CN113886911A - Household design scheme generation method and device and computer readable storage medium - Google Patents
Household design scheme generation method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN113886911A CN113886911A CN202111088392.8A CN202111088392A CN113886911A CN 113886911 A CN113886911 A CN 113886911A CN 202111088392 A CN202111088392 A CN 202111088392A CN 113886911 A CN113886911 A CN 113886911A
- Authority
- CN
- China
- Prior art keywords
- layout
- target
- plan
- model
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
Abstract
The invention discloses a method and a device for generating a household design scheme and a computer readable storage medium. Wherein, the method comprises the following steps: acquiring a plan view of a target room and a target sample plate, wherein the target room is a room needing home design; obtaining an initial layout corresponding to the plan by using a predetermined generated model, wherein the predetermined generated model is obtained by using a plurality of sets of training data through machine learning training, and each set of training data in the plurality of sets of training data comprises: a plan view and a layout corresponding to the plan view; and generating a home design scheme of the target room based on the initial layout and the target sample plates. The invention solves the technical problems that the layout result generated by the indoor home design mode used in the related technology is single and cannot meet the user requirement.
Description
Technical Field
The invention relates to the technical field of intelligent home furnishing, in particular to a method and a device for generating a home furnishing design scheme and a computer readable storage medium.
Background
At present, home design and computer technology are constantly fused, and the intelligent design of indoor home is concerned with. For the existing automatic design system in the market, a user can obtain a layout result output by the automatic design system only by selecting a house type to be designed and a sample plate of a heart instrument, and finally the user can complete a set of integral design by correspondingly modifying the layout result on the basis. Compared with the traditional manual design, the design efficiency is greatly improved, and meanwhile, good effects can be obtained.
However, some problems are faced in such an automated design flow, for example, the automated design can only generate a single layout result, the layout is probably not expected by the user, and the user can only passively accept and make secondary modification through the tool. At the same time, upgrading and optimization of automated design systems will become increasingly difficult.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a home design scheme generation method, a home design scheme generation device and a computer readable storage medium, which at least solve the technical problems that layout results generated by indoor home design modes used in the related technologies are single and cannot meet the requirements of users.
According to an aspect of an embodiment of the present invention, a method for generating a home design scheme is provided, including: acquiring a plan view of a target room and a target sample plate, wherein the target room is a room needing home design; obtaining an initial layout corresponding to the plan by using a predetermined generated model, wherein the predetermined generated model is obtained by using multiple sets of training data through machine learning training, and each set of training data in the multiple sets of training data includes: a plan view and a layout corresponding to the plan view; and generating a household design scheme of the target room based on the initial layout and the target sample plates.
Optionally, before obtaining the initial layout corresponding to the plan by using a predetermined generated model, the method further includes: acquiring a plurality of historical plane maps and a plurality of historical initial layout maps corresponding to the plurality of historical plane maps; and training an initial network model by using a plurality of groups of training data comprising the plurality of historical plan views and the plurality of historical initial layout views to obtain the predetermined generation model.
Optionally, the initial network model is a generative confrontation network GAN model.
Optionally, after obtaining an initial layout corresponding to the plan by a predetermined generative model, the method further includes: determining at least one furniture white mould in the initial layout; acquiring position information of the at least one furniture white mould; 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 a plurality of layout diagrams.
Optionally, generating a home design scheme of the target room based on the initial layout drawing and the target sample plate includes: displaying the layout drawings on a preset display terminal; acquiring a target layout diagram obtained by adjusting at least one of the plurality of layout diagrams based on a triggering operation, wherein the triggering operation is an operation on the preset display terminal; and generating a household design scheme of the target room based on the target layout and the target sample plates.
Optionally, generating a home design scheme of the target room based on the target layout drawing and the target sample plate includes: generating a furniture model based on the furniture white mould in the target layout; and fusing the furniture model into the target sample plate to generate a furniture design scheme of the target room.
Optionally, the method for generating a home design scheme further includes: acquiring a target layout diagram obtained by adjusting at least one of the plurality of layout diagrams based on a trigger operation, and acquiring adjustment information generated based on the trigger operation; optimizing the predetermined generative model using the adjustment information.
