A customized furniture intelligent design method, device and equipment

By using a user-designer co-working interface and voice recognition technology, furniture design schemes are generated and order breakdown data is automatically generated, solving the problem of low efficiency in traditional custom furniture design and achieving full-process automation and intelligence.

CN122490625APending Publication Date: 2026-07-31BEIJING TUQU TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIJING TUQU TECHNOLOGY CO LTD
Filing Date
2026-04-30
Publication Date
2026-07-31

AI Technical Summary

Technical Problem

Traditional custom furniture design processes rely on offline measurements and hand-drawn sketches, resulting in long cycles, low efficiency, and a high risk of errors.

Method used

By establishing a shared interactive interface between users and designers, voice commands are received and the intent is analyzed using a pre-trained speech recognition model. Initial furniture images are generated and matched with production processes and hardware accessories, automatically generating order breakdown data.

Benefits of technology

It has achieved full automation and intelligence from measurement to order breakdown, significantly improving design efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122490625A_ABST
    Figure CN122490625A_ABST
Patent Text Reader

Abstract

This invention discloses a smart design method, device, and equipment for customized furniture, relating to the field of customized furniture design technology. The method includes: responding to a user's request for simultaneous drawing operations, establishing a simultaneous interactive interface for remote drawing guidance between the user and a designer; receiving the user's voice commands and parsing them using a pre-trained speech recognition model to obtain the user's intent; generating an initial furniture image on the simultaneous interactive interface based on the user's intent, and matching the initial furniture image with corresponding production processes and hardware accessories to obtain a furniture design scheme; and generating order breakdown data based on the furniture design scheme. This achieves full automation and intelligence throughout the entire process of whole-house customization, from remote measurement, drawing, and modification to order breakdown pricing, hole layout, and direct connection to layout production, significantly improving the design efficiency, accuracy, and standardization of customized furniture.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of customized furniture design technology, and in particular to a method, apparatus and equipment for intelligent customized furniture design. Background Technology

[0002] In the custom furniture industry, traditional design processes typically rely on offline measurements, hand-drawn sketches, or the use of general-purpose design software for 2D / 3D design. Designers need to communicate repeatedly with users, take on-site measurements, manually draw drawings, and break down orders for quotations. The entire process is time-consuming, inefficient, and prone to production errors due to unclear communication or incorrect dimensions. Summary of the Invention

[0003] In view of the above, the present invention aims to provide a method, apparatus and equipment for intelligent design of customized furniture to solve the aforementioned technical problems.

[0004] The technical solution adopted in this invention is as follows:

[0005] This invention provides a method, apparatus, and device for intelligent design of customized furniture, including:

[0006] In response to users' requests for screen-sharing drawing operations, a screen-sharing interactive interface is established for users and designers to remotely guide drawing.

[0007] It receives the user's voice commands and parses the voice commands using a pre-trained speech recognition model to obtain the user's intent;

[0008] Based on the user's intent, an initial furniture image is generated on the same-screen interactive interface, and the corresponding production process and hardware accessories are automatically matched to the initial furniture image to obtain a furniture design scheme.

[0009] Based on the furniture design plan, the order breakdown data is automatically generated.

[0010] Optionally, the user intent can be obtained by parsing the voice command using a pre-trained speech recognition model, including:

[0011] The pre-trained qwen-plus model is invoked to extract keywords from voice commands.

[0012] Based on the keywords, the user's intent is obtained through associative reasoning using preset voice rules.

[0013] Optionally, the user intent may include furniture name, placement location, and size data;

[0014] The dimensional data includes length data, width data, and height data.

[0015] Optionally, the initial furniture image may include drawing templates for various furniture structure combinations.

[0016] Optionally, matching the initial furniture image with corresponding manufacturing processes and hardware accessories includes:

[0017] When the user intent includes size data, the structural dimensions of the furniture are filled into the data field of the initial furniture image according to the user intent to obtain the furniture structure.

[0018] When the user intent does not include size data, the structural dimensions of the furniture are filled into the data field of the initial furniture image according to the preset default size data to obtain the furniture structure.

[0019] Based on the furniture structure and placement, the hardware components and manufacturing process are automatically determined from the initial furniture image.

[0020] Optionally, when the user intent does not include size data, the structural dimensions of the furniture are filled into the initial furniture image according to preset default size data to obtain the furniture structure, including:

[0021] The furniture dimensions are obtained based on the furniture's placement and the preset default dimensions corresponding to the furniture's name.

[0022] The furniture structure is obtained based on the height data in the dimensional data.

[0023] Optionally, based on the furniture design scheme, generate order breakdown data, including:

[0024] Convert furniture design schemes into 2D engineering drawings;

[0025] Based on the 2D engineering drawing, the order is broken down and the order breakdown data is generated;

[0026] The order breakdown data includes: order breakdown price data, order breakdown details, six-view drawings of the furniture, and production layout diagram.

[0027] The present invention also provides a smart design device for customized furniture, comprising:

[0028] The interaction module is used to respond to users' requests for screen-sharing drawing operations and to establish a screen-sharing interactive interface for users and designers to remotely guide drawing.

[0029] The processing module is used to receive the user's voice commands and parse the voice commands through a pre-trained speech recognition model to obtain the user's intent; based on the user's intent, it generates an initial furniture image on the same-screen interactive interface, and matches the initial furniture image with corresponding production processes and hardware accessories to obtain a furniture design scheme; based on the furniture design scheme, it generates order breakdown data.

[0030] The present invention also provides a computing device, comprising: a processor and a memory storing a computer system, wherein the computer system, when run by the processor, executes the method described above.

