Design support device
The design support device simplifies CAD model construction by allowing input of design instructions through natural language, images, or files, using AI to build models and provide visual feedback, addressing the inefficiencies and inaccuracies of traditional CAD systems.
Patent Information
- Application Number
- JP2025068017
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2025-04-17
- Publication Date
- 2025-09-10
- Estimated Expiration
- 2045-04-17
AI Technical Summary
Existing CAD systems require time-consuming setup of sample file data and may lead to incorrect script generation due to unfamiliarity with the system, especially for designers not familiar with CAD systems.
A design support device with an input field for natural language, images, or files, utilizing a generation AI to build design models by stacking parts, and a display control unit to intuitively show the design model's reflection of input instructions.
Enables designers unfamiliar with CAD systems to easily construct design models by simplifying the input process and providing intuitive visual feedback, improving design efficiency and accuracy.
Smart Images

Figure 0007737581000001_ABST
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to a design support device that supports the construction of a design model. [Background technology]
[0002] Conventionally, there has been known an information processing device for a CAD (Computer-Aided Design) system used in BIM (Building Information Modeling), which is capable of constructing design models used in the design of structures such as buildings and bridges (see, for example, Patent Document 1). This CAD system includes AutoCAD and REVIT (registered trademark, omitted below), etc.
[0003] The information processing device of Patent Document 1 sets sample file data together with a prompt for specifying desired information (for example, the collision point between a pillar and a beam) from multiple file data, and generates a script by inputting these prompts and sample file data into an LLM (Large Scale Language Model). It also generates a script by inputting correct answer information for the desired information in the sample file data, and by accumulating this script, it extracts reproducible information with a certain degree of extraction accuracy. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Patent No. 7551203 Summary of the Invention [Problem to be solved by the invention]
[0005] The information processing device described in Patent Document 1 requires the setting of sample file data corresponding to desired information, which requires time and effort to support the construction of a design model. Also, because the script is generated by further inputting correct answer information for the sample file data, designers who are not familiar with CAD systems may input incorrect correct answer information.
[0006] Therefore, there is a demand for a design support device that allows even designers who are unfamiliar with CAD systems to easily design. [Means for solving the problem]
[0007] 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 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.
[0008] 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 only necessary 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, thereby building 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 users to intuitively understand how the design instructions entered in the input field will be reflected in the design model.
[0009] In this way, it is a design support device that allows even designers who are unfamiliar with CAD systems to easily design. [Brief explanation of the drawings]
[0010] [Figure 1] FIG. 1 is a block diagram showing the overall configuration of a drawing system. [Figure 2] FIG. 1 is a block diagram of a drawing system including a design support device. [Figure 3] 10 is a flowchart illustrating a control method for the drawing system. [Figure 4] 10 is a display example of a design support device. [Figure 5] 10 is a display example of a design support device. [Figure 6] 10 is a display example of a design support device. [Figure 7] 10 is another embodiment of the design support device. [Figure 8] 10 is another embodiment of the design support device. [Figure 9] 10 is another embodiment of the design support device. DETAILED DESCRIPTION OF THE INVENTION
[0011] An embodiment of a design support system according to the present disclosure will be described below with reference to the drawings. In this embodiment, a user terminal on which REVIT is installed will be used as an example of a CAD system. However, the present invention is not limited to the following embodiment, and various modifications are possible without departing from the spirit of the present invention.
[0012] As shown in Figure 1, the CAD system includes a BIM device 1, a design support device 2, and a user device 3. The BIM device 1 is a server owned by a vendor that manages and operates BIM. The design support 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 shown as a single terminal, but different users who design, construct, or manage structures own multiple terminals. These terminals may be desktop PCs, laptops, tablets, smartphones, etc.
[0013] The BIM device 1, design support device 2, and user device 3 are connected to each other so that they can 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.
[0014] 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, input ports, and output ports. The processor 11 may be an ASIC, FPGA, or SoC, and is not particularly limited.
[0015] The communication IF 12 is a communication interface that has a function of transmitting signals output from the processor 11 to the design support device 2 and the user device 3 via the network 4, and a function of sending signals received from the design support 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.).
[0016] 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.
[0017] 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 with REVIT as an example of a BIM. Note that the BIM program 13a may also be configured with other programs such as Archicad (registered trademark) or GLOBE (registered trademark).