According to another aspect of the embodiment of the present invention, there is provided a device for generating a home design scheme, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plan view of a target room and a target sample plate, and the target room is a room needing home design; a first generation module, configured to obtain an initial layout corresponding to the plan by using a predetermined generation model, where the predetermined generation model is obtained by using multiple sets of training data through machine learning training, and each set of training data in the multiple sets of training data includes: a plan view and a layout corresponding to the plan view; and the second generation module is used for generating the home design scheme of the target room based on the initial layout and the target sample plates.
Optionally, the apparatus further comprises: a second obtaining module, configured to obtain a plurality of historical plan views and a plurality of historical initial layout views corresponding to the plurality of historical plan views before obtaining an initial layout view corresponding to the plan view through a predetermined generation model; and the training module is used for training an initial network model by using a plurality of groups of training data including the plurality of historical plan views and the plurality of historical initial layout views to obtain the predetermined generation model.
Optionally, the initial network model is a generative confrontation network GAN model.
Optionally, the apparatus further comprises: the determining module is used for determining at least one furniture white mould in the initial layout after the initial layout corresponding to the plan is obtained through a preset generating model; the third acquisition module is used for acquiring the position information of the at least one furniture white mould; and the adjusting module is used for adjusting the at least one furniture white mold in the initial layout map based on the position information of the at least one furniture white mold to obtain a plurality of layout maps.
Optionally, the second generating module includes: the display unit is used for displaying the layout charts on a preset display terminal; an obtaining unit, configured to obtain a target layout obtained by adjusting at least one of the plurality of layouts based on a trigger operation, where the trigger operation is an operation performed on the predetermined display terminal; and the generating unit is used for generating a home design scheme of the target room based on the target layout and the target sample plates.
Optionally, the generating unit includes: a first generating subunit, configured to generate a furniture model based on the furniture white model in the target layout; and the second generation subunit is used for fusing the furniture model into the target sample plate to generate a furniture design scheme of the target room.
Optionally, the apparatus further comprises: a fourth obtaining module, configured to obtain a target layout obtained by adjusting at least one of the plurality of layouts based on a trigger operation, and obtain adjustment information generated based on the trigger operation; and the optimization module is used for optimizing the preset generation model by utilizing the adjusting information.
According to another aspect of the embodiment of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program is executed by a processor, the computer-readable storage medium controls a device where the computer-readable storage medium is located to execute any one of the above methods for generating a home design solution.
According to another aspect of the embodiment of the present invention, a processor is further provided, where the processor is configured to run a computer program, where the computer program executes the method for generating a home design solution according to any one of the above descriptions.
In the embodiment of the invention, a plan view of a target room and a target sample plate are obtained, wherein the target room is a room needing home design; obtaining an initial layout corresponding to the plan by using a predetermined generated model, wherein the predetermined generated model is obtained by using a plurality of sets of training data through machine learning training, and each set of training data in the plurality of sets of training data comprises: a plan view and a layout corresponding to the plan view; and generating a home design scheme of the target room based on the initial layout and the target sample plates. By the household design scheme generation method provided by the embodiment of the invention, the purpose of generating the household design scheme of the target room through the preset generation model based on the plan view of the target room and the target sample plate is achieved, so that the technical effect of enabling the indoor household design to be more personalized and intelligent is realized, and the technical problem that the layout result generated by the indoor household design mode used in the related technology is single and cannot meet the user requirement is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flowchart of a method for generating a home design solution according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a network architecture for generating a countermeasure network (GAN) in accordance with an embodiment of the present invention;
FIG. 3(a) is a schematic diagram of the inputs to a GAN model according to an embodiment of the present invention;
FIG. 3(b) is a diagram I of a GAN model input obtaining a plurality of layout effect maps according to an embodiment of the present invention;
FIG. 3(c) is a diagram II illustrating a plurality of layout effect graphs obtained by inputting a GAN model according to an embodiment of the present invention;
FIG. 3(d) is a diagram III of a plurality of layout effect graphs obtained by inputting a GAN model according to an embodiment of the present invention;
FIG. 4(a) is a schematic diagram of a user selecting an inter-sample layout interface according to an embodiment of the invention;
fig. 4(b) is a first schematic diagram of a system final effect diagram generated according to the home design scheme of the embodiment of the invention;
fig. 4(c) is a schematic diagram two of a final effect diagram of a system for generating a home design scheme according to an embodiment of the invention;
FIG. 5 is a logic flow diagram of a system for generating a home design solution in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of a device for generating a home design according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of description, some nouns or terms appearing in the embodiments of the present invention are explained below.