[0031] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above.

[0032] The above-described solution of the present invention has at least the following beneficial effects:

[0033] The above-described solution of the present invention establishes a shared-screen interactive interface for remote drawing guidance between the user and the designer in response to the user's request for simultaneous drawing. It receives the user's voice commands and parses them using a pre-trained speech recognition model to obtain the user's intent. Based on the user's intent, it generates an initial furniture image on the shared-screen interactive interface and matches the initial furniture image with corresponding production processes and hardware accessories to obtain a furniture design scheme. Based on the furniture design scheme, it generates order breakdown data. This achieves full automation and intelligence throughout the entire process from measurement, drawing, modification to order breakdown pricing, hole layout, and direct connection to layout production, significantly improving the design efficiency, accuracy, and standardization of customized furniture. Attached Figure Description

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described below with reference to the accompanying drawings, wherein:

[0035] Figure 1 A flowchart illustrating the intelligent design method for customized furniture provided in this embodiment of the invention.

[0036] Figure 2 A schematic diagram of the modules of the intelligent design device for customized furniture provided in an embodiment of the present invention. Detailed Implementation

[0037] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0038] This invention proposes an embodiment of a smart design method for customized furniture, specifically, as follows: Figure 1 As shown, it includes:

[0039] Step 11: In response to the user's request for screen-sharing drawing operation, establish a screen-sharing interactive interface for remote drawing guidance between the user and the designer;

[0040] Step 12: Receive the user's voice command and parse the voice command using a pre-trained speech recognition model to obtain the user's intent;

[0041] Step 13: Based on the user's intent, generate an initial furniture image on the same-screen interactive interface, and match the initial furniture image with corresponding production processes and hardware accessories to obtain a furniture design scheme;

[0042] Step 14: Generate order breakdown data based on the furniture design plan.

[0043] In step 11 of this embodiment, after the user enters the system, they click to request assistance. Upon hearing the request bell, the designer opens the screen-to-screen drawing interface and communicates directly with the user. After the three parties agree on the customized furniture drawing plan, the user begins to measure the dimensions of the customized furniture drawing under the remote video supervision and guidance of the designer. This includes furniture placement, covering pipes, flues, columns, sockets, instruments, etc., drilling, cutting, and avoiding obstacles. The system will automatically record and screenshot the measurement operation method and the confirmed drawing dimensions.

[0044] In step 12 of this embodiment, after the user completes the measurement, the user inputs the design requirements for the furniture via voice. The system extracts keywords from the voice command using the pre-trained qwen-plus model and performs associative reasoning based on preset voice rule statements to obtain the user's intent. The user intent includes at least one or more of the following: furniture category, furniture name, installation method, placement location, size data, and usage function.

[0045] The specific training process for the qwen-plus model is as follows:

[0046] Enter the training statement: "You are a function call assistant for a customized furniture system. Please select and call the appropriate function according to the user's needs." Further input: "1. If the current user has selected content, match based on the currently selected content. If no content is currently selected, do not refer to it."

[0047] 2. User input comes from speech recognition and may contain homophone errors or pauses in speech. Please ignore these noises and focus on extracting the core intent and parameters.

[0048] 3. All length descriptions are in millimeters by default; if not, they will be converted.

[0049] 4. Pay attention to colloquial quantifiers, such as "two" and "three," and correctly identify the quantity. For example, "add two door panels" means add two door panels.

[0050] 5. Parameters indicating length or distance cannot be 0; if none are specified, no value needs to be returned.

[0051] 6. If the user does not describe any space number, the space should be returned as empty []. It should not be returned arbitrarily. Note that space numbers should be segmented. For example, if the user's speech is converted to text, it might be space number 12345, which needs to be segmented into [1,2,3,4,5]. Or, space number 1213 needs to be segmented into [12,13].

[0052] 7. When the user description only contains descriptions such as "extend" or "shorten", but no other supporting descriptions, prioritize the part modification;

[0053] 8. Pay attention to the distinction between adding exterior trim and adding decorations, such as baseboards being considered part of the overall decoration;

[0054] 9. All extensions are positive numbers, and all shortenings are negative numbers;

[0055] 10. It is crucial to identify the user's primary intent and grasp their core objective. For example, if a user says they want to add a door panel and share a neutral panel on the right side, their primary intent is to add a door panel, not a neutral panel.

[0056] Furthermore, during training, speech rule statements were added. Within the scope of the language rules, if the instruction is unclear, the model will make associations and understandings in the direction of similar pronunciation. Hot words and homophones were set to enhance the model's associative understanding of speech input. For example, hot words include: distance, distance up, distance down, distance left, distance right, spacing, evenly divide space, add, create, shelf, board, neutral board, side panel, baffle, panel, back panel, partition, front panel, functional component, clothes rail, clothes rail, wine rack, light strip, desktop, tabletop, mirror, glass, upholstered, cabinet, door, drawer, punch, cut edge, modify, fix, semi-fixed, move, extend, wall, space, light-receiving panel, horizontal, vertical, horizontal, vertical, top line, edge line, add, extend up, extend down, extend left, extend right, move up, move down, move left, move right, pick at hands, Handle, corner cut, draw one, draw one, module, template, wall A, wall B, wall C, wall D, wall A, wall B, wall C, wall D, baseboard, skirting board, baseboard, kitchen, cabinet, wall cabinet, top cabinet, range hood, stove, sink, room, room type, center, distance from the ground, delete, above, top, bottom, bottom, left, left side, right side, right side, handle-free, edge-cut, shared, etc.

