House plan furniture layout processing method based on artificial intelligence and related device

Abstract

The invention is suitable for the technical field of graph processing, provides a house type graph furniture layout processing method based on artificial intelligence and a related device, and aims to realize furniture layout processing in a target house type graph based on the artificial intelligence technology and quickly obtain a furniture layout effect graph of the target house type. The method mainly comprises the following steps: acquiring a target house type image, wherein different functional areas in the target house type image are identified and labeled; the target house type image is input into a preset artificial intelligence model for furniture layout processing, a furniture layout color block image corresponding to the target house type image is obtained, and a color block of a specific color is marked at a target position of the furniture layout color block image in a functional area corresponding to the target house type image to represent the specific type of furniture; determining a target furniture model corresponding to a target color block in a furniture layout color block map, wherein the target color block is a color block of a specific color represented by the target position; and adaptively placing the target furniture model at a target position in the furniture layout color block map to obtain a target house type furniture layout effect map.

Description

Technical Field

[0001] This application belongs to the technical field of graphic processing, and particularly relates to a method and related device for processing furniture layout of a household floor plan based on artificial intelligence. Background Art

[0002] In the field of building decoration, processing the furniture layout of a household floor plan can present the furniture layout effect of the household floor plan, enabling users to intuitively understand the furniture layout situation based on the household floor plan before the furniture is arranged, so as to facilitate the user to modify and make decisions on the furniture layout plan of the household floor plan.

[0003] With the rapid development and maturity of Artificial Intelligence (AI), relevant artificial intelligence technologies can also be introduced into the process of processing the furniture layout of a household floor plan. However, there is currently a lack of relevant technical solutions for processing the furniture layout of a household floor plan based on artificial intelligence in the prior art. Summary of the Invention

[0004] The purpose of this application is to provide a method and related device for processing furniture layout of a household floor plan based on artificial intelligence, so as to realize processing the furniture layout in a target household floor plan based on artificial intelligence technology and quickly obtain the furniture layout effect diagram of the target household.

[0005] In a first aspect, this application provides a method for processing furniture layout of a household floor plan based on artificial intelligence, including: Obtain a target household floor plan, where different functional areas in the target household floor plan have been identified and marked; Input the target household floor plan into a preset artificial intelligence model for furniture layout processing to obtain a furniture layout color block diagram corresponding to the target household floor plan. In the furniture layout color block diagram, color blocks of specific colors marked at target positions in corresponding functional areas of the target household floor plan represent specific types of furniture, and the size of the color blocks of specific colors represents the space occupied by the specific type of furniture at the target position. The preset artificial intelligence model is a model that has been trained to be able to generate color blocks representing the appropriate specific types of furniture in corresponding functional areas of the household floor plan; Determine the target furniture model corresponding to the target color block in the furniture layout color block diagram, where the target color block is the color block of the specific color represented by the target position; Adaptively place the target furniture model at the target position in the furniture layout color block diagram to obtain the furniture layout effect diagram of the target household.

[0006] Optionally, the obtaining of the target household floor plan includes: Obtain an original household floor plan, where the original household floor plan is an empty household floor plan without furniture configured; Identify and segment the functional areas of the original house type plan to obtain a segmented map of the functional areas of the house type. Label the same functional areas in the segmented map of the functional areas of the house type with the same color value, and label different functional areas in the segmented map of the functional areas of the house type with different color values to obtain the target house type plan. The color value used to label the functional areas in the segmented map of the functional areas of the house type is different from the color value of the specific color represented by the target position.

[0007] Optionally, identifying and segmenting the functional areas of the original house type plan to obtain a segmented map of the functional areas of the house type includes: Identify the walls of the original house type plan to obtain wall features. Segment and identify the functional areas enclosed by the wall features to obtain the segmented map of the functional areas of the house type.

[0008] Optionally, determining the target furniture model corresponding to the target color block in the furniture layout color block map includes: Determine the target color value of the target color block. Determine the target furniture name corresponding to the target color value in a preset furniture model and color value comparison table. Determine the target furniture model in a preset furniture model database according to the target furniture name.

