An open kitchen intelligent design method, device and system

Abstract

This invention discloses a method, device, and system for intelligent design of open kitchens, belonging to the field of smart home design and information technology. By locating an area suitable for cabinet layout within an open space, this method overcomes the existing problem of only generating an overall cabinet layout within a non-enclosed local area, thereby improving design efficiency and applicability. The customized cabinet configuration information input by the user improves the overall cabinet design, further enhancing design efficiency and user experience.

Description

Technical Field

[0001] The present invention relates to the field of smart home design and information technology, and in particular to an open kitchen smart design method, device and system. Background Art

[0002] With the popularity of open kitchens, the demand for open kitchens in smart home design is also increasing, which requires a smart home design method specifically applied to open kitchens.

[0003] The existing home design system is mostly designed for closed spaces of standard area (10 square meters). It has limited effect on larger open spaces and cannot be applied to large open kitchen designs, so it has poor applicability.

[0004] In addition, the existing technology also provides an open kitchen design method, in which the designer artificially integrates and designs the living room and the kitchen. However, due to the need for artificial integration and design, it leads to low efficiency. Summary of the Invention

[0005] In order to solve the problems of the prior art, the embodiments of the present invention provide an open kitchen intelligent design method, device and system. The technical solution is as follows:

[0006] In one aspect, a method for intelligent design of an open kitchen is provided, the method comprising:

[0007] Configure an adversarial network model and, using the adversarial network model, perform the following operations:

[0008] Identify and locate areas suitable for cabinet layout within large spaces;

[0009] generating a corresponding cabinet layout within the area;

[0010] Obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0011] Optionally, the method further includes:

[0012] After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

[0013] Optionally, the method further includes:

[0014] Record the user's layout selection and modification results;

[0015] And according to the layout selection and the modification result, the adversarial network model is optimized.

[0016] Optionally, the identifying and locating an area suitable for cabinet layout in a large space includes:

[0017] Obtaining a floor plan, and inputting the floor plan into the adversarial network model, identifying and locating areas suitable for cabinet layout, and outputting a floor plan containing the areas;

[0018] The floor plan is post-processed to obtain areas in the apartment that are actually suitable for cabinet layout.

[0019] Optionally, generating a corresponding cabinet layout in the area includes:

[0020] Inputting the area into the adversarial network model and outputting the overall layout diagram of the cabinet;

[0021] Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram;

[0022] Inputting the overall cabinet layout diagram into a wall cabinet layout generation model, and outputting a wall cabinet layout diagram;

[0023] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

[0024] Optionally, the step of obtaining customized cabinet configuration information input by a user and improving and outputting an overall cabinet design based on the customized cabinet configuration information includes:

[0025] Obtain customized cabinet configuration information input by the user, and configure the overall cabinet design according to the customized cabinet configuration information.

[0026] Displaying the overall cabinet design on the front end and obtaining modification data of the overall cabinet design made by the user;

[0027] According to the modification information, the overall cabinet design is modified, and the modified overall cabinet design is matched to the corresponding area to improve the overall cabinet design.

[0028] In another aspect, an open kitchen intelligent design device is provided, comprising:

[0029] The configuration module is used to configure the adversarial network model and perform the following operations through the adversarial network model:

[0030] A positioning module is used to identify and locate areas suitable for cabinet layout in a large space;

[0031] A layout module, configured to generate a corresponding cabinet layout within the area;

[0032] The customization module is used to obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0033] Optionally, the device further includes a matching module, configured to:

[0034] After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

[0035] Optionally, the device further includes an optimization module, configured to:

[0036] Record the user's layout selection and modification results;

[0037] And according to the layout selection and the modification result, the adversarial network model is optimized.

[0038] Optionally, the positioning module is specifically used to:

[0039] Obtaining a floor plan, and inputting the floor plan into the adversarial network model, identifying and locating areas suitable for cabinet layout, and outputting a floor plan containing the areas;

[0040] The floor plan is post-processed to obtain areas in the apartment that are actually suitable for cabinet layout.

[0041] Optionally, the layout module is specifically used to:

[0042] Inputting the area into the adversarial network model and outputting the overall layout diagram of the cabinet;

[0043] Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram;

[0044] Inputting the overall cabinet layout diagram into a wall cabinet layout generation model, and outputting a wall cabinet layout diagram;

[0045] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

[0046] Optionally, the customization module is specifically used to:

[0047] Obtain customized cabinet configuration information input by the user, and configure the overall cabinet design according to the customized cabinet configuration information.