A Generative Adaptive Networks (GAN) is a deep learning model, and belongs to an unsupervised learning model. The model is formed by at least two modules in a frame: the mutual game learning of the generative model and the discriminant model produces a fairly good output.
Example 1
In accordance with an embodiment of the present invention, there is provided a method embodiment of a method for generating a home design solution, where the steps illustrated in the flowchart of the drawings may be executed in a computer system, such as a set of computer executable instructions, and where a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be executed in an order different than that illustrated or described herein.
Fig. 1 is a flowchart of a method for generating a home design scheme according to an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step S102, a plan view of a target room and a target sample plate are obtained, wherein the target room is a room needing home design.
In this embodiment, the target room may be a study room, living room, kitchen, bedroom, etc.
For example, for a house type diagram, if the user wants to use a corresponding room in the house type diagram as a study room, the room selected by the user in the house type diagram can be used as the target room.
The plan view is labeled with basic information of the target room, such as the size (length, width, and height), the position of the door, the position of the window, and the position of the curtain.
The target sample room is a room sample room in which a user browses a plurality of room sample rooms and selects one of the room sample rooms as a target sample room based on his/her preferred decoration style.
Step S104, obtaining an initial layout corresponding to the plan by a predetermined generated model, wherein the predetermined generated model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: a plan view and a layout corresponding to the plan view.
And S106, generating a home design scheme of the target room based on the initial layout and the target sample plates.
As can be seen from the above, in the embodiment of the present invention, a plan view of a target room and a target sample plate may be obtained first, where the target room is a room for which a home design needs to be performed; and then obtaining an initial layout corresponding to the plan by a predetermined generated model, wherein the predetermined generated model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: a plan view and a layout corresponding to the plan view; and finally, generating a home design scheme of the target room based on the initial layout drawing and the target sample plates, so that the purpose of generating the home design scheme of the target room based on the plan drawing of the target room and the target sample plates through a preset generation model is achieved, and the technical effect of enabling the indoor home design to be more personalized and intelligent is achieved.
By the method for generating the home design scheme, the technical problems that the layout result generated by an indoor home design mode used in the related technology is single and the user requirements cannot be met are solved.
It should be noted that, in the embodiment of the present invention, the obtaining of the target sample plate may be performed simultaneously with the obtaining of the plan view of the target room, or the obtaining of the plan view may be performed first and then the obtaining of the sample plate is performed. It is sufficient to acquire the target sample plates before executing step S106.
As an alternative embodiment, before obtaining the initial layout corresponding to the plan by the predetermined generative model, the method may further include: acquiring a plurality of historical plane graphs and a plurality of historical initial layout graphs corresponding to the plurality of historical plane graphs; and training the initial network model by using a plurality of groups of training data comprising a plurality of historical plane graphs and a plurality of historical initial layout graphs to obtain a preset generation model.
In this embodiment, some existing historical plan maps and historical initial layout maps corresponding to the historical plan maps may be collected as training data, and the training data is used to train the initial network model to obtain the predetermined generation model, so that after a plan map given by a user is obtained, the plan map is input to the predetermined generation model, that is, the initial layout map corresponding to the plan map is obtained, and the room layout map generation efficiency is improved.
As an alternative embodiment, the initial network model is a generative countermeasure network (GAN) model.