[0057] Homophone substitution examples: wall, wall B; wall wall, B wall; distance from the ground, distance from below; wall at distance from the ground, wall at distance from D wall; cotton handle, handle-free; public, shared; gravity board, neutral board, etc.

[0058] In step 13 of this embodiment, an initial furniture image is generated on the same-screen interactive interface according to the user's intention. The initial furniture image here is a general drawing specification template for furniture, and the internal and external positions of the template can be modified and additional requirements can be added.

[0059] Next, based on the user's intent and environmental factors such as obstacles like beams, columns, pipes, and instruments in the room, the furniture cabinet is cut and circumvented, and then the production process and hardware accessories are automatically rematched to confirm the furniture design scheme.

[0060] Specifically, when the user intent includes size data, the structural dimensions of the furniture are filled into the data requirement field of the initial furniture image according to the user intent;

[0061] When the user intent does not include size data, the structural dimensions of the furniture are filled into the data requirement field of the initial furniture image according to the furniture name and the preset default size data.

[0062] Next, hardware accessories are automatically added to the initial furniture image based on the structural dimensions and placement of the furniture.

[0063] Specifically, the system automatically determines the cabinet structure and configures appropriate hardware based on the cabinet's placement and height data. For example, consider the following three types of cabinets: top cabinet (cabinet whose bottom outline contacts / connects to other cabinets and has no skirt), wall cabinet (cabinet whose bottom outline does not contact / connect to other cabinets or table legs and has no skirt), and off-center cabinet (cabinet whose bottom outline connects to table legs and has no skirt). These three types of cabinets are structurally identical in appearance (all have side panels sandwiching the top and bottom panels). However, when adding them, top cabinets are supported by other cabinets below, and off-center cabinets are supported by the right leg below, so wall-mounting hardware is not required. Since the total height of off-center cabinets includes the leg height, the cabinet's height will automatically be reduced based on the leg height. Wall cabinets, lacking bottom support, will automatically be equipped with wall-mounting hardware such as brackets / expansion screws.

[0064] Example 2: First height (the position above the normal visual height of a standing person, the default is the height with the hardware facing upwards, which is >1600mm. Designers can modify the default value). Second height (the position below the normal visual height of a standing person, the default is the height with the hardware facing downwards, which is <=1600mm. Designers can modify the default value).

[0065] Example 3: First height (the normal hand position for a person standing, around >1100mm; designers can modify the default value), Second height (the normal hand position for a person standing, the default is the height with the hardware facing down, around <=1100mm; designers can modify the default value).

[0066] It can also add the same requirements at once in internal space and external location, or add multiple requirements and functions at once in one space, and automatically recognize drawing schemes and production processes. It can realize complex schemes such as automatic avoidance function and shared handles on all sides, and shared neutral panels.

[0067] The following is an example of furniture design based on user voice commands to recognize user intent:

[0068] 1. Add shelves:

[0069] If the user specifies a shelf location (e.g., space number), a fixed shelf will be added by default. If the user specifies a fixed shelf, semi-fixed shelf, or movable shelf, the shelf will be added accordingly. If the user does not specify the number of shelves, one shelf will be added by default. If the user specifies the number of shelves, the actual number will be added.

[0070] 2. Add a neutral panel:

[0071] If the user says in voice that they want to add a neutral board to a certain space, one board will be added by default if the number of boards is not specified. If a specific number is specified, the actual number will be added.

[0072] 3. Add front panel / back panel:

[0073] The user specifies in voice command which shelf space to add the back panel to. If the number of shelves is not specified, one shelf will be added by default. If a specific number is specified, the actual number will be added. Alternatively, the user can say "front panel / backstop / cover".

[0074] 4. After selecting a panel / wall, the user can say "add panel" via voice. If no type of panel is specified, a horizontal panel will be added by default. If the user describes the panel type (vertical panel / horizontal panel / panel / grid panel), the panel will be added according to the description. If the number of panels is not specified, one panel will be added by default. If a specific number is specified, the actual number will be added. If the panel size is not specified, it will be the same as the selected panel / wall size. If a size is specified, the described size will be automatically entered.

[0075] 5. After selecting a panel / wall, the user can say via voice to add a certain accessory model (simply say the accessory name, such as: range hood, refrigerator, washing machine, sink, stove, toilet, etc.). If no location is specified, it will be added automatically in the default position. If a specific location is described (distance from left / right / top / bottom), it will be added in the described location.

[0076] 6. Add decorations:

[0077] Select a panel or speak the space number followed by the name of the desired decoration (e.g., add LED strip / mirror / glass / table leg / cabinet leg / kickboard / tabletop / countertop / upholstered / coat hook, etc.). Multiple panels or spaces can be selected simultaneously to add decorations to multiple locations. When adding decorations, you can also describe their location, size, and quantity. If no description is provided, default values ​​will be used. (For example: 1. For countertops, you can describe the left, right, front, and back extensions, or whether there are cabinets / walls on the left / right / front / back side to change the countertop size; 2. For kickboards, you can describe the location (front, back, left, right, left, right) and the extensions (left and right).

[0078] 7. Remove decorations / plates:

[0079] After selecting multiple decorative elements / boards, you can use voice commands to delete the decorative elements / boards to complete the deletion operation.

[0080] 8. Add walls:

[0081] If the user says "add wall" via voice, the wall will be added using the default values ​​if the length, width, and thickness are not specified. If the wall is specified, it will be added according to the specified values.

