BIM parameter assignment method, system and device based on AI, medium and program product
By establishing a standardized equipment parameter database through AI tools and models, the integration challenges caused by the non-standardization of building equipment parameters were solved, enabling efficient and accurate data sharing and BIM modeling, and improving the quality of design and operation and maintenance.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA SOUTHWEST ARCHITECTURAL DESIGN & RES INST CORP LTD
- Filing Date
- 2025-12-16
- Publication Date
- 2026-04-28
AI Technical Summary
In existing technologies, the lack of unified data standards for building equipment parameters makes it difficult to effectively integrate and share data. Manual processing is inefficient and prone to errors, affecting the accuracy of BIM modeling and the effectiveness of operation and maintenance.
AI tools are used to extract equipment parameters, a standardized equipment parameter database is established, and the rationality is verified through AI models, so as to achieve automatic identification, intelligent standardized storage and seamless integration of equipment parameters with the BIM system.
It improved the efficiency of equipment parameter data processing, avoided erroneous designs, enhanced design precision and accuracy, and enabled data collaboration across projects and stages.
Smart Images
Figure CN121936009A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent building information processing technology, and in particular to an AI-based BIM parameter assignment method, system, device, medium, and program product. Background Technology
[0002] In the field of building engineering, the parameter information of building equipment (including HVAC, water supply and drainage, electrical systems, etc.) is a crucial data foundation supporting engineering design, cost calculation, construction organization, and subsequent operation and maintenance management. Currently, relevant equipment parameters are mainly provided by equipment manufacturers in unstructured formats, such as PDF documents, Word files, JPG images, or paper manuals. These formats vary widely, naming conventions differ, and there is a lack of unified data standards and semantic specifications. This non-standardized situation makes it difficult to effectively integrate and share parameters from different manufacturers and different equipment, severely restricting cross-project and cross-phase data collaboration.
[0003] In practical engineering applications, to meet the needs of BIM (Building Information Modeling) modeling, load calculation, equipment selection, and bill of quantities preparation, technicians typically need to manually extract key parameters from the aforementioned unstructured data and manually enter them into BIM software or related engineering systems one by one. This process is not only inefficient and labor-intensive, but also highly susceptible to human error, resulting in incorrect or missing parameters or unit confusion, which in turn affects design accuracy, construction accuracy, and even subsequent operation and maintenance effectiveness.
[0004] While some existing technologies have attempted to integrate equipment parameters with BIM platforms, most solutions still rely on manual data collection and structuring in the early stages, lacking an AI-based automated parsing, intelligent mapping, and consistency verification mechanism. Therefore, in the entire process of applying equipment parameters from raw data to the BIM model, core problems remain, including difficulty in data acquisition, low standardization, poor reusability, and susceptibility to errors, making it difficult to support the urgent needs of building construction projects for efficient, accurate, and intelligent data management. Thus, there is an urgent need for a technical solution that can automatically identify, intelligently standardize, and structurally store equipment parameters and seamlessly integrate with BIM systems to overcome the current bottlenecks. Summary of the Invention
[0005] The purpose of this invention is to overcome the shortcomings of existing BIM modeling in the entire process of equipment parameter application from raw data to BIM model, such as difficulty in data acquisition, low standardization, poor reusability, and easy error. It provides an AI-based BIM parameter assignment method, system, equipment, medium, and program product.
[0006] In a first aspect, the present invention provides an AI-based method for assigning BIM parameters, comprising the following steps: S1. Obtain data storage specifications and device parameter documents from various manufacturers; S2. Use AI tools to extract device parameters and establish a device parameter database according to the data storage specifications; S3. The BIM software retrieves equipment parameters from the database; S4. Detect the parameters of the called device, the detection including: using an AI model to verify the rationality of the called device parameters and generating a verification report; S5. Assign values to the component parameters of the BIM model using the equipment parameters detected by S4.
