Method and device for generating home design scheme, and computer-readable storage medium

Abstract

The present invention discloses a method for generating a home design scheme, a device thereof, and a computer-readable storage medium. The method comprises: obtaining a floor plan of a target room and a target model room, wherein the target room is a room that needs home design; obtaining an initial layout diagram corresponding to the floor plan through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; generating a home design scheme for the target room based on the initial layout diagram and the target model room. The present invention solves the technical problem that the layout results generated by the indoor home design method used in the related art are relatively simple and cannot meet user needs.

Description

Technical Field

[0001] The present invention relates to the field of smart home technology, and in particular to a method for generating a home design solution, a device thereof, and a computer-readable storage medium. Background Art

[0002] At present, home design and computer technology are constantly integrating, and the intelligent design of interior home furnishings has attracted much attention. For the existing automated design systems on the market, users usually only need to select the apartment type to be designed and the desired model room to obtain the layout results output by the automated design system. Finally, the user can complete a set of overall design by making corresponding modifications on this basis. Compared with traditional manual design, it can greatly improve design efficiency and achieve good results.

[0003] However, such an automated design process also faces some problems. For example, automated design can only generate a single layout result, which may not be what the user expects. The user can only passively accept it and make secondary modifications through the tool. At the same time, the upgrade and optimization of the automated design system will become increasingly difficult.

[0004] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0005] The embodiments of the present invention provide a method for generating a home design solution and a device thereof, as well as a computer-readable storage medium, to at least solve the technical problem that the layout results generated by the interior home design method used in the related art are relatively simple and cannot meet the user's needs.

[0006] According to one aspect of an embodiment of the present invention, there is provided a method for generating a home design scheme, comprising: obtaining a floor plan and a target model room of a target room, wherein the target room is a room that requires home design; obtaining an initial layout diagram corresponding to the floor plan through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; generating a home design scheme for the target room based on the initial layout diagram and the target model room.

[0007] Optionally, before obtaining the initial layout diagram corresponding to the floor plan through a predetermined generation model, the method further includes: acquiring multiple historical floor plans and multiple historical initial layout diagrams corresponding to the multiple historical floor plans; training the initial network model using multiple sets of training data including the multiple historical floor plans and the multiple historical initial layout diagrams to obtain the predetermined generation model.

[0008] Optionally, the initial network model is a generative adversarial network (GAN) model.

[0009] Optionally, after obtaining an initial layout diagram corresponding to the floor plan through a predetermined generation model, the method further includes: determining at least one furniture white mold in the initial layout diagram; obtaining position information of the at least one furniture white mold; and adjusting the at least one furniture white mold in the initial layout diagram based on the position information of the at least one furniture white mold to obtain multiple layout diagrams.

[0010] Optionally, generating a home design plan for the target room based on the initial layout diagram and the target model room includes: displaying the multiple layout diagrams on a predetermined display terminal; obtaining a target layout diagram obtained by adjusting at least one layout diagram among the multiple layout diagrams based on a trigger operation, wherein the trigger operation is an operation performed on the predetermined display terminal; generating a home design plan for the target room based on the target layout diagram and the target model room.

[0011] Optionally, a furniture design scheme for the target room is generated based on the target layout diagram and the target model room, including: generating a furniture model based on the furniture white mold in the target layout diagram; and integrating the furniture model into the target model room to generate a furniture design scheme for the target room.

[0012] Optionally, the method for generating a home design plan also includes: while obtaining a target layout diagram obtained by adjusting at least one of the multiple layout diagrams based on a trigger operation, obtaining adjustment information generated based on the trigger operation; and optimizing the predetermined generation model using the adjustment information.

[0013] According to another aspect of an embodiment of the present invention, there is also provided a device for generating a home design scheme, comprising: a first acquisition module, used to acquire a floor plan and a target model room of a target room, wherein the target room is a room that requires home design; a first generation module, used to obtain an initial layout diagram corresponding to the floor plan through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; a second generation module, used to generate a home design scheme for the target room based on the initial layout diagram and the target model room.

[0014] Optionally, the device also includes: a second acquisition module, used to acquire multiple historical floor plans and multiple historical initial layout drawings corresponding to the multiple historical floor plans before obtaining the initial layout drawing corresponding to the floor plan through a predetermined generation model; a training module, used to train the initial network model using multiple groups of training data including the multiple historical floor plans and the multiple historical initial layout drawings to obtain the predetermined generation model.

