Artificial intelligence-based building model design recognition method, device and equipment

Abstract

This application relates to a method, apparatus, computer equipment, and storage medium for architectural model design recognition based on artificial intelligence. The method includes: acquiring a building model to be recognized; the building model to be recognized is a 3D model drawn using design software; inputting the building model to be recognized into a preset recognition model; extracting the attributes of architectural model components and the object relationships between these attributes; and matching these attributes with architectural design rules in an architectural design rule base to obtain the recognition result of the architectural model design. This method can improve the recognition accuracy of architectural models.

Description

Technical Field

[0001] This application relates to the field of architectural design technology, and in particular to an artificial intelligence-based architectural model design recognition method, apparatus, device, and storage medium. Background Technology

[0002] With the development of science and technology, the field of architectural design has become increasingly automated.

[0003] Traditionally, after the architectural model is completed, the design software's built-in tools are used to check the model. However, existing tools can only perform simple checks such as collision rules; other more complex and in-depth indicators still require manual checks.

[0004] However, manually inspecting the designed architectural model relies on the experience and meticulousness of the personnel. When dealing with large models, the efficiency and accuracy of manual inspection are greatly reduced. Furthermore, due to factors such as the designer's experience, there is a high risk of omissions, resulting in a high error rate in the design model. Summary of the Invention

[0005] Therefore, it is necessary to provide an artificial intelligence-based architectural model design recognition method, device, computer equipment, and storage medium that can improve the accuracy of the above-mentioned technical problems.

[0006] In a first aspect, embodiments of this application provide an artificial intelligence-based architectural model design recognition method, the method comprising:

[0007] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0008] The building model to be identified is input into a preset identification model. The attributes of the building model components and the object relationships between the attributes of the building model components are extracted from the building model to be identified. The results are then matched with the building design rules in the building design rule base to obtain the identification result of the building model design.

[0009] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0010] In one embodiment, the matching with architectural design rules in the architectural design rule base to obtain the identification result of the architectural model design to be identified includes:

[0011] After sorting out the attributes of building model components and the object relationships between them, matching attribute data is formed.

[0012] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base.

[0013] In one embodiment, the process of obtaining the architectural design experience rules includes:

[0014] Obtain multiple sample models of the aforementioned buildings;

[0015] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0016] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0017] In one embodiment, the method for obtaining the standard rules includes:

[0018] Obtain electronic texts, including industry-standard documents;

[0019] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0020] The standard rules are derived based on the characteristic attributes of different objects in the electronic text and the hierarchical relationships between them.

[0021] In one embodiment, the rule categories in the building design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

[0022] Secondly, embodiments of this application provide an artificial intelligence-based architectural model design recognition method, the method comprising:

[0023] Obtain electronic texts, including industry-standard documents;

[0024] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0025] The standard rules are derived based on the characteristic attributes of different objects and the hierarchical relationships between them in the electronic text.

[0026] Obtain multiple sample models of the aforementioned buildings;

[0027] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0028] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0029] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0030] Input the building model to be identified into the identification model;

[0031] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0032] Prompts will be provided based on the recognition results.

[0033] Thirdly, embodiments of this application provide an artificial intelligence-based architectural model design recognition device, the device comprising:

[0034] The acquisition module is used to acquire the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software.

[0035] The identification module is used to input the building model to be identified into a preset identification model, extract the building model component attributes and the object relationships between the building model component attributes in the building model to be identified, and match them with the building design rules in the building design rule base to obtain the identification result of the building model design to be identified.