[0018] The BIM program 13a is software for integrated management of digital information related to the design, construction, and management of buildings. The BIM program 13a can create a three-dimensional digital model (design model 33a). Each part of the design model 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 design model 33a to be used throughout the lifecycle of the design, construction, and management of a structure.
[0019] The design support device 2 comprises 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 design support device 2 comprises other functional units, but only the functional units related to this embodiment are described here.
[0020] An add-in program 23a is stored in the memory 23. The add-in program 23a is stored in the 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 design support 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 builds a design model 33a by stacking parts in order by executing a script generated by a generation AI based on the contents of an input field IP. The add-in program 23a will be described in detail later.
[0021] The display 25 is provided in the design support device 2 and is a display device that displays text, images, videos, and other visual information. This display 25 can display a 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 design model 33a.
[0022] 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 design support device 2, so a detailed description thereof will be omitted. Note that the user device 3 includes other functional units, but only the functional units related to this embodiment are described here.
[0023] A building design model 33a 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, and a voice input speaker. When a user operates the operation unit 36, a signal corresponding to the operation is input to the processor 31.
[0024] (Configuration of design support device) FIG. 2 shows a block diagram of a design support device 2 that supports the construction of a design model 33a. The design support device 2 can exchange information with a generative AI (Artificial Intelligence). The generative AI includes any language model or large language model (LLM), such as ChatGPT, Gemini, or Claude. The design support device 2 includes a storage unit 23A and an add-in program 23a.
[0025] 2 functions as a secondary memory of the above-mentioned memory 23. The storage unit 23A stores a script database DBa and a design model database DBb.
[0026] The script database DBa contains program code (such as Dynamo Python) used by REVIT in JSON (JavaScript Object Notation) 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, accessories such as sleeves, and building equipment such as indoor and outdoor air conditioning units. The design model database DBb contains design models 33a that correspond to the program code stored in the script database DBa.
[0027] 2, the add-in program 23a includes a setting unit 231, an acquisition unit 232, a part generation unit 233, a display control unit 234, a learning unit 235, a management unit 236, and a restriction unit 237. The add-in program 23a is an API (Application Programming Interface) or plug-in system that adds these functional units to the BIM program 13a.
[0028] The setting unit 231 sets a single input field IP (see FIG. 4 ) on the top screen (display 35) of the CAD system (user device 3). As shown in FIG. 4 , the setting unit 231 may automatically display the single input field IP 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 input field IP on the top screen of the BIM browser. That is, the setting unit 231 inserts an add-in program 23 a for setting the single input field IP into the initial screen startup program of the BIM program 13 a. The user can input design instructions, including natural language, images, or files, into this input field IP. Input into the input field IP is performed via an operation unit 36 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 a combination of multiple phrases, etc. In this embodiment, the natural language is preferably a sentence including one or more attributes (such as names) of parts. The image may be a still image or a video. The file includes project data, Excel data, etc.
[0029] The acquisition unit 232 acquires attribute information about multiple types of parts included in the design model 33a stored in the CAD system (user device 3). In other words, the acquisition unit 232 acquires attribute information stored in the memory 33 of the CAD system (user device 3) for each part via the BIM apparatus 1 as attribute information about multiple types of parts included in the design model 33a.
[0030] At this time, the acquisition unit 232 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, or 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.
[0031] The natural language, image, or file entered in the input field IP may include a script modification instruction. The script modification instruction is a natural language instruction, such as "reduce the number of pillars and increase their thickness," "make the wall 1 meter higher," "add three doors," or "change the exterior wall material to concrete," that modifies at least one of the quantity, dimensions, and material of parts. The generation AI generates the modification script based on this natural language instruction. In this case, the acquisition unit 232 acquires parts corresponding to the script modification instruction from data stored in the memory 33 of the CAD system (user device 3) or from web data. If the script modification instruction 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 script modification instruction 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.
[0032] It is preferable that the script modification instruction is directed only to the part selected via the operation unit 36 of the user device 3, or only to the part based on the condition entered in the input field IP. The condition entered in the input field IP is a condition for selecting parts using natural language, such as "From the ten identical sleeves, please select one with a length of 400 or more."
[0033] The part generation unit 233 builds the design model 33a 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 in the input field IP from the operation unit 36 of the user device 3. The natural language, image, or file entered in the input field IP is sent to the design support device 2 via the BIM device 1 or directly from the user device 3, and the part generation unit 233 generates a script by the generation AI based on the contents of the input field IP. "Contents of the input field IP" includes cases where the natural language, image, or file entered in the input field IP is used as is, and cases where this natural language, image, or file is processed into one suitable for script generation.