[0082] 9. Add pipes:

[0083] After selecting a panel / wall, if the user says "add pipe" via voice, the pipe will be added vertically by default, aligning with the wall height. If the user specifies the pipe's direction, such as vertical / left / right, horizontal / up / down, front / back / vertical, the pipe will be added accordingly. Users can also describe the pipe's location, such as: distance from left / center / right; distance from top / center / right; horizontal offset / vertical offset; spacing value, etc.

[0084] 10. Add exterior decorations:

[0085] After selecting the panel, the user can say the name of the exterior trim to add (e.g., visible panel, headboard, edge trim, top trim, strip, edge strip, etc.). If no size is specified, the default size will be added. If the user specifies the dimensions for the top, bottom, left, right extensions or top, bottom, left, and right retractions, the extension / retraction will be adjusted according to the user's description.

[0086] 11. Panel / Wall Openings:

[0087] Select the panel / wall and say "open round hole / rectangular hole / perforated board" or "open window hole / window opening / doorway / doorway". If the user does not describe the opening size, the default size will be used. If the user describes the size and location of the opening (e.g., length / width; distance from the opening to the left, right, top, and bottom center), the size will be automatically filled in according to the user's description.

[0088] 12. Part modification:

[0089] After selecting a panel, the user can use voice commands to modify the material, color, thickness, texture, or length / shortening. This will bring up a panel editing window where modifications can be made. For length / shortening, the user can directly describe the length, and the system will automatically fill in the data based on the description.

[0090] 13. Panel movement:

[0091] After selecting the panel to be moved, the user describes the distance from the left / right / top / bottom / front of the panel to be moved, and the system will automatically fill in the data based on the description.

[0092] 14. Panel assembly:

[0093] After selecting two adjacent boards facing the same direction, the user can merge the two boards by saying "merge boards" via voice. If the two boards are separated by other boards, merging them will break the previous boards.

[0094] 15. Panel / Wall Chamfer:

[0095] After selecting the board / wall, the user can specify the corner cutting dimensions via voice. If the user does not describe the corner cutting dimensions, the default dimensions will be used. If the user describes the dimensions of the opening (e.g., length / width; distance from the opening to the left, right, top, and bottom center), the dimensions will be automatically filled in according to the user's description.

[0096] 16. Sheet metal edge trimming:

[0097] After selecting the board material, the user can say "cut edge" via voice, and the system will select based on the user's description (cut beveled edge / rounded edge).

[0098] 17. Part restoration:

[0099] After selecting a board that has been chamfered / drilled, the user can clear the chamfered corners / drills on the board by saying "restore" via voice.

[0100] 18. Begonia Corner:

[0101] By selecting two adjacent but opposite-oriented Begonia Corners, users can change the regular linking method to a Begonia Corner connection by speaking the name of the Begonia Corner.

[0102] 19. Cabinet resizing:

[0103] Select any panel in the cabinet that needs to be resized, and then say "Cabinet resized" and describe the cabinet dimensions.

[0104] 20. Create furniture:

[0105] With or without selecting a cabinet, users can create furniture / cabinets via voice command. Users can describe the specific cabinet name (e.g., wardrobe, walk-in closet, desk, bookcase, bookshelf, bed frame, bed box, tatami, train-style tatami, headboard, bedside table, drawer cabinet, TV cabinet, entryway cabinet), shoe cabinet, partition cabinet, storage cabinet, sideboard, wine cabinet, display cabinet, curio cabinet, multi-functional cabinet, bathroom cabinet, balcony cabinet, custom cabinet, kitchen base cabinet, kitchen wall cabinet, refrigerator cabinet, wall cabinet, top cabinet, base cabinet, etc.). The system will automatically fill in the dimensions based on the user's description. If the user does not provide detailed dimension information, the system will automatically fill in the missing width / height / depth according to the default dimensions based on the cabinet name. Furthermore, the system can automatically adjust the cabinet structure and hardware based on the user's description of the cabinet's location (e.g., if the user says "add TV cabinet, 150mm from the ground," the system will automatically change the cabinet structure to a wall cabinet, removing the cabinet base and adding the hardware required for wall cabinet installation).

[0106] 21. Delete the cabinet:

[0107] Select any panel in the cabinet you want to delete, and then say "Delete cabinet" in voice.

[0108] 22. Cutting the cabinet:

[0109] Select any panel in the cabinet that needs to be cut, and say "cut cabinet" in voice to bring up the cabinet cutting window.

[0110] 23. Mobile cabinet:

[0111] Select any panel in the cabinet that needs to be cut, and say "move cabinet" to bring up the "Move Cabinet" window.

[0112] 24. Add door panels:

[0113] Select or say the serial number of one or more spaces, then say "add door panel" and state the number of door panels to add them. When describing the number of door panels, specify the number of rows and columns to add, and describe the door panel's opening method (sliding / hinged), coverage method (full overlay / half overlay / recessed / shared center panel, etc.), opening direction (left / right / flip-up / flip-down), extension / retraction (upward extension / retraction, downward extension / retraction / shared handle-free with top or bottom), door panel style (single color / vacuum-formed / wrapped / molded / glass door, etc.), handle style (no handle / metal handle-free / wooden structure handle-free, etc.), edge banding / metal edge banding (you can specify top, bottom, left, and right separately).

[0114] 25. Editing the door panel:

[0115] After selecting the door panel you want to edit, simply say "modify door panel" to bring up the door panel editing window.