[0036] The identification result is used to characterize whether the design rules of the building model to be identified conform to the design specifications. The identification model is a neural network that includes a building design rule base. The building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0037] Fourthly, embodiments of this application provide an artificial intelligence-based architectural model design recognition device, the device comprising:

[0038] The rule acquisition module is used to acquire electronic text including industry standards, perform semantic recognition on the electronic text to obtain the feature attributes and hierarchical relationships of different objects in the electronic text, and obtain the standard rules based on the feature attributes and hierarchical relationships of different objects in the electronic text; and acquire multiple architectural sample models, parse the architectural sample models using a semantic recognition model to obtain the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models, and learn and classify the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models to obtain the architectural design experience rules;

[0039] The processing module is used to acquire a building model to be identified, input the building model to be identified into the identification model, and determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base to obtain the identification result; wherein, the building model to be identified is a three-dimensional model drawn based on design software, and the identification model is a neural network including the building design rule base, the building design rule base including building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards;

[0040] The prompting module is used to provide prompts based on the recognition results.

[0041] Fifthly, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0042] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0043] The building model to be identified is input into a preset identification model. The attributes of the building model components and the object relationships between the attributes of the building model components are extracted from the building model to be identified. The results are then matched with the building design rules in the building design rule base to obtain the identification result of the building model design.

[0044] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0045] Sixthly, embodiments of this application provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0046] Obtain electronic texts, including industry-standard documents;

[0047] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0048] The standard rules are derived based on the characteristic attributes of different objects and the hierarchical relationships between them in the electronic text.

[0049] Obtain multiple sample models of the aforementioned buildings;

[0050] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0051] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0052] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0053] Input the building model to be identified into the identification model;

[0054] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0055] Prompts will be provided based on the recognition results.

[0056] In a seventh aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the following steps:

[0057] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0058] The building model to be identified is input into a preset identification model. The attributes of the building model components and the object relationships between the attributes of the building model components are extracted from the building model to be identified. The results are then matched with the building design rules in the building design rule base to obtain the identification result of the building model design.

[0059] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0060] Eighthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, performs the following steps:

[0061] Obtain electronic texts, including industry-standard documents;

[0062] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0063] The standard rules are derived based on the characteristic attributes of different objects and the hierarchical relationships between them in the electronic text.

[0064] Obtain multiple sample models of the aforementioned buildings;

[0065] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0066] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0067] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0068] Input the building model to be identified into the identification model;

[0069] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0070] Prompts will be provided based on the recognition results.

[0071] The aforementioned AI-based architectural model design recognition method, apparatus, computer equipment, and storage medium involve the computer equipment acquiring the architectural model to be recognized and inputting it into a preset recognition model for design rule verification, thereby obtaining the AI-based architectural model design recognition result. Since the recognition model is a neural network including an architectural design rule base, and this rule base includes architectural design experience rules learned from multiple architectural sample models and architectural design standard rules obtained based on industry standards, the recognition result based on architectural design experience rules can be based on the rules of most architectural models, combined with the design experience of existing architectural models for verification. Simultaneously, the architectural design rule base also includes architectural design standard rules obtained based on industry standards, thus enabling verification in conjunction with industry norms, such as national standards, industry standards, and enterprise standards, ensuring that the architectural model to be recognized meets industry standards. This enables the identification model, which includes a building design rule base, to automatically identify non-compliant objects based on industry standards and design experience. This avoids the problems of low efficiency, low accuracy, incompleteness, and high human learning costs that may result from traditional manual inspection and identification. This method can automatically achieve building model design identification based on artificial intelligence using the identification model, thus greatly improving the identification efficiency. It can also more accurately and comprehensively inspect and identify the current building model to be identified, thereby greatly improving the accuracy of the building model to be identified. At the same time, it reduces the human learning cost and greatly saves time and manpower. Attached Figure Description

[0072] Figure 1 This is an internal structural diagram of a computer device in one embodiment;

[0073] Figure 2 A flowchart illustrating an AI-based building model design recognition method provided in one embodiment;

[0074] Figure 3 A flowchart illustrating an AI-based building model design recognition method for another embodiment;

[0075] Figure 4 A flowchart illustrating a method for obtaining architectural design experience rules, as provided in yet another embodiment;

[0076] Figure 5 A flowchart illustrating a standard rule acquisition method for yet another embodiment is provided.