Fig. 2 is a schematic diagram of a network structure of a generation countermeasure network (GAN) according to an embodiment of the present invention, and as shown in fig. 2, the generation countermeasure network includes two sub-networks: generating a network (generator (G)) and a discrimination network (discriminator (D)), wherein a potential space (late space) continuously adds noise to the Generated network, and a Generated network Generated sample (Generated frequency samples) Is input into the discrimination network for judgment (namely, step (Is) D Correct), meanwhile, an input Real sample (Real samples) Is input into the discrimination network for judgment, and if the judgment result Is true, the discrimination network Is returned to the cycle training (namely, step (Fine-tuning)); and if the judgment result is false, returning to the generated network for cyclic training so that the probability of judging the generated picture to be true is higher and higher until a Nash balance is reached, so that the data generated by the generated network is not different from the true sample, and the generated sample and the true sample cannot be correctly distinguished by the judging network, so that the enhanced unsupervised deep learning is realized, and the technical effects of simple use method, strong function and wide applicability are achieved.
It should be noted that nash balance in the above optional embodiment refers to a balance state when the generated network in the generated confrontation network recovers the distribution of the training data, and the determination network also determines that no obvious result (i.e., accuracy is 50%) is obtained, and this state may enable the generated network to estimate the distribution of the sample data, that is, the generated sample is more real and reliable.
In addition, the initial network model may be a model for generating a network and discriminating a network for other network configurations.
As an alternative embodiment, after obtaining the initial layout corresponding to the plan by the predetermined generative model, the method further comprises: determining at least one furniture white mould in the initial layout; acquiring position information of at least one furniture white mould; 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 a plurality of layout diagrams.
It should be noted that the output result of the model is finally displayed in the form of a white model, and for the study room space, the furniture white model generated at this stage comprises a desk, a book chair and a bookcase; for the bedroom space, various furniture white models including beds, wardrobes, dressing tables and desks can be generated, the furniture selection is very diversified, and the requirements of users can be met to the maximum extent.
In this embodiment, the initial layout diagram output by the plan through the predetermined generation model may be post-processed to obtain a plurality of layout diagrams, so that the plurality of adjusted layout diagrams may be obtained on the basis of the initial layout diagram, and the plurality of layout diagrams including the initial layout diagram may be presented to the user for selection by the user, thereby providing the user with various choices and improving user experience.
For example, the furniture white mold in the initial layout includes: the desk, the book chair and the bookcase in the initial layout drawing are all correspondingly arranged at certain positions, so that one or more of the desk, the book chair and the bookcase in the initial layout drawing can be adjusted in position, for example, the desk and the book chair in the initial layout drawing are on the left side, the desk and the book chair can be adjusted to the right side or other positions of the initial layout drawing together to obtain a plurality of layout drawings for a user to select, and accordingly diversified selections are provided for the user. The following description is made with reference to the accompanying drawings.
Fig. 3(a) is a schematic diagram of the input of the GAN model according to the embodiment of the present invention, and as shown in fig. 3(a), after the plan is input into the GAN model, the GAN model processes the plan to generate an initial layout containing furniture layout information.
Fig. 3(b) is a schematic diagram of a plurality of layout effect graphs obtained by inputting GAN model according to an embodiment of the present invention, as shown in fig. 3(b), after post-processing, the book room portion in the graph generates a desk, a chair and a cabinet (i.e., a furniture white model).
Fig. 3(c) is a schematic diagram of a plurality of layout effect diagrams obtained by inputting a GAN model according to an embodiment of the present invention, and as shown in fig. 3(c), after post-processing, the placement positions of a desk and a chair (i.e., a furniture white mold) generated in a book room in the diagram can be adjusted, which meets the user's requirements very well.
Fig. 3(d) is a schematic diagram three of obtaining a plurality of layout effect diagrams by inputting a GAN model according to an embodiment of the present invention, and as shown in fig. 3(d), after post-processing, the placement position of the cabinet (i.e., the furniture white model) generated in the book room in the diagram can be adjusted, so that the user's requirement is met to the maximum.