[0116] 26. Add drawers:

[0117] Select or voice-say one or more space numbers, then say "add drawer" and state the number of drawers to add. When describing the number of drawers, specify the number of rows and columns to add. You can also modify the drawer's cover method (full over / half over / inset / shared center panel, etc.), extend or shorten the drawer front (top / retract, bottom / retract / shared handle-free with top or bottom), handle style (no handle / metal handle-free / wooden handle-free, etc.), drawer front edge banding / metal snap-on (you can specify top, bottom, left, and right separately), and drawer style (standard / bottom support / grid / roller or train-style drawer).

[0118] When adding multiple drawers to a space, after extending the last drawer panel downwards, the other drawer panels will automatically adjust to ensure all panels are at the same height. Furthermore, if there are gaps / partitions / metal handleless / wooden handleless structures between drawer panels, the system will adjust the drawers to automatically avoid them. Additionally, when adding doors / drawers to adjacent spaces, if the covering method on one side is adjusted beforehand, the adjacent side will automatically adjust accordingly (e.g., if a door panel added to the left space is a half-coverage center panel, then when a door is added to the right, it will automatically adjust to a half-coverage to avoid collisions, and the hinges will automatically change to half-coverage hinges).

[0119] 27. Add functional components:

[0120] Select or speak the serial number of one or more spaces, then state the name of the functional component to be added (e.g., clothes rail, trouser rack, wine rack, internal cabinet, etc.) to add the corresponding functional component.

[0121] 28. Delete function component:

[0122] After selecting a functional component, simply say "delete functional component" to remove it. The system will then automatically modify the processing technology after deletion.

[0123] 29. Equally divided space:

[0124] After selecting or speaking multiple consecutive spaces, say "divide the spaces equally" to divide these spaces equally.

[0125] 30. Cancel / Restore:

[0126] When you say "Undo / Redo" via voice, the system will enlarge the "Undo / Forward" button to prompt you to click it.

[0127] 31. Create a room:

[0128] When creating a room via voice, you can describe the specific information about the room, such as: room type (other rooms, kitchen / bathroom), decoration status (unfinished room, fully furnished room: if described as unfinished room, the dimensions will be reduced accordingly based on the measured and filled dimensions), room wall dimensions (length (width), height, thickness), doorway dimensions (width, height), and doorway location (left, right, center).

[0129] In one optional embodiment, the system automatically matches different default cabinets for different situations during drawing. However, users can select preset special cabinet templates when they need to customize special furniture and cabinets.

[0130] In step 14 of this embodiment, after obtaining the furniture design scheme, order breakdown data is automatically generated. Specifically, the 3D furniture design scheme is converted into 2D engineering drawings; the order is broken down based on the 2D engineering drawings. The system scans and parses each component in the 2D engineering drawings, identifies the shape, size, and position of the components, extracts the complete geometric dimensions, material type, and surface treatment requirements of each component, creates a component database using the component data, assigns a unique identification code and corresponding specification parameters to each component, and extracts component data from the component database based on the user's order to generate order breakdown data, including order breakdown quotation, order breakdown details, six-sided renderings, and production hole layout diagrams.

[0131] Before production is initiated, the system can automatically modify the width, height, and thickness of furniture according to user needs, change furniture colors, change the style and covering method of doors and drawers, change the thickness of furniture back panels or doors, etc. It can automatically complete the modification of processing technology, automatically change the materials used, automatically re-split the order and provide a quote, and automatically connect with the factory for production without order splitting. This provides convenience for special users who change their needs under special circumstances and solves the problem of not being able to modify drawings after an order is placed.

[0132] In one exemplary embodiment, taking a kitchen as an example, the customized furniture intelligent design method and steps of this embodiment are described in detail:

[0133] When creating a room via voice, the system will recognize whether the voice mentions room names (other rooms and kitchen / bathroom), and whether it mentions a bare or furnished apartment. If it recognizes a bare apartment, the system will automatically reduce the dimensions based on the room name, wall height, and wall spacing mentioned in the voice.

[0134] User voice input: Draw a kitchen. Wall A is 1.9 meters high, wall B is 2.54 meters high, and the height is 2.6 meters. System analysis logic after recognition: 1. The voice mentions "draw a kitchen," the system recognizes the keyword and automatically selects to create a room - kitchen; 2. If the voice does not specify whether the room is a furnished or unfurnished apartment, the system defaults to unfurnished, increasing the wall and ceiling thickness, and automatically reducing the wall dimensions and height.

[0135] When users need to draw door / window openings, they can clearly describe the width and height of the door / window opening via voice, and describe its position on the wall (i.e., the specific values ​​of distance from top / bottom, left / right), and the opening can be made at the corresponding position on the wall.

[0136] For example, after selecting wall C, the voice input is: "Window opening width 1135, height 1140, distance from right 265, distance from bottom 800." The system's analysis logic is as follows: 1. When the voice mentions "window opening," the system recognizes the keyword and automatically selects "opening" - "square opening" - "window opening"; 2. When the voice mentions "width" and "height," the system recognizes the keyword and automatically creates the window opening according to the voiced dimensions; 3. When the voice mentions "distance from right" and "distance from bottom," the system recognizes the keyword and automatically creates the window opening according to the voiced location.

[0137] When a user needs to add a pipe, the system will automatically add a pipe of the default length based on the height of the walls in the room. Alternatively, the system can describe the actual pipe length based on on-site measurements. For example, after selecting wall D, the user can voice-input: "Add pipe, 350 from the left, 150 spacing." The system's logic is as follows: 1. The voice mentions "add pipe," the system recognizes the keywords and automatically selects to add a pipe; 2. If the voice does not mention the pipe direction, the system defaults to a vertical pipe; 3. If the voice does not mention the pipe length, the system defaults to the same height as the wall. When the voice mentions "from the left" or "spacing," the system recognizes the keywords and automatically creates the pipe according to the voice-input location.