[0015] Optionally, the initial network model is a generative adversarial network (GAN) model.

[0016] Optionally, the device also includes: a determination module, used to determine at least one furniture white mold in the initial layout diagram after obtaining the initial layout diagram corresponding to the plan view through a predetermined generation model; a third acquisition module, used to obtain position information of the at least one furniture white mold; and an adjustment module, used to adjust the at least one furniture white mold in the initial layout diagram based on the position information of the at least one furniture white mold to obtain multiple layout diagrams.

[0017] Optionally, the second generating module includes: a display unit, used to display the multiple layout drawings on a predetermined display terminal; an acquisition unit, used to acquire a target layout drawing obtained after adjusting at least one layout drawing among the multiple layout drawings based on a trigger operation, wherein the trigger operation is an operation acting on the predetermined display terminal; and a generation unit, used to generate a home design plan for the target room based on the target layout drawing and the target model room.

[0018] Optionally, the generation unit includes: a first generation subunit, used to generate a furniture model based on the furniture white mold in the target layout diagram; and a second generation subunit, used to integrate the furniture model into the target model room to generate a furniture design plan for the target room.

[0019] Optionally, the device also includes: a fourth acquisition module, used to obtain adjustment information generated based on the trigger operation while obtaining the target layout diagram obtained after adjusting at least one of the multiple layout diagrams based on the trigger operation; an optimization module, used to optimize the predetermined generation model using the adjustment information.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed by a processor, the device where the computer-readable storage medium is located is controlled to execute any of the above-mentioned methods for generating a home design plan.

[0021] According to another aspect of an embodiment of the present invention, a processor is provided, wherein the processor is used to run a computer program, wherein the computer program executes any one of the above-mentioned methods for generating a home design plan when running.

[0022] In an embodiment of the present invention, a floor plan of a target room and a target model room are obtained, wherein the target room is a room that needs home furnishing design; an initial layout diagram corresponding to the floor plan is obtained through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; a home furnishing design scheme for the target room is generated based on the initial layout diagram and the target model room. The method for generating a home furnishing design scheme provided by the embodiment of the present invention achieves the purpose of generating a home furnishing design scheme for the target room based on the floor plan of the target room and the target model room through a predetermined generation model, thereby achieving the technical effect of making interior home furnishing design more personalized and intelligent, and further solving the technical problem that the layout results generated by the interior home furnishing design method used in the related art are relatively simple and cannot meet user needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0024] Figure 1 is a flow chart of a method for generating a home design solution according to an embodiment of the present invention;

[0025] Figure 2 is a schematic diagram of a network structure of a generative adversarial network (GAN) according to an embodiment of the present invention;

[0026] FIG3( a) is a schematic diagram of the input of a GAN model according to an embodiment of the present invention;

[0027] FIG. 3( b ) is a schematic diagram of obtaining multiple layout effect diagrams according to the GAN model input of an embodiment of the present invention. Figure 1 ;

[0028] FIG. 3( c ) is a schematic diagram of obtaining multiple layout effect diagrams according to the GAN model input of an embodiment of the present invention. Figure 2 ;

[0029] FIG3( d ) is a third schematic diagram of obtaining multiple layout effect diagrams according to the GAN model input according to an embodiment of the present invention;

[0030] FIG4( a ) is a schematic diagram of a user selecting a layout interface between samples according to an embodiment of the present invention;

[0031] FIG. 4( b ) is a schematic diagram of the final effect diagram of the home design solution generation system according to an embodiment of the present invention. Figure 1 ;

[0032] FIG. 4( c ) is a schematic diagram of the final effect diagram of the home design solution generation system according to an embodiment of the present invention. Figure 2 ;

[0033] Figure 5 is a logic flow chart of a system for generating a home design solution according to an embodiment of the present invention;

[0034] Figure 6 is a schematic diagram of a device for generating a home design solution according to an embodiment of the present invention. DETAILED DESCRIPTION

[0035] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the 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 creative work should fall within the scope of protection of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] For the convenience of description, some nouns or terms appearing in the embodiments of the present invention are explained below.

[0038] Generative Adversarial Networks (GAN) is a deep learning model, a type of unsupervised learning. The model produces fairly good output through the mutual game learning of at least two modules in the framework: the generative model and the discriminative model.