[0077] Figure 6 A flowchart illustrating an AI-based building model design recognition method as another embodiment;

[0078] Figure 7A schematic diagram of the structure of a design model identification device provided in one embodiment;

[0079] Figure 8 A schematic diagram of the structure of a design model identification device provided for yet another embodiment. Detailed Implementation

[0080] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0081] The artificial intelligence-based building model design recognition method provided in this application embodiment can be applied to... Figure 1 The computer device shown includes a processor, memory, network interface, database, display screen, and input device connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores the identification model described in the following embodiments; a detailed description of the identification model is provided in the following embodiments. The network interface of the computer device can be used to communicate with other external devices via a network connection. Optionally, the computer device can be a server, a desktop computer, a personal digital assistant, or other terminal devices such as tablets, mobile phones, etc., or a cloud or remote server. This application does not limit the specific form of the computer device. The display screen of the computer device can be a liquid crystal display or an e-ink display. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device casing, or an external keyboard, touchpad, or mouse. Of course, input devices and displays may not be part of the computer equipment; they can be external devices to the computer equipment.

[0082] Those skilled in the art will understand that Figure 1 The structure shown 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 to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0083] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0084] It should be noted that the executing entity of the following method embodiments can be an artificial intelligence-based architectural model design recognition device. This device can be implemented as part or all of the aforementioned computer equipment through software, hardware, or a combination of software and hardware. The following method embodiments are described using a computer equipment as an example of the executing entity.

[0085] Figure 2 This is a flowchart illustrating an artificial intelligence-based architectural model design recognition method as provided in one embodiment. This embodiment relates to the process of using artificial neural networks with computer equipment to perform design checks on architectural models. Figure 2 As shown, it includes:

[0086] S11. Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software.

[0087] Specifically, the computer device can read pre-stored building models to be identified, receive building models to be identified sent by other devices, or download building models to be identified through a data platform; this embodiment does not limit the scope of these methods. It should be noted that the aforementioned building model to be identified is a three-dimensional model already designed by the computer device. Typically, this model can be a three-dimensional model of a set of rooms or a three-dimensional model of a building; this embodiment does not limit the scope of this method.

[0088] S12. Input the building model to be identified into a preset identification model, extract the building model component attributes and the object relationships between the building model component attributes in the building model to be identified, and match them with the building design rules in the building design rule library to obtain the identification result of the building model design to be identified.

[0089] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0090] Specifically, the computer inputs the aforementioned building model to be identified into a preset recognition model. Since this recognition model is a neural network including a building design rule base, it can identify the building model, obtain the attributes of different objects within the model and the relationships between these attributes, and then check each attribute and relationship against the rules in the building design rule base. This yields a result indicating whether the attributes and object relationships of the building model conform to design specifications. Because the building design rule base includes architectural design experience rules learned from multiple building sample models, the recognition results are based on the rules of most building models, combined with existing design experience. Furthermore, the building design rule base also includes architectural design standard rules obtained from industry standards, allowing for checks against industry standards such as national, industry, and enterprise standards, ensuring that the building model meets industry specifications.

[0091] In this embodiment, the computer device acquires the building model to be identified and inputs it into a preset identification model for design rule verification, thereby obtaining the design identification result of the building model based on artificial intelligence. Since the identification model is a neural network including a building design rule base, and this rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards, the building design experience rules allow the identification result to be based on the rules of most building models, combined with the design experience of existing building models for verification. Simultaneously, the building design rule base also includes building design standard rules obtained based on industry standards, thus enabling verification in conjunction with industry norms, such as national standards, industry standards, and enterprise standards, ensuring that the building model to be identified meets industry standards. This enables the identification model, which includes a building design rule base, to automatically identify non-compliant objects based on industry standards and design experience. This avoids the problems of low efficiency, low accuracy, incompleteness, and high human learning costs that may result from traditional manual inspection and identification. This method can automatically achieve building model design identification based on artificial intelligence using the identification model, thus greatly improving the identification efficiency. It can also more accurately and comprehensively inspect and identify the current building model to be identified, thereby greatly improving the accuracy of the building model to be identified. At the same time, it reduces the human learning cost and greatly saves time and manpower.