It should be noted that, after a certain layout is selected by a user, the position, size and angle of each white mold in the layout can be adjusted accordingly according to the desire of the user, and the layout finally selected by the user and the modification information of the white molds can be recorded and stored, so that the subsequent continuous iterative optimization of the model effect can be performed, and the satisfaction degree of the user can be increased.
As an optional embodiment, the generating a home design scheme of a target room based on an initial layout and target sample boards includes: displaying a plurality of layout drawings on a preset display terminal; acquiring a target layout diagram obtained by adjusting at least one of the plurality of layout diagrams based on a triggering operation, wherein the triggering operation is an operation on a preset display terminal; and generating a home design scheme of the target room based on the target layout and the target sample plates.
In this embodiment, since the plurality of layout diagrams presented to the user and the initial layout diagram may not meet the user requirement, the user may act on the display terminal (e.g., a mobile phone, a tablet, a computer, etc.) through a mouse, a touch pen, or a direct hand to adjust the plurality of presented layout diagrams, so as to obtain a target layout diagram meeting the user requirement.
Fig. 4(a) is a schematic diagram of a user selecting a layout interface between samples according to an embodiment of the present invention, and as shown in fig. 4(a), after the user may select any one of the above layout results, the user further selects a personalized sample plate, and starts to automatically design a home layout.
As an optional embodiment, the generating a home design scheme of a target room based on a target layout and target sample plates includes: generating a furniture model based on the furniture white mould in the target layout; and fusing the furniture model into the target sample plate to generate a furniture design scheme of the target room.
Fig. 4(b) is a schematic diagram of a final effect diagram of a home design solution generation system according to an embodiment of the present invention, and as shown in fig. 4(b), the home design solution generation system generates a top view (taking a study room as an example) of a final design solution according to position information between sample boards and a home white mould selected by a user. For furniture with white mold information, the intelligent design system can place corresponding furniture according to the type and position of the white mold. After the core furniture is placed, the system can further match and place other materials such as curtains, background walls, ornaments, hard-mounted suspended ceilings, pinch plates, paving tiles, floor tiles, customization and the like, and finally a complete set of design scheme is obtained.
Fig. 4(c) is a schematic diagram of a final effect diagram of a home design scheme generation system according to an embodiment of the present invention, and as shown in fig. 4(c), the home design scheme generation system generates a side view of a final design scheme (taking a study as an example) according to position information of a sample plate and a home white mould selected by a user, and can see that tables, cabinets and chairs selected by the user in the side view are combined by the system to generate a 3D view, so that the user is clear at a glance, and the design diagram of the home design scheme is very visually seen, so that the indoor home design becomes more personalized and intelligent.
As an optional embodiment, the method for generating the home design scheme further includes: acquiring target layout drawings obtained by adjusting at least one of the plurality of layout drawings based on a trigger operation, and acquiring adjustment information generated based on the trigger operation; the predetermined generative model is optimized using the adjustment information.
Furthermore, data such as layout and white mold adjustment information selected by a user can be recycled and filtered, and then the data is converted into a series of high-quality design schemes for model learning, and finally iterative optimization of the existing intelligent design model is realized, so that the individual requirements of the user are realized.
The present application will be described in detail with reference to specific examples.
Fig. 5 is a logic flow diagram of a home design scenario generation system according to an embodiment of the present invention, and as shown in fig. 5, the present invention is applicable to multiple spaces such as bedrooms, study rooms, and multi-functional rooms, and the present invention is described in detail below with the study room space as an example. The whole process of the invention can be divided into four stages which are respectively:
1) a user enters a generation system of a home scheme design, firstly selects a target room (such as a study room, a bedroom and the like), then calls a GAN model corresponding to the room type, and then the system generates a plurality of layout results for the user to select.
2) If the user is unsatisfied with the existing layout result, the user can perform selective adjustment on the home white mode in the layout by self individualization and then select the sample plates.
3) The system starts to design automatically and gives a whole set of design solution.
4) And recording the layout selection and modification results of the user, and continuously iterating and optimizing to generate a confrontation network model, so that the system can generate a scheme with higher user satisfaction.
