BIM search method, BIM device, and design assistance device

Abstract

A BIM search method capable of adding a function to a BIM system storing three-dimensional drawing data, said method being executed by a computer and comprising: a setting step (#21) of setting a single search window on a screen of the BIM system; an acquisition step (#22) of acquiring attribute information of each of a plurality of types of parts included in the three-dimensional drawing data stored in the BIM system; an extraction step (#26) of extracting attribute information of a part corresponding to natural language or an image input to the search window; and a display step (#27) of displaying, on a screen, a part group image including a three-dimensional arrangement in the three-dimensional drawing data of a set of parts corresponding to the attribute information extracted in the extraction step.

Description

BIM search method, BIM device, and design support device

[0001] The present disclosure relates to a BIM search method, a BIM device, and a design support device.

[0002] Conventionally, there has been known a BIM (Building Information Modeling) system that stores three-dimensional drawing data used in the lifecycle of the design, construction, and management of structures such as buildings and bridges (see, for example, Patent Document 1). Also, conventionally, there has been known an information processing device for a CAD (Computer-Aided Design) system used in BIM (Building Information Modeling) that can build design models used in the design of structures such as buildings and bridges (see, for example, Patent Document 2). Examples of such CAD systems include AutoCAD and REVIT (registered trademark, omitted below).

[0003] This BIM system includes not only 3D drawing data but also attribute information such as cost, finish, internal structure, and management information. Using the attribute information linked to each part in the 3D drawing data, designers can perform simulations of the structure, wind, heat, lighting, etc.

[0004] Patent Document 1 discloses a hierarchical data file structure that includes multiple entities as attribute information (see Figures 4 and 5 of Patent Document 1). The technology described in Patent Document 1 extracts extracted data from a data file based on building information and simulation type information requested by a user, and provides this extracted data to an application provider. This allows designers to obtain simulation results for structure, wind, heat, lighting, etc.

[0005] The information processing device of Patent Document 2 sets sample file data together with a prompt for specifying desired information (for example, a collision point between a pillar and a beam) from a plurality of file data, inputs these prompts and sample file data into an LLM (Large Scale Language Model) to generate a script, further inputs correct answer information for the desired information in the sample file data to generate a script, and stores this script to extract reproducible information with a certain extraction accuracy.

[0006] JP 2013-171579 A Japanese Patent No. 7551203 A

[0007] The BIM system described in Patent Document 1 includes a hierarchically structured data file containing attribute information associated with each part in the 3D drawing data. While the technology described in Patent Document 1 extracts necessary information from the data file to obtain simulation results, it does not improve the operability of the BIM system itself. For example, when a design designer transfers 3D drawing data to a structural engineer, complex search operations are required to extract information about specific parts located on the second floor from the hierarchically structured data file. Furthermore, some contractors and managers are unfamiliar with BIM search operations, which can lead to reduced work efficiency despite the introduction of a BIM system.

[0008] Furthermore, the information processing device described in Patent Document 2 requires the setting of sample file data corresponding to desired information, which requires time and effort to support the construction of a design model. Furthermore, because the script is generated by further inputting correct answer information for the sample file data, unless the designer is familiar with CAD systems, there is a risk that the correct answer information will be input incorrectly.

[0009] Therefore, there is a need for a highly convenient BIM search method and BIM device that can improve the work efficiency of BIM users. There is also a need for a design support device that allows even designers who are unfamiliar with CAD systems to easily design.

[0010] A BIM search method executed by a computer according to the present disclosure is characterized in that it is a BIM search method that can be added to a BIM system in which three-dimensional drawing data is stored, and includes: a setting step of setting a single search window on a screen of the BIM system; an acquisition step of acquiring attribute information for each of multiple types of parts included in the three-dimensional drawing data stored in the BIM system; an extraction step of extracting the attribute information for the parts corresponding to natural language or an image entered in the search window; and a display step of displaying on the screen a parts group image including a three-dimensional arrangement in the three-dimensional drawing data of an aggregate of the parts corresponding to the attribute information extracted in the extraction step. Further, a characteristic configuration according to the present disclosure relates to a BIM device equipped with a computer that executes the BIM search method.

[0011] The BIM search method and BIM device disclosed herein include a setting step of setting a single search window on a BIM system screen into which natural language or images can be input, and a display step of displaying a part group image including a collection of parts corresponding to attribute information. Therefore, a BIM user does not need to perform complex search operations to extract information about specific parts arranged on the second floor from a data file, for example. Instead, the BIM user can automatically view the part group image by simply inputting natural language or an image into the single search window. As a result, even someone unfamiliar with BIM search operations can obtain the information they need and check the quantity, arrangement, etc. by looking at the part group image.

[0012] Furthermore, by simply entering natural language or an image into a single search box, images of parts can be automatically viewed, making it possible to estimate and order any missing parts according to the progress of the project without any omissions. This makes it a highly convenient BIM search method and BIM device that can increase the work efficiency of BIM users.

[0013] A characteristic configuration of the design support device according to the present disclosure is that the design support device supports the construction of a design model, and includes a setting unit that sets an input field into which design instructions including natural language, images, or files can be input, a display control unit that displays the input field and the design model, and a part generation unit that builds the design model by stacking parts in order by executing a script generated by a generation AI based on the contents of the input field.

[0014] The design support device according to the present disclosure has an input field into which design instructions, including natural language, images, or files, can be entered, so that it is sufficient to enter design instructions for parts of a design model (walls, floors, roofs, equipment, etc.). Furthermore, the part generation unit of this configuration executes a script generated by a generation AI based on the contents of the input field to build a design model by stacking parts in order, making it easy for even designers unfamiliar with CAD systems to design. Furthermore, the display control unit of this configuration displays the input field and the design model, allowing designers to intuitively understand how the design instructions entered in the input field will be reflected in the design model.

[0015] In this way, the design support device allows even designers who are unfamiliar with CAD systems to easily design.

[0016] is a block diagram showing the overall configuration of a BIM system. is a block diagram of a BIM system including a BIM device. is an example of a database acquired from a BIM system. is a flowchart showing a BIM search method. is a flowchart showing a BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is an example of a screen display using the BIM search method. is a block diagram showing the overall configuration of a drafting system. is a block diagram of a drafting system including a design support device. is a flowchart showing a method of controlling the drafting system. is an example of a screen display by the design support device. is an example of a screen display by the design support device. is an example of a screen display by the design support device. is an example of a screen display by the design support device. is an example of a screen display by the design support device. is an example of a screen display by the design support device. 1 is an example of a screen display by the design support device.

[0017] Hereinafter, embodiments of a BIM search method, a BIM device, and a design support device according to the present disclosure will be described with reference to the drawings. In a first embodiment, a user terminal on which REVIT (registered trademark, omitted hereinafter) is installed will be used as an example of a BIM (Building Information Modeling) system. In a second embodiment, a user terminal on which REVIT is installed will be used as an example of a CAD system. However, the following embodiments are not limited to these, and various modifications are possible within the scope of the present disclosure.

[0018] (First embodiment) As shown in FIG. 1 , a BIM system 100 includes a BIM device 1, a search device 2, and a user device 3. The BIM device 1 is a server owned by a vendor that manages and operates BIM. The search device 2 is a server owned by a vendor that develops and provides add-in software for BIM. The user device 3 is a terminal on which BIM is installed, and is owned by a user who designs, constructs, and manages structures such as buildings and bridges. For convenience, the user device 3 is illustrated as a single terminal, but different users who design, construct, or manage structures own multiple terminals. These terminals are composed of desktop PCs, laptops, tablets, smartphones, etc.

[0019] The BIM device 1, search device 2, and user device 3 are connected to each other so as to be able to communicate with each other via a network 4. The BIM device 1 includes a processor 11, a communication IF 12, a memory 13, and an input / output IF 14. Although the BIM device 1 includes other functional units, only the functional units related to this embodiment are described here.

[0020] A BIM program 13a is stored in the memory 13. The processor 11 is the central part of the computer, receiving instructions and performing calculations and data processing. The processor 11 includes a CPU (central processing unit), a GPU (graphics processing unit), an NPU (neural network processing unit), or other hardware for executing the BIM program 13a stored in the memory 13. In other words, the processor 11 has an arithmetic processing circuit, an input port, and an output port. The processor 11 may be an ASIC, an FPGA, or an SoC, and is not particularly limited.

[0021] The communication IF 12 is a communication interface having a function of transmitting signals output from the processor 11 to the search device 2 and the user device 3 via the network 4, and a function of sending signals received from the search device 2 and the user device 3 via the network 4 to the processor 11. The processor 11 can transmit and receive signals between the memory 13 and the communication IF 12. The input / output IF 14 functions as an interface with input devices (e.g., keyboard, mouse, touch panel, touch pad, etc.) and output devices (e.g., display, speaker, etc.).

[0022] The memory 13 stores data within the computer and includes a main memory and a secondary memory. The main memory is a storage area for temporarily storing programs and data and is composed of RAM or the like. The secondary memory is a non-temporary storage area for permanently storing programs and data and is composed of an HDD, SSD or the like. The secondary memory may also be external hardware such as a cloud server or rental server.