[0048] Displaying the overall cabinet design on the front end and obtaining modification data of the overall cabinet design made by the user;

[0049] According to the modification information, the overall cabinet design is modified, and the modified overall cabinet design is matched to the corresponding area to improve the overall cabinet design.

[0050] In another aspect, an open kitchen intelligent design system is provided, comprising:

[0051] The configuration device is used to configure the adversarial network model and perform the following operations through the adversarial network model:

[0052] A positioning device for identifying and locating areas suitable for cabinet layout in a large space;

[0053] Layout means for generating a corresponding cabinet layout in the area;

[0054] The customization device is used to obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0055] Optionally, the system further includes a matching device for:

[0056] After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

[0057] Optionally, the system further comprises an optimization device for:

[0058] Record the user's layout selection and modification results;

[0059] And according to the layout selection and the modification result, the adversarial network model is optimized.

[0060] Optionally, the positioning module is specifically used to:

[0061] Obtaining a floor plan, and inputting the floor plan into the adversarial network model, identifying and locating areas suitable for cabinet layout, and outputting a floor plan containing the areas;

[0062] The floor plan is post-processed to obtain areas in the apartment that are actually suitable for cabinet layout.

[0063] Optionally, the layout module is specifically used to:

[0064] Inputting the area into the adversarial network model and outputting the overall layout diagram of the cabinet;

[0065] Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram;

[0066] Inputting the overall cabinet layout diagram into a wall cabinet layout generation model, and outputting a wall cabinet layout diagram;

[0067] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

[0068] Optionally, the customization module is specifically used to:

[0069] Obtain customized cabinet configuration information input by the user, and configure the overall cabinet design according to the customized cabinet configuration information.

[0070] Displaying the overall cabinet design on the front end and obtaining modification data of the overall cabinet design made by the user;

[0071] According to the modification information, the overall cabinet design is modified, and the modified overall cabinet design is matched to the corresponding area to improve the overall cabinet design.

[0072] The technical solution provided by the embodiment of the present invention has the following beneficial effects:

[0073] 1. By locating the area suitable for cabinet layout in the open space, the existing technology can only generate the overall cabinet layout in the non-enclosed local area, thereby improving the design efficiency and applicability;

[0074] 2. Through the customized cabinet configuration information input by the user, the overall cabinet design is improved, the design efficiency is further improved, and the user experience is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0076] Figure 1 This is a flow chart of the open kitchen intelligent design method provided by an embodiment of the present invention;

[0077] Figure 2 is a floor plan provided by an embodiment of the present invention;

[0078] Figure 3 is a plan view of an area provided by an embodiment of the present invention;

[0079] Figure 4 is a regional map provided by an embodiment of the present invention;

[0080] Figure 5 This is an overall layout diagram of a cabinet provided by an embodiment of the present invention;

[0081] Figure 6 It is a schematic diagram of another embodiment provided by the present invention. DETAILED DESCRIPTION

[0082] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0083] Reference Figure 1 As shown, an open kitchen intelligent design method is provided, the method comprising:

[0084] 101. Configure the adversarial network model and perform the following operations through the adversarial network model:

[0085] 102. Identify and locate areas suitable for cabinet layout in large spaces;

[0086] 103. Generate corresponding cabinet layout in the area;

[0087] 104. Obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0088] It should be noted that, in step 104, the user may input customized cabinet configuration information in the following ways:

[0089] On the user device, displaying the cabinet layout interface to the user;

[0090] The user enters customized cabinet configuration information on the cabinet layout interface. The customized cabinet configuration information includes at least customized materials, customized functional area divisions, customized metal parts, etc. In addition, the customized cabinet configuration information may also include the length, width, height, corner width, corner depth, cut corner width, and cut corner depth of various cabinets (such as single-door floor cabinets, double-door floor cabinets, wall cabinets, and functional cabinets, etc.);

[0091] It should be noted that in this step, the user inputs custom materials and custom metal parts by clicking the corresponding area in the cabinet layout and then completing it through the selection interface. Taking custom materials as an example, the process can be specifically as follows:

[0092] In the cabinet layout interface, after the user clicks on the cabinet surface or cabinet structure to be customized, a selection interface is displayed in the cabinet layout interface; or, after the user clicks on the cabinet surface or cabinet structure to be customized, the cabinet layout interface jumps to the selection interface. It should be noted that the selection interface includes at least:

[0093] Illustrations of multiple materials and their corresponding prices;

[0094] After the user selects the corresponding material, the material of the cabinet surface or cabinet structure is updated to the material indicated by the user and displayed.

