A bedroom intelligent home decoration layout method, medium, device and electronic equipment

Abstract

The application provides a bedroom intelligent home decoration layout method, medium, device and electronic equipment. The method comprises the following steps: extracting bedroom contour information by using a deep residual network ResNet18 to obtain first array information; performing mapping processing on the bedroom contour array information to obtain second array information; inputting the second array information, bedroom target furniture combination array information and bedroom target furniture combination category attribute into a deep learning model to predict bedroom furniture layout parameter information; selecting corresponding furniture according to the bedroom furniture layout parameter information and rendering a white model; receiving user modification requirements for the white model to adjust the white model to generate a first bedroom layout scheme; and modifying furniture attribute information in the second white model according to a preset checking rule to generate a second bedroom layout scheme. The application overcomes the limitation of contour similarity matching with the whole room as a granularity, improves the home decoration layout effect, is conducive to promoting the digitization and scaling of the home decoration platform, thereby improving the design efficiency of home decoration designers and accelerating the development of the digitization construction of the home decoration industry.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of home decoration layout, and in particular to a bedroom intelligent home decoration layout method, medium, device and electronic equipment. BACKGROUND

[0002] At present, in the home decoration experience scene, the stages of inspiration acquisition, scheme design and selection and purchase of home main materials are fragmented, and users need a lot of repeated inefficient communication interaction and manual operation to complete each home decoration stage. Inefficient communication interaction and manual operation greatly increase the link cost, reduce the user experience, and also limit the development of the home decoration platform in the direction of digitization and scaling.

[0003] In order to improve the user experience and further promote the data-based and intelligent development of the home decoration platform, current technologies often solve problems by designing rules. For example: a layout method and device (application number: CN201811085074.4) extracts the largest rectangle inside a regular polygon to realize the effective application and conversion of the regular polygon as a home decoration layout soft decoration area, and provides customers with a more clear and reasonable home decoration scheme, which can further provide an intelligent layout scheme. This method not only needs to write a large number of rules, but also needs to copy the geometric position information of the house type diagram. Therefore, it is not suitable for large-scale automatic deployment.

[0004] In recent years, with the entry of deep learning into the field of home decoration layout, a series of research results have emerged, such as the article "Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models" published in CVPR in 2018. The main problem studied is which objects and positions to place in a given room type and area.

[0005] However, although deep learning has made some progress in automatic layout of home decoration in recent years, it is often difficult to implement, and the main problems are as follows: the generated scheme is uncontrollable and does not meet the specified needs of the user; the user's taste is very picky and may not agree with the placement of some items in the layout, and most deep learning networks do not accept secondary modification, resulting in design failure; the training data of deep learning is greatly different from the actual production data of products, making it difficult to implement; and small-sized and one-room houses are difficult to design. SUMMARY

[0006] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a bedroom intelligent home decoration layout method, medium, device and electronic equipment to solve the above-mentioned problems in the prior art.

[0007] To achieve the above object and other related objects, the present application provides a bedroom intelligent home furnishing layout method, which comprises: extracting bedroom contour information by using a deep residual network ResNet18 to obtain first array information; performing mapping processing on the bedroom contour array information to obtain second array information; inputting the second array information, bedroom target furniture combination array information and bedroom target furniture combination category attribute into a deep learning model to predict bedroom furniture layout parameter information; selecting corresponding furniture according to the bedroom furniture layout parameter information and rendering a white model; receiving user modification requirements for the white model to adjust the white model to generate a first bedroom layout scheme; and modifying furniture attribute information in the second white model according to a preset checking rule to generate a second bedroom layout scheme.

[0008] In an embodiment of the present application, the method further comprises: establishing an array learning model in advance for a bedroom target furniture combination having similar contour information as the bedroom; and mapping the application positions of the category c, position s, size t and angle r of the bedroom target furniture combination to the bedroom target furniture combination array information F2 through an encoding concat dimension, as shown in the following formula:

[0009] (c, s, t, r) = [alpha(c), beta(s), beta(t), alpha(r)],

[0010] P(o j , F2) = P(c j , F2)P(t j | c j , F2)P(r j | c j , t j , F2)P(s j | c j , t j , r j , F2), wherein alpha represents a one-dimensional learnable parameter, beta represents a three-dimensional learnable parameter, (c, s, t, r) represents a category, a position, a size and an angle, o represents a candidate object set, j represents the jth object, P(o j , F2) represents that each attribute of the jth object in the candidate set o is encoded into the array F2, wherein the array dimensions of F1 and F2 are the same.

