A BIM intelligent building modeling method and system based on large language models

Abstract

The present invention relates to the technical field of BIM building modeling processing, and discloses a BIM intelligent building modeling method and system based on a large language model. The system includes a BIM building modeling object analysis module, a BIM building modeling instruction analysis module, and a BIM building modeling execution module. According to the analysis result of the building modeling object type, combined with an intelligent recognition algorithm and three-dimensional model information of different types of building modeling objects stored in a large data storage, an intelligent search for the three-dimensional model of the BIM building modeling object is carried out to realize the scientific and efficient generation of the three-dimensional structure of the BIM building modeling object based on natural language. Based on the text data of the modeling requirements of the relationship between the building modeling object and the position, shape, and size of the building modeling scene, combined with an intelligent search algorithm and different modeling requirement building modeling control instructions stored in a standard, an intelligent matching of the BIM building modeling control instructions is carried out to realize the intelligent and accurate selection of the BIM building modeling control instructions based on natural language and the design concept of the designer.

Description

Technical Field

[0001] The present invention relates to the technical field of BIM building modeling processing, and specifically to a BIM intelligent building modeling method and system based on a large language model. Background Art

[0002] BIM building modeling technology is an engineering management method based on three-dimensional digital technology. By integrating information throughout the building life cycle, including processes such as design, construction, and operation and maintenance, it realizes efficient collaboration and data sharing for projects; BIM building modeling technology includes core technical advantages such as visualization and information integration, simulation and optimization, and multi-disciplinary collaboration; among them, visualization and information integration means that the BIM model is based on three-dimensional graphics, integrating geometric information and non-geometric information to form a dynamic database. This feature significantly improves the communication efficiency of design intentions and provides data support for construction management; simulation and optimization means supporting complex scenario simulations (such as sunlight analysis, energy consumption assessment) to assist scientific decision-making; automatically detecting design conflicts, optimizing material utilization and structural safety, and reducing construction rework rates; multi-disciplinary collaboration means coordinating the design of disciplines such as architecture, structure, and mechanical and electrical through a unified platform; the existing BIM building modeling process still requires building modeling based on designers' manual operations or architectural CAD drawings, and cannot intelligently complete the building entity modeling process based on designers' natural language information and modeling design concept image information, reducing the efficiency and quality of BIM building modeling.

[0003] The Chinese patent application with publication number CN114880877A discloses a BIM modular modeling method and a BIM modular modeling system. The modeling method completes the model process analysis of BIM through Rhino model establishment, model refinement, model expansion, process selection, optimization layout, dimension collection, loss rate calculation, and prefabrication production. However, the above technical solutions cannot intelligently complete the building entity modeling process based on designers' natural language information and modeling concept image information. Summary of the Invention

[0004] (I) Technical Problems to be Solved

[0005] To solve the problem that the existing BIM building modeling process still requires building modeling based on designers' manual operations or architectural CAD drawings, and cannot intelligently complete the building entity modeling process based on designers' natural language information and modeling design concept image information, reducing the efficiency and quality of BIM building modeling, the purpose is to scientifically analyze the types of building modeling objects, accurately search for three-dimensional model information of building modeling objects, intelligently analyze building modeling control instruction information, and independently and efficiently execute building modeling operations.

[0006] (II) Technical Solutions

[0007] The present invention is realized through the following technical solutions: A BIM intelligent building modeling method based on a large language model, the method comprising the following steps:

[0008] S1. Collect the characteristic text data of the building modeling object;

[0009] S2. Perform BIM building modeling object type analysis and processing based on the characteristic text data of the building modeling object and the characteristic text data of different types of building modeling objects to generate building modeling object type analysis data;

[0010] S3. Perform three-dimensional model search processing of the BIM building modeling object based on the building modeling object type analysis data and the three-dimensional model data of different types of building modeling objects to generate the three-dimensional model data of the target building modeling object;

[0011] S4. Collect the three-dimensional image data of the building modeling object, the three-dimensional model data of the building modeling scene, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the position, shape and size relationship between the building modeling object and the building modeling scene;

[0012] S5. Perform recognition and processing of the modeling requirement text information of the spatial position and size of the building modeling object and the building modeling scene and the shape and size of the building modeling object based on the three-dimensional image data of the building modeling object, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the position, shape and size relationship between the building modeling object and the building modeling scene to generate the modeling requirement text data of the position, shape and size relationship between the building modeling object and the building modeling scene;

[0013] S6. Perform BIM building modeling control instruction screening and search processing based on the modeling requirement text data of the position, shape and size relationship between the building modeling object and the building modeling scene and the building modeling control instruction data of different modeling requirements to generate the target building modeling control instruction data;

[0014] S7. Construct the BIM building modeling summary data and execute the BIM building modeling operation.

[0015] Preferably, the operation steps of collecting the characteristic text data of the building modeling object are as follows:

[0016] S11. Online collect the characteristic description text information of the specific BIM building modeling object by the voice input module and generate the characteristic text data of the building modeling object .

[0017] Preferably, the operation steps of performing BIM building modeling object type analysis and processing based on the characteristic text data of the building modeling object and the characteristic text data of different types of building modeling objects to generate building modeling object type analysis data are as follows:

[0018] S21. Establishing feature text data sets of different types of building modeling objects , ;in Indicates Different types of building modeling object feature text data corresponding to different types of BIM building modeling object types, Indicates the maximum number of BIM building modeling object types; BIM building modeling object types include walls, floors, doors and windows, roofs, stairs, railings, beams, columns, plates, shear walls, pile foundations, pipes, valves and water pumps; the different types of building modeling object feature text data represent standard building modeling object feature text information set for different types of BIM building modeling objects;

[0019] S22, using an intelligent large language model to transform the building modeling object feature text data A collection of feature text data of different types of building modeling objects Characteristic text data of different types of building modeling objects described in Perform architectural modeling feature character matching to search for feature text data of the architectural modeling object Matching characteristic text data of different types of building modeling objects Corresponding building modeling object type text information, and constructing building modeling object type analysis data The intelligent large language model includes any one of DeepSeekV3, Alibaba Qwen2.5, and Tencent Hunyuan Turbo.