[0023] The BIM program 13a is an application stored in the secondary memory, read into the main memory, and executed by the processor 11. The BIM program 13a is configured using REVIT as an example of a BIM. Note that the BIM program 13a may also be configured using other programs such as Archicad (registered trademark) or GLOBE (registered trademark).

[0024] The BIM program 13a is software for integrated management of digital information related to the design, construction, and management of a building. The BIM program 13a can create a three-dimensional digital model (three-dimensional drawing data 33a). Each part in the three-dimensional drawing data 33a is associated with attribute information stored in secondary memory, such as the type of building material, specifications, performance, cost, construction procedure, and maintenance information. This allows the three-dimensional drawing data 33a to be used throughout the lifecycle of the design, construction, and management of a structure.

[0025] The search device 2 includes a processor 21, a communication IF 22, a memory 23, an input / output IF 24, and a display 25. The processor 21, the communication IF 22, the memory 23, and the input / output IF 24 have the same basic configuration as the processor 11, the communication IF 12, the memory 13, and the input / output IF 14 of the BIM device 1, so a brief description thereof will be omitted. Note that the search device 2 includes other functional units, but only the functional units related to this embodiment are described here.

[0026] An add-in program 23a is stored in the memory 23. The add-in program 23a is stored in a secondary memory (storage unit 23A) of the memory 23, read into the main memory, and executed by the processor 21. The add-in program 23a is a BIM search program that is sent to the BIM device 1 via the communication IF 22 and the network 4, and adds functions to the BIM program 13a. The add-in program 23a in this embodiment has an extended function that displays specific parts searched for from the three-dimensional drawing data 33a as a parts group image. Details of the add-in program 23a will be described later.

[0027] The display 25 is provided in the search device 2 and is a display device that displays text, images, videos, and other visual information. This display 25 can display the BIM by executing the BIM program 13a in which the add-in program 23a is implemented by the processor 21. The display 25 is configured with an LCD display, an LED display, an OLED display, a plasma display, or the like. Note that the display 25 is not particularly limited as long as it is hardware that can execute the BIM program 13a in which the add-in program 23a is implemented by the processor 21 and display the three-dimensional drawing data 33a.

[0028] The user device 3 includes a processor 31, a communication IF 32, a memory 33, an input / output IF 34, a display 35, and an operation unit 36. The processor 31, the communication IF 32, the memory 33, the input / output IF 34, and the display 35 have the same basic configuration as the processor 21, the communication IF 22, the memory 23, the input / output IF 24, and the display 25 of the search device 2, so a brief description thereof will be omitted. Note that the user device 3 includes other functional units, but only the functional units relevant to this embodiment are described here.

[0029] Three-dimensional drawing data 33a of the building is stored in the memory 33. The operation unit 36 ​​is constructed with at least one element selected from the group consisting of a touch switch, a keyboard, a mouse, a scanner, a voice input speaker, etc. When a user operates the operation unit 36, a signal corresponding to the operation is input to the processor 31.

[0030] (Configuration of Search Device) FIG. 2 shows a block diagram of a search device 2 for executing the BIM search method. The search device 2 can exchange information with generative AI (artificial intelligence) and image analysis AI (artificial intelligence). The generative AI includes any language model or large language model (LLM), such as ChatGPT, Gemini, or Cloude. The image analysis AI uses machine learning or deep learning algorithms to recognize patterns and features in images and perform tasks such as classification, detection, and segmentation.

[0031] 2 functions as a secondary memory of the above-mentioned memory 23. The storage unit 23A stores a table for each part, which is configured from a BIM source database DBa and an expanded database DBb.

[0032] The BIM source database DBa is the DB column name (the name used to identify the fields that make up the project data) used in REVIT, and is attribute information for each part set in JSON (JavaScript Object Notation) format. A DB column name is used for each part. Parts include structural equipment such as columns and beams, exterior and interior equipment such as windows, doors, and wall materials, accessory equipment such as sleeves, and building equipment such as indoor and outdoor air conditioning units, all of which fall under the category of "equipment." Individual tables are provided for the ducts, pipes, and other water supply and exhaust equipment connected to each part, lighting, transformers, and other electrical equipment, and toilets, washbasins, and other sanitary fixtures. Specifically, as shown in the first column of Figure 3, the column names UniqueID, Name, Category, Type, and Level are used as common items, and the column names Room, Volume, Area, Length, and System are used as individual items for equipment, Room, Length, System, Diameter, SystemType, Area, and SystemClassification are used for ducts, Room, Length, System, Diameter, SystemType, Area, and SystemClassification are used for piping, Room is used as a column name for lighting, and System and Room are used as column names for sanitary fixtures.

[0033] 3, the extended database DBb (BIM acquisition source parameter name) is a data file that extends the BIM source database DBa so that the extraction unit 233 can convert natural language into a search query in cooperation with the generation AI and extract attribute information of each part. The BIM source database DBa and the extended database DBb are associated with each other, and multiple tables (RDB: Relational Database) for each part are stored in the storage unit 23A.

[0034] For example, in the extended database DBb, the DB column name "Length" is set as an extended parameter of the BIM source parameter name "Length, L, Length." The DB column name "System" is also set as an extended parameter of the BIM source parameter name "System." Furthermore, because there is variation even within the same 101-1 system, systems such as piping and ducts, such as A101-1 and air conditioning 101-1, are normalized to an easy-to-search value such as "101-1" in the extended database DBb. The DB column name "SystemClassification" is also set as an extended parameter of the BIM source parameter name "System Classification: Air Intake Duct, Exhaust Duct, Drain Pipe, Water Supply Pipe, etc." This allows partial match searches for ducts using "Air Intake, Exhaust, etc." and for piping using "Drainage, Water Supply, etc."

[0035] 2, the add-in program 23a includes a setting unit 231, an acquisition unit 232, an extraction unit 233, a display control unit 234, a conversion unit 235, and a determination unit 236. The add-in program 23a is an API (Application Programming Interface) or a plug-in system that adds these functional units to the BIM program 13a.

[0036] The setting unit 231 sets a single search window SW (see Figures 6 and 7) on the top screen (display 35) of the BIM system 100 (user device 3). As shown in Figure 6, the setting unit 231 may automatically display the single search window SW on the top screen of the BIM browser displayed on the display 35 of the user device 3, or may provide a display button for the search window SW on the top screen of the BIM browser. In other words, the setting unit 231 inserts an add-in program 23a that sets the single search window SW into the initial screen startup program of the BIM program 13a. The user can input natural language or images into this search window SW. Here, natural language includes words such as keywords, word groups combining multiple words, phrases consisting of words and their associated words, sentences consisting of combinations of multiple phrases, etc. In this embodiment, the natural language is preferably a sentence containing one or more attributes (such as the name) of the part. The image may be a still image or a video.

[0037] The acquisition unit 232 acquires attribute information related to multiple types of parts included in the three-dimensional drawing data 33a stored in the BIM system 100 (user device 3). In other words, the acquisition unit 232 acquires attribute information stored in the memory 33 of the BIM system 100 (user device 3) as attribute information related to multiple types of parts included in the three-dimensional drawing data 33a, as a BIM source database DBa for each part via the BIM device 1. Then, as shown in FIG. 3 , the acquisition unit 232 provides multiple tables corresponding to each part, which are associated with the BIM source database DBa as an extended database DBb.

[0038] At this time, the acquisition unit 232 can acquire related words related to the attribute information by associating them with the attribute information. For example, "a component into which a pipe is inserted at a location where it interferes with a beam" is acquired in association with "sleeve." If the related words are ones that the generation AI has already learned, they may be acquired by linking with the generation AI. If the related words are ones that the generation AI has not yet learned, they may be customized by inputting learning data into the generation AI. In particular, in this embodiment, the acquisition unit 232 associates the BIM original database DBa with the expanded database DBb by using aliases (e.g., length and width) for the notations (e.g., length and width) in the BIM system 100. This allows searches to be performed by entering "ducts with a length of 10 m or less," further enhancing the versatility of the search method.

[0039] The natural language or image entered in the search window SW may include a change in the type of part. The change in type of part is a natural language change to change the type of part, such as "changing the door from a single swing to a double swing" or "changing the wall specifications to a more fire-resistant one than the current one." In this case, the acquisition unit 232 acquires parts corresponding to the change in type from data stored in the memory 33 of the BIM system 100 (user device 3) or from web data. If the change in type is a BIM part provided in advance by the BIM device 1 or a BIM part acquired by the user from an external source, the acquisition unit 232 acquires the parts from the data stored in the memory 33. On the other hand, if the change in type is a BIM part that is published as web data but not stored in the memory 33, the acquisition unit 232 acquires the parts from the web data.

[0040] Furthermore, the acquisition unit 232 preferably acquires interconnection information for multiple parts. The interconnection information refers to connection information between equipment and peripheral components, such as pipes and ducts, connected to the equipment. As described above, the extended database DBb is set as an extended parameter with the BIM source parameter name "System" for the DB column name "System." The interconnection information is set as words containing common values ​​for equipment and peripheral components of the same system. In this embodiment, the acquisition unit 232 acquires the interconnection information for multiple parts as the extended database DBb, normalized to values ​​that can be searched to indicate the same system. For example, ducts and pipes are connected to sleeves that pass pipes through the walls, floors, and ceilings of a structure, and these ducts and pipes are connected to air conditioning equipment, etc. In other words, for example, the interconnection information for sleeves, pipes, and ducts is acquired using words containing common values ​​for the same system.