[0011] In an embodiment of the present application, the method further comprises: predicting the bedroom furniture layout parameter information by inputting the second array information F1, the bedroom target furniture combination array information F2, and the bedroom furniture combination category attribute q into a Tansformer model, wherein the parameter information comprises a category c1, a position t1, a size r1, and an angle s1; and the prediction formula is: q=q1, q1=c1, (q1, a(c1))=t1, (q1, a(c1), b(t1))=r1, (q1, a(c1), b(t1), a(r1))=s1.

[0012] In an embodiment of the present application, the method further comprises: selecting furniture combination articles of the same category and size for three-dimensional rendering to generate a white model according to the bedroom furniture layout parameter information.

[0013] In an embodiment of the present application, the method further comprises: receiving user adjustments to the white model according to individualized needs, such as bedroom furniture size, similar furniture category, and adjustment needs; and receiving user-selected furniture styles and generating a first bedroom layout scheme according to the style ID representation query category and size of the same furniture combination.

[0014] In an embodiment of the present application, the method further comprises: step one, calculating the distance between the furniture combinations according to the size and position parameters of the bedroom furniture combinations; step two, verifying whether the distance meets the preset channel length and width standard, and if so, retaining the bedroom furniture combinations; if not, sorting the bedroom furniture combinations according to the importance and frequency of use of furniture combinations, core furniture, and furniture accessories from high to low, and deleting furniture from low to high according to the sorting results; and step three, repeating steps one and two until the bedroom furniture combinations meet the preset channel length and width standard.

[0015] In an embodiment of the present application, the method further comprises, after the bedroom furniture combinations meet the preset channel length and width standard: calculating the distance between the furniture combination area and the farthest pixel point in the dimension where no furniture is arranged; and when the distance between the corner point of the furniture combination area and the farthest pixel point in the dimension where no furniture is arranged is greater than a preset threshold, moving the furniture combination to the farthest pixel point in the dimension according to the optimal layout ratio.

[0016] To achieve the above object and other related objects, the present application provides a bedroom intelligent home furnishing layout system, which comprises: a data acquisition module for extracting bedroom contour information by using a deep residual network ResNet18 to obtain first array information; a data processing module for mapping the bedroom contour array information to obtain second array information; a prediction module for inputting the second array information, bedroom target furniture combination array information and bedroom target furniture combination category attribute into a deep learning model to predict the bedroom furniture layout parameter information; a white model generation module for selecting corresponding furniture according to the bedroom furniture layout parameter information and rendering a white model; a layout generation module for receiving user modification requirements for the white model, adjusting the white model to generate a first bedroom layout scheme, and generating a second bedroom layout scheme according to the verification module; and a verification module for verifying and modifying the furniture attribute information in the second white model according to a preset verification rule to pass the second bedroom layout scheme of the layout generation module.

[0017] To achieve the above object and other related objects, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is loaded and executed by a processor to implement the bedroom intelligent home furnishing layout method.

[0018] To achieve the above object and other related objects, the present application provides an electronic device, which comprises: a processor, a memory and a communication interface; wherein the memory is used to store a computer program; the processor is used to load and execute the computer program to make the electronic device execute the bedroom intelligent home furnishing layout method; and the communication interface is used to realize communication between the access device and other devices.

[0019] As described above, the present application provides a bedroom intelligent home furnishing layout method, which can solve the problems that the existing home furnishing layout technology cannot meet the personalized needs of customers, cannot be modified twice, and is difficult to design the layout for small-sized houses. The bedroom intelligent layout is realized based on the transforme model, which ensures that the matching of the house structure components to the appropriate furniture object combination conforms to the overall better position principle, overcomes the limitation of contour similarity matching with the whole room as the granularity, improves the home furnishing layout effect, and is conducive to promoting the digitization and scaling of the home furnishing platform, thereby improving the design efficiency of home furnishing designers and accelerating the development of the digitization construction of the home furnishing industry. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 A flowchart of the bedroom intelligent home furnishing layout method according to an embodiment of the present application is shown.

[0021] Figure 2 A verification method diagram of the bedroom intelligent home furnishing layout method according to an embodiment of the present application is shown.

[0022] Figure 3 A module schematic diagram of a bedroom intelligent home decoration layout system according to an embodiment of the present application is shown.