[0138] When a user adds a corner cabinet, and then adds a door panel to the corner cabinet via voice, the system will automatically add two door panels, and by default the side door panel will overlap the front door panel.

[0139] For example, after selecting wall C, the user can voice-input: "Create a right corner cabinet for the kitchen, width 1080, depth 800." After entering the width and depth, when the user then enters the front thickness (thickness 1) and side thickness (thickness 2), the system first checks whether the input values ​​form a corner (judgment method: width must be greater than front thickness, depth must be greater than side thickness, width = front thickness + front opening, depth = side thickness + side opening). After entering the width, depth, front thickness, and side thickness, the user can see the outer outline of the corner cabinet, which can be used as a basis to determine whether the cabinet size is appropriate. If the user mentions a cabinet name when creating the corner cabinet, the system will fill in the front thickness and side thickness with the default values ​​based on the cabinet name, quickly providing the outer outline of the cabinet to help the user quickly determine whether the width and depth of the corner cabinet are reasonable. Furthermore, when adding doors to different types of cabinets, the system will match different hinges according to the cabinet type. For example, when adding doors to ordinary cabinets (non-corner cabinets), ordinary hinges will be matched, and when adding doors to corner cabinets (left corner cabinet / right corner cabinet), 165° hinges will be matched. The system's analysis logic after recognition is as follows: 1. When the voice mentions "kitchen" and "right corner cabinet," the system recognizes the keywords, generates a kitchen base cabinet frame structure diagram, selects the right corner cabinet, and automatically aligns the cabinet to the far right of the wall; 2. When the voice mentions "width" and "depth," the system recognizes the keywords and automatically fills in the cabinet dimensions.

[0140] After the user selects the corner cabinet side panel, they can input via voice: "Draw a cabinet, 1080 pixels wide." The system then analyzes the following logic: 1. The voice mention of "cabinet" is recognized by the system, generating a kitchen base cabinet frame structure diagram; 2. The voice mention of "width" is recognized by the system, automatically filling in the cabinet dimensions. Following these steps, all kitchen base cabinets can be added.

[0141] When a user adds drawers to a kitchen cabinet via voice, the system automatically matches the appropriate metal handles to the drawers in the correct locations, meaning it adds the appropriate number of handle-free base cabinets and middle cabinets, and automatically calculates and adds them to the appropriate positions. For example, if the voice input is: "Add three drawers to drawer number six," the system's analysis logic is as follows: 1. The voice mentions "add drawers," the system recognizes the keyword, analyzes the cabinet as a kitchen base cabinet, and automatically adds hardware—handle-free base cabinets and middle cabinets; 2. The voice mentions "add three drawers," the system recognizes the keyword, and automatically fills in the number of drawers; 3. After automatically analyzing the first two pieces of information, the system automatically calculates the drawer size and position, and automatically calculates the drawer panel size and position after sharing handles; 4. After adding drawers, the cabinet automatically reduces the thickness of the drawer panels.

[0142] When users add cabinet doors via voice, the system automatically analyzes the coverage and matches the appropriate hinge angle (full overlay, half overlay, recessed, etc.). For example, if the voice input is: "Add two door panels to space number five," the system's analysis logic is as follows: 1. The voice mentions "add door panels," the system recognizes the keyword, analyzes the cabinet as a kitchen base cabinet, and automatically adds hardware – handle-free lower cabinet – when adding drawers; 2. The voice mentions "add two door panels," the system recognizes the keyword, and automatically fills in the number of door panels; 3. After automatically analyzing the first two pieces of information, the system automatically calculates the size and position of the door panels after using handle-free lower cabinets; 4. After adding door panels, the cabinet will automatically reduce the door panel thickness. Following the above method, all kitchen base cabinet door panels or drawers can be added.

[0143] When a user adds a kickboard to a kitchen base cabinet via voice, the cabinet will automatically move upwards according to the height of the kickboard. For example, after selecting the baseboards of multiple cabinets facing the same direction, the user can voice-indicate: "Add kickboard, extend 50mm to the left." The system will then analyze the following logic: 1. The voice mentions "add kickboard," the system recognizes the keyword and automatically adds the kickboard and cabinet legs; 2. The voice mentions "extend 50mm to the left," the system recognizes the keyword and automatically fills in the extension length; 3. The system automatically analyzes the first two pieces of information, and after adding the kickboard, the cabinet will automatically move upwards according to the height of the kickboard and cabinet legs. Using this method, kickboards for all selected cabinets facing the same direction can be added in one go.

[0144] When the user selects the right side panel of the cabinet, they can input via voice: "Add a visible panel." The system then analyzes the logic: the voice mentions "add a visible panel," the system recognizes the keyword, analyzes the cabinet as a kitchen base cabinet, and automatically aligns the visible panel to the bottom of the countertop when added.

[0145] When the user selects the left side panel of the cabinet, they can input "Add border line" via voice. After system recognition and analysis, the system recognizes the keyword "add border line," analyzes that the cabinet is a kitchen base cabinet, and automatically aligns the border line to the bottom of the countertop when adding the border line.