[0007] According to a preferred embodiment, the data storage specification includes: data classification methods, field definitions, and format requirements. Step S1 includes: setting up a device type tree to clearly define device classifications; and unifying data encoding rules.
[0008] According to a preferred embodiment, S2 includes: S21. Utilize visual language models for intelligent document parsing and device parameter extraction; S22. Use the edit distance algorithm to clean and verify the extracted device parameters; S23. According to the data storage specification, the device parameters processed in S22 are formatted and stored.
[0009] According to a preferred embodiment, S3 includes: the BIM software calling equipment parameters from the database after completing the model construction.
[0010] According to a preferred embodiment, step S4 further includes: performing parameter integrity detection and parameter compliance detection on the called device parameters. If both the parameter integrity detection and parameter compliance detection pass, it is determined that the called device parameters meet the requirements; otherwise, it is determined that the called device parameters do not meet the requirements, and the user is reminded to modify the called device parameters until the called device parameters pass both the parameter integrity detection and parameter compliance detection.
[0011] According to a preferred embodiment, step S5 includes: selecting a component in the BIM model; if the component in the BIM model corresponds to the model number of the called equipment parameter, then assigning the value corresponding to the called equipment parameter to the parameter item of the corresponding component in the BIM model.
[0012] The present invention also provides an AI-based BIM parameter assignment system, comprising: a processing unit for implementing an AI-based BIM parameter assignment method provided by the present invention.
[0013] The present invention also provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute an AI-based BIM parameter assignment method provided by the present invention.
[0014] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions that, when executed by a processor, implement an AI-based BIM parameter assignment method provided by the present invention.
[0015] The present invention also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements an AI-based BIM parameter assignment method provided by the present invention.
[0016] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention provides an AI-based BIM parameter assignment method, system, equipment, medium, and program product that combines BIM technology, AI models, and a standardized equipment parameter database. While solving the problem of unified sharing of equipment parameter data, it uses AI tools to process equipment parameter documents, improving data processing efficiency, and uses AI models to verify the rationality of equipment parameters, avoiding design based on erroneous data, thereby improving design efficiency and accuracy. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating a preferred embodiment of the AI-based BIM parameter assignment method of the present invention.
[0018] Figure 2 This is a schematic diagram of the device parameter extraction interface according to a preferred embodiment of the present invention. Detailed Implementation
[0019] The present invention will now be described in further detail with reference to specific embodiments. However, this should not be construed as limiting the scope of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.
[0020] Unless otherwise specified, the terms "upper," "lower," "left," "right," "center," "inner," and "outer," etc., used in the description of specific embodiments of the present invention to indicate orientation or positional relationships, are based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is usually placed during use. These terms are merely for the purpose of facilitating the description of the present invention or simplifying the description in specific embodiments, and for enabling those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on the present invention.
[0021] Furthermore, the use of terms such as "horizontal," "vertical," "suspended," "parallel," and "coaxial" does not imply that the corresponding device / component / element must be absolutely horizontal, vertical, suspended, parallel, or coaxial. Slight tilt or deviation is permissible, as long as it does not affect the normal function of the relevant component. For example, "horizontal" simply means that its direction is more horizontal relative to "vertical," not that the structure must be perfectly horizontal; a slight tilt is acceptable. "Coaxial" means that two components are arranged as coaxially as possible, allowing them to move coaxially or approximately coaxially when their relative positions change. Alternatively, it can be simplified to mean that the corresponding device / component / element, when arranged in "horizontal," "vertical," "suspended," "parallel," or "coaxial" directions, can have an error / deviation of ±10% relative to the corresponding direction, more preferably within ±8%, more preferably within ±6%, more preferably within ±5%, and more preferably within ±4%. For example, the deviation in the "coaxial" direction is controlled within 0.2-1mm, preferably within 0.2-0.5mm. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its function in the solution of the present invention.
[0022] Furthermore, the use of terms such as "first," "second," and "third" in terminology is merely for distinguishing descriptions of identical or similar components and should not be interpreted as emphasizing or implying the relative importance of a particular component.