[0023] Figure 4 A structural schematic diagram of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The present application will be described in greater detail by way of specific embodiments, from which its advantages and effects will be apparent to those skilled in the art. The present application can be implemented or applied in other different specific embodiments, and various modifications or changes can be made to the details based on different views and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of the present application.

[0025] It should be noted that the diagrams provided in the following embodiments only schematically illustrate the basic concept of the present application, and only the components related to the present application are shown in the diagrams, not the number, shape and size of the components when actually implemented. The actual implementation of each component can be a random change in shape, number and proportion, and the layout pattern of the components can be more complex.

[0026] In order to solve the problems in the prior art that a large number of setting rules are not suitable for large-scale automatic deployment, and it is difficult to land the intelligent layout of special small-sized houses and special requirements of customers through a deep learning method, the present application provides a bedroom intelligent home decoration layout method, medium, device and electronic equipment.

[0027] As shown in Figure 1 The present embodiment provides a bedroom intelligent home decoration layout method, which comprises the following steps:

[0028] S11: extracting bedroom contour information by using a deep residual network ResNet18 to obtain first array information.

[0029] Specifically, the deep residual network ResNet18 is used to extract the contour information of the bedroom in the input house type diagram, and the extracted array information is 128-dimensional array information, which is recorded as the first array information.

[0030] S12: mapping the bedroom contour array information to obtain second array information.

[0031] Specifically, the extracted 128 dimensions are mapped to a 512-dimensional array information by a fully connected layer, and the array information is recorded as a second array information F1.

[0032] S13: input the second array information, the bedroom target furniture combination array information and the bedroom furniture combination category attribute into a deep learning model to predict the bedroom target furniture layout parameter information.

[0033] Specifically, an array learning model is established in advance for the target furniture combination in the bedroom with similar contour information as the input bedroom: first, the target furniture combination in the bedroom is classified, such as bed combination (bed, bedside table, four-piece set, etc.), desk combination (desk, chair), TV cabinet combination, etc. The furniture combination name is represented by groupName; the attribute information of the single furniture in the furniture combination is defined, wherein the category c, the point position information in the three-dimensional space s, the scaling information t, and the orientation information r are used to define the furniture combination category, the point position information in the three-dimensional space, the scaling information, and the orientation information, respectively; finally, the category c, the position s, the size t, and the angle r of the target furniture combination in the bedroom are mapped to the target furniture combination array information F2 in the bedroom by encoding concat dimensions, and the formula is as follows:

[0034] (c, s, t, r) = [alpha(c), beta(s), beta(t), alpha(r)],

[0035] P(o j , F2) = P(c j , F2)P(t j |c j , F2)P(r j |c j , t j , F2)P(s j |c j , t j , r j , F2), wherein alpha represents a one-dimensional learnable parameter, beta represents a three-dimensional learnable parameter, (c, s, t, r) represents category, position, size and angle, o represents a candidate object set, j represents the jth object, and P(o j , F2) represents that the attributes of the jth object in the candidate set o are encoded into the array F2. It should be noted that the array information F2 and F1 are the same dimension array, i.e. 512-dimensional array information, so as to perform parameter prediction processing.

[0036] Further, the second array information F1, the bedroom target furniture combination array information F2, and the bedroom furniture combination category attribute q are input into the improved Tansformer model to predict the furniture bedroom furniture layout parameter information, which includes the category c1, the position t1, the size r1, and the angle s1. First, the input q is output as q1 through the Tansformer encoder, and the category c1 is predicted through q1. Second, the position t1 is predicted through q1 and the category c1. Third, the size r1 is predicted through q1, the category c1, and the position r1. Finally, the angle s1 is predicted through q1, the category c1, the position r1, and the size r1. The prediction formula is: q1 = c1, (q1, a(c1)) = t1, (q1, a(c1), b(t1)) = r1, and (q1, a(c1), b(t1), a(r1)) = s1.

[0037] Preferably, when the layout parameter information of a furniture combination category is predicted, the area is marked according to the layout position and size, and then the layout parameter information of the next furniture combination in the other area range in the bedroom space is predicted.

[0038] S14: Select the corresponding furniture according to the bedroom furniture layout parameter information and render the white model.

[0039] Specifically, the same type and size of furniture combination is selected according to the bedroom furniture layout parameter information, i.e., the category c, the position s, the size t, and the angle r, and three-dimensional rendering is performed to generate the white model.

[0040] S15: Receive user modification requirements for the white model to adjust the white model to generate a first bedroom layout scheme.