[0092] Optionally, based on the above embodiments, one possible implementation of step S12 can be as follows: Figure 3 As shown, it includes:

[0093] S121. After sorting out the attributes of the building model components and the object relationships between the attributes of the building model components, matching attribute data is formed.

[0094] Specifically, the computer device inputs the aforementioned building model to be identified into the aforementioned recognition model. This recognition model can identify, but is not limited to, multiple objects and their attributes, geometric information, and relationships between them. For example, when the building model to be identified is a house model, the recognition model can identify functional areas such as bedrooms, bathrooms, kitchens, and balconies. It can also identify objects within each functional area, such as sinks, toilets, and floor drains in the bathroom. Furthermore, it can identify the shape and orientation of the sink, as well as the distance requirements between the sink and the toilet, etc. Specifically, the data can be processed according to functional areas to form matching attribute data.

[0095] S122. Determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base, and obtain the identification result.

[0096] Specifically, the computer equipment compares the identified objects, object attributes, geometric relationships, and interrelationships with the design rules in the aforementioned architectural design rule base to determine whether they meet the requirements. If they do, the object, object attribute, or interrelationship meets the requirements, and the identification result can be recorded as PASS. If they do not meet the requirements, the object, object attribute, or interrelationship is considered not to meet the requirements, and there may be a design error; the identification result for this step can be recorded as FAIL. Optionally, there may also be unidentifiable results, such as if the architectural design rule base does not contain a rule for the object to be identified, which can be recorded as UNKNOW.

[0097] S123. Provide prompts based on the recognition results.

[0098] Specifically, when the object in the above identification results meets the rules in the above building design rule base, a correct prompt message can be displayed; when the object in the above identification results does not meet the rules in the above building design rule base, an incorrect prompt message can be displayed. Optionally, the prompt message can be a pop-up prompt box, a prompt message displayed in the status bar, or a prompt message highlighting the incorrect object; this embodiment does not limit this.

[0099] In this embodiment, the computer device inputs the building model to be identified into the recognition model; determines whether the building model meets each building design rule in the building design rule base, and obtains the recognition result; and provides prompts based on the recognition result. This enables prompts for objects that do not meet design specifications, achieving intelligent design model inspection and recognition. Therefore, the recognition results are more comprehensive and accurate, and the recognition efficiency is high, further improving the quality of the building model to be identified.

[0100] Optionally, the process of obtaining the aforementioned architectural design rules of experience can be as follows: Figure 4 As shown, it includes:

[0101] S131. Obtain multiple architectural sample models.

[0102] Specifically, the computer device can read multiple architectural sample models from the memory or download architectural sample models from the data platform. This embodiment does not limit the method of obtaining architectural sample models.

[0103] S132. Use a semantic recognition model to parse the building sample model to obtain the feature attributes, geometric information and hierarchical relationships of different objects in the building sample model.

[0104] Specifically, computer equipment can analyze the above-mentioned architectural sample model to obtain the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model. For example, it can analyze the architectural sample model to obtain the attribute that the dining table is furniture, the geometric information that it is square, round or elliptical, and the hierarchical relationship that the dining table is placed in the dining room and the dining room is located in the room.

[0105] Based on the aforementioned attribute features, which are represented as text records, deep learning semantic recognition models can be used to extract these attribute features, thereby obtaining the feature attributes, geometric information, and hierarchical relationships of different objects.

[0106] S133. The characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model are learned and classified to obtain the architectural design experience rules.

[0107] Specifically, the computer equipment learns and categorizes the characteristic attributes, geometric information, and hierarchical relationships of different objects in the aforementioned architectural sample model. For example, it categorizes dining tables and sofas as furniture, resulting in rules that furniture should be placed inside a room. Other rules include placing toilets in the bathroom and placing them in the same area as water outlets and drains, ensuring that water pipes within the room are interconnected, and preventing collisions between any entity models. The computer equipment then adds the learned architectural design experience rules to an architectural design rule base and loads this rule base into the aforementioned recognition model, thereby achieving automatic recognition of the model to be identified.