[0023] Furthermore, in the description of the embodiments of the present invention, "several", "more than", and "a number of" represent at least two. The number can be any number, such as two, three, four, five, six, seven, eight, or nine, and can even exceed nine.
[0024] Furthermore, in the description of the technical solution of this invention, unless otherwise explicitly specified / limited / restricted, the terms "set up," "install," "connect," "link," "provided with," "laid out," and "arranged" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to connection methods commonly used in the art, such as welding, riveting, bolting, and threaded connections. Such connections can be mechanical, electrical, or communication connections; they can be direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components.
[0025] Example 1 This embodiment provides an AI-based method for assigning BIM parameters. See also... Figure 1 The AI-based BIM parameter assignment method includes the following steps: S1. Obtain data storage specifications and device parameter documents from various manufacturers; S2. Use AI tools to extract equipment parameters and establish an equipment parameter database according to data storage specifications; S3 and BIM software retrieve equipment parameters from the database; S4. Detect the parameters of the called device. The detection includes: using an AI model to verify the rationality of the called device parameters and generating a verification report. S5. Assign values to the component parameters of the BIM model using the equipment parameters detected by S4.
[0026] The AI-based BIM parameter assignment method provided in this embodiment combines BIM technology, AI models, and a standardized equipment parameter database. While solving the problem of unified sharing of equipment parameter data, it uses AI tools to process equipment parameter documents, improving data processing efficiency. Furthermore, it uses AI models to verify the rationality of equipment parameters, avoiding design based on erroneous data, thereby improving design efficiency and accuracy.
[0027] Example 2 This embodiment is a further improvement on embodiment 1, and the repeated content will not be described again.
[0028] See Figure 1 and Figure 2 Preferably, S1 includes: acquiring data storage specifications and device parameter documents from various manufacturers.
[0029] Building equipment parameters are mostly stored in unstructured documents (such as PDF, Word, JPG) from different manufacturers. Different manufacturers operate independently, and there is no unified data standard in the industry. This results in significant differences in parameter naming and format among equipment parameter documents from different manufacturers, and a lack of a unified database standard.
[0030] This embodiment achieves the integration of device parameter documents from different manufacturers by establishing data storage specifications.
[0031] Data storage specifications can be developed based on industry association technical standards and common terminology. Such specifications should not only be compatible with the parameters of devices from different manufacturers, but also take into account the parameter characteristics of different device types.
[0032] Preferably, data storage specifications include: data classification methods, field definitions, format requirements, etc.
[0033] S1 includes: setting up a device type tree to clarify device classification; and unifying data coding rules.
[0034] Preferably, the data can be categorized by equipment type (e.g., HVAC equipment, electrical equipment, etc.). Each parameter should have a clearly defined field name and data type (e.g., numeric, text) to ensure consistency and standardization in subsequent data parsing, storage, and retrieval.
[0035] Preferably, the data storage specification standardizes the device name. For example, it defines a standard name for a certain type of device and associates different names for the same type of device from different manufacturers with the standard name of the same type of device. This can be done by treating different names for the same type of device from different manufacturers as synonyms of the standard name of the same type of device.
[0036] Preferably, the equipment type tree can be an extension of industry standards (e.g., ISO 12006-3, "Construction Engineering—Organization of Building Engineering Information—Part 3: Object-Oriented Information Framework"), clearly defining equipment classifications. A unified coding rule facilitates data retrieval and management. Example coding rule: GL-DLN-1-71, consisting of manufacturer code, equipment classification code, equipment style code, and model / specification. "GL": Gree; "DLN": Multi-split indoor unit; "1": Concealed medium-static-pressure ducted air conditioner; "71" represents an indoor unit with a cooling capacity of 71.
[0037] Preferably, S2 includes: S21. Utilize visual language models for intelligent document parsing and device parameter extraction.
[0038] Preferably, S21 can be the semantic understanding and intelligent extraction of unstructured device parameter documents (such as parameter tables in image format) using a vision-language model (such as Qwen-VL).