[0041] Specifically, after seeing the output white model, the user can adjust and modify the size of the furniture in the white model and the type of similar furniture according to his own personalized needs.

[0042] Further, after receiving the user's adjustment and modification request for the white model, and according to the user's selected furniture style, the same type and size of furniture combination is matched to generate a first bedroom layout scheme according to the style ID. For example, the user requests to replace the desk with a vanity table, and selects a Nordic style decoration, then according to the Nordic style id, the desk is replaced with a vanity table with the same parameters, and then the entire furniture in the bedroom is converted to the same type, position, size, and orientation of the Nordic style furniture.

[0043] S16: Modify the furniture attribute information in the second white model according to a preset verification rule to generate a second bedroom layout scheme.

[0044] Specifically, first, the channel standard between the furniture combinations is preset. For example, the width of the aisle area is defined to be greater than 60 cm, the width between the bed combination and the wardrobe is greater than 20 cm, and the furniture combinations cannot collide with each other. First, the actual width distance corresponding to each pixel point is determined according to the channel distance, and then the following steps are used to determine whether it meets the preset length-width standard:

[0045] Step one, calculate the distance between the furniture combinations according to the size of the bedroom furniture combination;

[0046] Step two, check whether the distance meets the preset channel length-width standard. If it meets the standard, the bedroom furniture combination is retained. If it does not meet the standard, the bedroom furniture combination is sorted according to the importance and use frequency of the furniture combination category, core furniture, and furniture accessories from high to low, and the furniture is deleted from low to high according to the sorting result;

[0047] Step three, repeat step one and step two until the bedroom furniture combinations meet the preset channel length-width standard.

[0048] For example, the bedroom furniture combination is sorted according to the importance and use frequency of the furniture combination category, core furniture, and furniture accessories from high to low, and the result is: bed combination core components (bed, bed accessories, ceiling lamp), bed combination other components (bedside table, tea table, sofa), wardrobe core components (wardrobe), wardrobe other components (wardrobe accessories), desk core components (desk, chair), desk other components (wardrobe accessories), etc. If the objects collide, the deletion order is: desk other components (wardrobe accessories), wardrobe other components (wardrobe accessories), bed combination other components (bedside table, tea table, sofa), desk core components (desk, chair), wardrobe core components (wardrobe), bed combination core components (bed, bed accessories, ceiling lamp). For example, if the width between the wardrobe and the bedside table is less than 20 cm, the bedside table is deleted.

[0049] Further, after the bedroom furniture combinations meet the preset channel length-width standard, the distance between the furniture combination area and the farthest pixel point in the area where furniture is not arranged in the dimension is calculated. When the distance between the corner point of the furniture combination area and the farthest pixel point in the area where furniture is not arranged in the dimension is greater than a preset threshold, the furniture combination is moved to the farthest pixel point in the dimension according to the optimal layout ratio. For example, as Figure 2As shown, after the layout area of the wardrobe / desk combination has been determined and the channel length-width standard is met, the bed combination area is moved by subtracting the area of the wardrobe combination and the desk combination, that is, the maximum point of the wardrobe combination plus 20 cm equals point A, and the maximum point B of the room in the same dimension, the midpoint of the longest non-collision area (i.e., the midpoint between points A and B) is defined as the optimal layout point of the bed, and the midpoint of the bed combination is slid along the y-axis direction at a speed of 2 pixel points per step from point A to the midpoint of points A and B.

[0050] All or part of the steps of the above-mentioned method embodiments can be completed by computer program-related hardware. Based on such understanding, the present application also provides a computer program product comprising one or more computer instructions. The computer instructions can be stored in a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computer can store or a data storage device such as a server, data center, etc. integrated with one or more available media.

[0051] Referring to Figure 3 The embodiment provides a bedroom intelligent home layout system 30, which is loaded in an electronic device as a software to execute the bedroom intelligent home layout method described in the foregoing method embodiments at runtime. Since the technical principle of the system embodiment is similar to that of the foregoing method embodiments, the same technical details will not be repeated.