[0020] Preferably, the steps of performing a 3D model search process of a BIM building modeling object according to the building modeling object type analysis data and the 3D model data of different types of building modeling objects to generate the 3D model data of the target building modeling object are as follows:

[0021] S31. Establishing 3D model data sets of different types of building modeling objects ,in Indicates Different types of building modeling object three-dimensional model data corresponding to the BIM building modeling object type, wherein the different types of building modeling object feature text data represent standard building modeling three-dimensional entity data set for different types of BIM building modeling objects;

[0022] S32, analyzing the building modeling object type data A three-dimensional model data set of different types of building modeling objects 3D model data of different types of building modeling objects Perform keyword matching for building modeling object types to search for the building modeling object type analysis data The corresponding 3D model data of different types of building modeling objects and construct the 3D model data of the target building modeling object Execute to generate the 3D model data of the target building modeling object The specific operation steps are as follows:

[0023] S321. In the search space of the 3D model data set of different types of building modeling objects Initialize all the 3D model data of different types of building modeling objects as nectar sources ; At the same time, initialize the number of nectar sources as , the current iteration number t, the maximum iteration number T, and the initial position of the nectar source , and the initial position The calculation formula is as follows: Randomly generated in the search space of the 3D model data set of different types of building modeling objects where represents a random number within , and respectively represent the upper and lower bounds in the search space of the 3D model data set of different types of building modeling objects ;

[0024] S322. Assign employed bees to the initial position . At the beginning of the search, the employed bees are in the search space of the 3D model data set of different types of building modeling objects around the initial position formed by all the 3D model data of different types of building modeling objects . According to the formula , search in the search space of the 3D model data set of different types of building modeling objects to generate the 3D model data of different types of building modeling objects that matches the building modeling object type analysis data at the new nectar source position ; where represents randomly selecting a nectar source other than i from nectar sources, represents the randomly selected nectar source in the search space of the 3D model data set of different types of building modeling objects The position in the search space, represents a random number within the range [-1, 1];

[0025] S323. According to the fitness value of the new nectar source position determine the nectar sources to be retained according to the method of greedy selection, and retain the three-dimensional model data of the different types of building modeling objects matching the building modeling object type analysis data ;

[0026] S324. The employed bees share the nectar source information, and the follower bees search for the three-dimensional model data of the different types of building modeling objects in the search space of the set according to the probability value, and the follower bees search for the three-dimensional model data of the different types of building modeling objects matching the building modeling object type analysis data according to the search results shared by the employed bees and retain the three-dimensional model data of the different types of building modeling objects , calculate the probability that the nectar source found by the employed bees is followed according to the probability formula. The probability calculation formula is as follows: , where represents the probability that the new nectar source position is found by the employed bees and followed, represents the fitness value of the new nectar source position shared by the follower bees according to the employed bees;

[0027] S325. The follower bees search in the same way as the employed bees, and search for the three-dimensional model data of the different types of building modeling objects in the search space of the set that matches the building modeling object type analysis data and retain the three-dimensional model data of the different types of building modeling objects nectar source and retain it;

[0028] S326. During the random search of the scout bees in the search space of the set of three-dimensional model data of the different types of building modeling objects , if the nectar source position reaches the iteration threshold after t iterations of search and no better nectar source is found, this nectar source position will be abandoned, and the corresponding employed bee will become a scout bee; the calculation formula for the scout bee to randomly generate a new nectar source position in the search space is as follows: , where represents generating a new nectar source after iterations In the position within the search space of the three-dimensional model data set of the different types of building modeling objects represents the position within the search space of the three-dimensional model data set of the different types of building modeling objects where a new nectar source is generated after t iterations In the position within the search space of the three-dimensional model data set of the different types of building modeling objects ;

[0029] S327. When the algorithm meets the maximum number of iterations T, output the three-dimensional model data of the different types of building modeling objects that match the building modeling object type analysis data , and generate the three-dimensional model data of the target building modeling object through data identification

[0030] Preferably, the operation steps for collecting the three-dimensional image data of the building modeling object, the three-dimensional model data of the building modeling scene, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the position, shape, and size relationship between the building modeling object and the building modeling scene are as follows:

[0031] S41. Import the three-dimensional model data of the target building modeling object into the BIM building modeling software for operation, and cooperate with the screenshot software to collect the axonometric drawing of the target building modeling object, and generate the three-dimensional image data of the building modeling object ; The BIM building modeling software includes any one of Autodesk Revit, ArchiCAD, and Bentley Systems, and the screenshot software includes any one of the screenshot tools built into Windows, Snipasteh, and Jinzhou Screenshot Software;

[0032] Online obtain the three-dimensional entity information of the building modeling scene of the modeling design assembly object that is the target building modeling object through the BIM building modeling software, and generate the three-dimensional model data of the building modeling scene ;

[0033] Online obtain the axonometric drawing of the building modeling scene corresponding to the three-dimensional model data of the building modeling scene in the BIM building modeling software through the screenshot software, and generate the three-dimensional image data of the building modeling scene ;

[0034] Online synchronously collect the positioning dimension design concept of the target building modeling object and the building modeling scene space position, as well as the shape and size design concept of the target building modeling object, through the brain-computer interface device, form the three-dimensional image information of the position dimension annotation and shape dimension annotation of the building modeling object, and generate the three-dimensional image data of the position, shape, and size relationship between the building modeling object and the building modeling scene , the brain-computer interface device includes any one of Neuralink brain-computer interface, Beibrain No. 1 system, and mixed reality brain-computer interface system.