[0039] The visual language model can be a multimodal large model, such as GPT-4V, Qwen-VL, Gemini, etc.; it can simultaneously understand text and images / audio / video, achieving cross-modal understanding and generation. Preferably, in this embodiment, the multimodal large model mainly performs semantic understanding and intelligent extraction for text and images.
[0040] The specific implementation steps of S21 include: S211, Image Preprocessing and Encoding: Obtain an image of the device parameter document, convert the image to Base64 encoding, and construct a request body conforming to the multimodal large model input standard. Preferably, the image of the device parameter document can be generated by taking a screenshot of the document using a screenshot tool.
[0041] S212, Pattern-Based Guided Extraction: Pattern definition: A pre-built JSON-formatted extraction pattern library defines unique identifiers for different device types (e.g., "multi-split indoor unit"). Each pattern contains a "Primary Element" (e.g., "Model Number") and a list of "Extraction Elements" (e.g., "Cooling Capacity" and "Noise"). Each element includes a standard name, unit, data format, and a thesaurus (Similar Words).
[0042] Two-phase asynchronous retrieval strategy: First, extract the primary key index: Construct prompt words to guide the multimodal large model to identify and extract the "primary element" column (usually the device model) in the table as the unique index key of the data row, and output the primary key list with a specific delimiter.
[0043] Then perform attribute association extraction: For each extracted "main element", instructions or questions containing synonym hints are dynamically generated and input into the multimodal large model, enabling the multimodal large model to extract the attribute values corresponding to the main element.
[0044] When performing attribute association extraction, multiple extraction tasks can be initiated simultaneously using asynchronous concurrency (asyncio.gather), significantly improving processing efficiency. The multimodal large model accurately locates and extracts the corresponding attribute values based on the primary key list extracted in the first stage.
[0045] Chain-of-Thought Enhancement: During the extraction process of the multimodal large model, the "Reasoning Content" function is enabled to leverage the logical reasoning capabilities of the multimodal large model to solve alignment problems in complex table structures (such as merged cells and cross-row data), thereby improving extraction accuracy.
[0046] S22. Use the edit distance algorithm to clean and verify the extracted device parameters.
[0047] After obtaining the output of the multimodal large model, the extraction results of the multimodal large model are cleaned and corrected, focusing on solving the data alignment offset problem caused by model illusion or OCR recognition error.
[0048] S22 includes: S221. Fuzzy matching and key-value alignment: For attribute value pairs (key:value) returned by a multimodal large model, the system first attempts to find an exact match in the primary key index. If no match is found (e.g., "Model-A" is identified as "Model_A"), the Levenshtein Distance algorithm is triggered.
[0049] The algorithm calculates the minimum number of steps required to find the character differences between the extracted key and all keys in the standard primary key index.
[0050] The current attribute value data is mapped to the standard key with the smallest edit distance (and less than the threshold), thereby automatically correcting character recognition errors and ensuring that the attribute value is accurately placed.
[0051] S222, Outlier Handling: For data returned as "none" or unrecognizable by the multimodal large model, mark it as an error or a specific placeholder to facilitate subsequent manual review or secondary cleaning.
[0052] Irrelevant reasoning text is removed, and only structured numerical results are retained.
[0053] S223, Standardized Format Cleaning: Based on the unit and format in the schema definition, the extracted values are automatically concatenated with metadata (such as standardizing column names to field name_unit_format) to ensure the uniqueness and standardization of the data meaning.
[0054] S23. According to the data storage specifications, perform format conversion and storage of the device parameters processed by S22.
[0055] The cleaned data is transformed into a standardized structured format according to data storage specifications, and then persistently stored. S231. Dynamic dictionary construction: Construct a nested dictionary structure (result_dict) in memory with the "main element" as the key and each "extracted element" as the value to normalize sparse data.
