feature extraction layer in the BIM evaluation model to obtain multiple candidate three-dimensional BIM model features; multiple candidate three-dimensional BIM model features are normalized through a normalization sublayer in a feature extraction layer in the BIM evaluation model to obtain multiple normalized model features; multiple normalized model features are nonlinearly transformed through a ReLU activation function sublayer in a feature extraction layer in the BIM evaluation model to obtain multiple target three-dimensional BIM model features; based on a feature merging algorithm preset in a feature merging layer in the BIM evaluation model, multiple target three-dimensional BIM model features are feature merged to obtain merged feature values ​​corresponding to the intermediate BIM model; the merged feature values ​​corresponding to the intermediate BIM model are classified through a probability distribution function preset in an image classification layer in the BIM evaluation model to obtain a correctness evaluation result corresponding to the intermediate BIM model; when the correctness evaluation result corresponding to the intermediate BIM model is correct, the intermediate BIM model is fed back to a user interface, and the intermediate BIM model is rendered in the user interface with the help of a model rendering tool to obtain a target BIM model.

[0082] The technical solution of the embodiment of the present invention is to obtain at least one two-dimensional component sketch that meets the BIM model generation requirements; input the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; extract features of the corresponding three-dimensional component drawings through the feature extraction layer in the component evaluation model to obtain three-dimensional image features corresponding to each three-dimensional component drawing; perform feature merging processing on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings through the feature merging layer in the component evaluation model to obtain merged feature values ​​corresponding to each three-dimensional component drawing; classify the merged feature values ​​corresponding to the corresponding three-dimensional component drawings through the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to each three-dimensional component drawing; when the correctness evaluation results corresponding to each three-dimensional component drawing are all correct, input the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model. The above technical solution reduces manual operations in the BIM model generation process, thereby reducing human errors in the BIM model generation process, thereby improving the generation efficiency of the BIM model, reducing the error rate of the BIM model, and improving the accuracy of the BIM model.

[0083] Embodiment 3

[0084] Figure 3 This is a schematic diagram of the structure of a BIM model generation device provided in the third embodiment of the present invention. This embodiment is applicable to the case of automatically generating a BIM model. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device. Figure 3 As shown, the device comprises:

[0085] A two-dimensional component sketch acquisition module 301 is used to acquire at least one two-dimensional component sketch that meets the BIM model generation requirements;

[0086] A three-dimensional component drawing generation module 302 is used to input a two-dimensional component sketch into a component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch;

[0087] The intermediate BIM model determination module 303 is used to use the component evaluation model to evaluate the correctness of each 3D component drawing, and when it is determined that each 3D component drawing is correct, input the 2D BIM sketch and each 3D component drawing into the BIM generation model to obtain the intermediate BIM model;

[0088] The target BIM model determination module 304 is used to use the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, perform model rendering on the intermediate BIM model to obtain the target BIM model.

[0089] The technical solution of the embodiment of the present invention is to obtain at least one two-dimensional component sketch that meets the BIM model generation requirements; input the two-dimensional component sketch into the component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; use the component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, input the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model; use the BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, render the intermediate BIM model to obtain the target BIM model. The above technical solution reduces manual operations in the BIM model generation process, thereby reducing human errors in the BIM model generation process, and further reduces the error rate of the BIM model, and improves the generation efficiency and accuracy of the BIM model.

[0090] Optionally, the three-dimensional component drawing generating module 302 is specifically used for:

[0091] Through the feature extraction layer in the component generation model, the feature extraction is performed on the two-dimensional component sketch to obtain the two-dimensional component features;

[0092] The two-dimensional component features are flattened through the feature flattening layer in the component generation model to obtain the one-dimensional component flattening features;

[0093] Through the fully connected layer in the component generation model, feature mapping is performed on the flattened features of the one-dimensional component to obtain the three-dimensional component features;

[0094] Through the deconvolution layer in the component generation model, the three-dimensional component features are reconstructed to obtain the three-dimensional component diagram.

[0095] Optionally, the intermediate BIM model determination module 303 includes a component drawing evaluation submodule, and the component drawing evaluation submodule includes:

[0096] A three-dimensional image feature determination unit is used to extract features of corresponding three-dimensional component drawings through a feature extraction layer in a component evaluation model to obtain three-dimensional image features corresponding to each three-dimensional component drawing;

[0097] A merged feature value determination unit is used to perform feature merging processing on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings through the feature merging layer in the component evaluation model to obtain the merged feature values ​​corresponding to each three-dimensional component drawing;

[0098] The evaluation result determination unit is used to classify the combined feature values ​​corresponding to the corresponding three-dimensional component drawings through the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to each three-dimensional component drawing.

[0099] Optionally, a combined characteristic value determination unit is specifically used for:

[0100] Determine a feature weight corresponding to each three-dimensional image feature corresponding to the corresponding three-dimensional component diagram;

[0101] According to the feature weights corresponding to the three-dimensional image features, weighted summing processing is performed on the three-dimensional image features corresponding to the corresponding three-dimensional component drawing to obtain a weighted summing result;

[0102] According to the weighted summation result, the combined eigenvalue corresponding to the corresponding three-dimensional component drawing is determined by the following formula:

[0103] ;

[0104] in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the kth 3D image feature corresponding to the corresponding 3D component diagram, represents the feature weight corresponding to the k-th 3D image feature, is the weighted summation result, and b is the preset constant term.

[0105] Optionally, the evaluation result determination unit is specifically used to:

[0106] The combined eigenvalues ​​corresponding to the corresponding three-dimensional component drawings are classified through the following probability distribution function in the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to the corresponding three-dimensional component drawings:

[0107] ;

[0108] in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the probability distribution function.

[0109] Optionally, the intermediate BIM model determination module 303 includes an intermediate BIM model determination submodule, and the intermediate BIM model determination submodule is specifically used to:

[0110] Through the first feature extraction layer in the BIM generation model, feature extraction is performed on the two-dimensional BIM sketch to obtain a first image feature;

[0111] Through the second feature extraction layer in the BIM generation model, feature extraction is performed on each three-dimensional component drawing to obtain a second image feature;

[0112] By generating a first feature flattening layer in the BIM model, the first image feature is feature flattened to obtain a first flattened feature;

[0113] The second image feature is flattened by using the second feature flattening layer in the BIM generation model to obtain a second flattened feature;

[0114] Through the feature fusion layer in the BIM generation model, the first flattened feature and the second flattened feature are subjected to feature fusion processing to obtain a fusion feature;

[0115] The deconvolution layer in the BIM generation model is used to reconstruct the fused features and obtain the intermediate BIM model.

[0116] The BIM model generation device provided in the embodiment of the present invention can execute the BIM model generation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each BIM model generation method.

[0117] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium and a computer program product.

[0118] Embodiment 4

[0119] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0120] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11 in communication, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0121] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0122] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a BIM model generation method.

[0123] In some embodiments, the BIM model generation method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the BIM model generation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the BIM model generation method in any other appropriate manner (e.g., by means of firmware).

[0124] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0126] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0127] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0128] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0129] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0130] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0131] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A BIM model generation method, characterized in that: include: Obtain at least one two-dimensional component sketch that meets the requirements for generating a BIM model; Inputting the two-dimensional component sketch into a component generation model to generate a three-dimensional component diagram corresponding to the two-dimensional component sketch; wherein the component generation model includes a feature extraction layer, a feature flattening layer, a fully connected layer and a deconvolution layer; the feature extraction layer is connected to the feature flattening layer, the feature flattening layer is connected to the fully connected layer, and the fully connected layer is connected to the deconvolution layer; A component evaluation model is used to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, the two-dimensional BIM sketch and each three-dimensional component drawing are input into the BIM generation model to obtain an intermediate BIM model; wherein the component evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer; the BIM generation model includes a first feature extraction layer, a second feature extraction layer, a first feature flattening layer, a second feature flattening layer, a feature fusion layer and a deconvolution layer; the first feature extraction layer is connected to the feature fusion layer through the first feature flattening layer, the second feature extraction layer is connected to the feature fusion layer through the second feature flattening layer, and the feature fusion layer is connected to the deconvolution layer; The intermediate BIM model is evaluated for correctness using a BIM evaluation model, and when it is determined that the intermediate BIM model is correct, the intermediate BIM model is rendered to obtain a target BIM model; wherein the BIM evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer; The step of inputting the two-dimensional component sketch into a component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch includes: Extracting features from the two-dimensional component sketch through a feature extraction layer in a component generation model to obtain two-dimensional component features; The two-dimensional component features are flattened through the feature flattening layer in the component generation model to obtain a one-dimensional component flattened feature; Performing feature mapping on the flattened features of the one-dimensional component through a fully connected layer in the component generation model to obtain three-dimensional component features; Reconstructing the three-dimensional component features through the deconvolution layer in the component generation model to obtain a three-dimensional component diagram; Among them, the component evaluation model is used to evaluate the correctness of each three-dimensional component drawing, including: Through the feature extraction layer in the component evaluation model, feature extraction is performed on the corresponding three-dimensional component drawings to obtain the three-dimensional image features corresponding to each three-dimensional component drawing; Through the feature merging layer in the component evaluation model, feature merging processing is performed on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings to obtain the merged feature values ​​corresponding to each three-dimensional component drawing; Classifying the merged feature values ​​corresponding to the corresponding three-dimensional component drawings through the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to the three-dimensional component drawings; Among them, the two-dimensional BIM sketch and each three-dimensional component drawing are input into the BIM generation model to obtain the intermediate BIM model, including: Through the first feature extraction layer in the BIM generation model, feature extraction is performed on the two-dimensional BIM sketch to obtain a first image feature; Through the second feature extraction layer in the BIM generation model, feature extraction is performed on each three-dimensional component drawing to obtain a second image feature; By generating a first feature flattening layer in the BIM model, the first image feature is feature flattened to obtain a first flattened feature; By generating a second feature flattening layer in the BIM model, the second image feature is feature flattened to obtain a second flattened feature; Performing feature fusion processing on the first flattened feature and the second flattened feature through a feature fusion layer in the BIM generation model to obtain a fusion feature; The fused features are reconstructed through the deconvolution layer in the BIM generation model to obtain an intermediate BIM model.

2. The method according to claim 1, characterized in that The feature merging layer in the component evaluation model is used to perform feature merging processing on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings to obtain the merged feature values ​​corresponding to each three-dimensional component drawing, including: Determine a feature weight corresponding to each three-dimensional image feature corresponding to the corresponding three-dimensional component diagram; According to the feature weights corresponding to the three-dimensional image features, weighted summing processing is performed on the three-dimensional image features corresponding to the corresponding three-dimensional component drawing to obtain a weighted summing result; According to the weighted summation result, the combined eigenvalue corresponding to the corresponding three-dimensional component drawing is determined by the following formula: ； in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the kth 3D image feature corresponding to the corresponding 3D component diagram, represents the feature weight corresponding to the k-th 3D image feature, represents the weighted summation result, and b represents the preset constant term.

3. The method according to claim 1, characterized in that The image classification layer in the component evaluation model is used to classify the merged feature values ​​corresponding to the corresponding three-dimensional component drawings to obtain the correctness evaluation results corresponding to the three-dimensional component drawings, including: The combined feature values ​​corresponding to the corresponding three-dimensional component drawings are classified by the following probability distribution function in the image classification layer in the component evaluation model to obtain the correctness evaluation results corresponding to the corresponding three-dimensional component drawings: ； in, represents the combined eigenvalue corresponding to the corresponding 3D component drawing, represents the probability distribution function.

4. A BIM model generation device, characterized in that: include: A two-dimensional component sketch acquisition module is used to acquire at least one two-dimensional component sketch that meets the BIM model generation requirements; A three-dimensional component drawing generation module, used for inputting the two-dimensional component sketch into a component generation model to generate a three-dimensional component drawing corresponding to the two-dimensional component sketch; wherein the component generation model includes a feature extraction layer, a feature flattening layer, a fully connected layer and a deconvolution layer; the feature extraction layer is connected to the feature flattening layer, the feature flattening layer is connected to the fully connected layer, and the fully connected layer is connected to the deconvolution layer; An intermediate BIM model determination module is used to use a component evaluation model to evaluate the correctness of each three-dimensional component drawing, and when it is determined that each three-dimensional component drawing is correct, input the two-dimensional BIM sketch and each three-dimensional component drawing into the BIM generation model to obtain an intermediate BIM model; wherein the component evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer; the BIM generation model includes a first feature extraction layer, a second feature extraction layer, a first feature flattening layer, a second feature flattening layer, a feature fusion layer and a deconvolution layer; the first feature extraction layer is connected to the feature fusion layer through the first feature flattening layer, the second feature extraction layer is connected to the feature fusion layer through the second feature flattening layer, and the feature fusion layer is connected to the deconvolution layer; A target BIM model determination module is used to use a BIM evaluation model to evaluate the correctness of the intermediate BIM model, and when it is determined that the intermediate BIM model is correct, the intermediate BIM model is rendered to obtain a target BIM model; wherein the BIM evaluation model includes a feature extraction layer, a feature merging layer and an image classification layer; the feature extraction layer is connected to the feature merging layer, and the feature merging layer is connected to the image classification layer; Wherein, the three-dimensional component drawing generation module is specifically used for: Extracting features from the two-dimensional component sketch through a feature extraction layer in a component generation model to obtain two-dimensional component features; The two-dimensional component features are flattened through the feature flattening layer in the component generation model to obtain a one-dimensional component flattened feature; Performing feature mapping on the flattened features of the one-dimensional component through a fully connected layer in the component generation model to obtain three-dimensional component features; Reconstructing the three-dimensional component features through the deconvolution layer in the component generation model to obtain a three-dimensional component diagram; The intermediate BIM model determination module includes a component drawing evaluation submodule, and the component drawing evaluation submodule includes: A three-dimensional image feature determination unit is used to extract features of corresponding three-dimensional component drawings through a feature extraction layer in a component evaluation model to obtain three-dimensional image features corresponding to each three-dimensional component drawing; A merged feature value determination unit is used to perform feature merging processing on the three-dimensional image features corresponding to the corresponding three-dimensional component drawings through the feature merging layer in the component evaluation model to obtain the merged feature values ​​corresponding to each three-dimensional component drawing; An evaluation result determination unit, used to classify the combined feature values ​​corresponding to the corresponding three-dimensional component drawings through the image classification layer in the component evaluation model, and obtain the correctness evaluation results corresponding to each three-dimensional component drawing; The intermediate BIM model determination module includes an intermediate BIM model determination submodule, and the intermediate BIM model determination submodule is specifically used to: Through the first feature extraction layer in the BIM generation model, feature extraction is performed on the two-dimensional BIM sketch to obtain a first image feature; Through the second feature extraction layer in the BIM generation model, feature extraction is performed on each three-dimensional component drawing to obtain a second image feature; By generating a first feature flattening layer in the BIM model, the first image feature is feature flattened to obtain a first flattened feature; By generating a second feature flattening layer in the BIM model, the second image feature is feature flattened to obtain a second flattened feature; Performing feature fusion processing on the first flattened feature and the second flattened feature through a feature fusion layer in the BIM generation model to obtain a fusion feature; The fused features are reconstructed through the deconvolution layer in the BIM generation model to obtain an intermediate BIM model.

5. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the BIM model generation method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the BIM model generation method according to any one of claims 1 to 3 when executed.

7. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the BIM model generation method according to any one of claims 1 to 3 is implemented.

Images