[0035] Preferably, based on the three-dimensional image data of the building modeling object, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the position, shape, and size relationship between the building modeling object and the building modeling scene, the operation steps for identifying and processing the text information of the modeling requirements for the spatial position and size of the building modeling object and the building modeling scene and the shape and size of the building modeling object, and generating the text data of the modeling requirements for the position, shape, and size relationship between the building modeling object and the building modeling scene are as follows:

[0036] S51. Import the three-dimensional image data of the building modeling object , the three-dimensional image data of the building modeling scene , and the three-dimensional image data of the position, shape, and size relationship between the building modeling object and the building modeling scene into the intelligent large language model respectively. The intelligent large language model identifies and processes the text information of the spatial position and size of the target building modeling object and the building modeling scene and the text information of the shape and size of the target building modeling object based on the image information, and generates the text data of the modeling requirements for the position, shape, and size relationship between the building modeling object and the building modeling scene . The text data of the modeling requirements for the position, shape, and size relationship between the building modeling object and the building modeling scene represents the positioning size text information of the target building modeling object and the building modeling scene and the text information of the shape and size of the target building modeling object.

[0037] Preferably, based on the text data of the modeling requirements for the position, shape, and size relationship between the building modeling object and the building modeling scene and the building modeling control instruction data with different modeling requirements, the operation steps for screening and searching the BIM building modeling control instructions to generate the target building modeling control instruction data are as follows:

[0038] S61. Establish a set of building modeling control instruction data with different modeling requirements , ; where represents the building modeling control instruction data with different modeling requirements corresponding to the th type of building modeling requirement feature combination type. The building modeling requirement feature combination type represents an index data type formed by combining the positioning size text information of the target building modeling object and the building modeling scene and the text information of the shape and size of the target building modeling object for searching the building modeling control instructions; the building modeling control instruction data with different modeling requirements represents the building modeling control instruction information of the BIM building modeling software set according to different building modeling requirement feature combination types.

[0039] S62, using the Rabin-Karp search algorithm to search the text data of the relationship between the building modeling object and the building modeling scene position, shape and size modeling requirements Building modeling control instruction data set with different modeling requirements Building modeling control instruction data for different modeling requirements described in Match the architectural modeling requirement feature information and search for the architectural modeling object and the architectural modeling scene position, shape, size relationship modeling requirement text data Corresponding to the different modeling requirements of building modeling control instruction data , and after data identification, the target building modeling control instruction data .

[0040] Preferably, the steps of constructing the BIM building modeling summary data and executing the BIM building modeling operation are as follows:

[0041] S71: The target building modeling object three-dimensional model data , the target building modeling control instruction data Construct BIM building modeling summary data through data combination identification ,in ;

[0042] S72, summarizing the BIM building modeling data The three-dimensional model data of the target building modeling object Import the 3D model data of the building modeling scene into the BIM building modeling software Running in the same building modeling space, the BIM building modeling software follows the target building modeling control instruction data Modeling is performed on the spatial position of the target building modeling object and the building modeling scene, as well as the spatial shape of the target building modeling object.

[0043] A BIM intelligent building modeling system based on a large language model, used to implement the BIM intelligent building modeling method based on a large language model, the system comprising a BIM building modeling object analysis module, a BIM building modeling instruction analysis module, and a BIM building modeling execution module;

[0044] The BIM building modeling object analysis module includes a building modeling object feature information acquisition unit, a different type of building modeling object feature information storage unit, a building modeling object type analysis unit, a different type of building modeling object three-dimensional model storage unit, and a building modeling object three-dimensional model search unit;

[0045] The building modeling object feature information acquisition unit collects the building modeling object feature text data through the voice input module; the different type building modeling object feature information storage unit is used to store the different type building modeling object feature text data; the building modeling object type analysis unit performs BIM building modeling object type analysis and processing based on the building modeling object feature text data in combination with the intelligent large language model and the different type building modeling object feature text data, and generates building modeling object type analysis data; the different type building modeling object three-dimensional model storage unit is used to store the different type building modeling object three-dimensional model data; the building modeling object three-dimensional model search unit performs BIM building modeling object three-dimensional model search processing according to the building modeling object type analysis data and the different type building modeling object three-dimensional model data, and generates the target building modeling object three-dimensional model data;

[0046] The BIM building modeling instruction analysis module includes a building modeling object three-dimensional image information acquisition unit, a building modeling scene three-dimensional model acquisition unit, a building modeling scene three-dimensional image information acquisition unit, a building modeling object and building modeling scene position shape size three-dimensional image information acquisition unit, a building modeling object and building modeling scene position shape size modeling requirement text information generation unit, a different modeling requirement building modeling control instruction storage unit, and a building modeling control instruction screening unit;

[0047] The three-dimensional image information acquisition unit of the building modeling object acquires three-dimensional image data of the building modeling object through screenshot software; the three-dimensional model acquisition unit of the building modeling scene acquires three-dimensional model data of the building modeling scene through BIM building modeling software; the three-dimensional image information acquisition unit of the building modeling scene acquires three-dimensional image data of the building modeling scene through screenshot software; the three-dimensional image information acquisition unit of the position, shape and size of the building modeling object and the building modeling scene acquires three-dimensional image data of the relationship between the position, shape and size of the building modeling object and the building modeling scene through a brain-computer interface device; the text information generation unit for the modeling requirements of the position, shape and size of the building modeling object and the building modeling scene performs identification and processing on the text information of the modeling requirements for the spatial position and size of the building modeling object and the building modeling scene and the shape and size of the building modeling object based on the three-dimensional image data of the building modeling object, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the relationship between the position, shape and size of the building modeling object and the building modeling scene in combination with an intelligent large language model, and generates text data of the modeling requirements for the relationship between the position, shape and size of the building modeling object and the building modeling scene; the storage unit for building modeling control instructions with different modeling requirements is used to store data of building modeling control instructions with different modeling requirements; the building modeling control instruction screening unit performs screening and search processing on BIM building modeling control instructions according to the text data of the modeling requirements for the relationship between the position, shape and size of the building modeling object and the building modeling scene and the data of building modeling control instructions with different modeling requirements, and generates target building modeling control instruction data;