[0052] The bedroom intelligent home layout system 30 of the embodiment specifically comprises a data acquisition module 31, a data processing module 32, a prediction module 33, a white model generation module 34, a layout generation module 35, and a verification module 36. The data acquisition module 31 is configured to extract bedroom contour information by using a deep residual network ResNet18 to obtain first array information; the data processing module 32 is configured to perform mapping processing on the bedroom contour array information to obtain second array information; the prediction module 33 is configured to input the second array information, bedroom target furniture combination array information, and bedroom target furniture combination category attribute into a deep learning model to predict the bedroom furniture layout parameter information; the white model generation module 34 is configured to select corresponding furniture according to the bedroom furniture layout parameter information and render a white model; the layout generation module 35 is configured to receive user modification requirements for the white model, adjust the white model to generate a first bedroom layout scheme, and generate a second bedroom layout scheme according to the verification of the verification module after modification; and the verification module 36 is configured to verify and modify the furniture attribute information in the second white model according to a preset verification rule to generate a second bedroom layout scheme through the layout generation module.

[0053] Those skilled in the art should understand that Figure 3The division of each module in the embodiment is only a logical function division, and all or part of the modules can be integrated into one or more physical entities in actual implementation. The modules can all be implemented in the form of software invoked by a processing element, all be implemented in the form of hardware, or part of the modules be implemented in the form of software invoked by a processing element and part of the modules be implemented in the form of hardware. For example, the data processing module 32 can be a separately established processing element, or can be integrated in a chip, and in addition, can be stored in the form of program code in a memory and the function of the data processing module 32 can be invoked and executed by a processing element. The implementation of other modules is similar. The processing element described herein can be an integrated circuit having a signal processing capability. In the implementation process, each step of the above method or each module can be completed by an integrated logic circuit of hardware in the processing element or an instruction in the form of software.

[0054] With reference to Figure 4 The embodiment provides an electronic device, which can be a portable computer, a smart phone, a tablet computer or the like. In detail, the electronic device at least comprises a memory 42, a processor 43 and a communication interface 44 connected through a bus 41, wherein the communication interface 44 is used for realizing communication between the database access device and other devices, the memory 42 is used for storing a computer program, and the processor 43 is used for executing the computer program stored in the memory 42 to execute all or part of the steps in the foregoing method embodiments.

[0055] The system bus mentioned above can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus or the like. The system bus can be divided into an address bus, a data bus and a control bus. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or only one type of bus. The communication interface is used for realizing communication between the database access device and other devices (for example, a client, a read-write library and a read-only library). The memory can contain a random access memory (RAM) and can also include a non-volatile memory such as at least one disk memory.

[0056] The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0057] To sum up, the bedroom intelligent home decoration layout method, medium, device and electronic equipment provided by the present application first improve the transformer model, give the predicted object category, area and backrest line direction, secondly select the object with appropriate area size from the pre-created white model scheme, replace and place it and render and display it to the user, thirdly select the appropriate size combination according to the white model area size modified by the user to replace the scheme, and finally correct the sufficient aisle area. Overcome the limitation of contour similarity matching with the whole room as the granularity, improve the home decoration layout effect, and is conducive to promoting the digitization and scaling of the home decoration platform, thereby improving the design efficiency of the home decoration designer and accelerating the development of the digital construction of the home decoration industry. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has high industrial utilization value.

[0058] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought disclosed by the present application should be covered by the claims of the present application.

Claims

1. A method for intelligent home decoration layout in a bedroom, characterized in that, include: The bedroom outline information was extracted using a deep residual network ResNet18 to obtain the first array of information; The bedroom outline array information is mapped and processed into a second array information F1; The second array information, the bedroom target furniture combination array information, and the bedroom target furniture combination category attributes are input into a deep learning model to predict the bedroom furniture layout parameters. It also includes pre-establishing an array learning model for target furniture combinations in bedrooms that have similar contour information to the bedroom: The application position of the target bedroom furniture combination, including category c, position s, size t, and angle r, is mapped to the target bedroom furniture combination array information F2 through encoding and concat dimension mapping, as shown in the following formula: (c,s,t,r)=[α(c),β(s),β(t),α(r)], P(o j F2)=P(c j ,F2)P(t j |c j ,F2)P(r j |c j ,t j ,F2)P(s j |c j ,t j ,r j ,F2), where α represents a one-dimensional learnable parameter, β represents a three-dimensional learnable parameter, (c,s,t,r) represents the category, position, size, and angle, o represents the candidate object set, j represents the j-th object, P(o j F2) means: Encoding the attributes of the j-th object in the candidate set o into the bedroom target furniture combination array information F2, where the array dimensions of F1 and F2 are the same; Select the corresponding furniture and items based on the bedroom furniture layout parameters and render a white model; Receive user requests to modify the white model and adjust the white model to generate a first bedroom layout scheme; The furniture attribute information in the second white model is modified according to the preset verification rules to generate the layout scheme of the second bedroom.