[0034] The part generation unit 233 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 IP, the generation AI processes the natural language and generates a script that reflects the content of the input field IP, "Create walls that are 20 cm thick and 5 m high for each floor to form the exterior walls of a 10-story building." Based on this script, the part generation unit 233 stacks up 10 floors of 20 cm thick, 5 m high walls to construct the design model 33a (see FIGS. 5 and 6). This script is program code (Dynamo Python, etc.) that constructs the design model 33a.
[0035] The parts generation unit 233 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. This script is program code (such as Dynamo Python) that extracts a parts group image including a collection of parts corresponding to the attribute information.
[0036] The part generation unit 233 may execute a change script generated by the generation AI based on a modification instruction input into the input field IP from the operation unit 36 of the user device 3. This change script is program code (Dynamo Python, etc.) that executes modification, deletion, and addition of parts to the design model 33a. For example, if an input is made such that "Please make the exterior walls of a 10-story building," but nine floors are stacked, the generation AI generates a change script based on a modification instruction input into the input field IP, such as "It is nine floors, so please change it to ten floors," and executes this change script to build the modified design model 33a.
[0037] The part generation unit 233 may confirm the design model 33a by a script confirmation operation via the operation unit 36 of the user device 3. For example, by confirming the design model 33a corrected based on a correction instruction input in the input field IP, such as "It is currently set to the 9th floor, please change it to the 10th floor," the part generation unit 233 constructs the design model 33a in which parts for 10 floors are stacked in order. The display control unit 234 may provide an operation button (for example, the "Accept" button shown in FIG. 4) on the display 35 for the script confirmation operation.
[0038] The display control unit 234 displays the input field IP set by the setting unit 231 and the design model 33a generated by the part generation unit 233 on the display 35 (see FIG. 5). The display control unit 234 displays the design model 33a constructed by the part generation unit 233 stacking parts in order based on the content of the natural language, image, or file input into the input field IP on the display 35. Specifically, the display control unit 234 activates the display control function of the BIM device 1 to display the design model 33a on the display 35 (the same applies hereinafter).
[0039] The display control unit 234 may display a parts group image including an assembly of parts on the display 35 based on the design instructions (see FIG. 7). For example, by inputting "Please design a sleeve corresponding to the piping I just designed" in the input field IP, the parts group image, which is an assembly of sleeves shown in FIG. 7, is displayed on the display 35. The display control unit 234 may also switch between a 3D view and a 2D view so that the "arrangement order of parts" and the "layer structure" can be seen. Furthermore, the display control unit 234 may provide operation buttons on the display 35 to enable "redo" and "partial undo."
[0040] The display control unit 234 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 IP (see FIG. 6). As shown in FIG. 6 → FIG. 5, for example, the flow of "design instructions" → "generated script" → "preview" is visualized. At this time, the display control unit 234 may display an explanation of the script generated by the generation AI. The display control unit 234 may also prepare a dashboard-like screen that displays a summary of the script or only important parameters in an easy-to-read format.
[0041] The display control unit 234 may display the script that has been changed based on the correction instructions entered in the input field IP via the operation unit 36 of the user device 3. This changed script may have a comment field displayed for each line, or a screen that allows comparison of the before and after changes may be provided. Parameters such as "part name," "dimensions," and "material" may be highlighted so that the changes can be understood at a glance. Then, the display control unit 234 causes the display 35 to display the design model 33a generated based on the changed script. At this time, an animation may be used to visually indicate which parts have been added to which positions.
[0042] The display control unit 234 may display on the display 35 a parts group image including an aggregation of parts corresponding to the attribute information based on a design instruction having attribute information including at least one selected from the quantity, dimensions, and material of the parts (see FIGS. 8 and 9). For example, by inputting "Please select the item in the basement that is 400 meters long or longer" into the input field IP, a parts group image of an aggregation of sleeves is displayed on the display 35 from the parts group image shown in FIG. 8. Then, by inputting a correction instruction into the input field IP, such as "Please change the sleeve in the basement that is 400 meters long to 380 meters long," the parts group image shown in FIG. 9 is displayed on the display 35. This allows the user to visually view the parts group image and check the design model 33a simply by inputting natural language, an image, or a file into a single input field IP.