[0095] User-defined functional area division is achieved by inputting in the cabinet layout or self-dividing the functional area. The process can be specifically as follows:

[0096] In the cabinet layout interface, the user selects an area by entering text information or lines (this part is used to instruct the user to customize the number and size of compartments in the cabinet, and does not clearly indicate the function);

[0097] After the user enters the above information, the customized cabinet layout interface is displayed.

[0098] Through the above process, the customized cabinet configuration information input by the user can improve the overall cabinet design, meet the user's personalized needs, and improve the user experience.

[0099] It should be noted that the principle and training method of the generative adversarial network (GAN) model are: the generative adversarial network consists of two sub-networks, namely the generator and the discriminator.

[0100] The generator generates a corresponding result for a given input, while the discriminator determines whether the input image is "real." Therefore, during GAN training, two networks, the generator and the discriminator, need to be trained. The generator's goal is to generate images that the discriminator considers "real" as much as possible, while the discriminator's goal is to detect "fake images" generated by the generator as much as possible. The specific method is alternating iterative training. First, the generator is fixed, and the binary discriminator is trained using the "fake images" it generates and the existing real labels. Then, the parameters of the discriminator are fixed, and the generator and discriminator are connected in series to calculate the loss function, thereby updating the generator's parameters. As training progresses, the generator and discriminator continue to compete with each other, eventually reaching a Nash equilibrium, which means that the model training is complete.

[0101] Correspondingly, the generator may be implemented by an image recognition model. The embodiment of the present invention does not limit the specific image recognition model, but the image recognition model at least includes, after inputting a specified type of image (such as a floor plan), identifying a specific area in the image where cabinets can be placed; and outputting the recognized image, in which at least the specific area is marked;

[0102] The discriminator is also constructed by an image recognition model. Unlike the above-mentioned generator, the image recognition model is used to identify the authenticity of the above-mentioned output image. The parameters of the image recognition model can be obtained by training a large number of floor plans including cabinet layouts. The authenticity can be understood as the location of the above-mentioned specific area is consistent with common sense and user usage habits. After the discriminator judges the above-mentioned output picture, it only outputs the real image.

[0103] It should be noted that after the training of the above generator and discriminator is completed, the actual design drawings can be used as samples for further real-time training to improve authenticity.

[0104] Through the adversarial network composed of the generator and the discriminator, it is possible to further improve the recognition accuracy based on the recognition of pictures such as floor plans, and through further real-time training, the accuracy of model recognition can be improved.

[0105] The generator is divided according to its function, which can be:

[0106] The locator generator, after inputting the floor plan, identifies and locates areas suitable for cabinet layout in a large space;

[0107] The layout sub-generator, after inputting the above area, generates the corresponding cabinet layout in the area;

[0108] The custom sub-generator, after inputting the cabinet layout, improves and outputs the overall cabinet design based on the customized cabinet configuration information input by the user.

[0109] The above sub-generators correspond to different discriminators.

[0110] It should be noted that the main way to divide the generator according to its function is to train it with different training samples and set the output information. Specifically:

[0111] The localizer generator is trained using floor plan samples containing the area, and the output is set to be the floor plan containing the area;

[0112] The layout sub-generator is trained using floor plans that include cabinet layouts, and its output is the floor plan with the cabinet layout added.

[0113] The custom sub-generator is set up in the same way as the two sub-generators above, so it will not be repeated here.

[0114] The positioning sub-generator, layout sub-generator and customization sub-generator are set within the generator, that is, they are set as multiple function generators within a single generator, thereby reducing deployment costs.

[0115] Optionally, the method further includes:

[0116] After the overall cabinet design is completed in the area, the furniture matching of the remaining areas is completed and output. This embodiment of the present invention does not limit this process.

[0117] Optionally, the method further includes:

[0118] Record the user's layout selection and modification results;

[0119] And according to the layout selection and modification results, the adversarial network model is optimized. The optimization process can be to use the layout selection and modification results as training samples to train the adversarial network model.

[0120] It should be noted that the user's layout selection mainly involves modifying and selecting the position, orientation, and size of the cabinets in the cabinet layout after the layout diagram is output. The process can be:

[0121] Set the cabinet layout to the area to be selected and modified, and display it;

[0122] Users can select operations by clicking;

[0123] By long pressing on various parts of the cabinet, the cabinet parts can be rotated, enlarged or reduced to modify the orientation and size. The position can also be selected and modified by dragging.

[0124] Optionally, the above process may also display a parameter interface to the user;

[0125] Users can select and modify layouts by adjusting or modifying parameters.

[0126] Through the above modifications and selections, users can modify the cabinet layout, improve the overall cabinet design, meet the user's personalized needs, and improve the user experience.

[0127] Optional, identifying and locating areas suitable for cabinet layout within a large space include:

[0128] Obtain a floor plan and input it into the adversarial network model to identify and locate areas suitable for cabinet layout and output a floor plan containing the areas. The specific process is as follows:

[0129] Convert the apartment plan selected by the user for open kitchen design into a floor plan, refer to Figure 2 As shown, the floor plan is input into the locator generator, and the floor plan containing the area is output. Figure 3 shown.

[0130] Post-process the floor plan to obtain the areas in the apartment that are actually suitable for cabinet layout:

[0131] It should be noted that when making the input, the house type in the tool coordinate system is drawn in a two-dimensional image. After it is fed into the model, the output result is also a two-dimensional image with the same size as the input image.

[0132] The post-processing process specifically includes:

[0133] Map the generated area in the image back to the tool coordinate system;

[0134] If there are multiple areas, or the generated area overlaps with the interior walls of the apartment, some additional work will be required to screen and process it to obtain the final open kitchen area that meets the expectations.

[0135] The above process can be completed manually, and the process can be:

[0136] Identify the output image where there are multiple such areas, or where the generated area overlaps with the interior walls of the apartment;

[0137] And show the floor plan including the layout area to the designer;

[0138] The designer edits and processes the floor plan to obtain the desired open kitchen area. Alternatively, the above process can be:

[0139] A recognizer and an automatic editor are provided; wherein the recognizer can be constructed using an image recognition model, and the recognizer can be configured such that: the input image is a floor plan containing an area, and the output image is an abnormal floor plan and an abnormal location, wherein the abnormal floor plan is an output image in which multiple areas exist, or the generated area overlaps with an interior wall of the floor plan; the image recognition model can be trained using multiple abnormal floor plans as samples;

[0140] The automatic editor edits the abnormal positions in the abnormal floor plan and re-inputs the edited abnormal floor plan into the identifier until the output floor plan is normal.

[0141] Through the post-processing process, the user experience and efficiency reduction problems caused by abnormal images are eliminated, thereby realizing abnormal processing and facilitating user use.

[0142] Optionally, generating a corresponding cabinet layout in the area includes:

[0143] The generation process can be:

[0144] By inputting the image containing the area into the layout sub-generator and the corresponding discriminator in the adversarial network model, the generation process has been described above and will not be repeated here.

[0145] Input the region into the adversarial network model and output the overall layout of the cabinet; the specific adversarial network model in this process is the layout sub-generator, such as Figure 4 The area shown is input to the layout sub-generator, and the output cabinet overall layout diagram is referenced Figure 5 shown.

[0146] Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram; the functional area at least includes the sink, stove, and refrigerator;

[0147] Input the overall cabinet layout diagram into the wall cabinet layout generation model and output the wall cabinet layout diagram;

[0148] The functional cabinet layout generation model at least includes a sink generation model, a stove generation model and a refrigerator generation model. The principles of the above generation models are the same as those of the generator and will not be repeated here.

[0149] It should be noted that the above-mentioned functional cabinets, sinks, stoves, refrigerators, etc. need to be set separately in the floor plan, that is, the images of the above-mentioned functional cabinets, sinks, stoves and refrigerators in the layout can be edited separately and displayed and marked according to different colors, so as to improve stability and facilitate user viewing.

[0150] The above diagrams including functional area layout and wall cabinet layout can be referred to Figure 6 shown.

[0151] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment. The actual functional areas and wall cabinet layout include at least the positions, sizes, and angles of the floor cabinets, sinks, stoves, and wall cabinets.

[0152] It should be noted that the post-processing method is the same as the above-mentioned post-processing method and will not be described in detail here.

[0153] Optionally, obtaining customized cabinet configuration information input by the user and improving and outputting the overall cabinet design based on the customized cabinet configuration information include:

[0154] Obtain the customized cabinet configuration information entered by the user and configure the overall cabinet design based on the customized cabinet configuration information. The customized cabinet configuration information includes the length, width, height, corner width, corner depth, corner cutting width and corner cutting depth of various cabinets (such as single-door floor cabinets, double-door floor cabinets, wall cabinets, and functional cabinets, etc.);

[0155] Display the overall cabinet design on the front end, allow users to modify it, and obtain the user's modification data on the overall cabinet design;

[0156] According to the modification information, the overall cabinet design is revised, and the revised overall cabinet design is matched to the corresponding areas in sequence to improve the overall cabinet design.

[0157] Exemplarily, the display process is to reconfigure the image of the overall cabinet design based on the above information and display the overall cabinet on the floor plan;

[0158] Then, according to the modified information, the images of the functional cabinets, sink, stove, and refrigerator are reset, and the reset functional cabinets, sink, stove, and refrigerator are matched to the areas in the new integrated cabinet; and displayed;

[0159] Then reset the material and display it.

[0160] Optionally, in actual applications, the revised overall cabinet design can be input into the discriminator to further determine whether the revised overall cabinet design conforms to common sense and user usage habits, thereby further improving the user's personalized experience.

[0161] It should be noted that in actual application, the user's customized cabinet configuration information may not be customized or modified for the entire cabinet, but for parts. Therefore, the pictures of the above-mentioned integrated cabinets, functional cabinets, sinks, stoves and refrigerators are not a whole, and can be modified or customized separately;

[0162] When a user customizes or modifies any one of the overall cabinets, functional cabinets, sinks, stoves, and refrigerators, after the modification is completed, the remaining parts need to be adjusted in applicability based on the modified part to adapt to the modified part.

[0163] Through the above process, the user can adjust parts of the cabinet design, thereby enabling the user to fine-tune the cabinet design.

[0164] The fine-tuned cabinet design is input into the discriminator to determine whether the fine-tuning is reasonable, that is, whether the fine-tuned overall cabinet design conforms to common sense and user usage habits, thereby further improving the user's personalized experience.

[0165] In another aspect, an open kitchen intelligent design device is provided, comprising:

[0166] The configuration module is used to configure the adversarial network model and perform the following operations through the adversarial network model:

[0167] A positioning module is used to identify and locate areas suitable for cabinet layout in a large space;

[0168] Layout module, used to generate corresponding cabinet layout in the area;

[0169] The customization module is used to obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0170] Optionally, the device further includes a matching module, configured to:

[0171] After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

[0172] Optionally, the device further includes an optimization module for:

[0173] Record the user's layout selection and modification results;

[0174] And based on the layout selection and modification results, the adversarial network model is optimized.

[0175] Optionally, the positioning module is specifically used for:

[0176] Obtain a floor plan and input it into the adversarial network model to identify and locate areas suitable for cabinet layout and output a floor plan containing the areas.

[0177] Post-process the floor plan to obtain the area in the apartment that is actually suitable for cabinet layout.

[0178] Optionally, the layout module is specifically used to:

[0179] Input the area into the adversarial network model and output the overall layout of the cabinet;

[0180] Input the overall cabinet layout diagram into the functional cabinet layout generation model and output the functional area layout diagram;

[0181] Input the overall cabinet layout diagram into the wall cabinet layout generation model and output the wall cabinet layout diagram;

[0182] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

[0183] Optionally, custom modules are used to:

[0184] Obtain the customized cabinet configuration information input by the user, and configure the overall cabinet design based on the customized cabinet configuration information.

[0185] Display the overall cabinet design on the front end and obtain the user's modification data on the overall cabinet design;

[0186] According to the modification information, the overall cabinet design is revised, and the revised overall cabinet design is matched to the corresponding area to improve the overall cabinet design.

[0187] In another aspect, an open kitchen intelligent design system is provided, comprising:

[0188] The configuration device is used to configure the adversarial network model and perform the following operations through the adversarial network model:

[0189] A positioning device for identifying and locating areas suitable for cabinet layout in a large space;

[0190] A layout device for generating a corresponding cabinet layout within the area;

[0191] The customization device is used to obtain the customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information.

[0192] Optionally, the system further includes a matching device for:

[0193] After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

[0194] Optionally, the system further includes an optimization device for:

[0195] Record the user's layout selection and modification results;

[0196] And based on the layout selection and modification results, the adversarial network model is optimized.