[0009] Optionally, adapting and placing the target furniture model at the target position in the furniture layout color block map includes: Identify the regional contour of the target color block to obtain the contour shape of the target color block. Perform size transformation processing on the target furniture model until the target furniture model can be properly placed into the contour shape of the target color block to obtain a target furniture model with adjusted size. Determine the placement angle of the target furniture model with adjusted size according to the furniture placement rules of the functional area corresponding to the target position. Place the target furniture model with adjusted size at the target position according to the placement angle.

[0010] Optionally, after placing the target furniture model with adjusted size at the target position according to the placement angle, the method further includes: Do not display the specific color represented by the target position.

[0011] In a second aspect, the present application provides a device for processing furniture layout of a house type plan based on artificial intelligence, including: An acquisition unit for acquiring a target house type plan, where different functional areas in the target house type plan have been identified and labeled. A processing unit, which is configured to input the target floor plan into a preset artificial intelligence model for furniture layout processing to obtain a furniture layout color block diagram corresponding to the target floor plan. In the furniture layout color block diagram, color blocks of a specific color marked at target positions in corresponding functional areas of the target floor plan represent specific types of furniture, and the size of the color blocks of a specific color represents the space occupied by the specific type of furniture at the target position. The preset artificial intelligence model is a trained model capable of generating color blocks representing the colors of appropriate specific types of furniture corresponding to corresponding functional areas of the floor plan; A determination unit, which is configured to determine a target furniture model corresponding to a target color block in the furniture layout color block diagram, where the target color block is the color block of the specific color represented by the target position; A placement unit, which is configured to adaptively place the target furniture model at the target position in the furniture layout color block diagram to obtain an effect diagram of the furniture layout of the target floor plan.

[0012] Optionally, when the acquisition unit acquires the target floor plan, it is specifically configured to: Acquire an original floor plan, where the original floor plan is an empty floor plan without configured furniture; Perform functional area recognition and segmentation on the original floor plan to obtain a floor plan functional area segmentation diagram; Mark the same functional areas in the floor plan functional area segmentation diagram with the same color value, and mark different functional areas in the floor plan functional area segmentation diagram with different color values to obtain the target floor plan. The color value used for marking the functional areas in the floor plan functional area segmentation diagram is different from the color value of the specific color represented by the target position.

[0013] Optionally, when the acquisition unit performs functional area recognition and segmentation on the original floor plan to obtain a floor plan functional area segmentation diagram, it is specifically configured to: Identify the walls of the original floor plan to obtain wall features; Perform segmentation and recognition on the functional areas enclosed by the wall features to obtain the floor plan functional area segmentation diagram.

[0014] Optionally, when the determination unit determines the target furniture model corresponding to the target color block in the furniture layout color block diagram, it is specifically configured to: Determine the target color value of the target color block; Determine the target furniture name corresponding to the target color value in a preset furniture model and color value comparison table; Determine the target furniture model in a preset furniture model database according to the target furniture name.

[0015] Optionally, when the placement unit adaptively places the target furniture model at the target position in the furniture layout color block diagram, it is specifically configured to: Identify the regional contour of the target color block to obtain the target color block contour shape; Perform size transformation processing on the target furniture model until the target furniture model can be appropriately placed into the target color block contour shape to obtain a target furniture model with adjusted size; Determine the placement angle of the target furniture model with adjusted size according to the furniture placement rules of the functional area corresponding to the target position; Place the target furniture model with adjusted size at the target position according to the placement angle.

[0016] Optionally, the device further includes: A display unit, configured to not display the specific color represented by the target position.

[0017] In a third aspect, the present application provides a computer device, including: A processor, a memory, a bus, an input / output interface, and a network interface; The processor is connected to the memory, the input / output interface, and the network interface through the bus; The memory stores a program; When the processor executes the program stored in the memory, it implements the method for processing the furniture layout of the apartment floor plan based on artificial intelligence according to any one of the above first aspects.

[0018] In a fourth aspect, the present application provides a computer storage medium, in which instructions are stored, and when the instructions are executed on a computer, the computer is enabled to execute the method for processing the furniture layout of the apartment floor plan based on artificial intelligence according to any one of the above first aspects.

[0019] In a fifth aspect, the present application provides a computer program product, and when the computer program product is executed on a computer, the computer is enabled to execute the method for processing the furniture layout of the apartment floor plan based on artificial intelligence according to any one of the above first aspects.