[0056] S232, DataFrame Serialization and Export: Using the Pandas data analysis library, convert nested dictionaries into two-dimensional data tables (DataFrames). During this process, column indices are aligned, and the data is exported as a UTF-8 encoded CSV file as an intermediate exchange format.
[0057] See Figure 2 In step S2, various extraction modes can be used to intelligently parse and extract equipment parameters from unstructured equipment parameter documents from different manufacturers. Preferably, in step S2, AI tools are used to parse and clean the equipment parameter documents. Compared with manual processing, this significantly improves the efficiency and accuracy of data parsing, ensures the quality of structured data storage, provides a reliable data foundation for subsequent BIM software calls, and enhances data processing efficiency and quality.
[0058] Preferably, the S3 and BIM software retrieve equipment parameters from the database.
[0059] Preferably, before retrieving equipment parameters from the database, the BIM software has completed model construction and named each component in the BIM model, forming an equipment cluster. Preferably, the same equipment cluster contains equipment of the same type in the BIM model; for example, a refrigeration unit equipment cluster contains all refrigeration units of a certain type in the BIM model.
[0060] Preferably, after completing the model construction, the BIM software retrieves the CSV file generated by S232 from the database.
[0061] Preferably, S4 includes: verifying the rationality of the called device parameters, checking the completeness of the parameters, and checking the compliance of the parameters.
[0062] Preferably, the rationality verification includes: using open-source large models (such as DeepSeek, GPT, Qwen, Llama, Claude, Gemini, etc.) to verify the rationality of the relevant parameters in the CSV file, and displaying the verification report in text form for user reference.
[0063] Preferably, the verification report includes: a determination of whether the relevant parameters in the CSV file are reasonable, and suggestions for unreasonable parameters (e.g., increasing or decreasing parameter values).
[0064] Preferably, if unreasonable parameters are found in the verification report, the user decides whether to adopt the suggestions (in whole or in part) based on the feedback in the verification report. If the suggestions are not adopted, the user proceeds directly to the parameter integrity and compliance testing stage; if the suggestions are adopted (in whole or in part), the user manually modifies the relevant content of the CSV file before proceeding to the parameter integrity and compliance testing stage.
[0065] Parameter completeness check: Automatically checks the number of parameter columns in the CSV file and whether the parameter list header name conforms to the preset settings. If it conforms, it proceeds to parameter compliance check; if it does not conform, it prompts the user about the relevant non-compliant items and ends the check.
[0066] Preferably, parameter compliance testing is performed only after the parameter integrity test has passed.
[0067] Parameter compliance check: Checks whether the parameter format in each parameter column cell meets the data storage specification requirements. If it meets the requirements, the check passes; if it does not meet the requirements, the user is prompted with the relevant non-compliant items and the check ends.
[0068] If both the parameter integrity check and the parameter compliance check pass, the called device parameters are deemed to meet the requirements; otherwise, the called device parameters are deemed not to meet the requirements, and the user is prompted to modify the called device parameters until the called device parameters pass both the parameter integrity check and the parameter compliance check.
[0069] Preferably, after the CSV file passes the reasonableness verification, it also needs to pass the parameter completeness check and parameter compliance check. If both checks pass, the CSV file is deemed to meet the requirements, and a corresponding table preview page is provided for the user to view; otherwise, it is deemed not to meet the program requirements, and the user is reminded to manually modify the CSV file until it passes the program's built-in parameter completeness check and parameter compliance check.
[0070] Preferably, S5 includes: selecting a component in the BIM model; if the component in the BIM model corresponds to the model number of the called equipment parameter, then assigning the value corresponding to the called equipment parameter to the parameter item of the corresponding component in the BIM model.
[0071] Preferably, based on the successful completion of the relevant checks in step S4, relevant components are selected from the BIM model file. If the model numbers (e.g., 22, 28...71...) contained in the component name match the relevant numbers (e.g., 22, 28...71...) in the corresponding model in the CSV file, it is determined that the two models correspond. The values corresponding to the parameter names (e.g., cooling capacity, heating capacity, power consumption, etc.) contained in the CSV file are directly assigned to the parameter items corresponding to the corresponding components in the BIM model file to achieve replacement.