[0039] Example 1

[0040] According to an embodiment of the present invention, a method embodiment of a method for generating a home design plan is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0041] Figure 1 is a flow chart of a method for generating a home design solution according to an embodiment of the present invention. Figure 1 As shown, the method comprises the following steps:

[0042] Step S102, obtaining a floor plan of a target room and a target model room, wherein the target room is a room that needs home furnishing design.

[0043] In this embodiment, the target room may be a study, a living room, a kitchen, a bedroom, etc.

[0044] For example, for a floor plan, if a user wants to use a corresponding room in the floor plan as a study, the room selected by the user in the floor plan can be used as the target room.

[0045] It should be noted that the above-mentioned floor plan is marked with basic information of the target room, such as size (length, width, height), location of doors, location of windows, location of curtains, etc.

[0046] In addition, the above-mentioned target sample room is selected as a target sample room from among multiple study sample rooms by the user after browsing multiple study sample rooms based on his / her favorite decoration style.

[0047] Step S104, obtaining an initial layout diagram corresponding to the plan view through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a plan view and a layout diagram corresponding to the plan view.

[0048] Step S106, generating a home design plan for the target room based on the initial layout diagram and the target model room.

[0049] As can be seen from the above, in an embodiment of the present invention, first, a floor plan of a target room and a target model room can be obtained, wherein the target room is a room that needs home furnishing design; then, an initial layout diagram corresponding to the floor plan is obtained through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; finally, a home furnishing design scheme for the target room is generated based on the initial layout diagram and the target model room, thereby achieving the purpose of generating a home furnishing design scheme for the target room based on the floor plan of the target room and the target model room through a predetermined generation model, thereby achieving the technical effect of making interior home furnishing design more personalized and intelligent.

[0050] The method for generating a home design solution provided by the embodiment of the present invention solves the technical problem that the layout results generated by the indoor home design method used in the related art are relatively simple and cannot meet the needs of users.

[0051] It should be noted that, in the embodiment of the present invention, obtaining the target model room can be performed simultaneously with obtaining the floor plan of the target room, or the floor plan can be obtained first and then the model room can be obtained, as long as the target model room is obtained before executing step S106.

[0052] As an optional embodiment, before obtaining the initial layout diagram corresponding to the floor plan through a predetermined generation model, the method may also include: obtaining multiple historical floor plans and multiple historical initial layout diagrams corresponding to the multiple historical floor plans; training the initial network model using multiple sets of training data including multiple historical floor plans and multiple historical initial layout diagrams to obtain a predetermined generation model.

[0053] In this embodiment, some existing historical floor plans and historical initial layout diagrams corresponding to the historical floor plans can be collected as training data, and the initial network model is trained using these training data to obtain the predetermined generation model. After obtaining the floor plan provided by the user, it is input into the predetermined generation model to obtain the initial layout diagram corresponding to the floor plan, thereby improving the efficiency of generating room layout diagrams.

[0054] As an optional embodiment, the initial network model is a generative adversarial network (GAN) model.

[0055] Figure 2 is a schematic diagram of a network structure of a generative adversarial network (GAN) according to an embodiment of the present invention, such as Figure 2As shown in the figure, the generative adversarial network includes two sub-networks: a generator network (Generator(G)) and a discriminator network (Discriminator(D)), in which the latent space (Latent space) continuously adds noise to the generator network, and generates samples (Generated fake samples) through the generator network and inputs them into the discriminator network for judgment (i.e., step "Is D Correct"), while the real samples (Real samples) are input into the discriminator network for judgment. If the judgment result is true, the discriminator network is returned to the loop training (i.e., step "Fine-tuning"); if the judgment result is false, the generator network is returned to the loop training, so that the probability of the generated image being judged as true is getting higher and higher, until a Nash equilibrium is reached, so that the data generated by the generator network is indistinguishable from the real samples, and the discriminator network cannot correctly distinguish between the generated samples and the real samples, so as to realize an enhanced version of unsupervised deep learning, achieving a technical effect of simple usage but powerful functions and wide applicability.