[0020] From the above technical solutions, it can be seen that the embodiments of the present application have the following advantages: The furniture layout processing method for house type diagrams based on artificial intelligence in this embodiment obtains the target house type diagram, that is, the house type diagram for which furniture layout is required, where different functional areas in the target house type diagram have been identified and labeled; inputs the target house type diagram into a preset artificial intelligence model for furniture layout processing to obtain a furniture layout color block diagram corresponding to the target house type diagram, where in the furniture layout color block diagram, color blocks of specific colors marked at target positions in corresponding functional areas of the target house type diagram represent specific types of furniture, and the size of the color blocks of specific colors represents the space occupied by specific types of furniture at the target positions. The preset artificial intelligence model is a model that has been trained to be able to generate color blocks representing the colors of appropriate specific types of furniture in corresponding functional areas of the house type diagram; determines the target furniture model corresponding to the target color block in the furniture layout color block diagram, where the target color block is the color block of the specific color represented by the target position; adaptively places the target furniture model at the target position in the furniture layout color block diagram to obtain the furniture layout effect diagram of the target house type, realizing furniture layout processing in the target house type diagram based on artificial intelligence technology, quickly obtaining the furniture layout effect diagram of the target house type, so as to facilitate users to quickly plan the furniture layout of the house type diagram they upload on the Internet and make modification decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic flowchart of an embodiment of the furniture layout processing method for house type diagrams based on artificial intelligence in this application; Figure 2 It is a schematic flowchart of another embodiment of the furniture layout processing method for house type diagrams based on artificial intelligence in this application; Figure 3 It is a schematic structural diagram of an embodiment of the furniture layout processing device for house type diagrams based on artificial intelligence in this application; Figure 4 It is a schematic structural diagram of another embodiment of the furniture layout processing device for house type diagrams based on artificial intelligence in this application; Figure 5 It is a schematic structural diagram of an embodiment of the computer device in this application; Figure 6 It is a schematic diagram of an embodiment of the original house type diagram in this application; Figure 7 is Figure 6 A schematic diagram of an embodiment of the target house type diagram after the original house type diagram is processed by functional areas; Figure 8 is Figure 7 A schematic diagram of an embodiment of the furniture layout color block diagram after the target house type diagram is processed by the preset artificial intelligence model for furniture layout; Figure 9 is Figure 6 A schematic diagram of an embodiment of the furniture layout effect diagram of the target house type after the original house type diagram is adaptively added with the target furniture model; Figure 10 For Figure 9 an embodiment schematic diagram of a three-dimensional rendering of the furniture layout of a target house type corresponding to the rendering of the furniture layout of the target house type. Detailed implementation manners

[0022] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0023] It should be noted that processing the furniture layout of a house type drawing can present the furniture layout effect of the house type drawing, enabling users to intuitively understand the furniture layout situation based on the house type drawing before the furniture is arranged, so as to facilitate the user to modify and make decisions on the furniture layout plan of the house type drawing. However, in the prior art, the process of processing the furniture layout of a house type drawing often requires a home improvement designer to plan and layout an empty house type drawing, that is, manually plan, place and adjust the furniture in each functional area of the empty house type drawing, with low efficiency and unable to meet the needs of ordinary users for quickly generating the rendering of the house type furniture layout on the Internet in a timely manner. The functional area of the house type drawing in this embodiment refers to: a closed space that can be enclosed by the wall features in the house type drawing, such as a bedroom, a bathroom, a living room, a kitchen, a balcony, etc.; the wall features in the house type drawing in this embodiment refer to: the walls, windows, doors, fences, etc. of the house type drawing. Currently, with the rapid development and maturity of related technologies of artificial intelligence (AI), this embodiment attempts to use a trained artificial intelligence model to process the furniture layout of a target house type drawing, so as to improve the efficiency of generating the rendering of the house type furniture layout from the house type drawing. Since the process of training an artificial intelligence model is a relatively mature prior art, this embodiment will not be described in too much detail.