[0043] 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 display how to draw multiple sleeves displayed as parts group images in association with pipes or ducts. This makes it possible to use the video as a tool for learning how to operate a CAD system, further improving user convenience.
[0044] The display control unit 234 may display design information based on design instructions including questions. For example, in response to the question "Is there anything strange?", the learning unit 235 (described later) checks the validity of the parameters and structure of the design model 33a, and the display control unit 234 displays "problematic points" as design information. In response to the question "What should I do next?", the learning unit 235 evaluates the design progress, and the display control unit 234 displays "the next operation" as design information.
[0045] The display control unit 234 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 235, or by optimizing the design using previous design information.
[0046] The learning unit 235 learns the design information of each part in the design model 33a stored in the design model database DBb. This design information is stored in the script database DBa in association with design instructions or modification instructions and generated scripts. The learning unit 235 learns the stored design information of each part in the design model 33a, and can check the validity of the parameters and structure of the design model 33a or evaluate the design progress. In addition, the learning unit 235 learns the stored design information of each part in the design model 33a, and can refer to and automatically present best practices and design examples for each learned part, or perform design optimization using previous design information.
[0047] The management unit 236 manages the versions of the scripts stored in the script database DBa. By managing the versions of the scripts by the management unit 236, it becomes possible to track which settings were used at which stage in the design model 33a.
[0048] The management unit 236 may manage access rights related to the construction of the design model 33a. The management unit 236 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 level of difficulty and importance of the design model 33a, for example, by allowing only the team leader to make major design changes.
[0049] The restriction unit 237 restricts the content of the input field IP and creates a simple command set to be input to the generation AI. For example, the content of the input field IP, "Create walls to form a 4x2 room...", becomes a simple command pattern such as "Make four walls, turn right, and make two more...". This eliminates the inconvenience of execution errors that tend to occur when the generation AI generates programming language from natural language, etc., which tends to result in complex code. Furthermore, it also eliminates the inconvenience of allowing free programming, which can lead to complex structures such as for statements, if statements, and functions, which can impair operational stability.
[0050] The restriction unit 237 may be configured to limit the simple command set to a simple command group that directly calls an API (Application Programming Interface), allowing multiple APIs to be called. This allows the script generated by the generation AI to operate stably, and allows complex operations to be realized with a combination of simple commands.
[0051] (Design support method) 3 shows a flowchart of a design support method executed by the design support device 2, which can add functions to a CAD system storing a design model 33a. The design support method shown in FIG. 3 is merely a representative example, and other flowcharts for executing each functional unit of the design support device 2 in the above-described embodiment are omitted. In this embodiment, an example is shown in which information from the user device 3 is transmitted and received to the design support device 2 via the BIM apparatus 1. However, information from the user device 3 may be transmitted and received directly to the design support device 2, or information may be transmitted and received only between the user device 3 and the BIM apparatus 1 with an add-in program 23a pre-installed in the BIM program 13a of the BIM apparatus 1.
[0052] As shown in FIG. 3, the add-in program 23a of the design support device 2 is sent to the BIM device 1, the add-in program 23a is installed in the BIM program 13a, and the BIM program 13a with the add-in program 23a installed is sent to the user device 3 (#21). As a result, as shown in FIG. 4, a BIM having a single input field IP can be displayed on the display 35 of the user device 3. Next, the user (designer) inputs design instructions using the input field IP (#31), and the parts generation unit 233 executes a script generated by the generation AI based on the content of the natural language, image, or file entered in the input field IP (#22). In the example of FIG. 4, the user enters "Please create the exterior walls of a 10-story building" in the input field IP, and the generation AI processes the natural language and executes a script that reflects the content of the input field IP: "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 233 executes the script, causing the BIM device 1 to edit, arrange, and adjust each part, and stack the parts to build the design model 33a (#11). At this time, a part may be selected by inputting a natural language, an image, or a file into the input field IP in Fig. 4, or by selecting a part from the corresponding tab.
[0053] Next, the design model 33a is sent from the BIM apparatus 1 to the user apparatus 3, and the display control unit 234 activates the display control function of the BIM apparatus 1 to display the design model 33a on the display 35 of the user apparatus 3. If the design model 33a constructed in this manner does not meet the user's intentions, the user inputs a correction instruction in the input field IP (#32). For example, by inputting "Please select the item in the basement whose length is 400 or more" in the input field IP, a parts group image of a collection of sleeves is displayed on the display 35 from the parts group image shown in FIG. 8, and a correction instruction is input in the input field IP shown in FIG. 9, "Please change the sleeve in the basement whose length is 400 to 380." Next, the parts generation unit 233 executes the change script generated by the generation AI based on the correction instruction input in the input field IP (#23). By executing the change script, the parts generation unit 233 causes the BIM apparatus 1 to edit, arrange, and adjust each part, correct the parts, and reconstruct the design model 33a (#12).