[0048] The BIM building modeling execution module includes a BIM building modeling information construction unit and a BIM building modeling operation execution unit;

[0049] The BIM building modeling information construction unit constructs BIM building modeling summary data based on the three-dimensional model of the target building modeling object and the target building modeling control instruction in combination with data processing; the BIM building modeling operation execution unit performs BIM building modeling operations according to the BIM building modeling summary data and in combination with BIM building modeling software.

[0050] (III) Beneficial effects

[0051] The present invention provides a BIM intelligent building modeling method and system based on a large language model. It has the following beneficial effects:

[0052] 1. Through the building modeling object feature information acquisition unit, the voice input module is used to quickly and accurately obtain the feature information of the target building modeling object, providing reliable data support for efficient BIM building modeling; the building modeling object type analysis unit, based on the building modeling object feature information, combines the intelligent large language model and the scientifically preset feature information of different types of building modeling objects to conduct efficient and intelligent analysis of the BIM building modeling object types, realizing the efficient and accurate identification of building component, main structure, and mechanical and electrical equipment object types in BIM building modeling based on the large language model; the building modeling object 3D model search unit, according to the building modeling object type analysis results, combines the intelligent recognition algorithm and the 3D model information of different types of building modeling objects stored based on big data to conduct intelligent search of the BIM building modeling object 3D model, realizing the scientific and efficient generation of the BIM building modeling object 3D structure based on the designer's natural language, and improving the efficiency of BIM building modeling.

[0053] 2. Through the mutual cooperation among the building modeling object 3D image information acquisition unit, the building modeling scene 3D model acquisition unit, the building modeling scene 3D image information acquisition unit, and the building modeling object and building modeling scene position shape size 3D image information acquisition unit, the dynamic and scientific acquisition of the target building modeling object 3D image information, the building modeling scene 3D model information, the building modeling scene 3D image information, and the 3D information of the position, shape, and size relationship between the target building modeling object and the building modeling scene is realized, providing reliable data support for accurate and efficient BIM building modeling; the building modeling object and building modeling scene position shape size modeling requirement text information generation unit, based on the intelligent large language model, conducts intelligent translation of the modeling requirement text information of the spatial position and size between the building modeling object and the building modeling scene and the shape and size of the building modeling object, realizing the scientific and standard generation of the building modeling object and building modeling scene position shape size relationship modeling requirement text information based on the designer's design concept; the building modeling control instruction screening unit, based on the building modeling object and building modeling scene position shape size relationship modeling requirement text data, combines the intelligent search algorithm and the building modeling control instructions for different modeling requirements stored in the standard to conduct intelligent matching of the BIM building modeling control instructions, realizing the intelligent and precise selection of the BIM building modeling control instructions based on the designer's natural language and design concept, and realizing the intelligent BIM building modeling.

[0054] 3. Through the mutual cooperation of the BIM building modeling information construction unit and the BIM building modeling operation execution unit, based on the target building modeling object 3D model information and the target building modeling control instruction information, the BIM building modeling summary information is autonomously and efficiently constructed by combining data processing, and at the same time, the BIM building modeling operation is dynamically and accurately executed in combination with the BIM building modeling software, realizing the dynamic and intelligent BIM building modeling based on the designer's natural language and design concept image information, and improving the accuracy and applicability of BIM building modeling. Brief Description of the Drawings

[0055] Figure 1 It is a schematic diagram of the modules of a BIM intelligent building modeling system based on a large language model provided by the present invention;

[0056] Figure 2 It is a flowchart of a BIM intelligent building modeling method based on a large language model provided by the present invention. Detailed Embodiments

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0058] Embodiments of the BIM intelligent building modeling method and system based on a large language model are as follows:

[0059] Embodiment 1:

[0060] Please refer to Figure 1 - Figure 2 , a BIM intelligent building modeling method based on a large language model, the method includes the following steps:

[0061] S1. Collect the characteristic text data of the building modeling object;

[0062] S2. Analyze and process the BIM building modeling object type based on the characteristic text data of the building modeling object and the characteristic text data of different types of building modeling objects to generate building modeling object type analysis data;

[0063] S3. Perform a 3D model search process on the BIM building modeling object according to the building modeling object type analysis data and the 3D model data of different types of building modeling objects to generate the 3D model data of the target building modeling object;

[0064] S4. Collect the 3D image data of the building modeling object, the 3D model data of the building modeling scene, the 3D image data of the building modeling scene, and the 3D image data of the position, shape, and size relationship between the building modeling object and the building modeling scene;

[0065] S5. Identify and process the text information of the modeling requirements for the spatial position and dimensions of the building modeling object and the building modeling scene, as well as the shape and dimensions of the building modeling object, based on the 3D image data of the building modeling object, the 3D image data of the building modeling scene, and the 3D image data of the positional, shape, and dimensional relationships between the building modeling object and the building modeling scene, and generate the text data of the modeling requirements for the positional, shape, and dimensional relationships between the building modeling object and the building modeling scene;

[0066] S6. Screen and search the BIM building modeling control instructions based on the text data of the modeling requirements for the positional, shape, and dimensional relationships between the building modeling object and the building modeling scene and the building modeling control instruction data for different modeling requirements, and generate the target building modeling control instruction data;

[0067] S7. Construct the BIM building modeling summary data and execute the BIM building modeling operation.