[0056] It should be noted that the Nash equilibrium in the above optional embodiment refers to the equilibrium state when the generative network in the generative adversarial network restores the distribution of training data and the discriminative network cannot distinguish obvious results (that is, the accuracy rate is 50%). This state can enable the generative network to estimate the distribution of sample data, that is, the generated samples are more real and reliable.

[0057] In addition, it should be noted that the above initial network model can also be a model of other network structures including a generative network and a discriminative network.

[0058] As an optional embodiment, after obtaining an initial layout diagram corresponding to the floor plan through a predetermined generation model, the method further includes: determining at least one furniture white mold in the initial layout diagram; obtaining position information of at least one furniture white mold; and adjusting at least one furniture white mold in the initial layout diagram based on the position information of at least one furniture white mold to obtain multiple layout diagrams.

[0059] It should be pointed out that the results of the model output will eventually be displayed in the form of white models. For the study space, the furniture white models generated at this stage include desks, desk chairs and bookcases; for the bedroom space, a variety of furniture white models including beds, wardrobes, dressing tables and desks can be generated. The furniture selection is very diverse and can maximize user needs.

[0060] In this embodiment, the initial layout diagram output by the plan view through a predetermined generation model can be post-processed to obtain multiple layout diagrams, so that multiple adjusted layout diagrams can be obtained based on the initial layout diagram, and the multiple layout diagrams including the initial layout diagram can be presented to the user for selection, thereby providing the user with a variety of choices and improving the user experience.

[0061] For example, the furniture white model in the initial layout diagram includes: desks, desk chairs and bookcases. In the initial layout diagram, the desks, desk chairs and bookcases all have corresponding positions. Then, one or more of the desks, desk chairs and bookcases in the initial layout diagram can be adjusted. For example, in the initial layout diagram, the desk and desk chair are on the left side. Then, the desk and desk chair can be adjusted to the right side of the initial layout diagram or other positions. Multiple layout diagrams are obtained for users to choose from, thus providing users with a variety of choices. The following is an explanation with reference to the accompanying drawings.

[0062] Figure 3(a) is a schematic diagram of the input of the GAN model according to an embodiment of the present invention. As shown in Figure 3(a), after the floor plan is input into the GAN model, the GAN model processes the floor plan to generate an initial layout diagram containing furniture layout information.

[0063] FIG. 3( b ) is a schematic diagram of obtaining multiple layout effect diagrams according to the GAN model input of an embodiment of the present invention. Figure 1 ,As shown in Figure 3(b), after post-processing, the study part in the figure generates a desk, a chair and a cabinet (i.e., the furniture white model).

[0064] FIG. 3( c ) is a schematic diagram of obtaining multiple layout effect diagrams according to the GAN model input of an embodiment of the present invention. Figure 2 ,As shown in Figure 3(c), after post-processing, the placement of the desk and chair (i.e., the furniture white model) generated in the study in the figure can be adjusted to meet user needs.

[0065] Figure 3(d) is a third schematic diagram of multiple layout effect diagrams obtained by inputting the GAN model according to an embodiment of the present invention. As shown in Figure 3(d), after post-processing, the placement of the cabinets (i.e., furniture white models) generated in the bookstore in the figure can be further adjusted to maximize the satisfaction of user needs.

[0066] It should be pointed out that after the user selects a layout, he or she can adjust the position, size and angle of each white model in the layout according to his or her own expectations, and the layout and white model modification information finally selected by the user will be recorded and saved, so as to facilitate the subsequent continuous iterative optimization of the model effect, which can increase user satisfaction.

[0067] As an optional embodiment, a home design plan for a target room is generated based on an initial layout diagram and a target model room, including: displaying multiple layout diagrams on a predetermined display terminal; obtaining a target layout diagram obtained by adjusting at least one layout diagram among the multiple layout diagrams based on a trigger operation, wherein the trigger operation is an operation performed on a predetermined display terminal; and generating a home design plan for the target room based on the target layout diagram and the target model room.

[0068] In this embodiment, since the multiple layout diagrams presented to the user and the initial layout diagram may not meet the user's needs, the user can use a mouse, a touch pen or direct hand action on a display terminal (for example, a mobile phone, a tablet, a computer, etc.) to adjust the multiple layout diagrams presented to obtain a target layout diagram that meets his or her needs.

[0069] Figure 4(a) is a schematic diagram of a user selecting a sample room layout interface according to an embodiment of the present invention. As shown in Figure 4(a), after selecting any of the above layout results, the user can further select a personalized model room and start automatically designing the home layout.

