BIM parametric modeling method and system, computer equipment and storage medium

Abstract

The invention discloses a BIM parametric modeling method and system, computer equipment and a storage medium, and the method comprises the following steps: receiving a natural language modeling instruction input by a user, extracting key modeling information based on a natural language processing technology of a large language model, and obtaining a modeling demand of the user; performing deep understanding and task decomposition on a natural language modeling instruction input by a user, decomposing an overall modeling task into executable sub-tasks, and determining an association relationship and an execution sequence among the sub-tasks; based on the code template library and the code writing capability of the large language model, generating script codes of parametric modeling according to the structured modeling step; the generated footstep code is verified; if the verification is passed, executing the verified parameterized modeling script, and generating a BIM model; according to the method, automatic generation from the natural language instruction to the editable BIM model can be realized, and the BIM modeling threshold is remarkably reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of building information modeling, and in particular to a BIM parametric modeling method, system, computer equipment and storage medium. Background Art

[0002] Existing BIM (Building Information Modeling) modeling technologies mainly include three methods: traditional manual modeling, laser scanning modeling, and CAD drawing recognition modeling. Among them, the traditional manual modeling method relies on designers to manually operate BIM software, which not only requires the mastery of complex software functions and modeling commands, but also has low modeling efficiency, is prone to errors, and has obvious obstacles in cross-disciplinary collaboration. Although laser scanning modeling is suitable for rapid modeling of large-scale areas, it lacks the expressiveness of internal components of buildings, and the accuracy and integrity of the generated models are limited, making later editing difficult. CAD drawing recognition modeling requires high-quality CAD drawings as input, and its recognition accuracy is heavily dependent on the quality of the drawings. The degree of automation is not high, and a lot of manual intervention is still required.

[0003] These existing technologies generally have the following shortcomings: first, the technical threshold is high, and professionals need to undergo long-term training to master complex software operations, and the learning cost is high; second, the collaborative efficiency is low, and model deviations often occur in the process of cross-disciplinary cooperation, making it difficult to ensure data consistency; third, the model quality problem is prominent, which is manifested in insufficient accuracy and integrity, low degree of standardization, and poor editability; finally, the scalability is limited, it is difficult to flexibly adapt to new modeling needs, lacks continuous learning ability, and the level of intelligence is insufficient. These problems have seriously restricted the promotion and application of BIM technology in engineering practice. Summary of the invention

[0004] The purpose of the present invention is to provide a BIM parametric modeling method, system, computer equipment and storage medium, which can realize the automatic generation of editable BIM models from natural language instructions, and significantly reduce the threshold of BIM modeling.

[0005] To achieve this object, the present invention adopts the following technical solutions: A BIM parametric modeling method based on a large language model is provided, comprising the following steps: S1: Receive natural language modeling instructions input by users and extract key modeling information based on natural language processing technology of large language models to obtain user modeling requirements; S2: judging whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; S3: If yes, then deeply understand and decompose the natural language modeling instructions input by the user, decompose the overall modeling task into executable subtasks, and clarify the relationship and execution order between the subtasks; S4: If not, output corresponding suggestive natural language according to the missing necessary parameters; S5: receiving a natural language supplementary instruction input by the user according to the suggestive natural language and extracting supplementary modeling information based on the natural language processing technology of the large language model; S6: judging whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; S7: If not, return to step S4; S8: If yes, execute step S3; S9: Based on the code template library and the code writing capability of the large language model, the script code for parameterized modeling is generated according to the structured modeling steps; S10: Verify the generated script code; S11: If the verification fails, return to step S9; S12: If the verification is passed, the verified parametric modeling script is executed to generate a BIM model.

[0006] As a preferred solution of the BIM parametric modeling method based on the large language model, after the step S12 of executing the verified parametric modeling script to generate the BIM model if the verification is passed, the method includes: S13: After the script code that has passed the verification is structurally processed according to the characteristics of the basic code script library, it is added to the code template library.