[0108] In this embodiment, the computer device acquires and parses multiple architectural sample models to obtain the characteristic attributes, geometric information, and hierarchical relationships of different objects in the architectural sample models. It also learns and classifies the characteristic attributes, geometric information, and hierarchical relationships of different objects in the architectural sample models to obtain architectural design experience rules, thereby forming a recognition model. This enables the acquisition of architectural design experience rules based on architectural models through parsing and learning, and further enables the abstraction of design experience into rules for artificial intelligence-based architectural model design recognition. This achieves the checking based on design experience, making the recognition results of the model to be recognized more accurate and more in line with the actual design requirements.

[0109] Optionally, the process of obtaining the above standard rules can be as follows: Figure 5 As shown, it includes:

[0110] S141. Obtain electronic texts including industry standards.

[0111] Specifically, computer equipment can read electronic text, including industry standards, stored in memory, or receive electronic text sent by other devices. It should be noted that this electronic text can include texts of national standards or enterprise standards; the electronic text refers to documents that are currently publicly issued documents adhering to standards.

[0112] S142. Perform semantic recognition on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects.

[0113] Specifically, the computer equipment uses a semantic recognition model to perform semantic recognition on the aforementioned electronic text, obtaining the characteristic attributes of different objects in the electronic text and the hierarchical relationships between different objects. Optionally, a preset semantic recognition model can be used to recognize the electronic text, thereby obtaining the characteristic attributes of objects in the electronic text and the hierarchical relationships between different objects. For example, the hierarchical structure of water pipes can be identified, with the water pipe entering the house as the root node, the water supply point as the terminal node, and the root node as the node above the terminal node. For example, the next layer of the water supply and drainage system is domestic water supply, sewage drainage, and fire drainage, the next layer is the pipe material and inner diameter, the next layer is the branch pipe of the main pipe, and so on, thus obtaining the complete hierarchical relationship of water supply and drainage. Furthermore, it can also include that when the diameter of the outdoor domestic pipe is less than or equal to 150mm, the spacing between inspection wells should not exceed 20m; when the pipe diameter is greater than 200mm, the spacing between inspection wells should not exceed 30m.

[0114] S143. Based on the characteristic attributes of different objects in the electronic text and the hierarchical relationship of different objects, the standard rules are obtained.

[0115] Specifically, the computer device defines the characteristic attributes of objects in the aforementioned electronic text and the hierarchical relationships between different objects, thereby obtaining standard rules.

[0116] In this embodiment, the computer device acquires electronic text including industry standards and performs semantic recognition on the electronic text to obtain the characteristic attributes of objects in the electronic text and the hierarchical relationship between different objects. Finally, based on the characteristic attributes of objects in the electronic text and the hierarchical relationship between different objects, standard rules are obtained, thereby realizing the logicalization of industry standards. This enables the computer device to automatically judge the identification of the building model design to be identified based on the above standard rules, making the identification result of the model to be identified more accurate and more in line with the actual design requirements.

[0117] Optionally, the computer device can also update the above-mentioned building design rule base based on the objects, object attributes, geometric information or hierarchical relationships obtained by parsing the building model to be identified, so that the building design rule base can be updated based on new design requirements, making it easier to identify with the latest design requirements, thereby making the matching degree between the identification results and design requirements higher, and further improving the quality of the building model to be identified.

[0118] Optionally, the rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules. Collision rules are used to regulate whether there are positional conflicts between architectural model components; specification rules are used to regulate whether the dimensions of architectural model components meet preset requirements; connectivity rules are used to regulate whether the connectivity relationships between architectural model components meet preset requirements; and object relationship rules are used to regulate whether the relationships between architectural model components and their attributes meet preset requirements. Therefore, based on the architectural design rule base, the collision rules, specification rules, connectivity rules, and object relationship rules of the architectural model to be identified can be verified, further comprehensively improving the quality of the architectural model to be identified.