[0070] As an optional embodiment, a furniture design plan for a target room is generated based on a target layout diagram and a target model room, including: generating a furniture model based on the furniture white mold in the target layout diagram; integrating the furniture model into the target model room to generate a furniture design plan for the target room.

[0071] FIG. 4( b ) is a schematic diagram of the final effect diagram of the home design solution generation system according to an embodiment of the present invention. Figure 1 As shown in Figure 4(b), the home design scheme generation system generates a top view of the final design scheme (taking the study room as an example) based on the location information of the model room and home white model selected by the user. For furniture with white model information, the intelligent design system will place the corresponding furniture according to the type and location of the white model. When the core furniture is placed, the system will further match and place curtains, background walls, accessories, hard ceilings, gussets, paving, floor tiles, and other customized materials to finally obtain a complete design scheme.

[0072] FIG. 4( c ) is a schematic diagram of the final effect diagram of the home design solution generation system according to an embodiment of the present invention. Figure 2 As shown in Figure 4(c), the home design scheme generation system generates a side view of the final design scheme (taking the study room as an example) based on the location information of the model room and the home white model selected by the user. It can be seen that the table, cabinet and chair selected by the user in the figure are generated into a 3D view by the system in combination with the model room, so that the user can see the design drawings of the home design scheme at a glance and very intuitively, making the interior home design more personalized and intelligent.

[0073] As an optional embodiment, the method for generating a home design plan also includes: while obtaining a target layout diagram obtained by adjusting at least one of the multiple layout diagrams based on a trigger operation, obtaining adjustment information generated based on the trigger operation; and optimizing a predetermined generation model using the adjustment information.

[0074] Furthermore, data such as the layout selected by the user and the white model adjustment information will be recycled and filtered, and then transformed into a series of high-quality design solutions for the model to learn, ultimately achieving iterative optimization of the existing intelligent design model to meet the user's personalized needs.

[0075] The present application is described in detail below with reference to specific embodiments.

[0076] Figure 5 is a logic flow chart of a system for generating a home design solution according to an embodiment of the present invention. Figure 5 As shown, the present invention can be applied to various spaces such as bedrooms, study rooms and multi-functional rooms. The present invention will be specifically described below using the study room as an example. The overall process of the present invention can be divided into four stages, namely:

[0077] 1) The user enters the home design generation system and first selects the target room (e.g., study, bedroom, etc.), then calls the GAN model of the corresponding room type, and then the system generates multiple layout results for the user to choose.

[0078] 2) If the user is not satisfied with the existing layout results, he or she can make selective adjustments to the home white model in the layout and then choose a model room.

[0079] 3) The system starts to design automatically and provides a complete design plan.

[0080] 4) Record the user's layout selection and modification results, and continuously iterate and optimize the generative adversarial network model so that the system can generate solutions that increase user satisfaction.

[0081] As can be seen from the above, in order to solve the problems of single layout, continuous optimization difficulties and over-reliance on model rooms in the current automatic design process, the present invention creatively combines deep learning with home design, and proposes an indoor home intelligent design system based on generative adversarial network (GAN), which is currently applicable to the intelligent design of homes in spaces such as bedrooms, study rooms and multi-functional rooms. Compared with the existing indoor automatic design system, the present invention can generate a variety of layout results for the input apartment type, thereby providing users with more choices. At the same time, the present invention supports users to make corresponding modifications to the layout results output by the model before automatic design, further ensuring that the application effect meets the user's expectations. In addition, the method for generating a home design scheme provided in the embodiment of the present invention can also continuously optimize the GAN model used according to the user's selection and modification results, so that the layout generated by it is more in line with the user's mind, making the indoor home design more personalized and intelligent.