In order to solve the problems of single layout, difficulty in continuous optimization, excessive dependence on sample plates and the like in the automatic design process at present, the embodiment of the invention creatively combines deep learning with home design, and provides an indoor home intelligent design system based on a generation countermeasure network (GAN). Compared with the existing indoor automatic design system, the indoor automatic design system can generate various layout results aiming at the input house type, and further provides more choices for users. Meanwhile, the method and the device support the user to correspondingly modify the layout result output by the model before automatic design, and further ensure that the application effect meets the expectation of the user. In addition, the method for generating the home design scheme provided by the embodiment of the invention can also continuously optimize the used GAN model according to the selection and modification results of the user, so that the generated layout is more consistent with the mind of the user, and the indoor home design becomes more personalized and intelligent.
In summary, in the embodiment of the present invention, compared with the existing automatic design system for indoor furniture in the market, the home scheme generation system creatively adopts a combination of home design and deep learning, so that the generated layout result is more stable and diversified. This is reflected in the fact that for some more specific dwellings, layouts generated using so-called "established rules" tend to be less effective, even facing the embarrassment of a failed design. In addition, the layout generated by the intelligent design system is separated from the constraint of the rule and is completely determined by the output result of the model, so that the quality and the availability of the design result can be greatly improved. In addition, due to the use of the GAN model, the system can generate a plurality of different layout results, and provide more choices for users. In the aspect of design flow, a user can adjust a furniture white mold result generated by the model in advance before automatic design, so that an expected design effect is obtained, and secondary modification of the user is avoided. In addition, the generation method of the home design scheme provided by the embodiment of the invention can also store the layout selected by the user and the modification condition of the layout result, and further convert the data into the input of model training, thereby realizing the iterative optimization of the intelligent design system. This also means that while the model outputs layout results that are satisfactory to the user, the user's selection will in turn push the lifting of the model to form a positive feedback closed loop system.
Example 2
According to another aspect of the embodiment of the present invention, there is further provided a device for generating a home design scheme, fig. 6 is a schematic diagram of the device for generating a home design scheme according to the embodiment of the present invention, and as shown in fig. 6, the device for generating a home design scheme further includes: a first acquisition module 61, a first generation module 63 and a second generation module 65. The following describes a device for creating the home design.
The first obtaining module 61 is configured to obtain a plan view of a target room and a target sample plate, where the target room is a room that needs to be designed for home.
A first generating module 63, configured to obtain an initial layout corresponding to the plan by using a predetermined generating model, where the predetermined generating model is obtained by using multiple sets of training data through machine learning training, and each set of training data in the multiple sets of training data includes: a plan view and a layout corresponding to the plan view.
And a second generating module 65, configured to generate a home design plan of the target room based on the initial layout and the target sample plate.
It should be noted here that the first obtaining module 61, the first generating module 63, and the second generating module 65 correspond to steps S102 to S106 in embodiment 1, and the modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.
As can be seen from the above, in the embodiment of the present invention, first, the first obtaining module 61 is used to obtain the plan view of the target room and the target sample plate, where the target room is a room that needs to be designed for home; then, the first generating module 63 is used to obtain an initial layout corresponding to the plan through a predetermined generating model, where 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 corresponding to the plan view; and finally, generating a home design scheme of the target room based on the initial layout drawing and the target sample plates by using a second generation module 65. By the household design scheme generation device provided by the embodiment of the invention, the purpose of generating the household design scheme of the target room through the preset generation model based on the plan view of the target room and the target sample plate is achieved, so that the technical effect of enabling the indoor household design to be more personalized and intelligent is realized, and the technical problem that the layout result generated by the indoor household design mode used in the related technology is single and cannot meet the user requirement is solved.
Optionally, the apparatus further comprises: the second acquisition module is used for acquiring a plurality of historical plane maps and a plurality of historical initial layout maps corresponding to the plurality of historical plane maps before the initial layout maps corresponding to the plane maps are obtained through a preset generation model; and the training module is used for training the initial network model by utilizing a plurality of groups of training data comprising a plurality of historical plane graphs and a plurality of historical initial layout graphs to obtain a preset generation model.