[0007] As a preferred solution of the BIM parametric modeling method based on the large language model, the step S10 of verifying the generated step code includes: S101: Conduct code review, where the code review includes: syntax check, logic check and style check; S102: Execute test: run the code and output the test results.

[0008] The present invention also provides a BIM parametric modeling system based on a large language model, comprising: An analysis and extraction module is used to receive natural language modeling instructions input by users and extract key modeling information based on natural language processing technology of large language models to obtain user modeling requirements; A judgment module, used to judge whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; The planning module is used to deeply understand and decompose the natural language modeling instructions input by the user, decompose the overall modeling task into executable subtasks, and clarify the relationship and execution order between the subtasks; A prompt module, used for outputting corresponding prompt natural language according to the missing necessary parameters; The analysis and extraction module is further used to receive the natural language supplementary instruction input by the user according to the suggestive natural language and extract the supplementary modeling information based on the natural language processing technology of the large language model; The judgment module is further used to judge whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; Program module, used to generate script code for parametric modeling according to structured modeling steps based on the code template library and the code writing capability of the large language model; Check module, used to verify the generated script code; The execution module is used to execute the verified parametric modeling script to generate a BIM model.

[0009] As a preferred solution of the BIM parametric modeling system based on the large language model, it also includes: The storage module is used to add the script code that has passed the verification to the code template library after structural processing according to the characteristics of the basic code script library.

[0010] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the BIM parametric modeling method based on a large language model as described in any one of the above items when executing the computer program.

[0011] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps of the BIM parametric modeling method based on a large language model as described in any one of the above items are implemented.

[0012] Beneficial effects of the invention: The BIM parametric modeling method, system, computer equipment and storage medium proposed in the invention can realize the automatic generation of editable BIM models from natural language instructions. The natural language interaction mode enables users to complete modeling tasks without having to master the modeling operation skills of complex BIM software, which significantly reduces the threshold of BIM modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1It is a flow chart of a BIM parametric modeling method based on a large language model according to an embodiment of the present invention; Figure 2 It is a structural schematic block diagram of a BIM parametric modeling system based on a large language model according to an embodiment of the present invention; Figure 3 A schematic block diagram of the structure of a computer device according to an embodiment of the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0015] The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0016] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0017] Reference Figure 1 An embodiment of the present invention provides a BIM parametric modeling method based on a large language model, comprising the following steps: S1: receiving the natural language modeling instructions input by the user and extracting key modeling information based on the natural language processing technology of the large language model to obtain the user's modeling requirements; the key modeling information includes but is not limited to: Target component: The type of component the user wants to create, such as "wall", "door", "window", etc.

[0018] Geometry parameters: The geometric parameters of the component, such as length, width, height, radius, etc.

[0019] Position: The location information of the component, such as coordinates, direction, etc.

[0020] Others: Other modeling requirements, such as color, texture, material, etc.

[0021] S2: judging whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; S3: If yes, then the natural language modeling instructions input by the user are deeply understood and task-decomposed, the overall modeling task is decomposed into executable subtasks, and the relationship and execution order between the subtasks are clarified; the details are as follows: Decomposition steps: Decompose the natural language modeling instructions input by the user into a series of clear modeling steps. For example, the user instruction "create a wall with a window" can be decomposed into the steps of creating a wall, creating a window, and digging a window hole in the wall.

[0022] Select code snippet: Select the appropriate code snippet for each step; Determine parameters: Determine the parameter value of each step based on the natural language modeling instructions and parameter list of the code snippet input by the user; Output step list: Output the decomposed step list and parameter values.