[0119] To describe the technical solution provided in this application in more detail, a specific embodiment is used to illustrate this application, such as... Figure 6 As shown, it includes:

[0120] S21. Obtain electronic text including industry standards, perform semantic recognition on the electronic text to obtain the feature attributes of different objects in the electronic text and the hierarchical relationship of different objects, and obtain the standard rules based on the feature attributes of different objects in the electronic text and the hierarchical relationship of different objects.

[0121] S22. Obtain multiple architectural sample models, use a semantic recognition model to parse the architectural sample models, obtain the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models, and learn and classify the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models to obtain the architectural design experience rules.

[0122] S23. Obtain the building model to be identified and input the building model to be identified into the identification model; wherein, the building model to be identified is a three-dimensional model drawn based on design software;

[0123] S24. Determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base, and obtain the identification result; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards;

[0124] S25. Provide prompts based on the recognition results.

[0125] For a detailed description of the steps and technical effects in this embodiment, please refer to the foregoing embodiments, which will not be repeated here.

[0126] It should be understood that, although Figure 2-6 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2-6 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0127] In one embodiment, such as Figure 7 As shown, an artificial intelligence-based architectural model design recognition device is provided, comprising:

[0128] The acquisition module 100 is used to acquire the building model to be identified; wherein, the building model to be identified is a three-dimensional model drawn based on design software;

[0129] The recognition module 200 is used to input the building model to be recognized into a preset recognition model, extract the building model component attributes and the object relationships between the building model component attributes in the building model to be recognized, and match them with the building design rules in the building design rule library to obtain the recognition result of the building model design to be recognized.

[0130] The identification result is used to characterize whether the design rules of the building model to be identified conform to the design specifications. The identification model is a neural network that includes a building design rule base. The building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0131] In one embodiment, the identification module 200 is specifically used to sort out the attributes of building model components and the object relationships between the attributes of building model components to form matching attribute data; determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base, and obtain the identification result; and then provide a prompt based on the identification result.

[0132] In one embodiment, the identification module 200 is specifically used to acquire multiple building sample models; parse the building sample models using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample models; and learn and classify the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample models to obtain the architectural design experience rules.

[0133] In one embodiment, the identification module 200 is specifically used to acquire electronic text including industry standards; perform semantic recognition on the electronic text to obtain the feature attributes of different objects in the electronic text and the hierarchical relationship of different objects; and obtain the standard rules based on the feature attributes of different objects in the electronic text and the hierarchical relationship of different objects.

[0134] In one embodiment, the rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

[0135] In one embodiment, such as Figure 8 As shown, an artificial intelligence-based architectural model design recognition device is provided, comprising:

[0136] The rule acquisition module 300 is used to acquire electronic text including industry standards, perform semantic recognition on the electronic text to obtain the feature attributes and hierarchical relationships of different objects in the electronic text, and obtain the standard rules based on the feature attributes and hierarchical relationships of different objects in the electronic text; and acquire multiple architectural sample models, parse the architectural sample models using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the architectural sample models, and learn and classify the feature attributes, geometric information, and hierarchical relationships of different objects in the architectural sample models to obtain the architectural design experience rules.

[0137] The processing module 400 is used to acquire a building model to be identified, input the building model to be identified into the identification model, and determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base to obtain the identification result; wherein, the building model to be identified is a three-dimensional model drawn based on design software, and the identification model is a neural network including the building design rule base, the building design rule base including building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards;

[0138] The prompting module 500 is used to provide prompts based on the recognition results.

[0139] Specific limitations regarding the recognition device for architectural design models can be found in the limitations of the recognition method for architectural design models described above, and will not be repeated here. Each module in the aforementioned architectural design model recognition device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0140] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0141] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0142] The building model to be identified is input into a preset identification model. The attributes of the building model components and the object relationships between the attributes of the building model components are extracted from the building model to be identified. The results are then matched with the building design rules in the building design rule base to obtain the identification result of the building model design.

[0143] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0144] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0145] After sorting out the attributes of building model components and the object relationships between them, matching attribute data is formed.

[0146] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base.