Optionally, the initial network model is a generative confrontation network GAN model.
Optionally, the apparatus further comprises: the determining module is used for determining at least one furniture white mould in the initial layout after the initial layout corresponding to the plan is obtained through a preset generating model; the third acquisition module is used for acquiring the position information of at least one furniture white mould; and the adjusting module is used for adjusting the at least one furniture white mold in the initial layout map based on the position information of the at least one furniture white mold to obtain a plurality of layout maps.
Optionally, the second generating module includes: the display unit is used for displaying the layout charts on a preset display terminal; the device comprises an acquisition unit, a display unit and a processing unit, wherein the acquisition unit is used for acquiring a target layout obtained by adjusting at least one of a plurality of layouts based on a trigger operation, and the trigger operation is an operation on a preset display terminal; and the generating unit is used for generating a home design scheme of the target room based on the target layout and the target sample plates.
Optionally, the generating unit includes: the first generation subunit is used for generating a furniture model based on the furniture white mould in the target layout; and the second generation subunit is used for fusing the furniture model into the target sample plate to generate a furniture design scheme of the target room.
Optionally, the apparatus further comprises: the fourth obtaining module is used for obtaining a target layout diagram obtained after at least one of the plurality of layout diagrams is adjusted based on the trigger operation, and obtaining adjustment information generated based on the trigger operation; and the optimization module is used for optimizing the preset generation model by utilizing the adjustment information.
Example 3
According to another aspect of the embodiment of the present invention, there is also provided a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, and when the computer program is executed by a processor, the computer-readable storage medium controls an apparatus to execute the method for generating a home design solution according to any one of the foregoing descriptions.
Example 4
According to another aspect of the embodiment of the present invention, there is further provided a processor, where the processor is configured to execute a computer program, where the computer program executes the method for generating a home design solution according to any one of the above descriptions. The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for generating a home design scheme is characterized by comprising the following steps:
acquiring a plan view of a target room and a target sample plate, wherein the target room is a room needing home design;
obtaining an initial layout corresponding to the plan by using a predetermined generated model, wherein the predetermined generated model is obtained by using multiple sets of training data through machine learning training, and each set of training data in the multiple sets of training data includes: a plan view and a layout corresponding to the plan view;
and generating a household design scheme of the target room based on the initial layout and the target sample plates.
2. The method of claim 1, wherein before obtaining an initial layout corresponding to the plan by a predetermined generative model, the method further comprises:
acquiring a plurality of historical plane maps and a plurality of historical initial layout maps corresponding to the plurality of historical plane maps;
and training an initial network model by using a plurality of groups of training data comprising the plurality of historical plan views and the plurality of historical initial layout views to obtain the predetermined generation model.
3. The method of claim 2, wherein the initial network model is a generative countermeasure network (GAN) model.
4. The method of claim 1, wherein after obtaining an initial layout corresponding to the plan view through a predetermined generative model, the method further comprises:
determining at least one furniture white mould in the initial layout;
acquiring position information of the at least one furniture white mould;
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 a plurality of layout diagrams.
5. The method of claim 4, wherein generating the home design plan for the target room based on the initial layout and the target panels comprises:
displaying the layout drawings on a preset display terminal;
acquiring a target layout diagram obtained by adjusting at least one of the plurality of layout diagrams based on a triggering operation, wherein the triggering operation is an operation on the preset display terminal;
and generating a household design scheme of the target room based on the target layout and the target sample plates.
6. The method of claim 5, wherein generating the home design plan for the target room based on the target layout and the target sample panel comprises:
generating a furniture model based on the furniture white mould in the target layout;
and fusing the furniture model into the target sample plate to generate a furniture design scheme of the target room.
7. The method of claim 5 or 6, further comprising:
acquiring a target layout diagram obtained by adjusting at least one of the plurality of layout diagrams based on a trigger operation, and acquiring adjustment information generated based on the trigger operation;
optimizing the predetermined generative model using the adjustment information.