[0146] When a user adds countertops via voice, if the voice prompt mentions whether there are walls / cabinets / obstacles in front, behind, left, or right, the system will not extend the countertop. For example, if multiple cabinet tops are selected, and the voice input is: "Add countertop, extend left 50, extend right 260," the system will analyze the following logic: 1. When the voice prompt mentions "add countertop," the system recognizes the keyword and automatically adds the cabinet countertop, replacing the current top panel with a pull strap by default; 2. When the voice prompt mentions "extend left," "extend right," or a wall / cabinet on one side, the system recognizes the keyword and automatically fills in the extension data. Following these methods, all kitchen base countertops can be added.

[0147] When a user selects a countertop / base cabinet and adds a wall cabinet via voice command, the wall cabinet depth will be the default value for the cabinet body, and the width will be the same as the selected cabinet below. The system will automatically calculate the wall cabinet height based on the wall height, the default spacing between the wall cabinet and the countertop, and the height of the base cabinet. The wall cabinet will automatically match the corresponding hanging hardware accessories according to the installation method. To add the same wall cabinet to the left and right, simply click on the left or right side panel to add it. When adding a door panel to the kitchen wall cabinet via voice command, the system will automatically match it with a special handle-free design for wall cabinets.

[0148] For example, after selecting the countertop, the system can voice-input: "Add a wall cabinet, 550mm wide." The system's logic after recognition is as follows: 1. When the voice mentions "add a wall cabinet," the system recognizes the keyword, automatically adds a kitchen wall cabinet, and calculates its height using the formula: Kitchen wall cabinet height = Room height - Height from the top of the countertop to the ground - Spacing (default 800mm); 2. When the voice mentions "width," the system recognizes the keyword and automatically fills in the cabinet width.

[0149] After the user selects the wall cabinet side panel, they can input via voice: "Add wall cabinet, width 900". The system then analyzes the following logic: 1. The voice mentions "add wall cabinet", the system recognizes the keyword and automatically calls up the kitchen wall cabinet template; 2. The voice mentions "width", the system recognizes the keyword and automatically fills in the cabinet width. Following these steps, all kitchen wall cabinets can be added.

[0150] When a user voice inputs: "Add two door panels to space number 13," the system recognizes and analyzes the following logic: 1. The voice mentions "add door panels," the system recognizes the keyword, analyzes the cabinet as a kitchen wall cabinet, and automatically uses hardware—a handle-free design for wall cabinets—when adding door panels; 2. The voice mentions "add two door panels," the system recognizes the keyword, and automatically fills in the number of door panels. Following these steps, all kitchen wall cabinet door panels can be added.

[0151] When the user selects the countertop, they can input via voice: "Add a sink, 600mm wide, 350mm deep." The system then analyzes the following logic: 1. The voice mentions "add a sink," the system recognizes the keyword and automatically adds the decorative accessory – the sink; 2. The voice mentions "width" and "depth," the system recognizes the keyword, automatically fills in the sink's width and depth, and automatically cuts a hole in the countertop according to the required dimensions.

[0152] When the user selects the countertop, they can input via voice: "Add stovetop." The system then analyzes the following logic: 1. The voice mentions "add stovetop," the system recognizes the keyword, and automatically adds the accessory / decoration - stovetop; 2. The voice does not mention the stovetop size, so the system automatically uses the default size and automatically cuts a hole in the countertop according to the required groove size.

[0153] When a user selects the bottom panel of a wall cabinet and adds a range hood via voice command, the cabinet height will automatically decrease according to the height of the range hood. The default distance between the range hood and the countertop is 700-750mm.

[0154] For example, after a user selects the bottom panel of a wall cabinet, they can voice-indicate: "Add range hood." The system then analyzes the following logic: 1. The voice mentions "add range hood," the system recognizes the keyword, and automatically adds the accessory / decoration - range hood; 2. The voice does not mention the range hood size, so the default size is used automatically.

[0155] In this embodiment of the intelligent custom furniture design method, the designer and user communicate via voice and video calls. The designer directly guides the user on-site to take measurements according to the designer's requirements (including measurement locations and methods). During the measurement process, the on-site personnel inform the designer of the measurement data approved by the designer. Based on the measurement data broadcast on-site, the designer then directly guides the user to confirm and modify the room via voice broadcast, locating the dimensions of the room's doors and windows, their positions on the walls, and their distances from the top, bottom, left, and right sides. The interior layout of the room, including the location of recessed and protruding walls, pipes, instruments, water supply and drainage systems, is also determined. Then, using the intelligent voice recognition function, based on the room's interior conditions and the designer's design plan, the designer guides the on-site personnel to voice broadcast the furniture name, dimensions, type, location, and other details, thus completing the custom furniture design plan.

[0156] It solves the problem that designers must be present in person to measure and draw, saving designers' design time; it can automatically recognize the user's voice intent, automatically generate drawing templates based on spoken instructions, and automatically match hardware accessories and processing technology, realizing an intelligent design experience of "drawing while speaking and generating automatically", solving the problem of relying on human experience; it realizes full-process automation and intelligence from measurement, drawing, modification to order breakdown and quotation, significantly improving the design efficiency and accuracy of customized furniture.

[0157] like Figure 2 As shown, this embodiment also provides a smart design device 20 for customized furniture, including:

[0158] Interaction module 21 is used to respond to the user's request for screen-sharing drawing operations and establish a screen-sharing interactive interface for remote guidance of drawing between the user and the designer.

[0159] The processing module 22 is used to receive the user's voice commands and parse the voice commands through a pre-trained speech recognition model to obtain the user's intent; based on the user's intent, it generates an initial furniture image on the same-screen interactive interface, and matches the initial furniture image with corresponding production processes and hardware accessories to obtain a furniture design scheme; based on the furniture design scheme, it generates order breakdown data.