[0068] Furthermore, please refer to Figure 1 - Figure 2 , and the operation steps for collecting the text data of the building modeling object features are as follows:

[0069] S11. Online collect the text information of the features of the specific BIM building modeling object described by the designer through the voice input module, and generate the text data of the building modeling object features .

[0070] The operation steps for analyzing the type of the BIM building modeling object based on the text data of the building modeling object features and the text data of the features of different types of building modeling objects to generate the analysis data of the building modeling object type are as follows:

[0071] S21. Establish a set of text data of the features of different types of building modeling objects , ; where represents the text data of the features of different types of building modeling objects corresponding to the th type of BIM building modeling object type, represents the maximum value of the number of BIM building modeling object types; the BIM building modeling object types include walls, floors, doors and windows, roofs, stairs, railings, beams, columns, slabs, shear walls, pile foundations, pipes, valves, and pumps; the text data of the features of different types of building modeling objects represents the standard text information of the features of the building modeling objects set for different types of BIM building modeling objects;

[0072] S22. Use the intelligent large language model to compare the text data of the building modeling object features with the text data of the features of different types of building modeling objects in the set of text data of the features of different types of building modeling objects ​Perform building modeling feature character matching to search for building modeling object feature text data that matches different types of building modeling object feature text data The corresponding building modeling object type text information is obtained, and building modeling object type analysis data is constructed The intelligent large language model includes any one of DeepSeekV3, Alibaba Tongyi Qianwen Qwen2.5, and Tencent Hunyuan Turbo

[0073] The operation steps for performing 3D model search processing on BIM building modeling objects based on building modeling object type analysis data and 3D model data of different types of building modeling objects to generate target building modeling object 3D model data are as follows:

[0074] S31. Establish a set of 3D model data for different types of building modeling objects where represents the 3D model data of different types of building modeling objects corresponding to the th type of BIM building modeling object. The different types of building modeling object feature text data represent the standard building modeling 3D entity data set for different types of BIM building modeling objects;

[0075] S32. Perform building modeling object type keyword matching on the building modeling object type analysis data and the 3D model data of different types of building modeling objects in the set of 3D model data of different types of building modeling objects to search for the 3D model data of different types of building modeling objects corresponding to the building modeling object type analysis data and construct the target building modeling object 3D model data The specific operation steps for generating the target building modeling object 3D model data are as follows:

[0076] S321. Initialize all the 3D model data of different types of building modeling objects in the search space of the set of 3D model data of different types of building modeling objects as nectar sources ; at the same time, initialize the number of nectar sources as , the current iteration number t, the maximum iteration number T, and the initial position of the nectar source . The calculation formula for the initial position is as follows: In the set of 3D model data of different types of building modeling objects ​​​Randomly generated in the search space, where represents a random number within and respectively represent the upper and lower bounds of the search space of the three-dimensional model data sets of different types of building modeling objects ;

[0077] S322. Assign employed bees to the initial position At the beginning of the search, the employed bees are in the search space of the three-dimensional model data sets of different types of building modeling objects surrounding the initial position formed by all the three-dimensional model data of different types of building modeling objects According to the formula in the search space of the three-dimensional model data sets of different types of building modeling objects search for and generate different types of building modeling object three-dimensional model data matching the building modeling object type analysis data new nectar source position ; where represents randomly selecting a nectar source not equal to i from nectar sources, represents the randomly selected nectar source in the search space of the three-dimensional model data sets of different types of building modeling objects position, represents a random number in the range [-1, 1];

[0078] S323. Based on the fitness value of the new nectar source position determine the retained nectar sources according to the method of greedy selection, and retain the different types of building modeling object three-dimensional model data matching the building modeling object type analysis data ;

[0079] S324. The employed bees share the nectar source information, and the follower bees search for different types of building modeling object three-dimensional model data in the search space of the three-dimensional model data sets of different types of building modeling objects according to the probability value, and the follower bees search for different types of building modeling object three-dimensional model data matching the building modeling object type analysis data according to the search results shared by the employed bees, and calculate the probability that the nectar source found by the employed bees is followed by the follower bees according to the probability formula. The probability calculation formula is as follows: , where and represents the new nectar source position The probability that the employed bee finds the one being followed, indicating the fitness value of the follower bee based on the new nectar source location shared by the employed bee ;

[0080] S325. The follower bee conducts searches in the same way as the employed bee, and searches for 3D model data of different types of building modeling objects that match the building modeling object type analysis data in the search space of the 3D model data set of different types of building modeling objects and retains it; nectar source ;

[0081] S326. During the random search process of the scout bee in the search space of the 3D model data set of different types of building modeling objects, if the nectar source location has not found a better nectar source after t iterations of search reaching the iteration threshold , this nectar source location will be abandoned, and the corresponding employed bee will become a scout bee; the calculation formula for the scout bee to randomly generate a new nectar source location in the search space is as follows: , where represents generating a new nectar source after iterations at the position in the search space of the 3D model data set of different types of building modeling objects ; represents generating a new nectar source after t iterations at the position in the search space of the 3D model data set of different types of building modeling objects ; ;

[0082] S327. When the algorithm meets the maximum number of iterations T, it outputs 3D model data of different types of building modeling objects that match the building modeling object type analysis data and generates the 3D model data of the target building modeling object through data identification . .

[0083] Through the building modeling object feature information acquisition unit, the voice input module is used to quickly and accurately obtain the feature information of the target building modeling object, providing reliable data support for efficient BIM building modeling; the building modeling object type analysis unit combines the intelligent large language model with the feature information of different types of building modeling objects preset scientifically according to the building modeling object feature information to conduct efficient and intelligent analysis of the BIM building modeling object types, realizing the efficient and accurate identification of building component, main structure, and mechanical and electrical equipment object types in BIM building modeling based on the large language model; the building modeling object three-dimensional model search unit combines the intelligent recognition algorithm with the three-dimensional model information of different types of building modeling objects stored based on big data according to the analysis result of the building modeling object type to conduct intelligent search for the three-dimensional model of the BIM building modeling object, realizing the scientific and efficient generation of the three-dimensional structure of the BIM building modeling object based on the natural language of the designer and improving the efficiency of BIM building modeling.

[0084] Further, please refer to Figure 1 - Figure 2 , the operation steps for collecting three-dimensional image data of the building modeling object, three-dimensional model data of the building modeling scene, three-dimensional image data of the building modeling scene, and three-dimensional image data of the position, shape, and size relationship between the building modeling object and the building modeling scene are as follows:

[0085] S41. Import the three-dimensional model data of the target building modeling object into the BIM building modeling software for operation, and cooperate with the screenshot software to collect the axonometric drawing of the target building modeling object, and generate three-dimensional image data of the building modeling object ; The BIM building modeling software includes any one of Autodesk Revit, ArchiCAD, and Bentley Systems, and the screenshot software includes any one of the screenshot tools built in Windows, Snipasteh, and Jinzhou Screenshot Software;

[0086] Obtain the three-dimensional entity information of the building modeling scene of the modeling design assembly object serving as the target building modeling object online through the BIM building modeling software, and generate three-dimensional model data of the building modeling scene ;

[0087] Obtain the axonometric drawing of the building modeling scene three-dimensional model data corresponding to the building modeling scene in the BIM building modeling software online through the screenshot software, and generate three-dimensional image data of the building modeling scene ;

[0088] Online synchronously collect the designer's positioning dimension design concepts regarding the target building modeling object and the spatial position of the building modeling scene through a brain-computer interface device, as well as the shape dimension design concepts of the target building modeling object, form three-dimensional image information of the position dimension annotation and shape dimension annotation of the building modeling object, and generate three-dimensional image data of the position and shape dimension relationship between the building modeling object and the building modeling scene , the brain-computer interface device includes any one of the Neuralink brain-computer interface, the Beibrain-1 system, and the mixed reality brain-computer interface system.

[0089] Based on the three-dimensional image data of the building modeling object, the three-dimensional image data of the building modeling scene, and the three-dimensional image data of the position and shape dimension relationship between the building modeling object and the building modeling scene, perform identification and processing on the text information of the spatial position dimensions of the building modeling object and the building modeling scene and the shape dimensions of the building modeling object, and the operation steps for generating the text data of the modeling requirements for the position and shape dimension relationship between the building modeling object and the building modeling scene are as follows:

[0090] S51. Import the three-dimensional image data of the building modeling object , the three-dimensional image data of the building modeling scene , and the three-dimensional image data of the position and shape dimension relationship between the building modeling object and the building modeling scene into the intelligent large language model respectively. The intelligent large language model performs identification and processing on the text information of the spatial position dimensions of the target building modeling object and the building modeling scene and the text information of the shape dimensions of the target building modeling object based on the image information, and generates the text data of the modeling requirements for the position and shape dimension relationship between the building modeling object and the building modeling scene , and the text data of the modeling requirements for the position and shape dimension relationship between the building modeling object and the building modeling scene represents the positioning dimension text information of the target building modeling object and the building modeling scene and the shape dimension text information of the target building modeling object.

[0091] Based on the text data of the modeling requirements for the position and shape dimension relationship between the building modeling object and the building modeling scene and the building modeling control instruction data with different modeling requirements, perform screening and search processing on the BIM building modeling control instructions, and the operation steps for generating the target building modeling control instruction data are as follows:

[0092] S61. Establish a set of building modeling control instruction data with different modeling requirements , ; where represents the Different building modeling control instruction data corresponding to different combinations of building modeling requirement characteristics, where the combination type of building modeling requirement characteristics represents an index data type formed by combining the positioning dimension text information of the target building modeling object and the building modeling scene, as well as the shape dimension text information of the target building modeling object for searching building modeling control instructions; different building modeling control instruction data for different modeling requirements represents the building modeling control instruction information of the BIM building modeling software set according to different combinations of building modeling requirement characteristics.

[0093] S62. Use the Rabin-Karp search algorithm to model the text data of the relationship between the position and shape dimensions of the building modeling object and the building modeling scene and the set of different building modeling control instruction data for different modeling requirements in the different building modeling control instruction data for different modeling requirements to perform matching of building modeling requirement feature information, and search for the different building modeling control instruction data corresponding to the text data of the relationship between the position and shape dimensions of the building modeling object and the building modeling scene and identify the target building modeling control instruction data through data . .

[0094] Through the mutual cooperation between the three-dimensional image information acquisition unit of the building modeling object, the three-dimensional model acquisition unit of the building modeling scene, the three-dimensional image information acquisition unit of the building modeling scene, and the three-dimensional image information acquisition unit of the position and shape dimensions of the building modeling object and the building modeling scene, dynamic and scientific acquisition of the three-dimensional image information of the target building modeling object, the three-dimensional model information of the building modeling scene, the three-dimensional image information of the building modeling scene, and the three-dimensional information of the relationship between the position and shape dimensions of the target building modeling object and the building modeling scene is realized, providing reliable data support for accurate and efficient BIM building modeling; the text information generation unit for the position and shape dimensions of the building modeling object and the building modeling scene, based on the intelligent large language model, performs intelligent translation of the text information of the modeling requirements for the spatial position dimensions of the building modeling object and the building modeling scene and the shape dimensions of the building modeling object, and realizes the scientific and standard generation of the text information of the relationship between the position and shape dimensions of the building modeling object and the building modeling scene based on the design concept of the designer; the building modeling control instruction screening unit, based on the text data of the relationship between the position and shape dimensions of the building modeling object and the building modeling scene, combines the intelligent search algorithm and the different building modeling control instructions stored in the standard to perform intelligent matching of the BIM building modeling control instructions, realizes the intelligent and accurate selection of the BIM building modeling control instructions based on the natural language of the designer and the design concept of the designer, and realizes the intelligent BIM building modeling.

[0095] Furthermore, please refer toFigure 1 - Figure 2 The operation steps for constructing the BIM building modeling summary data and executing the BIM building modeling operations are as follows:

[0096] S71. Combine the 3D model data of the target building modeling object and the target building modeling control instruction data to construct the BIM building modeling summary data through data combination identification where ;

[0097] S72. Import the 3D model data of the target building modeling object in the BIM building modeling summary data into the BIM building modeling software to run in the same building modeling space as the 3D model data of the building modeling scene . The BIM building modeling software performs modeling operations on the spatial positions of the target building modeling object and the building modeling scene, as well as the spatial shape of the target building modeling object, according to the target building modeling control instruction data . The BIM building modeling information construction unit and the BIM building modeling operation execution unit cooperate with each other to autonomously and efficiently construct the BIM building modeling summary information based on the 3D model information of the target building modeling object and the target building modeling control instruction information combined with data processing. At the same time, combined with the BIM building modeling software, the BIM building modeling operations are dynamically and accurately executed, realizing dynamic and intelligent BIM building modeling based on the natural language of designers and the design concept image information, and improving the accuracy and applicability of BIM building modeling.

[0098] Example 2:

[0099] Please refer to

[0100] - Figure 1 - Figure 2 A BIM intelligent building modeling system based on a large language model for implementing a BIM intelligent building modeling method based on a large language model. The system includes a BIM building modeling object analysis module, a BIM building modeling instruction analysis module, and a BIM building modeling execution module;

[0101] The BIM building modeling object analysis module includes a building modeling object feature information collection unit, a storage unit for feature information of different types of building modeling objects, a building modeling object type analysis unit, a storage unit for 3D models of different types of building modeling objects, and a 3D model search unit for building modeling objects;

[0102] The building modeling object feature information collection unit collects the building modeling object feature text data through the voice input module; the different types of building modeling object feature information storage unit is used to store the building modeling object feature text data of different types; the building modeling object type analysis unit performs BIM building modeling object type analysis and processing based on the building modeling object feature text data in combination with the intelligent large language model and the building modeling object feature text data of different types, and generates building modeling object type analysis data; the different types of building modeling object three-dimensional model storage unit is used to store the building modeling object three-dimensional model data of different types; the building modeling object three-dimensional model search unit performs three-dimensional model search processing of the BIM building modeling object according to the building modeling object type analysis data and the building modeling object three-dimensional model data of different types, and generates the target building modeling object three-dimensional model data;

[0103] The BIM building modeling instruction analysis module includes a building modeling object three-dimensional image information collection unit, a building modeling scene three-dimensional model collection unit, a building modeling scene three-dimensional image information collection unit, a building modeling object and building modeling scene position shape size three-dimensional image information collection unit, a building modeling object and building modeling scene position shape size modeling requirement text information generation unit, a different modeling requirement building modeling control instruction storage unit, and a building modeling control instruction screening unit;

[0104] The building modeling object three-dimensional image information collection unit collects the building modeling object three-dimensional image data through screenshot software; the building modeling scene three-dimensional model collection unit collects the building modeling scene three-dimensional model data through BIM building modeling software; the building modeling scene three-dimensional image information collection unit collects the building modeling scene three-dimensional image data through screenshot software; the building modeling object and building modeling scene position shape size three-dimensional image information collection unit collects the three-dimensional image data of the relationship between the building modeling object and the building modeling scene position shape size through a brain-computer interface device; the building modeling object and building modeling scene position shape size modeling requirement text information generation unit performs recognition processing of the modeling requirement text information of the spatial position and size of the building modeling object and the building modeling scene and the shape and size of the building modeling object based on the building modeling object three-dimensional image data, the building modeling scene three-dimensional image data, and the three-dimensional image data of the relationship between the building modeling object and the building modeling scene position shape size in combination with the intelligent large language model, and generates the building modeling object and building modeling scene position shape size relationship modeling requirement text data; the different modeling requirement building modeling control instruction storage unit is used to store the different modeling requirement building modeling control instruction data; the building modeling control instruction screening unit performs BIM building modeling control instruction screening and search processing based on the building modeling object and building modeling scene position shape size relationship modeling requirement text data and the different modeling requirement building modeling control instruction data, and generates the target building modeling control instruction data;

[0105] The BIM building modeling execution module includes a BIM building modeling information construction unit and a BIM building modeling operation execution unit;

[0106] The BIM building modeling information construction unit constructs BIM building modeling summary data based on the three-dimensional model of the target building modeling object, the target building modeling control instruction, and data processing; the BIM building modeling operation execution unit executes the BIM building modeling operation according to the BIM building modeling summary data and in combination with the BIM building modeling software.