[0024] The method for processing furniture layout in a house floor plan based on artificial intelligence of this application runs in a system for processing furniture layout in a house floor plan based on artificial intelligence. The system for processing furniture layout in a house floor plan includes: a central processing unit module, a memory module, an artificial intelligence chip module, a communication module, a power supply module, etc. The above-mentioned various modules are connected through a Printed Circuit Board (PCB) to obtain the system for processing furniture layout in a house floor plan. Among them, the central processing unit is mainly used to comprehensively schedule each component module connected to it to implement the method for processing furniture layout in a house floor plan based on artificial intelligence mentioned in this embodiment. The power supply module is mainly used to provide appropriate working voltages for the central processing unit module, the memory module, the artificial intelligence chip module, the communication module, etc. The power supply module can be in a mode of self-powered by a battery or a mode of mains supply. The power source of the power supply module is not limited here. The memory module mainly stores programs for implementing the relevant steps of this embodiment. At the same time, the memory also stores various pre-trained artificial intelligence models, a preset furniture model database, a preset comparison table of furniture models and color values, etc. The artificial intelligence chip module is used to quickly load and run the artificial intelligence models stored in the memory module, and perform furniture layout processing on the target house floor plan to obtain the target house floor furniture layout effect diagram and store it in the memory module. The communication module is mainly used to communicate with external devices (such as electronic devices like mobile phones, tablets, and computers) (for example, obtain the target house floor plan, output the target house floor furniture layout effect diagram, etc.).

[0025] Based on the above understanding, please refer to Figure 1 , an embodiment of the method for processing furniture layout in a house floor plan based on artificial intelligence of this application, includes: 101. Obtain the target house floor plan.

[0026] It should be noted that the target house floor plan in this embodiment is an empty house floor plan in which the functional areas have been identified and marked. The empty house floor plan in this embodiment means that no furniture models are placed in each functional area of the target house floor plan. For example Figure 7 as shown. Figure 7 The target house floor plan shown is Figure 6 the house floor plan obtained after the functional areas of the empty original house floor plan shown are identified and segmented, and different functional areas have been marked in this embodiment Figure 7 different functional areas in the target house floor plan are distinguished and marked with color blocks of different color values. Combining Figure 6 it can be seen that Figure 7 in the target house floor plan shown, various functional areas are marked with color blocks of different color values: the balcony is marked with a dark blue color block, the bedrooms (master bedroom and secondary bedroom) are marked with a light blue color block, the living and dining rooms are marked with an orange color block, the bathroom is marked with a brown color block, and the kitchen is marked with a gray-yellow color block. Of course, it can be understood thatFigure 7 For the wall features in the displayed target floor plan, color bars with different color values are used to label different types of wall features: gray color bars are used to label walls, off-white color bars are used to label windows (ordinary windows or bay windows), and green color bars are used to label doors or sliding doors. It can be understood that in actual applications, the target floor plan can be customized to use various colors to represent different types of functional areas and wall features, which are not limited here as long as they can be distinguished.

[0027] 102. Input the target floor plan into a preset artificial intelligence model for furniture layout processing to obtain a furniture layout color block diagram of the target floor plan.

[0028] Input the target floor plan obtained in step 101 into the preset artificial intelligence model for furniture layout processing, and a furniture layout color block diagram for furniture layout in each functional area can be obtained. The furniture layout color block diagram in this embodiment refers to using color blocks of specific colors on the basis of the target floor plan to represent specific types of furniture placed at the target positions in the corresponding functional areas, and the size of the color blocks of the specific colors represents the space occupancy of the specific types of furniture at the target positions in the functional areas, as Figure 8 shown. Combining Figure 6 analysis shows that Figure 8 The furniture layout color block diagram of the target floor plan shown only selects the living and dining rooms, bathrooms, master bedrooms, and secondary bedrooms with bay windows in the target floor plan for furniture layout processing. In actual applications, in this step, the user can choose to perform furniture layout processing on one, multiple, or all functional areas in the target floor plan, which is not specifically limited here.