[0160] Optionally, the user intent can be obtained by parsing the voice command using a pre-trained speech recognition model, including:

[0161] The pre-trained qwen-plus model is invoked to extract keywords from voice commands.

[0162] Based on the keywords, the user's intent is obtained through associative reasoning using preset voice rules.

[0163] Optionally, the user intent may include at least one or more of the following: furniture category, furniture name, installation method, placement location, size data, and usage function.

[0164] Optionally, matching the initial furniture image with corresponding manufacturing processes and hardware accessories includes:

[0165] When the user intent includes size data, the structural dimensions of the furniture are filled into the initial furniture image according to the user intent;

[0166] When the user intent does not include size data, the structural dimensions of the furniture are filled into the initial furniture image according to the furniture name and the preset default size data;

[0167] Based on the structural dimensions and placement of the furniture, hardware accessories are automatically added to the initial furniture image.

[0168] Optionally, when the user intent does not include size data, the structural dimensions of the furniture are filled into the initial furniture image according to preset default size data to obtain the furniture structure, including:

[0169] Based on the furniture's placement and name, obtain the furniture's dimensions.

[0170] The furniture structure is obtained based on the height data in the dimension data.

[0171] Optionally, based on the furniture design scheme, generate order breakdown data, including:

[0172] Convert furniture design schemes into 2D engineering drawings;

[0173] Based on the 2D engineering drawing, the order is broken down and the order breakdown data is generated;

[0174] The order breakdown data includes: order breakdown price data, order breakdown details, six-view drawings of the furniture, and production layout diagram.

[0175] It should be noted that this device is the same as the method described above. All implementations in the above method embodiments are applicable to the embodiments of this device and can achieve the same technical effect.

[0176] An embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer system, wherein the computer system, when run by the processor, executes the method described in the above embodiments. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0177] In this embodiment of the invention, a computer-readable storage medium is also provided, storing instructions that, when executed on a computer, cause the computer to perform the method described in the above embodiments. All implementations of the methods described in the above embodiments are applicable to this embodiment and can achieve the same technical effect.

[0178] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0179] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0180] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0181] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0182] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0183] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing system code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0184] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This is something that those skilled in the art can achieve by using their basic programming skills after reading the description of the present invention.

[0185] Therefore, the object of the present invention can also be achieved by running a system or a set of systems on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a system product containing system code implementing the method or apparatus. That is, such a system product also constitutes the present invention, and the storage medium storing such a system product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0186] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for intelligent design of customized furniture, characterized in that, include: In response to users' requests for screen-sharing drawing operations, a screen-sharing interactive interface is established for users and designers to remotely guide drawing. It receives the user's voice commands and parses the voice commands using a pre-trained speech recognition model to obtain the user's intent; Based on the user's intent, an initial furniture image is generated on the same-screen interactive interface, and the corresponding production process and hardware accessories are automatically matched to the initial furniture image to obtain a furniture design scheme. Based on the furniture design plan, the order breakdown data is automatically generated.

2. The intelligent design method for customized furniture according to claim 1, characterized in that, The user's intent is obtained by parsing the voice command through a pre-trained speech recognition model, including: The pre-trained qwen-plus model is invoked to extract keywords from voice commands; Based on the keywords, the user's intent is obtained through associative reasoning using preset voice rules.

3. The intelligent design method for customized furniture according to claim 1, characterized in that, The user intent includes furniture name, placement location, and size data; The dimensional data includes length data, width data, and height data.

4. The intelligent design method for customized furniture according to claim 1, characterized in that, The initial furniture images include initial frame images of various furniture structure combinations.

5. The intelligent design method for customized furniture according to claim 3, characterized in that, Matching the initial furniture image with corresponding manufacturing processes and hardware accessories includes: When the user intent includes size data, the structural dimensions of the furniture are filled into the data field of the initial furniture image according to the user intent to obtain the furniture structure. When the user intent does not include size data, the structural dimensions of the furniture are filled into the data field of the initial furniture image according to the preset default size data to obtain the furniture structure. Based on the furniture structure and placement, hardware accessories are automatically added to the initial furniture image.

6. The intelligent design method for customized furniture according to claim 5, characterized in that, When the user intent does not include size data, the structural dimensions of the furniture are filled into the initial furniture image according to the preset default size data to obtain the furniture structure, including: Based on the furniture's placement and name, obtain the furniture's dimensions. The furniture structure is obtained based on the height data in the dimension data.

7. The intelligent design method for customized furniture according to claim 1, characterized in that, Based on the furniture design plan and the data and materials used in the factory (as well as the material data of the unified supplier), order breakdown data is generated, including: Convert furniture design schemes into 2D engineering drawings; Based on the 2D engineering drawing, the order is broken down and the order breakdown data is generated; The order breakdown data includes: order breakdown price data, order breakdown details, six-view drawings of the furniture, and production layout diagram.

8. A smart design device for customized furniture, characterized in that, include: The interaction module is used to respond to users' requests for screen-sharing drawing operations and to establish a screen-sharing interactive interface for users and designers to remotely guide drawing. The processing module is used to receive the user's voice commands and parse the voice commands through a pre-trained speech recognition model to obtain the user's intent; Based on the user's intent, an initial furniture image is generated on the same-screen interactive interface, and the corresponding production process and hardware accessories are automatically matched to the initial furniture image to obtain a furniture design scheme; based on the furniture design scheme, order breakdown data is generated.

9. A computing device, characterized in that, include: A processor and a memory storing a computer system, wherein the computer system, when run by the processor, performs the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.