[0147] Prompts will be provided based on the recognition results.

[0148] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0149] Obtain multiple sample models of the aforementioned buildings;

[0150] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0151] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0153] Obtain electronic texts, including industry-standard documents;

[0154] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0155] The standard rules are derived based on the characteristic attributes of different objects in the electronic text and the hierarchical relationships between them.

[0156] In one embodiment, the rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

[0157] It should be clear that the process of the processor executing the computer program in the embodiments of this application is consistent with the execution process of each step in the above method, as can be seen in the description above.

[0158] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0159] Obtain electronic texts, including industry-standard documents;

[0160] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0161] The standard rules are derived based on the characteristic attributes of different objects and the hierarchical relationships between them in the electronic text.

[0162] Obtain multiple sample models of the aforementioned buildings;

[0163] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0164] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0165] Obtain the building model to be identified; wherein the building model to be identified is a three-dimensional model drawn based on design software;

[0166] Input the building model to be identified into the identification model;

[0167] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0168] Prompts will be provided based on the recognition results.

[0169] It should be clear that the process of the processor executing the computer program in the embodiments of this application is consistent with the execution process of each step in the above method, as can be seen in the description above.

[0170] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0171] Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software;

[0172] The building model to be identified is input into a preset identification model. The attributes of the building model components and the object relationships between the attributes of the building model components are extracted from the building model to be identified. The results are then matched with the building design rules in the building design rule base to obtain the identification result of the building model design.

[0173] The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The identification model is a neural network including a building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0174] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0175] After sorting out the attributes of building model components and the object relationships between them, matching attribute data is formed.

[0176] Determine whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base, and obtain the identification result;

[0177] Prompts will be provided based on the recognition results.

[0178] In one embodiment, the rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] Obtain multiple sample models of the aforementioned buildings;

[0181] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0182] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0183] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0184] Obtain electronic texts, including industry-standard documents;

[0185] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0186] The standard rules are derived based on the characteristic attributes of different objects in the electronic text and the hierarchical relationships between them.

[0187] It should be clear that the process of the processor executing the computer program in the embodiments of this application is consistent with the execution process of each step in the above method, as can be seen in the description above.

[0188] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0189] Obtain electronic texts, including industry-standard documents;

[0190] Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects;

[0191] The standard rules are derived based on the characteristic attributes of different objects and the hierarchical relationships between them in the electronic text.

[0192] Obtain multiple sample models of the aforementioned buildings;

[0193] The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model.

[0194] The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model.

[0195] Obtain the building model to be identified; wherein the building model to be identified is a three-dimensional model drawn based on design software;

[0196] Input the building model to be identified into the identification model;

[0197] The identification result is obtained by determining whether the matching attribute data of the building model to be identified satisfies each of the building design rules in the building design rule base; wherein, the identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards.

[0198] Prompts will be provided based on the recognition results.

[0199] It should be clear that the process of the processor executing the computer program in the embodiments of this application is consistent with the execution process of each step in the above method, as can be seen in the description above.

[0200] Those skilled in the art will understand 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 can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0201] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0202] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for architectural model design recognition based on artificial intelligence, characterized in that, The method includes: Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software; Input the building model to be identified into a preset identification model, and extract the building model component attributes and the object relationships between the building model component attributes in the building model to be identified. After sorting out the attributes of the building model components and the object relationships between the attributes of the building model components, matching attribute data is formed; it is determined whether the matching attribute data of the building model to be identified meets each building design rule in the building design rule base, the identification result is obtained, and prompts are given according to the identification result; The identification result is used to characterize the matching degree between the design rules of the building model to be identified and the building design rules. The preset identification model is a neural network including the building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards. The process of obtaining the architectural design experience rules includes: Obtain multiple sample models of the aforementioned buildings; The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model. The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model. The methods for obtaining the standard rules include: Obtain electronic texts, including industry-standard documents; Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects; The standard rules are derived based on the characteristic attributes of different objects in the electronic text and the hierarchical relationships between them.