[0082] In summary, in the embodiment of the present invention, the home solution generation system is compared with the existing indoor furniture automatic design system on the market. The present invention creatively adopts a combination of home design and deep learning to make the generated layout results more stable and diverse. This is reflected in the fact that for some special house types, the layout generated by the so-called "established rules" often has poor results, and even faces the dilemma of design failure. Moreover, the layout generated by the intelligent design system in the present invention is free from the constraints of the rules and is completely determined by the output results of the model, so the quality and availability of the design results can be greatly improved. In addition, thanks to the use of the GAN model, the system can also generate a variety of different layout results, providing users with more choices. In terms of the design process, the user can adjust the furniture white model results generated by the model in advance before automatic design, so as to obtain the expected design effect, eliminating the need for the user to make secondary modifications. In addition, the method for generating a home design solution provided in the embodiment of the present invention can also save the layout selected by the user and the modification of the layout results, and further transform these data into the input of the model training, thereby realizing the iterative optimization of the intelligent design system. This also means that while the model outputs a layout result that satisfies the user, the user's choice will in turn promote the improvement of the model, forming a positive feedback closed-loop system.

[0083] Example 2

[0084] According to another aspect of the embodiments of the present invention, a device for generating a home design solution is also provided. Figure 6 is a schematic diagram of a device for generating a home design solution according to an embodiment of the present invention. Figure 6 As shown, the device for generating a home design solution further includes: a first acquisition module 61, a first generation module 63 and a second generation module 65. The device for generating a home design solution is described below.

[0085] The first acquisition module 61 is used to acquire the floor plan of a target room and a target model room, wherein the target room is a room that needs home furnishing design.

[0086] The first generation module 63 is used to obtain an initial layout diagram corresponding to the plan view through a predetermined generation model, wherein the predetermined generation model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a plan view and a layout diagram corresponding to the plan view.

[0087] The second generating module 65 is used to generate a home design plan for a target room based on the initial layout diagram and the target model room.

[0088] It should be noted that the first acquisition module 61, the first generation module 63 and the second generation module 65 correspond to steps S102 to S106 in Embodiment 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the modules as part of the device can be executed in a computer system such as a set of computer executable instructions.

[0089] As can be seen from the above, in the embodiment of the present invention, the first acquisition module 61 is first used to obtain the floor plan of the target room and the target model room, wherein the target room is a room that needs home furnishing design; then the first generation module 63 is used to obtain the initial layout diagram corresponding to the floor plan through a predetermined generation model, wherein the predetermined generation model is obtained by machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a floor plan and a layout diagram corresponding to the floor plan; finally, the second generation module 65 is used to generate the home furnishing design scheme of the target room based on the initial layout diagram and the target model room. The home furnishing design scheme generation device provided by the embodiment of the present invention achieves the purpose of generating the home furnishing design scheme of the target room based on the floor plan of the target room and the target model room through a predetermined generation model, thereby achieving the technical effect of making the interior home furnishing design more personalized and intelligent, and then solving the technical problem that the layout results generated by the interior home furnishing design method used in the related technology are relatively simple and cannot meet the needs of users.

[0090] Optionally, the device also includes: a second acquisition module, used to acquire multiple historical floor plans and multiple historical initial layout drawings corresponding to the multiple historical floor plans before obtaining the initial layout drawing corresponding to the floor plan through a predetermined generation model; a training module, used to train the initial network model using multiple sets of training data including multiple historical floor plans and multiple historical initial layout drawings to obtain a predetermined generation model.

[0091] Optionally, the initial network model is a generative adversarial network (GAN) model.

[0092] Optionally, the device also includes: a determination module, used to determine at least one furniture white mold in the initial layout diagram after obtaining the initial layout diagram corresponding to the floor plan through a predetermined generation model; a third acquisition module, used to obtain position information of at least one furniture white mold; and an adjustment module, used to adjust at least one furniture white mold in the initial layout diagram based on the position information of at least one furniture white mold to obtain multiple layout diagrams.

[0093] Optionally, the second generation module includes: a display unit for displaying multiple layout drawings on a predetermined display terminal; an acquisition unit for acquiring a target layout drawing obtained by adjusting at least one of the multiple layout drawings based on a trigger operation, wherein the trigger operation is an operation performed on a predetermined display terminal; and a generation unit for generating a home design plan for a target room based on the target layout drawing and a target model room.

[0094] Optionally, the generation unit includes: a first generation subunit, used to generate a furniture model based on the furniture white mold in the target layout diagram; and a second generation subunit, used to integrate the furniture model into the target model room to generate a furniture design plan for the target room.

[0095] Optionally, the device also includes: a fourth acquisition module, used to obtain adjustment information generated based on the trigger operation while obtaining the target layout diagram obtained after adjusting at least one layout diagram among the multiple layout diagrams based on the trigger operation; an optimization module, used to optimize the predetermined generation model using the adjustment information.