[0041] The extraction unit 233 extracts attribute information corresponding to natural language or images entered into the search window SW from the operation unit 36 ​​of the user device 3. The natural language or images entered into the search window SW are sent to the search device 2 via the BIM device 1 or directly from the user device 3, and the extraction unit 233 works with the generation AI to convert the natural language or images into a search query and extract attribute information for each part. The extraction unit 233 extracts equipment, etc., for which the search query matches a parameter name registered in the extended database DBb. As described above, the extended database DBb contains words (e.g., length) different from names (e.g., length) registered in the BIM source database DBa as related words. Therefore, by entering "duct with a length of 10 m or less," attribute information for each part can be reliably extracted.

[0042] The extraction unit 233 may also extract attribute information of each part corresponding to the construction completion information. This construction completion information is voice as natural language or construction photos as images. For example, by uploading construction photos using the operation unit 36 ​​(e.g., a touch panel) of the user device 3 at the construction site or transmitting construction completion information by voice to the operation unit 36 ​​(e.g., a voice input speaker) of the user device 3 at the construction site, the attribute information of each part can be extracted from the image features in cooperation with the image analysis AI, or the attribute information of each part can be extracted from natural language based on voice in cooperation with the generation AI.

[0043] Furthermore, the extraction unit 233 may extract matching or differences between the three-dimensional drawing data 33 a and the construction completion information. For example, if the length of a joint differs from that in the three-dimensional drawing data 33 a, the construction details can be shared with a designer or the like, and the details of design changes can be easily confirmed, and the changes can be approved or instructions for correction work can be issued to the construction site.

[0044] The display control unit 234 displays on the display 35 a part group image including a collection of parts corresponding to the attribute information extracted by the extraction unit 233 (see Figures 8 and 9). In Figure 8, by entering the ambiguous phrase "sleeve-type equipment" in the search window SW, a part group image of a collection of sleeves from the part group image shown in Figure 7 is displayed on the display 35. In Figure 9, by entering the ambiguous phrase "sleeve-type equipment located in the basement and measuring 400 mm or longer" in the search window SW, a part group image of a collection of sleeves 400 mm or longer located in the basement is displayed on the display 35 from the part group image shown in Figure 7 or the part group image shown in Figure 8. This allows users to automatically view part group images simply by entering natural language or images in a single search window SW. As a result, even users unfamiliar with BIM search operations can obtain the information they need and check the quantity, placement, etc. by looking at the part group image.

[0045] The display control unit 234 may display on the display 35 a list of information about parts corresponding to the attribute information extracted by the extraction unit 233 (see the type quantity table in FIG. 9 ). This information list may be configured to be selectable in a pull-down menu format. By displaying the list of information about parts on the display 35, even if an incorrect part has been mixed in with the parts group image, the user can check the list and make corrections, such as deleting the incorrect part. The display control unit 234 may also display elements other than the parts group image in a skeleton form on the display 35. As described above, since the acquisition unit 232 acquires interconnection information about multiple parts, for example, pipes, ducts, etc. inserted into multiple sleeves displayed as the parts group image can be displayed in a skeleton form. This makes the connection relationships with other elements clear at a glance, making it easier for the user to notice errors in quantity, dimensions, etc.

[0046] The display control unit 234 may display a video showing the steps for creating a parts group image on the display 35. For example, it may be possible to display how to create a diagram of multiple sleeves displayed as a parts group image in association with pipes or ducts. This makes it possible to use the video as a tool for learning how to operate the BIM system 100, further improving user convenience.

[0047] The conversion unit 235 converts all dimensions of parts corresponding to the attribute information extracted by the extraction unit 233 based on a dimension change instruction entered in the search window SW. For example, as shown in Fig. 10, based on a dimension change instruction entered in the search window SW, such as "change the length of a sleeve in the basement that is 400 to 380", the dimensions of the sleeve indicated by the dashed line are converted all at once.

[0048] The determination unit 236 determines whether or not the parts corresponding to the attribute information extracted by the extraction unit 233 deviate from the design standards. For example, when an ambiguous sentence such as "the type on the 2nd floor has joints" is input, the determination unit 236 automatically detects joints whose quantity differs from the design standards and should be added or deleted from the displayed multiple joints.

[0049] 4 and 5 show flowcharts of a BIM search method executed by the search device 2, which can be added as a function to the BIM system 100 storing three-dimensional drawing data 33a. In this embodiment, an example is shown in which information from the user device 3 is transmitted to and received from the search device 2 via the BIM device 1, but information from the user device 3 may be transmitted to and received directly from the search device 2, or information may be transmitted and received only between the user device 3 and the BIM device 1 in a state in which an add-in program 23a is pre-installed in the BIM program 13a of the BIM device 1.

[0050] As shown in FIG. 4 , the add-in program 23a of the search device 2 is sent to the BIM device 1, the add-in program 23a is implemented in the BIM program 13a, and the BIM program 13a with the add-in program 23a implemented is sent to the user device 3 (#21). As a result, as shown in FIG. 6 , a BIM having a single search window SW can be displayed on the display 35 of the user device 3. Next, the user (designer) searches for parts (#31), edits, arranges, and adjusts each selected part, and creates 3D drawing data 33a (#32). At this time, parts can be searched and selected by entering natural language or an image in the search window SW of FIG. 6 , or by searching and selecting parts from the corresponding tab. Alternatively, a list of information on parts corresponding to the natural language or image entered in the search window SW can be displayed and selected. In other words, the natural language is composed of multiple candidates displayed in the search window SW. In this case, although not shown in the figure, the natural language or image entered in the search window SW is sent to the search device 2, the extraction unit 233 extracts attribute information corresponding to the natural language or image, and the display control unit 234 displays a list of part information on the display 35 of the user device 3.

[0051] Next, the user device 3 sends the 3D drawing data 33a to the BIM device 1 (#11), and the acquisition unit 232 of the search device 2 acquires attribute information for multiple types of parts included in the 3D drawing data 33a (#22). Next, as shown in FIG. 3 , the acquisition unit 232 creates (acquires) multiple tables corresponding to each part, associating the BIM source database DBa with the extended database DBb (#23). If necessary, the acquisition unit 232 may acquire attribute information for each part from an image in natural language in cooperation with an image analysis AI. In this case, the acquisition unit 232 performs image analysis of the shape of a special part customized by the user in cooperation with the image analysis AI (#24). Next, the acquisition unit 232 acquires attribute information for each part in natural language associated with the image-analyzed shape of the part, and reflects the acquired attribute information in a table consisting of the BIM source database DBa and the extended database DBb (#25). This makes it easy to search for parts with special shapes, for example, by entering "a pillar with a trapezoidal cross section" or "a door with a bulge in the middle."

[0052] FIG. 7 shows 3D drawing data 33a including sleeves, pipes, ducts, etc., in which building walls and other components are shown with dashed lines as an example of a skeleton display. Because equipment and other components inside the building walls are usually invisible, a user must perform complex search operations to display the required parts. Therefore, in this embodiment, the setting unit 231 sets a single search window SW on the top screen of the BIM browser. In the example shown in FIG. 7, the display control unit 234 automatically displays a single search window SW on the top screen of the BIM browser. This single search window SW may be displayed overlapping a portion of the 3D drawing data 33a, or it may be displayed at the bottom or top of the BIM browser without overlapping with the 3D drawing data 33a.

[0053] When a user wants to display the required parts, the user inputs natural language or an image into the search window SW to perform a fuzzy search (#33). Next, the natural language or image input into the search window SW is sent from the user device 3 to the search device 2 via the BIM device 1 or directly, and the extraction unit 233 of the search device 2 extracts attribute information corresponding to the natural language or image input into the search window SW (#26). For example, as shown in FIG. 8 , if "sleeve-type equipment" is input into the search window SW, the extraction unit 233 extracts all sleeve parts based on multiple tables stored in the BIM source database DBa and the expanded database DBb created by the acquisition unit 232. Next, the display control unit 234 generates a display signal for displaying on the display 35 a parts group image including a collection of parts corresponding to the attribute information extracted by the extraction unit 233, and transmits the display signal to the user device 3 via the BIM device 1 or directly (#27). Then, a parts group image including an aggregate of parts corresponding to the attribute information extracted by the extraction unit 233 is displayed on the display 35 of the user device 3 (#34). In the example shown in Fig. 8, "device of type sleeve" is entered in the search window SW, and a parts group image of sleeves included in a building is displayed on the display 35 of the user device 3.

[0054] FIG. 5 shows another flowchart relating to a BIM search method executed by the search device 2, which can be added as a function to the BIM system 100 in which the three-dimensional drawing data 33a is stored.

[0055] In another example, when a dimension conversion instruction is entered in the search window SW (#60), the conversion unit 235 of the search device 2 converts the dimensions of the corresponding parts in the part group image corresponding to the attribute information extracted by the extraction unit 233 (#50). Then, 3D drawing data 33a including the dimension-converted parts is transmitted to the user device 3 (#12). In the example shown in Fig. 10, the dimensions of the sleeves indicated by the dashed lines are converted in bulk based on a dimension change instruction entered in the search window SW in natural language, such as "Change the length of the sleeve in the basement that is 400 to 380."