2. The method according to claim 1, characterized in that, Also includes: By inputting the second array information F1, the bedroom target furniture combination array information F2, and the bedroom furniture combination category attribute q into the Tansformer model, the bedroom furniture layout parameter information is predicted. The parameter information includes category c1, position t1, size r1, and angle s1. The prediction formula is: q = q1, q1 = c1, (q1, α(c1)) = t1, (q1, α(c1), β(t1)) = r1, (q1, α(c1), β(t1), α(r1)) = s1.

3. The method according to claim 1 or 2, characterized in that, Also includes: By selecting furniture sets of the same type and size based on the bedroom furniture layout parameter information, a 3D rendering is performed to generate a white model.

4. The method according to claim 3, characterized in that, Also includes: The system receives user requests to adjust the size of bedroom furniture and the types of similar furniture in the white model according to their personalized needs, and modifies the white model accordingly. Receive the furniture style selected by the user and, based on the style ID, query furniture combinations of the same type and size to generate a first bedroom layout scheme.

5. The method according to claim 1 or 4, characterized in that, Also includes: Step 1: Calculate the distance between the furniture sets based on the dimensions and location parameters of the target bedroom furniture set; Step 2: Verify whether the distance meets the preset channel length and width standards. If it meets the standards, retain the target bedroom furniture combination. If it does not meet the standards, sort the target bedroom furniture combination from high to low according to the furniture combination category, the importance of core furniture, furniture accessories, and frequency of use. Delete furniture from low to high according to the sorting results. Step 3: Repeat Step 1 and Step 2 until the target furniture combination in the bedroom meets the preset passage length and width standards.

6. The method according to claim 5, characterized in that, This also includes the condition that the length and width of the passageway between the target furniture sets in the bedroom meet the preset standard: Calculate the distance between the area where the furniture combination is located and the farthest pixel in the area where no furniture is placed in the same dimension; When the distance between the corner point of the area where the furniture combination is located and the farthest pixel point of the unfurnished area in the same dimension is greater than a preset threshold, the furniture combination is moved to the farthest pixel point in the same dimension according to the optimal layout ratio.

7. A smart bedroom layout system, characterized in that, The system includes: The data acquisition module is used to extract bedroom outline information using the deep residual network ResNet18 to obtain the first array information; The data processing module is used to map the bedroom outline array information into a second array information F1; The prediction module is used to input the second array information, the bedroom target furniture combination array information, and the bedroom target furniture combination category attributes into the deep learning model to predict the bedroom furniture layout parameter information; It also includes pre-establishing an array learning model for target furniture combinations in bedrooms that have similar contour information to the bedroom: The application position of the target bedroom furniture combination, including category c, position s, size t, and angle r, is mapped to the target bedroom furniture combination array information F2 through encoding and concat dimension mapping, as shown in the following formula: (c,s,t,r)=[α(c),β(s),β(t),α(r)], P(o j F2)=P(c j ,F2)P(t j |c j ,F2)P(r j |c j ,t j ,F2)P(s j |c j ,t j ,r j ,F2), where α represents a one-dimensional learnable parameter, β represents a three-dimensional learnable parameter, (c,s,t,r) represents the category, position, size, and angle, o represents the candidate object set, j represents the j-th object, P(o j F2) means: Encoding the attributes of the j-th object in the candidate set o into the bedroom target furniture combination array information F2, where the array dimensions of F1 and F2 are the same; The white model generation module is used to select corresponding furniture items and render and generate white models based on the bedroom furniture layout parameter information. The layout generation module is used to receive user requests to modify the white model, adjust the white model to generate a first bedroom layout scheme, and generate a second bedroom layout scheme after verification by the verification module. The verification module is used to verify and modify the furniture attribute information in the second white model according to preset verification rules so as to generate the second bedroom layout scheme through the layout generation module.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the intelligent home decoration layout method for bedrooms as described in any one of claims 1 to 6.

9. An electronic device, characterized in that, include: Processor, memory, and communication interface; among which, The memory is used to store computer programs; The processor is used to load and execute the computer program to cause the electronic device to perform the intelligent home decoration layout method for bedrooms as described in any one of claims 1 to 6; The communication interface is used to enable communication between the access device and other devices.

Images