[0054] Next, the modified design model 33a is sent from the BIM device 1 to the user device 3, and the display control unit 234 activates the display control function of the BIM device 1 to display this design model 33a on the display 35 of the user device 3. Then, if the modified design model 33a is in line with the user's intentions, the part generation unit 233 confirms the design model 33a in which the parts are stacked in order by a script confirmation operation (#33) via the operation unit 36 of the user device 3. Next, the learning unit 235 associates the design instructions or correction instructions with the generated script, stores them in the script database DBa, and learns the design information of each part (#24).
[0055] When displaying the required parts, the user enters natural language, an image, or a file into the input field IP to provide design instructions, including attribute information (#34). The natural language, image, or file entered into the input field IP is then sent from the user device 3 to the design support device 2 via the BIM device 1 or directly. The part generation unit 233 of the design support device 2 then executes the script generated by the generation AI based on the attribute information of each part, including at least one of the part's quantity, dimensions, and material (#25). For example, if the design instruction "Please design a sleeve corresponding to the piping I just designed" is entered into the input field IP shown in FIG. 7, a parts group image representing a collection of sleeves is constructed from the parts group images. The BIM device 1 then sends the modified design model 33a to the user device 3, and the display control unit 234 activates the display control function of the BIM device 1 to display the design model 33a, consisting of the parts group image, on the display 35 of the user device 3 (#35).
[0056] In the above-described embodiment, the following configurations are envisioned. (1) The design support device 2 that supports the construction of the design model 33a includes a setting unit 231 that sets an input field IP into which design instructions including natural language, images, or files can be input, a display control unit 234 that displays the input field IP and the design model 33a, and a part generation unit 233 that builds the design model 33a by stacking parts in order by executing a script generated by a generation AI based on the contents of the input field IP.
[0057] The design support device 2 according to this embodiment is provided with an input field IP into which design instructions, including natural language, images, or files, can be input. Therefore, it is sufficient to input design instructions for parts (walls, floors, roofs, equipment, etc.) of the design model 33a. Furthermore, the part generation unit 233 according to this embodiment executes a script generated by a generation AI based on the contents of the input field IP to build the design model 33a by stacking parts in order, allowing even designers unfamiliar with CAD systems to easily design. Furthermore, the display control unit 234 according to this embodiment displays the input field IP and the design model 33a, allowing designers to intuitively understand how the design instructions entered in the input field IP will be reflected in the design model 33a. Thus, the design support device 2 according to this embodiment allows even designers unfamiliar with CAD systems to easily design.
[0058] (2) In the design support device 2 of (1), it is preferable that the display control unit 234 further displays the script generated by the generation AI based on the contents of the input field IP.
[0059] As in this embodiment, by displaying the script generated by the generation AI based on the contents of the input field IP, the programming process can be understood, which also contributes to improving programming skills.
[0060] (3) In the design support device 2 of (2), the display control unit 234 is preferably configured to be able to display the script that has been changed based on the correction instruction input in the input field IP.
[0061] As in this embodiment, by displaying the modified script based on the modification instructions entered in the input field IP, the validity of the modified script can be evaluated and the level of the modification instructions can be improved.
[0062] (4) In the design support device 2 of (3), it is preferable that the design instructions include at least one modification instruction selected from the number, dimensions, and material of parts.
[0063] 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.
[0064] (5) In the design support device 2 of (4), it is preferable that the correction instruction is directed only to the selected part or to the part based on the condition entered in the input field IP.
[0065] 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 IP, it is possible to prevent the inconvenience of accidentally correcting other parts.
[0066] (6) In any one of the design support devices 2 of (1) to (5), it is preferable that the display control unit 234 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.
[0067] By displaying a parts group image including an aggregate 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 33a even for complex structures.
[0068] (7) It is preferable that the design support device 2 of any one of (1) to (6) further comprises a learning unit 235 that learns design information of parts in the design model 33a.
[0069] If the design information of the parts in the design model 33a is learned as in this embodiment, the performance of the design support device 2 can be improved.