[0072] Preferably, after the parameters of the components in the BIM model are assigned, equipment calculation sheets (such as equipment performance calculations, energy consumption calculations, etc.) and equipment lists (a list containing detailed information such as equipment name, model, quantity, and parameters) can be automatically generated based on the BIM model with real parameters, providing a basis for engineering design, cost accounting, construction management, etc.
[0073] Preferably, after calling the structured data, the BIM software automatically assigns values to the component parameters, avoiding the tedious operation and error risk of manually inputting parameters. This allows the equipment parameters to be applied quickly and accurately in the BIM model, significantly improving design efficiency and the accuracy of design results. The final output calculation sheets and equipment lists are also more reliable.
[0074] Example 3 This embodiment provides an AI-based BIM parameter assignment system, including: a processing unit, used to implement an AI-based BIM parameter assignment method involved in Embodiment 1 or Embodiment 2.
[0075] The system has a built-in automated data cleaning and error correction mechanism, which focuses on solving the data alignment offset problem caused by model illusion or OCR recognition error.
[0076] Example 4 This embodiment provides an electronic device. The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to execute an AI-based BIM parameter assignment method according to Embodiment 1 or Embodiment 2.
[0077] Example 5 This embodiment provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions that are used to cause a processor to execute and implement an AI-based BIM parameter assignment method according to Embodiment 1 or Embodiment 2.
[0078] Example 6 This embodiment provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements an AI-based BIM parameter assignment method as described in Embodiment 1 or Embodiment 2.
[0079] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. A BIM parameter assignment method based on AI, characterized in that, Includes the following steps: S1. Obtain data storage specifications and device parameter documents from various manufacturers; S2. Use AI tools to extract device parameters and establish a device parameter database according to the data storage specifications; S3. The BIM software retrieves equipment parameters from the database; S4. Detect the parameters of the called device, the detection including: using an AI model to verify the rationality of the called device parameters and generating a verification report; S5. Assign values to the component parameters of the BIM model using the equipment parameters detected by S4.
2. The AI-based BIM parameter assignment method according to claim 1, characterized in that, The data storage specifications include: data classification methods, field definitions, and format requirements; S1 includes: setting up a device type tree to clarify device classification; and unifying data encoding rules.
3. The AI-based BIM parameter assignment method according to claim 1, characterized in that, S2 includes: S21. Utilize visual language models for intelligent document parsing and device parameter extraction; S22. Use the edit distance algorithm to clean and verify the extracted device parameters; S23. According to the data storage specification, the device parameters processed in S22 are formatted and stored.
4. The AI-based BIM parameter assignment method according to claim 1, characterized in that, S3 includes: Once the model is built, the BIM software retrieves the equipment parameters from the database.
5. The AI-based BIM parameter assignment method according to claim 1, characterized in that, S4 further includes: performing parameter integrity detection and parameter compliance detection on the called device parameters; if both parameter integrity detection and parameter compliance detection pass, it is determined that the called device parameters meet the requirements; otherwise, it is determined that the called device parameters do not meet the requirements, and the user is reminded to modify the called device parameters until the called device parameters pass the parameter integrity detection and parameter compliance detection.
6. The AI-based BIM parameter assignment method according to claim 1, characterized in that, S5 includes: If a component in the BIM model is selected and the component in the BIM model corresponds to the model number of the called equipment parameter, then the value corresponding to the called equipment parameter is assigned to the parameter item of the corresponding component in the BIM model.
7. An AI-based BIM parameter assignment system, characterized in that, include: The processing unit is used to implement the AI-based BIM parameter assignment method as described in any one of claims 1 to 6.
8. An electronic device, characterized in that, The electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform an AI-based BIM parameter assignment method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the AI-based BIM parameter assignment method according to any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements an AI-based BIM parameter assignment method as described in any one of claims 1 to 6.