[0197] Optionally, the positioning module is specifically used for:

[0198] Obtain a floor plan and input it into the adversarial network model to identify and locate areas suitable for cabinet layout and output a floor plan containing the areas.

[0199] Post-process the floor plan to obtain the area in the apartment that is actually suitable for cabinet layout.

[0200] Optionally, the layout module is specifically used to:

[0201] Input the area into the adversarial network model and output the overall layout of the cabinet;

[0202] Input the overall cabinet layout diagram into the functional cabinet layout generation model and output the functional area layout diagram;

[0203] Input the overall cabinet layout diagram into the wall cabinet layout generation model and output the wall cabinet layout diagram;

[0204] The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

[0205] Optionally, custom modules are used to:

[0206] Obtain the customized cabinet configuration information input by the user, and configure the overall cabinet design based on the customized cabinet configuration information.

[0207] Display the overall cabinet design on the front end and obtain the user's modification data on the overall cabinet design;

[0208] According to the modification information, the overall cabinet design is revised, and the revised overall cabinet design is matched to the corresponding area to improve the overall cabinet design.

[0209] All the above optional technical solutions can be arbitrarily combined to form optional embodiments of the present invention, and will not be described in detail here.

[0210] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0211] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An open kitchen intelligent design method, characterized in that: The method comprises: Configure an adversarial network model and, using the adversarial network model, perform the following operations: Identify and locate areas in open-plan spaces suitable for cabinet layout; generating a corresponding cabinet layout within the area; Obtaining customized cabinet configuration information input by the user, and improving and outputting the overall cabinet design based on the customized cabinet configuration information; The step of identifying and locating an area suitable for cabinet layout in the open space includes: Obtaining a floor plan, and inputting the floor plan into the adversarial network model, identifying and locating areas suitable for cabinet layout, and outputting a floor plan containing the areas; Post-processing the floor plan to obtain areas in the apartment that are actually suitable for cabinet layout; The obtaining of customized cabinet configuration information input by the user includes: On the user device, displaying the cabinet layout interface to the user; The user enters customized cabinet configuration information on the cabinet layout interface; Generating a corresponding cabinet layout within the area includes: Inputting the area into the adversarial network model and outputting the overall layout diagram of the cabinet; Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram; Inputting the overall cabinet layout diagram into a wall cabinet layout generation model, and outputting a wall cabinet layout diagram; The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

2. The method according to claim 1, characterized in that The method further comprises: After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

3. The method according to claim 1 or 2, characterized in that The method further comprises: Record the user's layout selection and modification results; And according to the layout selection and the modification result, the adversarial network model is optimized.

4. An open kitchen intelligent design device, characterized in that: The device comprises: The configuration module is used to configure the adversarial network model and perform the following operations through the adversarial network model: A positioning module is used to identify and locate areas suitable for cabinet layout in an open space; A layout module, configured to generate a corresponding cabinet layout within the area; A customization module is used to obtain customized cabinet configuration information input by the user, and improve and output the overall cabinet design based on the customized cabinet configuration information; The step of identifying and locating an area suitable for cabinet layout in the open space includes: Obtaining a floor plan, and inputting the floor plan into the adversarial network model, identifying and locating areas suitable for cabinet layout, and outputting a floor plan containing the areas; Post-processing the floor plan to obtain areas in the apartment that are actually suitable for cabinet layout; The obtaining of customized cabinet configuration information input by the user includes: On the user device, displaying the cabinet layout interface to the user; The user enters customized cabinet configuration information on the cabinet layout interface; Generating a corresponding cabinet layout within the area includes: Inputting the area into the adversarial network model and outputting the overall layout diagram of the cabinet; Input the overall cabinet layout diagram into the functional cabinet layout generation model, and output the functional area layout diagram; Inputting the overall cabinet layout diagram into a wall cabinet layout generation model, and outputting a wall cabinet layout diagram; The functional area layout diagram and the wall cabinet layout diagram are post-processed to obtain the actual functional areas and wall cabinet layout in the apartment.

5. The device according to claim 4, characterized in that The device further includes a matching module, configured to: After completing the overall cabinet design in the area, complete and output the furniture matching for the remaining areas.

6. The device according to claim 4 or 5, characterized in that The device further includes an optimization module, configured to: Record the user's layout selection and modification results; And according to the layout selection and the modification result, the adversarial network model is optimized.

Images