[0023] S4: If not, output corresponding suggestive natural language according to the missing necessary parameters; the suggestive natural language specifically includes: Direct questions: You can ask questions directly to the user, such as: "What is the radius of the cylinder you want to create?" "How big do you mean by 'relatively large'?" "Do you want to create a cuboid or a square?" etc.; Provide options: You can provide some options for users to choose, such as: "Do you want to create a wall made of concrete, steel or wood?" "Do you want to create a window that opens in a sliding, casement or folding way?" etc. Example description: You can provide some examples to illustrate the information needed, such as: "For example, you can say 'Create a cylinder with a radius of 100mm and a height of 200mm'." "For example, you can say 'I want to create a concrete wall with a length of 5000mm and a thickness of 200mm'." etc. Confirm understanding: You can confirm with the user whether your understanding is correct, for example: "I understand that you want to create a cuboid with a length of 1000mm and a width of 500mm, right?" "You want to create a red cylinder, right?" S5: receiving a natural language supplementary instruction input by the user according to the suggestive natural language and extracting supplementary modeling information based on the natural language processing technology of the large language model; S6: judging whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; S7: If not, return to step S4; S8: If yes, execute step S3; S9: Based on the code template library and the code writing capability of the large language model, the script code for parametric modeling is generated according to the structured modeling steps; these scripts contain complete geometric information, parameter constraints and modeling operation instructions. This includes standardizing keywords, embedding them into word vectors, and performing multi-dimensional similarity matching in the historical BIM component code library to find the most relevant historical code fragments, including but not limited to: Functional similarity: How well the functionality of the code snippet matches the user's instructions.

[0024] Parameter similarity: the degree to which the parameters of the code snippet match the user's instructions.

[0025] Scenario similarity: the degree of match between the application scenario of the code snippet and the user instruction.

[0026] S10: Verify the generated script code; S11: If the verification fails, return to step S9; S12: If the verification is passed, the verified parametric modeling script is executed to generate an editable standardized BIM model that meets the requirements.

[0027] In the above embodiments, automatic generation from natural language instructions to editable BIM models is achieved. The natural language interaction method allows users to complete modeling tasks without having to master the modeling operation skills of complex BIM software, which significantly lowers the threshold for BIM modeling.

[0028] In some embodiments, after the step S12 of executing the verified parametric modeling script to generate the BIM model if the verification is passed, the following steps are included: S13: After the verified script code is structured according to the characteristics of the basic code script library, it is added to the code template library to expand the code template library. The Python script code of the verified historical BIM component is analyzed, classified according to the modeling functions and characteristics to be realized by the code, and key parameters and information are extracted to obtain a structured basic code script library. The basic code script library is stored in json format. According to the characteristics of parametric modeling, the json format entry template of the code library is designed.

[0029] In some embodiments, the step S10 of verifying the generated script code includes: S101: Conduct code review, where the code review includes: Syntax check: Check the code for syntax errors, such as spelling errors, mismatched brackets, etc. Logic check: Analyze the logic of the code, such as checking whether there are dead loops, undefined variables, etc.; Style check: Check whether the code style meets the standards, such as naming standards, code indentation, etc. S102: Execute test: run the code and output the test results.

[0030] Reference Figure 2 The present invention also provides a BIM parametric modeling system based on a large language model, comprising: An analysis and extraction module is used to receive natural language modeling instructions input by users and extract key modeling information based on natural language processing technology of large language models to obtain user modeling requirements; A judgment module, used to judge whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; The planning module is used to deeply understand and decompose the natural language modeling instructions input by the user, decompose the overall modeling task into executable subtasks, and clarify the relationship and execution order between the subtasks; A prompt module, used for outputting corresponding prompt natural language according to the missing necessary parameters; The analysis and extraction module is further used to receive the natural language supplementary instruction input by the user according to the suggestive natural language and extract the supplementary modeling information based on the natural language processing technology of the large language model; The judgment module is further used to judge whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; Program module, used to generate script code for parametric modeling according to structured modeling steps based on the code template library and the code writing capability of the large language model; Check module, used to verify the generated script code; The execution module is used to execute the verified parametric modeling script to generate a BIM model.

[0031] In some implementations, the BIM parametric modeling system based on the large language model further includes: The storage module is used to add the script code that has passed the verification to the code template library after structural processing according to the characteristics of the basic code script library.

[0032] Reference Figure 3 In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a storage medium and an internal memory. The storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store script codes, etc. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the BIM parametric modeling method based on the large language model described in any of the above embodiments can be implemented.

[0033] Those skilled in the art will understand that Figure 3 The structure shown in is merely a block diagram of a portion of the structure related to the present application solution and does not constitute a limitation on the computer device to which the present application solution is applied.

[0034] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the BIM parametric modeling method based on the large language model described in any of the above embodiments can be implemented.

[0035] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM). In the description of the present invention, it is necessary to understand that the terms "middle", "length", "up", "down", "front", "back", "vertical", "horizontal", "inside", "outside", "radial", "circumferential" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0036] In the present invention, unless otherwise clearly specified and limited, the first feature "on" the second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. "Multiple" means at least two, such as two, three, etc., unless otherwise clearly and specifically limited.

[0037] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection, an electrical connection, or communication with each other; it can be a direct connection, or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0038] The above is only for explaining the implementation mode of the present invention and is not intended to limit the present invention. For those skilled in the art, any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention without creative work should be included in the protection scope of the present invention.

Claims

1. A BIM parametric modeling method based on a large language model, characterized in that: The following steps are involved: S1: Receive natural language modeling instructions input by users and extract key modeling information based on natural language processing technology of large language models to obtain user modeling requirements; S2: judging whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; S3: If yes, then deeply understand and decompose the natural language modeling instructions input by the user, decompose the overall modeling task into executable subtasks, and clarify the relationship and execution order between the subtasks; S4: If not, output corresponding suggestive natural language according to the missing necessary parameters; S5: receiving a natural language supplementary instruction input by the user according to the suggestive natural language and extracting supplementary modeling information based on the natural language processing technology of the large language model; S6: judging whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; S7: If not, return to step S4; S8: If yes, execute step S3; S9: Based on the code template library and the code writing capability of the large language model, the script code for parameterized modeling is generated according to the structured modeling steps; S10: Verify the generated script code; S11: If the verification fails, return to step S9; S12: If the verification is passed, the verified parametric modeling script is executed to generate a BIM model.

2. The BIM parametric modeling method based on a large language model according to claim 1, characterized in that: After the step S12 of executing the verified parametric modeling script to generate the BIM model if the verification is passed, the following steps are included: S13: After the script code that has passed the verification is structurally processed according to the characteristics of the basic code script library, it is added to the code template library.

3. The BIM parametric modeling method based on a large language model according to claim 1, characterized in that: The step S10 of verifying the generated code includes: S101: Conduct code review, where the code review includes: syntax check, logic check and style check; S102: Execute test: run the code and output the test results.

4. A BIM parametric modeling system based on a large language model, characterized in that: include: An analysis and extraction module is used to receive natural language modeling instructions input by users and extract key modeling information based on natural language processing technology of large language models to obtain user modeling requirements; A judgment module, used to judge whether the natural language modeling instruction input by the user contains complete necessary parameters based on the extracted key modeling information; The planning module is used to deeply understand and decompose the natural language modeling instructions input by the user, decompose the overall modeling task into executable subtasks, and clarify the relationship and execution order between the subtasks; A prompt module, used for outputting corresponding prompt natural language according to the missing necessary parameters; The analysis and extraction module is further used to receive the natural language supplementary instruction input by the user according to the suggestive natural language and extract the supplementary modeling information based on the natural language processing technology of the large language model; The judgment module is further used to judge whether the natural language supplementary instruction input by the user contains the missing necessary parameters based on the extracted supplementary modeling information; Program module, used to generate script code for parametric modeling according to structured modeling steps based on the code template library and the code writing capability of the large language model; Check module, used to verify the generated script code; The execution module is used to execute the verified parametric modeling script to generate a BIM model.

5. The BIM parametric modeling system based on the large language model according to claim 4 is characterized in that: Also includes: The storage module is used to add the script code that has passed the verification to the code template library after structural processing according to the characteristics of the basic code script library.

6. 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, the steps of the BIM parametric modeling method based on a large language model are implemented as described in any one of claims 1 to 3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the BIM parametric modeling method based on a large language model as described in any one of claims 1 to 3 are implemented.

Images