2. The method according to claim 1, characterized in that, The rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

3. The method according to claim 2, characterized in that, The collision rules are used to regulate whether there are any positional conflicts between the various architectural model components in the architectural model; The specifications and rules are used to determine whether the dimensions of each architectural model component in the architectural model meet the preset requirements; The connectivity rules are used to regulate whether the connectivity relationships between various building model components meet preset requirements; The object relationship rules are used to regulate whether the relationships between building model components and their attributes meet preset requirements.

4. The method according to claim 1, characterized in that, The method further includes: The building design rule base is updated based on the objects obtained from parsing the building model to be identified, the object attributes, the geometric information, or the hierarchical relationship.

5. A method for architectural model design recognition based on artificial intelligence, characterized in that, The method includes: Obtain electronic texts, including industry-standard documents; Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects; Standard rules are derived based on the characteristic attributes of different objects in electronic text and the hierarchical relationships between them; Obtain multiple architectural sample models; The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model. The characteristic attributes, geometric information, and hierarchical relationships of different objects in the architectural sample model are learned and classified to obtain architectural design experience rules. Obtain the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software; Input the building model to be identified into the preset identification model; After sorting out the attributes of building model components and the object relationships between them, matching attribute data is formed; it is then determined whether the matching attribute data of the building model to be identified satisfies each building design rule in the building design rule base to obtain the identification result; wherein, the preset identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards; Prompts will be provided based on the recognition results.

6. An artificial intelligence-based architectural model design recognition device, characterized in that, The device includes: The acquisition module is used to acquire the building model to be identified; the building model to be identified is a three-dimensional model drawn based on design software. The identification module is used to input the building model to be identified into a preset identification model, and extract the building model component attributes and the object relationships between the building model component attributes in the building model to be identified. After sorting out the attributes of the building model components and the object relationships between the attributes of the building model components, matching attribute data is formed; it is determined whether the matching attribute data of the building model to be identified meets each building design rule in the building design rule base, the identification result is obtained, and prompts are given according to the identification result; The identification result is used to characterize whether the design rules of the building model to be identified conform to the design specifications. The preset identification model is a neural network that includes the building design rule library. The building design rule library includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards. The identification module is further configured to: acquire multiple building sample models; The building sample model is analyzed using a semantic recognition model to obtain the feature attributes, geometric information, and hierarchical relationships of different objects in the building sample model. The architectural design experience rules are obtained by learning and classifying the characteristic attributes, geometric information and hierarchical relationships of different objects in the architectural sample model. The identification module is also used for: Obtain electronic texts, including industry-standard documents; Semantic recognition is performed on the electronic text to obtain the characteristic attributes of different objects in the electronic text and the hierarchical relationship between different objects; The standard rules are derived based on the characteristic attributes of different objects in the electronic text and the hierarchical relationships between them.

7. The apparatus according to claim 6, characterized in that, The rule categories in the architectural design rule base include: collision rules, specification rules, connectivity rules, and object relationship rules.

8. A building model design recognition device based on artificial intelligence, characterized in that, The device includes: The rule acquisition module is used to acquire electronic text including industry standards, perform semantic recognition on the electronic text to obtain the feature attributes and hierarchical relationships of different objects in the electronic text, and obtain standard rules based on the feature attributes and hierarchical relationships of different objects in the electronic text; and acquire multiple architectural sample models, use a semantic recognition model to parse the architectural sample models to obtain the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models, and learn and classify the feature attributes, geometric information and hierarchical relationships of different objects in the architectural sample models to obtain architectural design experience rules; The processing module is used to acquire a building model to be identified, input the building model to be identified into a preset identification model, and determine whether the matching attribute data of the building model to be identified satisfies each building design rule in the building design rule base to obtain the identification result; wherein, the building model to be identified is a three-dimensional model drawn based on design software, and the preset identification model is a neural network including the building design rule base, and the building design rule base includes building design experience rules learned from multiple building sample models and building design standard rules obtained based on industry standards; The prompting module is used to provide prompts based on the recognition results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images