[0070] In the design support device 2 of (8)(7), it is preferable that the display control unit 234 displays the design information based on a design instruction including a question.
[0071] 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 235 can evaluate the design progress, and the display control unit 234 can display the "next operation" as design information.
[0072] In the design support device 2 of (9), (7) or (8), the display control unit 234 is preferably configured to be able to display an optimal solution of the design information.
[0073] If the optimal solution for the design information is displayed as in this embodiment, for example, best practices and design examples for each part learned by the learning unit 235 can be referenced and automatically presented.
[0074] (10) In the design support device 2 of any one of (2) to (5), it is preferable that the parts generation unit 233 finalizes the design model 33a by a finalization operation of the script.
[0075] If the design model 33a is confirmed by a confirmation operation of the script as in this embodiment, an incorrect design model 33a can be eliminated, and the accuracy of the design support device 2 can be improved.
[0076] (11) In the design support device 2 of any one of (2) to (5), the display control unit 234 is preferably configured to be able to display an explanation of the script generated by the generating AI.
[0077] 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 to easily construct the design model 33a.
[0078] (12) It is preferable that the design support device 2 of any one of (1) to (11) further comprises a management unit 236 that manages the version of the script.
[0079] By managing script versions as in this embodiment, it becomes possible to trace which settings were used at which stage in the design model 33a.
[0080] (13) It is preferable that the design support device 2 of any one of (1) to (12) further comprises a management unit 236 that manages access rights related to the construction of the design model 33a.
[0081] By managing access rights for constructing the design model 33a as in this embodiment, it is possible to manage access rights according to the difficulty and importance of the design model 33a, such as allowing only the team leader to make major design changes.
[0082] (14) In any one of the design support devices 2 of (1) to (13), it is preferable to further include a restriction unit 237 that restricts the contents of the input field IP and creates a simple command set to be input to the generation AI.
[0083] By limiting the contents of the input field IP 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.
[0084] [Other embodiments] (a) In the above-described embodiment, the design support device 2 is described as being added to the BIM device 1, but the design support device 2 may be added to AutoCAD or open source CAD. (b) Some of the steps in the above-described embodiments may be omitted, or may be combined appropriately to implement the functions. [Industrial Applicability]
[0085] The present disclosure can be used in a design support device that supports the construction of a design model. [Explanation of symbols]
[0086] 2: Design support device, 231: Setting unit, 233: Part generation unit, 234: Display control unit, 235: Learning unit, 236: Management unit, 237: Restriction unit, 33a: Design model, IP: Input field
Claims
1. A design support device that supports the construction of a design model, 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; a parts generation unit that builds the design model by stacking different parts out of a plurality of parts in order by executing a script generated by the generation AI based on the contents of the input field, The display control unit is a design support device that can display only a parts group image including an aggregate of the 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.
2. The design support device according to claim 1 , wherein the display control unit further displays the script.
3. 3. The design support device according to claim 2, wherein the display control unit is configured to be able to display the script that has been modified based on a modification instruction input in the input field.
4. 4. The design support device according to claim 3, wherein the design instructions include at least one modification instruction selected from the number, dimensions, and material of the parts.
5. 5. The design support device according to claim 4, wherein the modification instruction is directed only to the selected part or to the part based on the condition input in the input field.
6. 2. The design support device according to claim 1, further comprising a learning unit that learns design information of the part in the design model.
7. The design support device according to claim 6 , wherein the display control unit displays the design information based on the design instructions including a question.
8. The design support device according to claim 6 , wherein the display control unit is configured to be able to display an optimal solution of the design information.
9. The design support device according to claim 2 , wherein the parts generation unit finalizes the design model by a finalization operation of the script.
10. The design support device according to claim 2 , wherein the display control unit is configured to be able to display an explanation of the script generated by the generation AI.
11. The design support device according to claim 1 , further comprising a management unit that manages versions of the script.
12. 2. The design support device according to claim 1, further comprising a management unit that manages access rights relating to the construction of the design model.
13. 2. The design support device according to claim 1, further comprising a restriction unit that restricts the content of the input field and creates a simple command set to be input to the generating AI.
Citation Information
Patent Citations
Design support device and design support model learning device
JP2019200721A
Machine learning system for building renderings and building information modeling data
JP2020030786A
Automatic teaching material creation support system for interactive type ai prompt generating program
JP2024148117A
Information processing system, information processing method and information processing program
JP2025035212A
System
JP2025049159A