[0107] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A BIM intelligent building modeling method based on large language models, characterized in that, The method includes the following steps: S1. Collect characteristic text data of building modeling objects; S1 includes the following steps: S11. Online collect the feature description text information of the specific BIM building modeling object through the voice input module, and generate the building modeling object feature text data ; S2. Conduct BIM building modeling object type analysis and processing to generate building modeling object type analysis data; S3. Conduct 3D model search processing of BIM building modeling objects to generate 3D model data of target building modeling objects; S4. Collect 3D image data of building modeling objects, 3D model data of building modeling scenes, 3D image data of building modeling scenes, and 3D image data of the positional shape and size relationship between building modeling objects and building modeling scenes; S5. Conduct identification and processing of modeling requirement text information on the spatial position and size of building modeling objects and building modeling scenes and the shape and size of building modeling objects to generate modeling requirement text data on the positional shape and size relationship between building modeling objects and building modeling scenes; S6. Conduct BIM building modeling control instruction screening and search processing to generate target building modeling control instruction data; S7. Construct BIM building modeling summary data and execute BIM building modeling operations.

2. The BIM intelligent building modeling method based on a large language model according to claim 1, characterized in that: S2 includes the following steps: S21. Establish a collection of characteristic text data for building modeling objects of different types , ; where represents the characteristic text data of different types of building modeling objects corresponding to the th type of BIM building modeling object type, represents the maximum value of the number of BIM building modeling object types; S22. Use an intelligent large language model to with the described in the perform building modeling feature character matching, and search for the matched corresponding building modeling object type text information, and construct building modeling object type analysis data .

3. The BIM intelligent building modeling method based on a large language model according to claim 2, wherein: S3 includes the following steps: S31. Establish a three-dimensional model data set of building modeling objects of different types , where represents the three-dimensional model data of different types of building modeling objects corresponding to the th type of BIM building modeling object type; S32. Match the with the described in the for building modeling object type keyword matching, search for the corresponding , and construct the three-dimensional model data of the target building modeling object . The specific operation steps for generating the three-dimensional model data of the target building modeling object are as follows: S321. Initialize all the in the search space of as nectar sources ; meanwhile, initialize the number of nectar sources as , the current iteration number t, the maximum iteration number T, and the initial position of the nectar source ; S322. It is the initial position Allocate employed bees. At the beginning of the search, the employed bees are in the search space and around the initial position formed by all the . In the search space of , search for and generate a new nectar source position that matches the ; new nectar source position ;​ S323. According to the fitness value of the new nectar source location , determine the nectar sources to be retained according to the method of greedy selection, and retain the ones that match the ; ​ S324. Employed bees share nectar source information, and follower bees search for the in the search space according to the probability value, and follower bees search for the based on the search results shared by the employed bees, and calculate the probability that the nectar source found by the employed bees is followed; matching the ​ S325. The follower bees search in the same way as the employed bees, and search for the nectar source that matches the in the search space of the according to the greedy selection method and retain it; in the search space of the to match the nectar source and retain it; S326. During the random search of the scout bee in the search space, if the nectar source location has not found a better nectar source after t iterations of search reaching the iteration threshold , the nectar source location will be abandoned, and the employed bee corresponding to it will become a scout bee; the scout bee randomly generates a new nectar source location in the search space; S327. When the algorithm meets the maximum number of iterations T, output the that matches the , and generate the 3D model data of the target building modeling object through data identification .

4. The BIM intelligent building modeling method based on a large language model according to claim 3, wherein: S4 includes the following steps: S41. Import the into the BIM building modeling software for operation, and cooperate with the screenshot software to collect the axonometric drawing of the target building modeling object, and generate the three-dimensional image data of the building modeling object ; Online obtain the 3D entity information of the building modeling scene of the modeling design and assembly object that is the target building modeling object through BIM building modeling software, and generate the 3D model data of the building modeling scene ; Obtain the corresponding axonometric drawing of the building modeling scene in the BIM building modeling software, and generate three-dimensional image data of the building modeling scene ; Online synchronously collect, through a brain-computer interface device, the designer's design concepts for the positioning dimensions of the target building modeling object and the spatial position of the building modeling scene, as well as the design concepts for the shape and dimensions of the target building modeling object, to form three-dimensional image information of the position and dimension markings and shape and dimension markings of the building modeling object, and generate three-dimensional image data on the position, shape, and dimension relationship between the building modeling object and the building modeling scene .

5. The BIM intelligent building modeling method based on a large language model according to claim 4, characterized in that: S5 includes the following steps: S51. Import the , the , and the into the intelligent large language model respectively. The intelligent large language model performs recognition and processing on the spatial position dimension text information of the target building modeling object and the building modeling scene, as well as the shape dimension text information of the target building modeling object according to the image information, and generates the modeling requirement text data of the position, shape, and dimension relationship between the building modeling object and the building modeling scene .

6. The BIM intelligent building modeling method based on a large language model according to claim 5, characterized in that: S6 includes the following steps: S61. Establish a data set of building modeling control instructions for different modeling requirements , ; where represents different building modeling control instructions for the th combination type of building modeling requirement features; S62. Using the Rabin-Karp search algorithm to match the with the described in the for building modeling requirement feature information matching, and searching for the corresponding , and passing through the data identification target building modeling control instruction data .

7. A BIM intelligent building modeling method based on a large language model according to claim 6, characterized in that: S7 includes the following steps: S71. Combine the and the through data combination identification to construct BIM building modeling summary data ; S72. Import the described in into the BIM building modeling software to run in the same building modeling space. The BIM building modeling software performs modeling operations on the spatial positions of the target building modeling objects and the building modeling scene, as well as the spatial shapes of the target building modeling objects, according to the target building modeling control instruction data ​ 8. A BIM intelligent building modeling system based on a large language model, which is used to implement a BIM intelligent building modeling method according to any one of claims 1-7, and is characterized in that: The system includes a BIM building modeling object analysis module, a BIM building modeling instruction analysis module, and a BIM building modeling execution module.

Images