[0056] In another example, upon a user request for determination (#61), the determination unit 236 of the search device 2 determines whether the part group image corresponding to the attribute information extracted by the extraction unit 233 deviates from the design standard (#51). For example, for multiple joints displayed by inputting an ambiguous sentence such as "the type of joint on the 2nd floor" (#61), the determination unit 236 automatically detects joints whose quantity differs from the design standard and should be added or deleted. The determination result is then transmitted to the user device 3 via the BIM device 1 or directly, and the display control unit 234 displays the determination result together with the part group image on the display 35 of the user device 3 (#62). Based on this determination result, the user (e.g., a designer) can add, delete, or modify parts. The determination result may be displayed in a table format, or by displaying parts that deviate from the design standard in a different color. Any display format that clearly indicates the determination result may be used.

[0057] In another example, a user inputs a part type change request in natural language or an image into the search window SW (#63, an example of a specification change instruction). This part type change request is sent to the search device 2 via the BIM device 1 or directly. If the type change request is a BIM part provided in advance by the BIM device 1 or a BIM part acquired from an external source by the user, the acquisition unit 232 of the search device 2 searches for and acquires the part from the data stored in the memory 13 of the BIM device 1 or the memory 33 of the user device 3 (#13, #52). On the other hand, if the type change request is a BIM part published as web data but not stored in the memory 33, the part is searched for and acquired from the web data (#52). For example, if "change door from single swing to double swing" is input into the search window SW, a list of information about double swing doors with the same dimensions or a list of images of double swing doors may be displayed. This allows the user to easily change the type of parts by simply inputting the type change content into the search window SW.

[0058] In another example, the user requests the creation procedure for a parts group image using natural language or images in the search window SW (#64). Next, the acquisition unit 232 of the search device 2 acquires a video showing the creation procedure for the parts group image in cooperation with the generation AI or the BIM device 1, and transmits the video signal to the user device 3 via the BIM device 1 or directly (#53). Next, the display control unit 234 displays the video of the creation procedure for the parts group image on the display 35 of the user device 3 (#65). For example, a vague sentence such as "One of the doors on the second floor that has a single swing" is input, and a video of the creation procedure for the parts group image is played for multiple doors displayed. This video explains the creation procedure, such as double-clicking "View" - "Floor Plan" - "Level" in the "Project Browser," then clicking the "Architecture" tab - "Construction" panel - "Door." This allows the BIM system 100 to be used as a learning tool for operation, further enhancing user convenience.

[0059] In another example, when a user such as a contractor completes scheduled construction, the user transmits construction completion information to the search device 2 via the BIM device 1 or directly (#66). This construction completion information is voice in natural language or construction photos as images. The acquisition unit 232 of the search device 2 acquires 3D drawing data 33a stored in the user device 3 or the BIM device 1 (#14). In the example shown in FIG. 11, construction completion information for a sleeve in a basement is transmitted, and the acquisition unit 232 of the search device 2 cooperates with the generation AI and the BIM device 1 to acquire part group images related to the construction completion information.

[0060] Next, the extraction unit 233 of the search device 2 extracts matches or differences between the three-dimensional drawing data 33a and the construction completion information, and transmits a match / difference signal to the user device 3 via the BIM device 1 or directly (#54). In the example shown in FIG. 11, the construction completion information for the sleeve in the basement is compared with the three-dimensional drawing data 33a, and one sleeve is added. Next, if a user, such as a manager or designer, approves the changes, the three-dimensional drawing data 33a is changed (#67, #15). In the example shown in FIG. 10, the added sleeve is approved, and the three-dimensional drawing data 33a is modified.

[0061] In the above-described embodiment, the following configuration is contemplated: (1) A BIM search method executed by a computer is a BIM search method that can be added to a BIM system 100 in which three-dimensional drawing data 33a is stored, and includes a setting step (#21) of setting a single search window SW on the screen (display 35) of the BIM system 100, an acquisition step (#22) of acquiring attribute information on multiple types of parts included in the three-dimensional drawing data 33a stored in the BIM system 100, an extraction step (#26) of extracting attribute information of parts corresponding to natural language or an image entered in the search window SW, and a display step (#27) of displaying on the screen (display 35) a part group image including the three-dimensional arrangement in the three-dimensional drawing data 33a of an aggregate of parts corresponding to the attribute information extracted in the extraction step (#26).

[0062] The BIM search method according to this embodiment includes a setting step (#21) of setting a single search window SW on the screen of the BIM system 100 into which natural language or images can be input, and a display step (#27) of displaying a parts group image including a collection of parts corresponding to attribute information. Therefore, a BIM user does not need to perform complex search operations to extract, for example, information about specific parts arranged on the second floor from a data file; they can automatically view the parts group image simply by inputting natural language or the like into the single search window SW. As a result, even someone unfamiliar with BIM search operations can obtain the information they need and check the quantity, arrangement, etc. by looking at the parts group image.

[0063] Furthermore, by simply entering natural language into a single search window, images of parts can be automatically viewed, making it possible to estimate and order any missing parts according to the progress of the project without any omissions. This makes it a highly convenient BIM search method that can increase the work efficiency of BIM users.

[0064] (2) In the BIM search method of (1), it is preferable that the natural language is a sentence containing one or more attributes of the part.

[0065] As in this embodiment, if the natural language input into a single search window SW is a sentence that includes one or more part attributes, it is possible to improve the convenience of BIM users involved in design, construction, and management. For example, if an ambiguous sentence such as "the equipment on the second floor that is a sleeve type" is input, an image of the sleeve on the second floor will be displayed as a part group image, allowing the BIM user to easily check the parts.

[0066] (3) In the BIM search method of (1) or (2), in the display step (#27), it is preferable to further display on the screen (display 35) a list of information on parts corresponding to the attribute information extracted in the extraction step (#26).

[0067] As in this embodiment, by displaying a list of information on parts corresponding to the attribute information extracted in the extraction step (#26), not only can you confirm whether the natural language you entered is correct, but you can also select the parts you want to display from the list of information on parts.

[0068] (4) In any one of the BIM search methods (1) to (3), it is preferable to further include a conversion step (#50) of collectively converting the dimensions of parts corresponding to the attribute information extracted in the extraction step, based on a dimension change instruction written in natural language entered in the search window SW, for which a dimension change instruction has been issued.

[0069] As in this embodiment, if a conversion step (#50) for converting part dimensions in bulk is provided, it is possible to input an ambiguous sentence such as "a sleeve-type device on the 2nd floor with a length of 400" and change the dimensions of multiple displayed sleeves in bulk.

[0070] (5) In any one of the BIM search methods (1) to (4), it is preferable to further include a judgment step (#51) for determining whether the parts corresponding to the attribute information extracted in the extraction step (#26) deviate from the design criteria.

[0071] As in this embodiment, by providing a judgment step (#51) that judges whether or not there is a deviation from the design standards, it is possible to automatically detect joints that differ in quantity from the design standards and should be added or deleted from the multiple joints displayed by inputting vague sentences such as "the type on the 2nd floor is a joint."

[0072] (6) In any one of the BIM search methods (1) to (5), in the display step (#27), it is preferable to display elements other than the part group image in the three-dimensional drawing data 33a in a skeleton format on the screen (display 35).

[0073] As in this embodiment, by displaying elements other than the part group image as a skeleton, the connection relationships with other elements become clear at a glance, making it easier for BIM users to notice errors in quantities, dimensions, etc.

[0074] (7) In any one of the BIM search methods (1) to (6), in the acquisition step (#23), it is preferable to acquire attribute information for each part and store the acquired attribute information in multiple tables corresponding to each part.

[0075] The BIM system 100 stores attribute information for parts using a unique data structure. Therefore, by acquiring attribute information for each part and providing a table corresponding to each part, as in this embodiment, it becomes easier to associate natural language and images with each part, thereby improving search accuracy.

[0076] In the BIM search method of (8) (7), in the extraction step (#26), it is preferable to convert natural language into a search query for each table and extract attribute information from the table.

[0077] As in this embodiment, the extraction step (#26) converts natural language into a table search query, making it possible to accurately extract attribute information for parts, and allowing the user to check all parts that correspond to the input natural language or image.

[0078] (9) In any one of the BIM search methods (1) to (8), in the acquisition step (#23), related words related to the attribute information are acquired in association with the attribute information, and in the extraction step (#26), attribute information of parts corresponding to the related words entered in the search window SW is preferably extracted.

[0079] As in this embodiment, by acquiring related words related to attribute information in association with the attribute information, it is possible to acquire attribute information corresponding to natural language, etc., even if the notation is unique to the BIM system 100. For example, if "a component for inserting piping where it interferes with a beam" is entered, it is possible to display an image of a group of sleeve parts, making it a search method that is easy for users to use.

[0080] (10) In the BIM search method of (9), it is preferable that the related words are different from the names registered in the BIM system 100.

[0081] If the related words are different from the names registered in the BIM system 100, as in this embodiment, then it becomes possible to search by entering "ducts less than 10m in length" using aliases (for example, length or width) for the notation on the BIM system (for example, L or W), thereby further increasing the versatility of the search method.

[0082] (11) In any one of the BIM search methods (1) to (10), in the acquisition step (#23), interconnection information of multiple parts is further acquired by associating it with attribute information as a word containing a common value, and in the extraction step (#26), attribute information of parts corresponding to natural language containing the word entered in the search window SW is preferably extracted.

[0083] As in this embodiment, by acquiring interconnection information for parts, it becomes possible to search for connection information for outdoor units, indoor units, air conditioning equipment, piping, etc. As a result, by entering, for example, "air conditioning-related connection diagram on the second floor," it is possible to confirm the positional relationships of connected devices related to air conditioning.

[0084] (12) In any one of the BIM search methods (1) to (11), it is preferable that the natural language entered in the search window SW is selected from a plurality of natural language candidates displayed in the search window SW.

[0085] As in this embodiment, by displaying natural language candidates related to the word entered by the user in the search window SW, search convenience can be improved.

[0086] (13) In any one of the BIM search methods (1) to (12), in the extraction step (#26), it is preferable to extract attribute information of the parts from natural language generated by image analysis of the image entered in the search window SW and linked to the shape of the parts.

[0087] As in this embodiment, if natural language is linked to the shape of parts analyzed using image analysis, then, for example, by entering "a column with a trapezoidal cross section," it is possible to easily search for parts with special shapes.

[0088] (14) In any one of the BIM search methods (1) to (13), it is preferable that the display step (#53) displays a video showing the steps for creating a part group image.

[0089] As in this embodiment, by displaying a video showing the steps for creating a part group image, it can also be used as a tool for learning how to operate the BIM system 100, thereby further improving user convenience.

[0090] (15) In any one of the BIM search methods (1) to (14), it is preferable that the extraction step (#54) extracts attribute information corresponding to the construction completion information (#66).

[0091] As in this embodiment, by extracting attribute information corresponding to the construction completion information (#66), the completed portion can be easily confirmed in the three-dimensional drawing data 33a.

[0092] (16) In the BIM search method of (15), the construction completion information (#66) is preferably voice as natural language or construction photographs as images.

[0093] If the construction completion information (#66) is voice or construction photographs as in this embodiment, the construction completion information can be input in real time at the construction site.

[0094] In the BIM search method of (17) (15) or (16), it is preferable that in the extraction step (#54), the matching points or differences between the three-dimensional drawing data 33a and the construction completion information (#66) are further extracted, and in the display step (#53), the matching points or differences are reflected in the part group image and displayed on the screen (display 35).

[0095] As in this embodiment, by extracting the similarities or differences between the three-dimensional drawing data 33a and the construction completion information (#66), the construction details can be shared with designers, etc., and the details of design changes, etc. can be easily confirmed.

[0096] (18) In any one of the BIM search methods (1) to (17), it is preferable that the natural language generated by image analysis of natural language or images includes part specification change instructions (#63).

[0097] By executing a part specification change instruction as in this embodiment, it is possible to easily search for a door that needs to be changed from a single swing to a double swing, or for a wall that needs to be made fireproof.

[0098] In the BIM search method of (19) (18), it is preferable that the acquisition step (#52) acquires attribute information of parts corresponding to the specification change instruction (#63) from data stored in the BIM system 100 or web data, and further includes a conversion step (#50) that converts parts for which specification change instructions have been issued among the parts corresponding to the attribute information extracted in the extraction step (#54) based on the specification change instruction entered in the search window SW.

[0099] As in this embodiment, if parts corresponding to specification change instructions can be obtained from web data in addition to data stored in the BIM system 100, the range of parts selection can be expanded.

[0100] (20) A BIM device 1 equipped with any one of the BIM search methods (1) to (19).

[0101] According to this embodiment, the added value of a BIM can be increased by installing a BIM search method having the above-described effects.

[0102] [Other Embodiments] (a) The BIM source database DBa and the extended database DBb described above may be in NoSQL format or SQL format, and may be in any form as long as they are databases. (b) Some of the steps in the above-described embodiments may be omitted, or may be combined appropriately to implement the functions.

[0103] Second Embodiment As shown in FIG. 12 , the CAD system includes a BIM device 1X, a design support device 2X, and a user device 3X. The BIM device 1X is a server owned by a vendor that manages and operates BIM. The design support device 2X is a server owned by a vendor that develops and provides add-in software for BIM. The user device 3X is a terminal on which BIM is installed and owned by a user who designs, constructs, and manages structures such as buildings and bridges. For convenience, one user device 3X is shown as an example terminal, but different users who design, construct, or manage structures may own multiple terminals. These terminals may be desktop PCs, laptops, tablets, smartphones, or the like.

[0104] The BIM device 1X, the design support device 2X, and the user device 3X are connected to each other via a network 4X so that they can communicate with each other. The BIM device 1X includes a processor 11X, a communication IF 12X, a memory 13X, and an input / output IF 14X. Although the BIM device 1X includes other functional units, only the functional units related to this embodiment are described.

[0105] The memory 13X stores a BIM program 13aX. The processor 11X is the central part of the computer, receiving instructions and performing calculations and data processing. The processor 11X includes a CPU (central processing unit), a GPU (graphics processing unit), an NPU (neural network processing unit), or other hardware for executing the BIM program 13aX stored in the memory 13X. In other words, the processor 11X has an arithmetic processing circuit, input ports, and output ports. The processor 11X may be an ASIC, FPGA, or SoC, and is not particularly limited.

[0106] The communication IF 12X is a communication interface that has a function of transmitting signals output from the processor 11X to the design support device 2X and the user device 3X via the network 4X and a function of sending signals received from the design support device 2X and the user device 3X via the network 4X to the processor 11X. The processor 11X can transmit and receive signals between the memory 13X and the communication IF 12X. The input / output IF 14X functions as an interface with input devices (e.g., a keyboard, a mouse, a touch panel, a touch pad, etc.) and output devices (e.g., a display, a speaker, etc.).

[0107] The memory 13X stores data within the computer and includes a main memory and a secondary memory. The main memory is a storage area for temporarily storing programs and data and is composed of RAM or the like. The secondary memory is a non-temporary storage area for permanently storing programs and data and is composed of an HDD, SSD or the like. The secondary memory may also be external hardware such as a cloud server or a rental server.

[0108] The BIM program 13aX is an application stored in the secondary memory, read into the main memory, and executed by the processor 11X. The BIM program 13aX is configured using REVIT, an example of a BIM. Note that the BIM program 13aX may be configured using other programs such as Archicad (registered trademark) or GLOBE (registered trademark).

[0109] The BIM program 13aX is software for integrated management of digital information related to the design, construction, and management of buildings. The BIM program 13aX can create a three-dimensional digital model (design model 33aX). Each part of the design model 33aX is associated with attribute information stored in secondary memory, such as the type of building material, specifications, performance, cost, construction procedure, and maintenance information. This allows the design model 33aX to be used throughout the lifecycle of the design, construction, and management of a structure.

[0110] The design support device 2X includes a processor 21X, a communication IF 22X, a memory 23X, an input / output IF 24X, and a display 25X. The processor 21X, the communication IF 22X, the memory 23X, and the input / output IF 24X have the same basic configuration as the processor 11X, the communication IF 12X, the memory 13X, and the input / output IF 14X of the BIM device 1X, so a brief description thereof will be omitted. Note that the design support device 2X includes other functional units, but only the functional units relevant to this embodiment are described.

[0111] The memory 23X stores an add-in program 23aX. The add-in program 23aX is stored in the secondary memory (storage unit 23AX) of the memory 23X, read into the main memory, and executed by the processor 21X. The add-in program 23aX is a design support program that is sent to the BIM device 1X via the communication IF 22X and the network 4X, and adds functions to the BIM program 13aX. In this embodiment, the add-in program 23aX has an extended function that builds a design model 33aX by stacking parts in order by executing a script generated by the generation AI based on the contents of the input field IPX. Details of the add-in program 23aX will be described later.

[0112] The display 25X is provided in the design support device 2X and is a display device that displays text, images, videos, and other visual information. This display 25X can display a BIM by executing the BIM program 13aX in which the add-in program 23aX is implemented by the processor 21X. The display 25X is configured with an LCD display, an LED display, an OLED display, a plasma display, or the like. Note that the display 25X is not particularly limited as long as it is hardware that can execute the BIM program 13aX in which the add-in program 23aX is implemented by the processor 21X and display the design model 33aX.

[0113] The user device 3X includes a processor 31X, a communication IF 32X, a memory 33X, an input / output IF 34X, a display 35X, and an operation unit 36X. The processor 31X, the communication IF 32X, the memory 33X, the input / output IF 34X, and the display 35X have the same basic configuration as the processor 21X, the communication IF 22X, the memory 23X, the input / output IF 24X, and the display 25X of the design support device 2X, and therefore a detailed description thereof will be omitted. Note that the user device 3X includes other functional units, but only the functional units relevant to this embodiment are described here.

[0114] A building design model 33aX is stored in the memory 33X. The operation unit 36X is constructed with at least one element selected from the group consisting of a touch switch, a keyboard, a mouse, a scanner, and a voice input speaker. When a user operates the operation unit 36X, a signal corresponding to the operation is input to the processor 31X.

[0115] (Configuration of Design Support Device) FIG. 13 shows a block diagram of a design support device 2X that supports the construction of a design model 33aX. The design support device 2X can exchange information with a generation AI (Artificial Intelligence). The generation AI includes any language model or large language model (LLM), and is configured, for example, by ChatGPT, Gemini, or Cloude. The design support device 2X includes a storage unit 23AX and an add-in program 23aX.

[0116] 13 functions as a secondary memory of the above-mentioned memory 23X. The storage unit 23AX stores a script database DBaX and a design model database DBbX.

[0117] The script database DBaX contains program code (such as Dynamo Python) used in REVIT in JavaScript Object Notation (JSON) format, with DB column names for each part. The parts include structural equipment such as columns and beams, exterior and interior equipment such as windows, doors, and wall materials, accessory equipment such as sleeves, and building equipment such as indoor and outdoor air conditioning units. The design model database DBbX contains design models 33aX that correspond to the program code stored in the script database DBaX.

[0118] 13, the add-in program 23aX includes a setting unit 231X, an acquisition unit 232X, a part generation unit 233X, a display control unit 234X, a learning unit 235X, a management unit 236X, and a restriction unit 237X. The add-in program 23aX is an API (Application Programming Interface) or a plug-in system that adds these functional units to the BIM program 13aX.

[0119] The setting unit 231X sets a single input field IPX (see FIG. 15 ) on the top screen (display 35X) of the CAD system (user device 3X). As shown in FIG. 15 , the setting unit 231X may automatically display the single input field IPX on the top screen of the BIM browser displayed on the display 35X of the user device 3X, or may provide a display button for the input field IPX on the top screen of the BIM browser. That is, the setting unit 231X inserts an add-in program 23aX that sets the single input field IPX into the initial screen startup program of the BIM program 13aX. The user can input design instructions, including natural language, images, or files, into this input field IPX. Input into the input field IPX is performed via an operation unit 36X consisting of at least one element of a touch switch, keyboard, mouse, scanner, voice input speaker, etc. Here, natural language includes words such as keywords, word groups combining multiple words, phrases consisting of words and associated words, sentences consisting of combinations of multiple phrases, etc. In this embodiment, the natural language is preferably a sentence containing one or more part attributes (such as names). The images may be still images or videos. The files include project data, Excel data, etc.

[0120] The acquisition unit 232X acquires attribute information related to multiple types of parts included in the design model 33aX stored in the CAD system (user device 3X). In other words, the acquisition unit 232X acquires attribute information stored in the memory 33X of the CAD system (user device 3X) as attribute information related to multiple types of parts included in the design model 33aX for each part via the BIM device 1X.

[0121] At this time, the acquisition unit 232X can acquire related words related to the attribute information in association with the attribute information. For example, "a component into which a pipe is inserted at a location where it interferes with a beam" is acquired in association with "sleeve." If the related words are ones that the generation AI has already learned, they may be acquired by linking with the generation AI. If the related words are ones that the generation AI has not learned, they may be customized by inputting learning data into the generation AI.

[0122] The natural language, image, or file entered in the input field IPX may include script modification instructions. The script modification instructions are natural language instructions for changing at least one selected from the quantity, dimensions, and material of parts, such as "reduce the number of pillars and make them thicker," "make the wall 1 meter higher," "add three doors," or "change the exterior wall material to concrete." The generation AI generates the modification script based on this natural language. In this case, the acquisition unit 232X acquires parts corresponding to the script modification instructions from data stored in the memory 33X of the CAD system (user device 3X) or from web data. If the script modification instructions are for BIM parts provided in advance by the BIM device 1X or BIM parts acquired by the user from an external source, the acquisition unit 232X acquires the parts from the data stored in the memory 33X. On the other hand, if the script modification instructions are for BIM parts that are published as web data but not stored in the memory 33X, the acquisition unit 232X acquires the parts from web data.

[0123] It is preferable that the script modification instruction is directed only to the parts selected via the operation unit 36X of the user device 3X or only to the parts based on the conditions entered in the input field IPX. The conditions entered in the input field IPX are conditions for selecting parts using natural language, such as "From the ten identical sleeves, please select one with a length of 400 or more."

[0124] The parts generation unit 233X builds the design model 33aX by stacking parts in order by executing a script generated by the generation AI based on the contents of the natural language, image, or file entered into the input field IPX from the operation unit 36X of the user device 3X. The natural language, image, or file entered into the input field IPX is sent to the design support device 2X via the BIM device 1X or directly from the user device 3X, and the parts generation unit 233X generates a script based on the contents of the input field IPX. The "contents of the input field IPX" includes cases where the natural language, image, or file entered into the input field IPX is used as is, and cases where the natural language, image, or file is processed into one suitable for script generation.

[0125] The part generation unit 233X executes the script generated by the generation AI and stacks the parts in order. For example, if "Please make the exterior walls of a 10-story building" is input into the input field IPX, the generation AI processes the natural language and generates a script that reflects the content of the input field IPX, "Create walls 20 cm thick and 5 m high for each floor to create the exterior walls of a 10-story building." Based on this script, the part generation unit 233X builds the design model 33aX by stacking 10 floors of 20 cm thick, 5 m high walls (see Figures 16 and 17). This script is program code (such as Dynamo Python) that builds the design model 33aX.

[0126] The part generation unit 233X may execute a script generated by the generation AI based on attribute information of each part, including at least one of the part's quantity, dimensions, and material. The script is program code (such as Dynamo Python) that extracts a parts group image including an assembly of parts corresponding to the attribute information.

[0127] The part generation unit 233X may execute a change script generated by the generation AI based on a modification instruction entered into an input field IPX from the operation unit 36X of the user device 3X. This change script is program code (such as Dynamo Python) that executes modification, deletion, and addition of parts to the design model 33aX. For example, if a user inputs a command to "make the exterior walls of a 10-story building," but the parts are stacked up to nine floors, the generation AI generates a change script based on a modification instruction entered into the input field IPX, such as "It is nine floors, so please change it to ten floors," and executes this change script to construct the modified design model 33aX.

[0128] The parts generation unit 233X may confirm the design model 33aX by a script confirmation operation via the operation unit 36X of the user device 3X. For example, by confirming the design model 33aX corrected based on a correction instruction input in the input field IPX, such as "This is the 9th floor, please change it to the 10th floor," the design model 33aX is constructed by stacking parts for 10 floors in order. The display control unit 234X may provide an operation button (for example, an "Accept" button shown in FIG. 15 ) on the display 35X for the script confirmation operation.

[0129] The display control unit 234X displays the input field IPX set by the setting unit 231X and the design model 33aX generated by the part generation unit 233X on the display 35X (see FIG. 16 ). The display control unit 234X displays the design model 33aX constructed by the part generation unit 233X by stacking parts in order based on the content of the natural language, image, or file input into the input field IPX on the display 35X. Specifically, the display control unit 234X activates the display control function of the BIM device 1X to display the design model 33aX on the display 35X (the same applies below).

[0130] The display control unit 234X may display a parts group image including an assembly of parts on the display 35X based on the design instructions (see FIG. 18). For example, by inputting "Please design a sleeve corresponding to the piping I just designed" in the input field IPX, the parts group image, which is an assembly of sleeves shown in FIG. 18, is displayed on the display 35X. The display control unit 234X may also switch between a 3D view and a 2D view so that the "arrangement order of parts" and "layer structure" can be seen. Furthermore, the display control unit 234X may provide operation buttons on the display 35X to enable "redo" and "partial undo."

[0131] The display control unit 234X may display the script generated by the generation AI based on the content of the natural language, image, or file entered in the input field IPX (see FIG. 17). As shown in FIG. 17 → FIG. 16, for example, the flow of "design instructions" → "generated script" → "preview" is visualized. At this time, the display control unit 234X may display an explanation of the script generated by the generation AI. The display control unit 234X may also provide a dashboard-like screen that displays a summary of the script or only important parameters in an easy-to-read format.

[0132] The display control unit 234X may display a script that has been modified based on modification instructions entered in the input field IPX via the operation unit 36X of the user device 3X. This modified script may display a comment field for each line, or a screen may be provided that allows comparison of the before and after modifications. Parameters such as "part name," "dimensions," and "material" may be highlighted so that changes can be seen at a glance. The display control unit 234X then displays a design model 33aX generated based on the modified script on the display 35X. At this time, an animation may be used to visually indicate which parts have been added to which positions.

[0133] The display control unit 234X may display a parts group image including an aggregate of parts corresponding to the attribute information on the display 35X based on design instructions having attribute information including at least one selected from the quantity, dimensions, and material of the parts (see FIGS. 19 and 20 ). For example, by inputting "Select the item in the basement that is 400 meters long or longer" into the input field IPX, a parts group image of an aggregate of sleeves from the parts group image shown in FIG. 19 is displayed on the display 35X. Then, by inputting a correction instruction into the input field IPX, such as "Change the sleeve in the basement that is 400 meters long to 380 meters," the parts group image shown in FIG. 20 is displayed on the display 35X. This allows the user to visually view the parts group image and confirm the design model 33aX simply by inputting natural language, an image, or a file into a single input field IPX.

[0134] The display control unit 234X may display a video on the display 35X showing the steps for creating a part group image. For example, it may display how to draw multiple sleeves displayed as part group images in association with pipes or ducts. This makes it possible to use the video as a learning tool for operating a CAD system, further improving user convenience.

[0135] The display control unit 234X may display design information based on design instructions including questions. For example, in response to the question "Is there anything strange?", the learning unit 235X (described later) checks the validity of the parameters and structure of the design model 33aX, and the display control unit 234X displays "problematic points" as design information. In response to the question "What should I do next?", the learning unit 235X evaluates the design progress status, and the display control unit 234X displays "the next operation" as design information.

[0136] The display control unit 234X may display an optimal solution of the design information. For example, the optimal solution of the design information utilizes past learning data, such as by referencing and automatically presenting best practices and design examples for each part learned by the learning unit 235X, or by optimizing the design using previous design information.

[0137] The learning unit 235X learns the design information of each part in the design model 33aX stored in the design model database DBbX. This design information is stored in the script database DBaX in association with design instructions or modification instructions and generated scripts. The learning unit 235X learns the design information of each part in the stored design model 33aX, and can check the validity of the parameters and structure of the design model 33aX or evaluate the design progress. The learning unit 235X also learns the design information of each part in the stored design model 33aX, and can refer to and automatically present best practices and design examples for each learned part, or perform design optimization using previous design information.

[0138] The management unit 236X manages the versions of the scripts stored in the script database DBaX. By managing the versions of the scripts by the management unit 236X, it becomes possible to track which settings were used at which stage in the design model 33aX.

[0139] The management unit 236X may manage access rights related to the construction of the design model 33aX. The management unit 236X assigns different rights to each user and limits the range of operations that can be performed. This makes it possible to manage access rights according to the difficulty and importance of the design model 33aX, such as allowing only the team leader to make major design changes.

[0140] The restriction unit 237X restricts the contents of the input field IPX to create a simple command set to be input to the generation AI. For example, the contents of the input field IPX, such as "Create walls to form a 4x2 room...", are converted into a simple command pattern such as "Make four walls, turn right, and make two more...". This eliminates the inconvenience of the generation AI generating programming language from natural language, which tends to result in complex code and prone to execution errors. Furthermore, allowing free programming can eliminate the inconvenience of complex structures such as for statements, if statements, and functions, which can lead to a loss of operational stability.

[0141] The restriction unit 237X may be configured to limit the simple command set to a group of simple commands that directly call APIs (Application Programming Interfaces), allowing multiple APIs to be called, thereby ensuring stable operation of the scripts generated by the generation AI and enabling complex operations to be realized with a combination of simple commands.

[0142] (Design Support Method) Figure 14 shows a flowchart of a design support method executed by a design support device 2X, which can add functions to a CAD system storing a design model 33aX. The design support method shown in Figure 14 is merely a representative example, and other flowcharts for executing each functional unit of the design support device 2X in the above-described embodiment are omitted. In this embodiment, an example is shown in which information from a user device 3X is transmitted and received to a design support device 2X via a BIM device 1X. However, information from the user device 3X may be transmitted and received directly to the design support device 2X, or information may be transmitted and received only between the user device 3X and the BIM device 1X with an add-in program 23aX pre-installed in the BIM program 13aX of the BIM device 1X.

[0143] As shown in FIG. 14 , the add-in program 23aX of the design support device 2X is sent to the BIM device 1X, the add-in program 23aX is implemented in the BIM program 13aX, and the BIM program 13aX with the add-in program 23aX implemented is sent to the user device 3X (#21X). This allows a BIM having a single input field IPX to be displayed on the display 35X of the user device 3X, as shown in FIG. 15 . Next, the user (designer) inputs design instructions using the input field IPX (#31X), and the parts generation unit 233X executes a script generated by the generation AI based on the content of the natural language, image, or file entered in the input field IPX (#22X). In the example of FIG. 15 , the user enters "Please create the exterior walls of a 10-story building" into the input field IPX, and the generation AI processes the natural language and executes a script with the content of the input field IPX: "Create walls 20 cm thick and 5 m high for each floor to create the exterior walls of a 10-story building." The parts generation unit 233X executes the script, and the BIM device 1X edits, arranges, and adjusts each part, and stacks the parts to construct the design model 33aX (#11X). At this time, a part may be selected by inputting a natural language, an image, or a file into the input field IPX in FIG. 15, or by selecting a part from the corresponding tab.

[0144] Next, the design model 33aX is sent from the BIM device 1X to the user device 3X, and the display control unit 234X activates the display control function of the BIM device 1X to display the design model 33aX on the display 35X of the user device 3X. If the design model 33aX constructed in this manner does not meet the user's expectations, the user inputs a correction instruction into the input field IPX (#32X). For example, by inputting "Please select the item in the basement that is 400 meters long or longer" into the input field IPX, a parts group image representing a collection of sleeves is displayed on the display 35X from the parts group image shown in FIG. 19, and a correction instruction is input into the input field IPX shown in FIG. 20, such as "Please change the sleeve in the basement that is 400 meters long to 380 meters." Next, the parts generation unit 233X executes the change script generated by the generation AI based on the correction instruction input into the input field IPX (#23X). The part generation unit 233X executes the change script, causing the BIM device 1X to edit, arrange, and adjust each part, modify the parts, and reconstruct the design model 33aX (#12X).

[0145] Next, the modified design model 33aX is sent from the BIM apparatus 1X to the user apparatus 3X, and the display control unit 234X activates the display control function of the BIM apparatus 1X to display the design model 33aX on the display 35X of the user apparatus 3X. If the modified design model 33aX is in line with the user's intentions, the part generation unit 233X confirms the design model 33aX, in which the parts are stacked in order, by performing a script confirmation operation (#33X) via the operation unit 36X of the user apparatus 3X. Next, the learning unit 235X associates the design instructions or correction instructions with the generated script, stores them in the script database DBaX, and learns the design information of each part (#24X).

[0146] When displaying the required parts, the user enters natural language, images, or files into the input field IPX to provide design instructions, including attribute information (#34X). The natural language, images, or files entered into the input field IPX are then sent from the user device 3X to the design support device 2X via the BIM device 1X or directly. The part generation unit 233X of the design support device 2X then executes the script generated by the generation AI based on the attribute information for each part, including at least one of the part's quantity, dimensions, and material (#25X). For example, if the design instruction "Please design a sleeve corresponding to the piping I just designed" is entered into the input field IPX shown in FIG. 18, a parts group image representing a collection of sleeves is constructed from the parts group image. The modified design model 33aX is then sent from the BIM device 1X to the user device 3X, and the display control unit 234X activates the display control function of the BIM device 1X to display the design model 33aX, consisting of the parts group image, on the display 35X of the user device 3X (#35X).

[0147] The above-described embodiment brings to mind the following configuration: (1) A design support device 2X that supports the construction of a design model 33aX includes a setting unit 231X that sets an input field IPX into which design instructions including natural language, images, or files can be input, a display control unit 234X that displays the input field IPX and the design model 33aX, and a part generation unit 233X that builds the design model 33aX by stacking parts in order by executing a script generated by a generation AI based on the contents of the input field IPX.

[0148] The design support device 2X according to this embodiment includes an input field IPX that allows input of design instructions, including natural language, images, or files. Therefore, it is sufficient to input design instructions for the parts (walls, floors, roofs, equipment, etc.) of the design model 33aX. Furthermore, the part generation unit 233X according to this embodiment executes a script generated by a generation AI based on the contents of the input field IPX to build the design model 33aX by stacking the parts in order, making design easy even for designers unfamiliar with CAD systems. Furthermore, the display control unit 234X according to this embodiment displays the input field IPX and the design model 33aX, allowing designers to intuitively understand how the design instructions entered in the input field IPX will be reflected in the design model 33aX. Thus, the design support device 2X allows even designers unfamiliar with CAD systems to easily design.

[0149] (2) In the design support device 2X of (1), it is preferable that the display control unit 234X further displays the script generated by the generation AI based on the contents of the input field IPX.

[0150] As in this embodiment, by displaying the script generated by the generation AI based on the contents of the input field IPX, the programming process can be understood, which also contributes to improving programming skills.

[0151] (3) In the design support device 2X of (2), it is preferable that the display control unit 234X is configured to be able to display the script that has been changed based on the correction instructions input in the input field IPX.

[0152] As in this embodiment, by displaying the modified script based on the modification instructions entered in the input field IPX, the validity of the modified script can be evaluated and the level of the modification instructions can be improved.

[0153] (4) In the design support device 2X of (3), it is preferable that the design instructions include at least one correction instruction selected from the number, dimensions, and material of parts.

[0154] As in this embodiment, if at least one modification instruction selected from the quantity, dimensions, and material of the parts is included, it becomes possible to make batch conversions such as, for example, "Please change the length of the sleeve in the basement that is 400 to 380," thereby improving convenience.

[0155] (5) In the design support device 2X of (4), it is preferable that the correction instruction is directed only to the selected part or to the part based on the conditions input in the input field IPX.

[0156] As in this embodiment, if the correction instruction is directed only to the selected part or the part based on the conditions entered in the input field IPX, it is possible to prevent the inconvenience of accidentally correcting other parts.

[0157] (6) In any one of the design support devices 2X described in (1) to (5), it is preferable that the display control unit 234X displays a parts group image including a collection of parts corresponding to the attribute information based on a design instruction having attribute information including at least one of the quantity, dimensions, and material of the parts.

[0158] By displaying a parts group image including a collection of parts corresponding to attribute information as in this embodiment, unnecessary parts group images are hidden, making it possible to easily construct a design model 33aX even for complex structures.

[0159] (7) It is preferable that the design support device 2X of any one of (1) to (6) further comprises a learning unit 235X that learns design information of parts in the design model 33aX.

[0160] By learning the design information of the parts in the design model 33aX as in this embodiment, the performance of the design support device 2X can be improved.

[0161] (8) In the design support device 2X of (7), it is preferable that the display control unit 234X displays design information based on design instructions including questions.

[0162] As in this embodiment, if design information is displayed based on design instructions that include questions, for example, in response to a question such as "What should I do next?", the learning unit 235X can evaluate the design progress status, and the display control unit 234X can display the "next operation" as design information.

[0163] (9) In the design support device 2X of (7) or (8), it is preferable that the display control unit 234X is configured to be able to display an optimal solution of the design information.

[0164] As in this embodiment, by displaying the optimal solution for the design information, for example, best practices and design examples for each part learned by the learning unit 235X can be referenced and automatically presented.

[0165] (10) In the design support device 2X of any one of (2) to (5), it is preferable that the parts generation unit 233X finalizes the design model 33aX by a confirmation operation of the script.

[0166] If the design model 33aX is confirmed by a confirmation operation of the script as in this embodiment, an incorrect design model 33aX can be eliminated, and the accuracy of the design support device 2X can be improved.

[0167] (11) In any one of the design support devices 2X described in (2) to (5), it is preferable that the display control unit 234X is configured to be able to display an explanation of the script generated by the generation AI.

[0168] As in this embodiment, by displaying an explanation of the script generated by the generation AI, even a beginner programmer can understand the programming process, making it easier to give correction instructions and easily construct the design model 33aX.

[0169] (12) It is preferable that any one of the design support devices 2X in (1) to (11) further includes a management unit 236X that manages the version of the script.

[0170] By managing script versions as in this embodiment, it becomes possible to track which settings were used at which stage in the design model 33aX.

[0171] (13) It is preferable that any one of the design support devices 2X of (1) to (12) further includes a management unit 236X that manages access rights related to the construction of the design model 33aX.

[0172] By managing access rights for the construction of the design model 33aX as in this embodiment, it is possible to manage access rights according to the difficulty and importance of the design model 33aX, such as allowing only the team leader to make major design changes.

[0173] (14) It is preferable that any one of the design support devices 2X of (1) to (13) further comprises a restriction unit 237X that restricts the contents of the input field IPX and creates a simple command set to be input to the generation AI.

[0174] By limiting the contents of the input field IPX and creating a simple command set to be input to the generation AI, as in this embodiment, it is possible to eliminate the inconvenience that when the generation AI generates a programming language from natural language, etc., the code tends to become complex and execution errors are likely to occur.

[0175] [Other Embodiments] (a) In the above-described embodiment, the design support device 2X is added to the BIM device 1X, but the design support device 2X may be added to AutoCAD or open source CAD. (b) Some of the steps in the above-described embodiment may be omitted, or the steps may be combined appropriately to implement the functions.

[0176] The present disclosure is applicable to a BIM search method, a BIM device, and a design support device that supports the construction of a design model.

[0177] 1: BIM device, 2: search device, 3: user device, 4: network, 33a: 3D drawing data, 100: BIM system, 2X: design support device, 231X: setting unit, 233X: part generation unit, 234X: display control unit, 235X: learning unit, 236X: management unit, 237X: restriction unit, 33aX: design model, IPX: input field, SW: search window

Claims

1. A BIM search method that can be added to a BIM system in which three-dimensional drawing data is stored, the BIM search method being executed by a computer and comprising: a setting step of setting a single search window on the screen of the BIM system; an acquisition step of acquiring attribute information for each of multiple types of parts included in the three-dimensional drawing data stored in the BIM system; an extraction step of extracting the attribute information of the parts corresponding to natural language or an image entered in the search window; and a display step of displaying on the screen a parts group image including the three-dimensional arrangement in the three-dimensional drawing data of the collection of parts corresponding to the attribute information extracted in the extraction step.

2. The BIM search method according to claim 1, wherein the natural language is a sentence containing one or more attributes of the part.

3. A BIM search method as described in claim 1, wherein the display step further displays on the screen a list of information on the parts corresponding to the attribute information extracted in the extraction step.

4. A BIM search method as described in claim 1, further comprising a conversion step of collectively converting the dimensions of the parts corresponding to the attribute information extracted in the extraction step, based on the dimension change instructions composed of the natural language entered into the search window.

5. A BIM search method as described in claim 1, further comprising a determination step of determining whether the part corresponding to the attribute information extracted in the extraction step deviates from the design criteria.

6. A BIM search method as described in claim 1, wherein in the display step, elements other than the part group image in the three-dimensional drawing data are displayed as a skeleton on the screen.

7. A BIM search method as described in claim 1, wherein in the acquisition step, the attribute information is acquired for each of the parts, and the acquired attribute information is stored in a plurality of tables corresponding to each of the parts.

8. A BIM search method according to claim 7, wherein the extraction step converts the natural language into a search query for each of the tables and extracts the attribute information from the tables.

9. A BIM search method as described in claim 1, wherein in the acquisition step, related words related to the attribute information are acquired in association with the attribute information, and in the extraction step, the attribute information of the parts corresponding to the related words entered in the search window is extracted.

10. A BIM search method as described in claim 9, wherein the related words are different from the names registered in the BIM system.

11. A BIM search method as described in claim 1, wherein in the acquisition step, interconnection information of a plurality of the parts is further acquired by associating it with the attribute information as a word containing a common value, and in the extraction step, the attribute information of the parts corresponding to the natural language containing the word entered in the search window is extracted.

12. A BIM search method as described in claim 1, wherein the natural language entered in the search box is selected from a plurality of natural language candidates displayed in the search box.

13. A BIM search method as described in claim 1, wherein the extraction step extracts the attribute information of the part from natural language generated by image analysis of the image entered into the search window and linked to the shape of the part.

14. A BIM search method as described in claim 1, wherein the extraction step extracts attribute information corresponding to construction completion information that is voice as the natural language or construction photographs as the image.

15. A BIM search method as described in claim 14, wherein the extraction step further extracts points of agreement or differences between the three-dimensional drawing data and the construction completion information, and the display step reflects the points of agreement or differences in the part group image and displays it on the screen.

16. A BIM search method as described in claim 1, wherein the natural language or the natural language generated by image analysis of the image includes an instruction to change the specifications of the part.

17. A BIM search method as described in claim 16, further comprising a conversion step in which, in the acquisition step, the attribute information of the parts corresponding to the specification change instruction is acquired from data stored in the BIM system or web data, and the parts for which the specification change instruction has been issued are converted from the parts corresponding to the attribute information extracted in the extraction step based on the specification change instruction entered in the search window.

18. A BIM device comprising the computer that executes the BIM search method according to any one of claims 1 to 17.

19. A design support device that supports the construction of a design model, comprising: a setting unit that sets an input field into which design instructions including natural language, images, or files can be entered; a display control unit that displays the input field and the design model; and a parts generation unit that builds the design model by stacking parts in order by executing a script generated by a generation AI based on the contents of the input field.

20. The design support device according to claim 19, wherein the display control unit further displays the script.

21. The design support device according to claim 20, wherein the display control unit is configured to be able to display the script that has been modified based on the modification instructions entered in the input field.

22. A design support system according to claim 21, wherein said design instructions include at least one modification instruction selected from the number, dimensions and material of said parts.

23. A design support system according to claim 22, wherein the correction instruction is directed only to the selected part or to the part based on the conditions entered in the entry field.

24. A design support device as described in claim 19, wherein the display control unit displays a parts group image including a collection of parts corresponding to the attribute information based on the design instructions having attribute information including at least one of the quantity, dimensions, and material of the parts.

25. The design support device according to claim 19, further comprising a learning unit that learns design information of the part in the design model.

26. A design support device according to claim 25, wherein the display control unit displays the design information based on the design instructions including a question.

27. A design support device according to claim 25, wherein the display control unit is configured to be able to display an optimal solution of the design information.

28. A design support device according to claim 19, wherein the parts generation unit finalizes the design model by a confirmation operation of the script.

29. A design support device according to claim 19, wherein the display control unit is configured to be able to display an explanation of the script generated by the generation AI.

30. The design support device according to claim 19, further comprising a management unit that manages the versions of the scripts.

31. The design support device according to claim 19, further comprising a management unit for managing access rights relating to the construction of said design model.

32. The design support device according to claim 19, further comprising a restriction unit that restricts the content of the input field to create a simple command set to be input to the generating AI.

Images