8. A generation device of a household design scheme is characterized by comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring a plan view of a target room and a target sample plate, and the target room is a room needing home design;
a first generation module, configured to obtain an initial layout corresponding to the plan by using a predetermined generation model, where the predetermined generation model is obtained by using multiple sets of training data through machine learning training, and each set of training data in the multiple sets of training data includes: a plan view and a layout corresponding to the plan view;
and the second generation module is used for generating the home design scheme of the target room based on the initial layout and the target sample plates.
9. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program is executed by a processor, the computer-readable storage medium controls a device to execute the method for generating a home design solution according to any one of claims 1 to 7.
10. A processor, configured to run a computer program, wherein the computer program is configured to perform the method for generating a home design solution according to any one of claims 1 to 7 when running.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111088392.8A CN113886911A (en) | 2021-09-16 | 2021-09-16 | Household design scheme generation method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111088392.8A CN113886911A (en) | 2021-09-16 | 2021-09-16 | Household design scheme generation method and device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113886911A true CN113886911A (en) | 2022-01-04 |
Family
ID=79009361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111088392.8A Pending CN113886911A (en) | 2021-09-16 | 2021-09-16 | Household design scheme generation method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113886911A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114462207A (en) * | 2022-01-07 | 2022-05-10 | 广州极点三维信息科技有限公司 | Matching method, system, equipment and medium for home decoration template |
-
2021
- 2021-09-16 CN CN202111088392.8A patent/CN113886911A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114462207A (en) * | 2022-01-07 | 2022-05-10 | 广州极点三维信息科技有限公司 | Matching method, system, equipment and medium for home decoration template |
| CN114462207B (en) * | 2022-01-07 | 2023-03-14 | 广州极点三维信息科技有限公司 | Matching method, system, equipment and medium for home decoration template |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106484940B (en) | A kind of home decoration Intelligentized design method and system | |
| CN108694266A (en) | intelligent decoration design method and system based on machine learning | |
| US10430525B2 (en) | Reconfigurable spaces | |
| CN108648276A (en) | A kind of construction and decoration design method, device, equipment and mixed reality equipment | |
| CN106096153A (en) | Indoor decoration outdoor scene is experienced scene and is provided method and system | |
| CN107369203B (en) | Indoor three-dimensional scene self-adaptive construction method and device | |
| CN107240151A (en) | A kind of scene layout based on parent-child constraint preserves and reproducting method | |
| CN104899403B (en) | A kind of method and system that decoration budget quotation is automatically generated from CAD design drawing | |
| CN110287626A (en) | Automatically generate method, medium, equipment and the device of interior decoration design scheme | |
| CN109948305A (en) | A kind of house ornamentation display systems based on line modeling | |
| CN103258092A (en) | Cupboard design method based on adaptive schemes | |
| CN113886911A (en) | Household design scheme generation method and device and computer readable storage medium | |
| CN109598058A (en) | Generate the method and device of smart machine bit map/bitmap | |
| CN109903369A (en) | Three-dimensional house type model building method, device, equipment and readable storage medium storing program for executing | |
| CN107590852B (en) | Behavior-constrained automatic indoor three-dimensional scene construction method | |
| CN113536680A (en) | Home decoration design method and device, computer readable storage medium and processor | |
| CN114925432A (en) | Automatic generation method for customized home decoration design | |
| KR20220072385A (en) | Apparatus and method for recommending object on adjacent trunk line based on data structure of trunk line connection generated from big data of interior service | |
| Apotheker | Designing an entertainment cabinet for the living room | |
| Zhang et al. | SceneDirector: Interactive Scene Synthesis by Simultaneously Editing Multiple Objects in Real-Time | |
| KR101912686B1 (en) | Method and server for providing downsized house model or downsized oneroom model corresponding to needs | |
| CN113449372A (en) | Home decoration design method and device, computer readable storage medium and processor | |
| JP7340825B2 (en) | Storage simulation device, storage simulation method and program | |
| US20220357718A1 (en) | Automated custom funiture design, manufacturing, and packaging system and method | |
| CN110443895B (en) | House lighting scheme generation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |