AI-driven CAD-to-BIM model automatic generation method, device and equipment and medium
By using an AI-driven method to automatically generate CAD to BIM models, layer information and neural network models are used to automatically identify and construct 3D models, solving the problems of low efficiency and high accuracy risk in existing technologies, and achieving efficient and accurate model conversion.
Patent Information
- Application Number
- CN202510821425.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-17
- Publication Date
- 2025-11-11
AI Technical Summary
In existing technologies, the process of converting CAD to BIM relies on manual operation, which leads to low efficiency and high risk of information conversion accuracy, especially in large or complex engineering projects, where the manual input is large and prone to errors.
Using an AI-driven approach, the system receives CAD drawing files, utilizes layer identification information and layer images, and combines them with a pre-trained neural network model to automatically identify target objects and their construction parameters. It then constructs a 3D model in BIM software, injects non-geometric attributes, and achieves fully automatic conversion.
It significantly improves conversion efficiency, reduces human error, ensures model accuracy and integrity, and supports rapid project progress and high-quality management.
Smart Images
Figure CN120930211A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of BIM conversion technology, and in particular to an AI-driven method, apparatus, equipment and medium for automatic generation of CAD to BIM models. Background Technology
[0002] In the field of architecture, engineering, and construction (AEC), the conversion from computer-aided design (CAD) drawings to building information modeling (BIM) is a crucial and fundamental task. BIM models, with their three-dimensional structured data representation that includes both geometric and non-geometric attribute information (such as material, cost, and maintenance data), are significantly superior to traditional two-dimensional CAD drawings, providing robust data support for project design refinement, clash detection, construction simulation, cost management, and post-construction operation and maintenance. However, current mainstream CAD-to-BIM technology pathways still heavily rely on manual operation in their core processes, resulting in significant efficiency and accuracy bottlenecks.
[0003] Brief description of existing technical processes:
[0004] Manually creating CAD drawings: Designers first need to use CAD software to manually create various two-dimensional drawings that express the architectural design intent, including floor plans, elevations, and sections. This is the starting point and data source of the entire process.
[0005] Manual reading and parsing of CAD information: Professional personnel must then manually review, understand, and parse these generated CAD drawing files. This step requires operators to possess specialized knowledge to accurately identify and extract key design information contained in the drawings, such as structural components, spatial relationships, material specifications, and dimensions. Essentially, this process involves converting graphic symbols into semantic understanding.
[0006] Manually constructing a BIM model: Based on the interpretation of CAD drawings, professionals need to manually create a 3D model from scratch in a BIM platform (such as Revit). This process not only requires the geometric reconstruction from 2D views to 3D components, but also requires adding or associating rich non-geometric information attributes (such as material specifications, cost estimates, performance parameters, etc.) to the model objects one by one according to project requirements, ultimately forming a BIM model that meets the needs of the entire life cycle of design, construction, and operation and maintenance.
[0007] The main problems with existing technical solutions:
[0008] This traditional transformation model, which is centered on manual labor, inevitably brings about the following two fundamental technical problems:
[0009] Low conversion efficiency: Every step of the process—from drawing interpretation to information extraction, and then to 3D modeling and attribute entry—requires a significant amount of manual labor and time. This is especially true for large-scale, structurally complex, or component-rich engineering projects, where the required manual input and work cycle increase non-linearly, severely restricting the overall project progress and the breadth of BIM technology application.
[0010] High Risk of Errors in Information Conversion Accuracy: The heavily reliant on manual intervention inherently carries the risk of errors. During the information reading phase, misunderstandings of design intent or omissions of crucial information may occur due to the complexity of drawings, human oversight, or differences in experience. During the model building phase, manual input of geometric dimensions, coordinates, or attribute data is highly susceptible to operational errors or data entry mistakes. Once these errors are transmitted to the BIM model, they not only reduce the model's reliability and value but may also mislead subsequent design decisions, construction implementation, and cost control, ultimately impacting project quality, schedule, and potentially leading to economic losses.
[0011] Therefore, exploring and developing an automated or semi-automated CAD to BIM conversion method that can significantly reduce reliance on manual labor, improve conversion efficiency, and ensure the accuracy of information transmission has become a key technical problem that the industry urgently needs to solve. Summary of the Invention
[0012] This invention provides an AI-driven method, apparatus, device, and medium for automatically generating CAD to BIM models, aiming to solve the problems of low efficiency and low accuracy in existing CAD to BIM conversion methods that rely on manual methods.
[0013] In a first aspect, embodiments of the present invention provide an AI-driven method for automatically generating CAD to BIM models, comprising:
[0014] Receive CAD drawing files, wherein the CAD drawing files include at least one layer;
[0015] Based on the identification information of the layer, determine the target object corresponding to the layer;
[0016] Based on the layer image of the layer, determine the construction parameter information of the target object;
[0017] Based on the construction parameter information of the target object, a three-dimensional model of the target object is constructed in a preset BIM software.
[0018] A further technical solution is that, based on the identification information of the layer, determining the target object corresponding to the layer includes:
[0019] Identify the category keywords contained in the identification information;
[0020] The target object corresponding to the layer is determined based on the category keywords.
[0021] A further technical solution is that, based on the layer image of the layer, determining the construction parameter information of the target object includes:
[0022] The layer image is preprocessed to obtain the input image;
[0023] The construction parameter information of the target object is determined based on the input image using a pre-trained neural network model.
[0024] A further technical solution is that the preprocessing of the layer image to obtain the input image includes:
[0025] The layer image is standardized to obtain a standardized image;
[0026] The standardized image is subjected to noise reduction processing to obtain the input image.
[0027] A further technical solution is that, based on the construction parameter information of the target object, constructing a three-dimensional model of the target object in a preset BIM software includes:
[0028] The construction parameter information of the target object is organized according to the BIM standard format to generate the component attribute table of the target object;
[0029] The API interface of the BIM software is invoked to construct a three-dimensional model of the target object based on the component attribute table.
[0030] A further technical solution is that, after constructing a three-dimensional model of the target object in preset BIM software based on the construction parameter information of the target object, the method further includes:
[0031] Non-geometric properties are injected into the three-dimensional model of the target object.
[0032] A further technical solution is that the non-geometric properties include material properties, cost properties, and structural properties, and the injection of non-geometric properties into the three-dimensional model of the target object includes:
[0033] Identify the material keywords contained in the identification information;
[0034] Based on the material keywords, the material properties of the target object are matched against a preset material database;
[0035] The unit cost of the target object is determined based on a pre-set cost library;
[0036] The cost attributes of the target object are determined based on the construction parameter information and unit cost of the target object.
[0037] The structural attributes of the target object are determined based on a pre-defined structural specification library;
[0038] The API interface of the BIM software is invoked to write the material properties, cost properties, and structural properties into the attribute parameters of the three-dimensional model of the target object.
[0039] Secondly, embodiments of the present invention also provide an AI-driven CAD to BIM model automatic generation device, which includes a unit for performing the above-described method.
[0040] Thirdly, embodiments of the present invention also provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.
[0041] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the above-described method.
[0042] This invention provides an AI-driven method, apparatus, device, and medium for automatically generating CAD to BIM models. The method includes: receiving a CAD drawing file, the CAD drawing file including at least one layer; determining a target object corresponding to the layer based on the layer's identifier information; determining the construction parameter information of the target object based on the layer's image; and constructing a 3D model of the target object in preset BIM software based on the target object's construction parameter information. This invention can automatically determine the target object corresponding to the layer based on the layer's identifier information, further identify the target object's construction parameter information based on the layer's image, and further invoke BIM software to construct a 3D model of the target object based on the construction parameter information, thereby achieving fully automatic conversion from CAD to BIM models. Compared to manual conversion, this effectively improves efficiency and avoids human error. Attached Figure Description
[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0044] Figure 1A flowchart illustrating an AI-driven automatic generation method for CAD to BIM models provided in an embodiment of the present invention;
[0045] Figure 2 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation
[0046] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0047] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0048] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0049] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0050] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrases "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."
[0051] Please see Figure 1 This invention provides an AI-driven method for automatically generating CAD to BIM models. For example... Figure 1 As shown, the method includes the following steps:
[0052] S1, Receive CAD drawing file, the CAD drawing file including at least one layer.
[0053] In practice, the CAD drawing file can be input by the user, and this invention is not specifically limited to this. The CAD drawing file can specifically be an architectural CAD drawing file, including architectural components (target objects), such as walls, doors, and windows, etc., and this embodiment of the invention is not specifically limited to this. The CAD drawing file includes at least one layer, for example, it can have multiple layers, with one layer corresponding to one target object, such as walls, doors, and windows.
[0054] S2, Based on the identification information of the layer, determine the target object corresponding to the layer.
[0055] In practice, since CAD drawing files are usually classified into layers according to function or type, by extracting the layer identification information (such as layer name) and directly mapping it to the target object (such as building component), the correspondence between drawing layers and BIM objects can be quickly established, avoiding the inefficient operation of manually traversing the entire drawing file in the traditional method.
[0056] In some preferred embodiments, the above step "determining the target object corresponding to the layer based on the layer's identification information" specifically includes the following steps: identifying the category keywords contained in the identification information; and determining the target object corresponding to the layer based on the category keywords.
[0057] In practice, the identification information can specifically be the name of the layer. The layer's identification information includes structured identifiers such as "wall" and "beam / column," which are category keywords. By extracting these keywords through natural language processing or predefined thesaurus matching, a mapping rule base from text tags to BIM object classification systems can be established. For example, identifying the keyword "wall" directly corresponds to the "wall structural component" object in BIM, and this automated classification process reduces the time spent manually selecting layers.
[0058] Furthermore, if no category keywords are identified, the target object is determined using an image recognition model based on the layer image; if recognition fails, the user is prompted to correct the identification information or manually specify the target object. Specifically, if no category keywords are identified, it indicates that the identification information is not standardized. In this case, the corresponding target object can be identified using an image recognition model based on the layer image. Alternatively, an error message can be issued, reminding the user to modify the layer's identification information, or the user can specify the target object corresponding to the layer.
[0059] S3, Based on the layer image of the layer, determine the construction parameter information of the target object.
[0060] In practice, the process of extracting construction parameter information from the layer image of each layer is essentially to transform two-dimensional geometric information into the physical properties and spatial relationship parameters required by the three-dimensional model, such as size, material, and connection method.
[0061] In this embodiment of the invention, the above-mentioned parameterization conversion process is automated through image recognition, which effectively solves the efficiency bottleneck caused by the reliance on designers' experience to manually input parameters in traditional CAD to BIM modeling. At the same time, the standardized parameter output ensures a high degree of consistency between the BIM model and the original design intent.
[0062] Furthermore, to ensure accuracy, after parsing and obtaining the construction parameter information of the target object, a secondary verification and correction can be performed manually. This method can improve the accuracy of identification, especially when dealing with complex or uncertain drawings, where manual intervention can compensate for the shortcomings of automatic identification.
[0063] In some preferred embodiments, the above step "determine the construction parameter information of the target object based on the layer image of the layer" specifically includes the following steps: preprocessing the layer image to obtain an input image; and determining the construction parameter information of the target object based on the input image using a pre-trained neural network model.
[0064] In practice, CAD layer images may contain unstructured information such as hand-drawn lines, annotations, or local shadows. Image preprocessing transforms the layer images into standardized inputs suitable for neural network models. Furthermore, combined with a pre-trained neural network model, it is possible to efficiently identify geometric features (such as lines and arcs), dimension values, and texture features (such as material patterns) from the image. Specifically, the identified construction parameter information of the target object may include contours, categories, coordinates (positions), and size information, etc., which are not specifically limited in this invention.
[0065] Compared to rule-based geometric analysis algorithms, neural network models can cope with a wider range of image distortions, differences in annotation formats, and local noise interference. Their effectiveness is reflected in the robustness and generalization ability of parameter extraction.
[0066] For example, even if the font or position of the dimension annotations in the drawings are not consistent, the model can accurately identify the values through feature learning. This capability significantly improves the compatibility with historical drawings or non-standard design documents, while avoiding fatigue errors caused by manually entering parameters one by one.
[0067] Specifically, the neural network model can be a convolutional neural network (CNN) or a recurrent neural network (RNN), etc., and this embodiment of the invention is not specifically limited to any particular model. The neural network model is pre-trained with a large amount of labeled training data to enable it to recognize the construction parameter information of the target object based on the input image.
[0068] In some preferred embodiments, the above step "preprocessing the layer image to obtain the input image" specifically includes the following steps: standardizing the layer image to obtain a standardized image; and denoising the standardized image to obtain the input image.
[0069] In practice, standardization processes can specifically include:
[0070] Unified coordinate system: Forces all CAD elements to the World Coordinate System (WCS), eliminating user coordinate system (UCS) deviations;
[0071] Unit calibration: Identify the units (mm / m) marked on the drawings and uniformly scale them to a millimeter-level accuracy benchmark.
[0072] Noise reduction processing can specifically include:
[0073] Discrete point removal: Delete micro-line segments with a length <0.5mm (residual fragments from mapping); remove isolated points (coordinate points with no connection relationship).
[0074] Overlapping element elimination: The Euclidean distance clustering algorithm is used to merge coincident lines (threshold ≤ 0.1mm) and delete completely overlapping redundant tiles (such as duplicate door and window tiles).
[0075] Line segment fitting: Fit multiple short straight lines into a continuous long line (a line with a length of less than 1 mm is defined as a short straight line, and two straight lines with an angle of less than 5° are considered collinear).
[0076] In this embodiment of the invention, standardization processing unifies layer images from different sources to a uniform resolution, color space, and coordinate system, ensuring the standardization of model input; noise reduction processing eliminates noisy data in the layer images. The synergistic effect of these two steps enables the neural network model to focus on effective geometric features during parameter extraction, such as accurately identifying the direction of labeled and occluded pipelines or distinguishing subtle differences between similar structures. This preprocessing workflow can effectively improve the accuracy of parameter identification.
[0077] S4. Based on the construction parameter information of the target object, construct a three-dimensional model of the target object in a preset BIM software.
[0078] In practice, based on the construction parameter information of the target object, a three-dimensional model of the target object is constructed in a preset BIM software. Constructing a three-dimensional model using preset BIM software can improve modeling efficiency while maintaining the quality standards of the BIM model.
[0079] In some preferred embodiments, the above step "constructing a three-dimensional model of the target object in a preset BIM software based on the construction parameter information of the target object" specifically includes the following steps: organizing the construction parameter information of the target object according to the BIM standard format to generate a component attribute table of the target object; calling the API interface of the BIM software to construct a three-dimensional model of the target object according to the component attribute table.
[0080] In practice, the construction parameter information of the target object is organized according to IFC (Industry Foundation Classes) or project-customized standards to ensure the integrity and semantic consistency of the attributes.
[0081] The BIM software has an API interface. By calling this API, the component attribute table can be input into the BIM software to construct the 3D model of the target object. This allows the modeling process to directly utilize the BIM software's built-in parametric modeling engine and conflict detection mechanism. For example, when creating beam components, it automatically associates their spatial constraints with floor levels. Compared to generating intermediate format files and then importing them, this direct interaction reduces data conversion steps and avoids attribute loss or hierarchical breakage caused by format conversion.
[0082] In some preferred embodiments, after the step of "constructing a three-dimensional model of the target object in a preset BIM software based on the construction parameter information of the target object", the method further includes the following step: injecting non-geometric attributes into the three-dimensional model of the target object.
[0083] In practice, traditional CAD to BIM conversion often focuses on geometric data migration, while this method actively fills in non-geometric attributes such as materials, costs, and structures after generating a 3D model, which essentially builds a mapping channel from 2D design data to full lifecycle management information.
[0084] For example, the injection of material attributes allows BIM models to directly connect to material procurement systems, the embedding of cost attributes supports real-time cost analysis, and structural attributes provide parameter basis for structural verification. The automated integration of these non-geometric attributes avoids the inefficiency of relying on manual attribute table entry, while the standardized data source of preset databases (such as material libraries and cost libraries) ensures the authority and consistency of attribute values.
[0085] In some preferred embodiments, the non-geometric attributes include material attributes, cost attributes, and structural attributes. The step "constructing a 3D model of the target object in preset BIM software based on the construction parameter information of the target object" specifically includes the following steps: identifying material keywords contained in the identification information; matching the material attributes of the target object with the material attributes in a preset material database based on the material keywords; determining the unit cost of the target object based on a preset cost database; determining the cost attribute of the target object based on the construction parameter information and unit cost of the target object; determining the structural attributes of the target object based on a preset structural specification database; and calling the API interface of the BIM software to write the material attributes, cost attributes, and structural attributes into the attribute parameters of the 3D model of the target object.
[0086] In practice, the layer's identification information includes material keywords. By recognizing these keywords (such as "steel structure" or "glass curtain wall"), the system can directly retrieve the material's physical parameters (material properties) such as thermal conductivity and compressive strength from a pre-set material database, eliminating the need for designers to manually search or input them. Furthermore, if no category keywords are identified, it indicates that the identification information is not standardized. In this case, the system can match the corresponding material based on the target object's type and retrieve the material's properties from the pre-set material database. Afterward, a prompt message is issued, asking the user to confirm the accuracy of the material and its properties. If the user confirms accuracy, the material properties are confirmed to be correct; otherwise, the user is prompted to input the material properties.
[0087] Furthermore, the calculation of cost attributes combines unit cost and structural parameters (such as area and volume), realizing automatic cost estimation based on design parameters. This process dynamically links the modification of the BIM model with cost changes, providing real-time data support for design optimization.
[0088] Furthermore, the structural attributes of the target object are determined based on a preset structural specification library, ensuring that the construction of the target object can meet the specification requirements and realize automatic standardized design.
[0089] By calling the BIM software API to write these attributes into the model attribute parameters, the final generated model not only contains geometric data, but also becomes an intelligent carrier integrating design, cost, and structural information.
[0090] This invention proposes an AI-driven method for automatically generating CAD to BIM models, comprising: receiving a CAD drawing file, the CAD drawing file including at least one layer; determining a target object corresponding to the layer based on the layer's identification information; determining the construction parameter information of the target object based on the layer's layer image; and constructing a 3D model of the target object in preset BIM software based on the target object's construction parameter information. This invention can automatically determine the target object corresponding to the layer based on the layer's identification information, further identify the target object's construction parameter information based on the layer's layer image, and further invoke BIM software to construct a 3D model of the target object based on the construction parameter information, thereby achieving fully automatic conversion from CAD to BIM models. Compared with manual conversion, this method effectively improves efficiency and avoids human error.
[0091] In this embodiment of the invention, the parsing and modeling tasks (steps S2-S4 above) can be migrated to the cloud, utilizing the resources and distributed computing capabilities of cloud computing to improve processing speed and efficiency.
[0092] Advantages: Cloud services can provide powerful computing capabilities and storage resources, making them suitable for handling large-scale projects and complex computing tasks.
[0093] The embodiments of the present invention have the following technical effects:
[0094] 1. High degree of automation: This invention utilizes advanced deep learning and image recognition technology to automatically parse CAD drawing files and accurately identify various architectural elements (such as walls, doors, and windows) and their attributes (such as dimensions and materials). This means that tasks that previously required a lot of manual operation can now be completed automatically by the system, greatly reducing manpower input.
[0095] 2. Efficiency Improvement: Automation replaces manual operations, significantly accelerating the conversion from CAD drawings to BIM models and drastically reducing the overall time cost. This is particularly important for large projects, effectively shortening project cycles and improving project execution efficiency.
[0096] 3. Reduced error rate: Automated processing reduces the impact of human factors, lowers the probability of errors caused by human negligence, and ensures the accuracy and reliability of the BIM model. This is crucial for ensuring consistency between architectural design and actual construction.
[0097] 4. Cost-effectiveness: By improving work efficiency and reducing errors, this system can help companies save significant amounts of manpower and time costs, thereby achieving greater economic benefits. Furthermore, accurate BIM models can help optimize project management and resource allocation, further reducing costs.
[0098] 5. Increased information richness: In addition to basic geometric information, the system can also add more diverse information during the conversion process, such as structure, materials, and costs, making the final BIM model more comprehensive and practical, and better serving the full life cycle management of the project.
[0099] In summary, this patented technology significantly improves the efficiency and quality of CAD to BIM conversion through automated processing, reduces labor costs and error rates, enhances the information richness of BIM models, and provides strong support for the digital transformation of the construction industry.
[0100] Corresponding to the above-described AI-driven CAD to BIM model automatic generation method, this invention also provides an AI-driven CAD to BIM model automatic generation device. This AI-driven CAD to BIM model automatic generation device includes a unit for executing the above-described AI-driven CAD to BIM model automatic generation method, and can be configured in a desktop computer, tablet computer, laptop computer, or other terminal. Specifically, the AI-driven CAD to BIM model automatic generation device includes:
[0101] A receiving unit is configured to receive CAD drawing files, wherein the CAD drawing files include at least one layer;
[0102] The first determining unit is used to determine the target object corresponding to the layer based on the identification information of the layer;
[0103] The second determining unit is used to determine the construction parameter information of the target object based on the layer image of the layer;
[0104] The construction unit is used to construct a three-dimensional model of the target object in a preset BIM software based on the construction parameter information of the target object.
[0105] In some preferred embodiments, determining the target object corresponding to the layer based on the layer's identification information includes:
[0106] Identify the category keywords contained in the identification information;
[0107] The target object corresponding to the layer is determined based on the category keywords.
[0108] In some preferred embodiments, determining the construction parameter information of the target object based on the layer image of the layer includes:
[0109] The layer image is preprocessed to obtain the input image;
[0110] The construction parameter information of the target object is determined based on the input image using a pre-trained neural network model.
[0111] In some preferred embodiments, the preprocessing of the layer image to obtain the input image includes:
[0112] The layer image is standardized to obtain a standardized image;
[0113] The standardized image is subjected to noise reduction processing to obtain the input image.
[0114] In some preferred embodiments, constructing a three-dimensional model of the target object in preset BIM software based on the construction parameter information of the target object includes:
[0115] The construction parameter information of the target object is organized according to the BIM standard format to generate the component attribute table of the target object;
[0116] The API interface of the BIM software is invoked to construct a three-dimensional model of the target object based on the component attribute table.
[0117] In some preferred embodiments, the AI-driven CAD to BIM model automatic generation device further includes:
[0118] An injection unit is used to inject non-geometric attributes into the three-dimensional model of the target object.
[0119] In some preferred embodiments, the non-geometric properties include material properties, cost properties, and structural properties, and the injection of non-geometric properties into the three-dimensional model of the target object includes:
[0120] Identify the material keywords contained in the identification information;
[0121] Based on the material keywords, the material properties of the target object are matched against a preset material database;
[0122] The unit cost of the target object is determined based on a pre-set cost library;
[0123] The cost attributes of the target object are determined based on the construction parameter information and unit cost of the target object.
[0124] The structural attributes of the target object are determined based on a pre-defined structural specification library;
[0125] The API interface of the BIM software is invoked to write the material properties, cost properties, and structural properties into the attribute parameters of the three-dimensional model of the target object.
[0126] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned AI-driven CAD to BIM model automatic generation device and its various units can be referred to the corresponding descriptions in the foregoing method embodiments. For the sake of convenience and brevity, these details will not be repeated here.
[0127] The aforementioned AI-driven CAD to BIM model automatic generation device can be implemented as a computer program, which can, for example... Figure 2 It runs on the computer device shown.
[0128] Please see Figure 2 , Figure 2 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a terminal or a server. The terminal can be an electronic device with communication functions, such as a smartphone, tablet, laptop, desktop computer, personal digital assistant, or wearable device. The server can be a standalone server or a server cluster composed of multiple servers.
[0129] The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.
[0130] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. When the computer program 5032 is executed, it causes the processor 502 to execute an AI-driven method for automatically generating CAD to BIM models.
[0131] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.
[0132] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute an AI-driven CAD to BIM model automatic generation method.
[0133] The network interface 505 is used for network communication with other devices. Those skilled in the art will understand that the above structure is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. A specific computer device 500 may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements.
[0134] The processor 502 is used to run a computer program 5032 stored in a memory to implement the steps of an AI-driven CAD to BIM model automatic generation method provided in any of the above method embodiments.
[0135] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0136] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program may be stored in a storage medium, which is a computer-readable storage medium. The computer program is executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.
[0137] Therefore, the present invention also provides a storage medium. This storage medium may be a computer-readable storage medium. The storage medium stores a computer program. When executed by a processor, the computer program causes the processor to perform the steps of an AI-driven CAD to BIM model automatic generation method as provided in any of the above method embodiments.
[0138] The storage medium is a physical, non-transient storage medium, such as a USB flash drive, external hard drive, read-only memory (ROM), magnetic disk, or optical disk, or any other physical storage medium capable of storing program code. The computer-readable storage medium can be non-volatile or volatile.
[0139] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0140] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.
[0141] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0142] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.
[0143] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0144] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Since these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.
[0145] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. An AI-driven method for automatic generation of CAD to BIM models, characterized in that, include: Receive CAD drawing files, wherein the CAD drawing files include at least one layer; Based on the identification information of the layer, determine the target object corresponding to the layer; Based on the layer image of the layer, determine the construction parameter information of the target object; Based on the construction parameter information of the target object, a three-dimensional model of the target object is constructed in a preset BIM software.
2. The AI-driven automatic generation method for CAD to BIM models according to claim 1, characterized in that, Determining the target object corresponding to the layer based on the layer's identification information includes: Identify the category keywords contained in the identification information; The target object corresponding to the layer is determined based on the category keywords.
3. The AI-driven automatic generation method for CAD to BIM models according to claim 1, characterized in that, The determination of the construction parameter information of the target object based on the layer image of the layer includes: The layer image is preprocessed to obtain the input image; The construction parameter information of the target object is determined based on the input image using a pre-trained neural network model.
4. The AI-driven automatic generation method for CAD to BIM models according to claim 3, characterized in that, The preprocessing of the layer image to obtain the input image includes: The layer image is standardized to obtain a standardized image; The standardized image is subjected to noise reduction processing to obtain the input image.
5. The AI-driven automatic generation method for CAD to BIM models according to claim 1, characterized in that, The construction of a 3D model of the target object in a preset BIM software based on the construction parameter information of the target object includes: The construction parameter information of the target object is organized according to the BIM standard format to generate the component attribute table of the target object; The API interface of the BIM software is invoked to construct a three-dimensional model of the target object based on the component attribute table.
6. The AI-driven automatic generation method for CAD to BIM models according to claim 1, characterized in that, After constructing a three-dimensional model of the target object in preset BIM software based on the target object's construction parameter information, the method further includes: Non-geometric properties are injected into the three-dimensional model of the target object.
7. The AI-driven automatic generation method for CAD to BIM models according to claim 6, characterized in that, The non-geometric properties include material properties, cost properties, and structural properties. Injecting non-geometric properties into the 3D model of the target object includes: Identify the material keywords contained in the identification information; Based on the material keywords, the material properties of the target object are matched against a preset material database; The unit cost of the target object is determined based on a pre-set cost library; The cost attributes of the target object are determined based on the construction parameter information and unit cost of the target object. The structural attributes of the target object are determined based on a pre-defined structural specification library; The API interface of the BIM software is invoked to write the material properties, cost properties, and structural properties into the attribute parameters of the three-dimensional model of the target object.
8. An AI-driven automatic CAD to BIM model generation device, characterized in that, Includes a unit for performing the method as described in any one of claims 1-7.
9. A computer device, characterized in that, The computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1-7.