[0096] Example 3

[0097] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is executed by a processor, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for generating a home design plan.

[0098] Example 4

[0099] According to another aspect of an embodiment of the present invention, a processor is provided, the processor is used to run a computer program, wherein when the computer program is run, any of the above methods for generating a home design solution is executed. The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0100] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0101] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0102] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0103] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0104] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0105] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for generating a home design scheme, characterized in that: include: Obtaining a floor plan of a target room and a target model room, wherein the target room is a room that needs home furnishing design; An initial layout diagram corresponding to the plan view is obtained by a predetermined generation model, wherein the predetermined generation model is obtained by machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a plan view and a layout diagram corresponding to the plan view; Generate a home design plan for the target room based on the initial layout diagram and the target model room, After obtaining an initial layout diagram corresponding to the plan diagram through a predetermined generation model, the method further includes: Determine at least one furniture white model in the initial layout diagram; Obtaining location information of at least one furniture white mold; Based on the position information of the at least one furniture white mold, the at least one furniture white mold is adjusted in the initial layout diagram to obtain a plurality of layout diagrams, Generating a home design scheme for the target room based on the initial layout diagram and the target model room includes: Displaying the plurality of layout diagrams on a predetermined display terminal; Acquire a target layout diagram obtained by adjusting at least one layout diagram among the multiple layout diagrams based on a trigger operation, wherein the trigger operation is an operation acting on the predetermined display terminal; Generate a home design plan for the target room based on the target layout diagram and the target model room, Generating a home design scheme for the target room based on the target layout diagram and the target model room includes: Generate a furniture model based on the furniture white model in the target layout diagram; The furniture model is integrated into the target model room to generate a furniture design plan for the target room.

2. The method according to claim 1, characterized in that Before obtaining an initial layout diagram corresponding to the plan diagram by using a predetermined generation model, the method further includes: Acquire a plurality of historical floor plans and a plurality of historical initial layout drawings corresponding to the plurality of historical floor plans; The initial network model is trained using multiple sets of training data including the multiple historical floor plans and the multiple historical initial layout plans to obtain the predetermined generation model.

3. The method according to claim 2, characterized in that The initial network model is a generative adversarial network (GAN) model.

4. The method according to claim 1, characterized in that The method further comprises: While acquiring a target layout diagram obtained by adjusting at least one layout diagram among the multiple layout diagrams based on a trigger operation, acquiring adjustment information generated based on the trigger operation; The predetermined generation model is optimized using the adjustment information.

5. A device for generating a home design scheme, characterized in that: include: A first acquisition module is used to acquire a floor plan of a target room and a target model room, wherein the target room is a room that needs home furnishing design; A first generating module is used to obtain an initial layout diagram corresponding to the plan view through a predetermined generating model, wherein the predetermined generating model is obtained through machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: a plan view and a layout diagram corresponding to the plan view; The second generation module is used to generate a home design plan for the target room based on the initial layout diagram and the target model room. a determination module, for determining at least one furniture white mold in the initial layout diagram after obtaining the initial layout diagram corresponding to the plan diagram through a predetermined generation model; a third acquisition module, for obtaining the position information of at least one furniture white mold; an adjustment module, for adjusting at least one furniture white mold in the initial layout diagram based on the position information of at least one furniture white mold, to obtain a plurality of layout diagrams, The second generation module includes: a display unit, which is used to display multiple layout diagrams on a predetermined display terminal; an acquisition unit, which is used to acquire a target layout diagram obtained by adjusting at least one layout diagram among the multiple layout diagrams based on a trigger operation, wherein the trigger operation is an operation acting on the predetermined display terminal; and a generation unit, which is used to generate a home design plan for a target room based on the target layout diagram and the target model room. The generation unit includes: a first generation subunit, which is used to generate a furniture model based on the furniture white mold in the target layout diagram; and a second generation subunit, which is used to integrate the furniture model into the target model room to generate a furniture design plan for the target room.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed by a processor, the device where the computer-readable storage medium is located is controlled to execute the method for generating a home design solution according to any one of claims 1 to 4.

7. A processor, characterized in that: The processor is used to run a computer program, wherein the computer program, when running, executes the method for generating a home design solution according to any one of claims 1 to 4.

Images