[0029] The preset artificial intelligence model in this embodiment is a trained model that can generate color blocks representing the colors of appropriate specific types of furniture adapted to the corresponding functional areas in the floor plan. The training of the above preset artificial intelligence model can collect different types of floor plans whose functional areas have been identified and labeled, as well as the corresponding floor plan furniture layout effect diagrams of this type of floor plan as training samples, and combine manual labeling and classification of color blocks with preset color values for data labels such as the type of furniture, furniture name, coordinate position, and size of each furniture in the floor plan furniture layout effect diagrams corresponding to different types of floor plans, so that the artificial intelligence model can be trained to obtain a trained model that can generate color blocks representing the color values of specific types of furniture adapted to the corresponding functional areas in the floor plan. It can be understood that the preset artificial intelligence model in this embodiment includes deep learning models, convolutional neural networks (CNNs), etc., and preferably the pix2pix model.

[0030] 103. Determine the target furniture model corresponding to the target color block in the furniture layout color block diagram.

[0031] It can be understood that various styles and types of furniture models (which can be two-dimensional models and / or three-dimensional models) are pre-stored in the furniture model database in this embodiment. Specifically, in this step, the target color value of a target color block representing furniture in the furniture layout color block diagram can be determined first. For example, Figure 8 the deep purple color of the deep purple color block shown; determine the target furniture name corresponding to the target color value in the preset furniture model and color value comparison table. Suppose Figure 8 the furniture name corresponding to the deep purple color of the deep purple color block shown is: 1.5-meter bed. In practical applications, the target color block representing furniture also records a lot of vector data. For example, the vector data includes the coordinate position of placing the furniture in the furniture layout color block diagram, the type of furniture, the size of the furniture, etc.; then determine the target furniture model in the preset furniture model database according to the target furniture name. For example, according to Figure 8 the furniture name "1.5-meter bed" corresponding to the deep purple color of the deep purple color block in, find the furniture model that conforms to the description or label of the furniture name "1.5-meter bed" in the preset furniture model database as the target furniture model; in fact, there may be many furniture models of different styles that conform to the target furniture name (such as "1.5-meter bed") in the preset furniture model database. In this step, one can be selected according to the default rule or style type labels can be listed for the user to select one of them, and then the target furniture model is determined. The default rule here can be to select the first style type in the sorting or list all style type labels in the form of a pop-up window for display, and let the user select one of the style types. Similarly, Figure 8 the other furniture models corresponding to the other color blocks in the furniture layout color block diagram shown can also be determined according to the similar process above.

[0032] 104. Adaptively place the target furniture model at the target position to obtain the furniture layout effect diagram of the target household type.

[0033] Adaptively place all the target furniture models determined in step 103 at the target positions in the corresponding functional areas of the target household type diagram, and then the furniture layout effect diagram of the target household type can be obtained, realizing fast furniture layout processing in the target household type diagram based on artificial intelligence technology, with higher efficiency and being able to meet the needs of ordinary users for generating furniture layout effect diagrams of household type diagrams on the Internet in a timely manner.

[0034] Please refer to Figure 2 , another embodiment of the method for processing furniture layout of household type diagrams based on artificial intelligence in this application, includes: 201. Obtain the target household type diagram.

[0035] The execution of this step is similar to the operation executed in step 101 of the foregoing Figure 1 embodiment and will not be elaborated here.

[0036] It should be noted that to obtain the target floor plan, this step needs to first obtain the original floor plan. The so-called original floor plan is an empty floor plan without furniture configured, as shown in, for example Figure 6 shown. The original floor plan can be provided by the user or drawn by the designer according to the user's description or on-site measurement. The source method of the original floor plan is not limited here. In this embodiment, the original floor plan is further subjected to functional area recognition and segmentation to obtain a functional area segmentation diagram. To facilitate the recognition of different functional areas in the functional area segmentation diagram, the same color value is used to label the same functional areas (such as bedrooms like the master bedroom and secondary bedroom) in the floor plan functional area segmentation diagram, and different color values are used to label different functional areas (kitchen, living and dining room, bathroom, balcony, etc.) in the floor plan functional area segmentation diagram to obtain the target floor plan, as shown in Figure 7 shown. Among them, the color value used to label the functional areas in the floor plan functional area segmentation diagram is different from the color value of the specific color represented by the target position of the target color block representing furniture in this embodiment to avoid misrecognition. Specifically, the target floor plan of this embodiment can also be directly obtained by a trained specific artificial intelligence model for functional area recognition and segmentation of the original floor plan, that is, through the specific artificial intelligence model to complete the functional area recognition, segmentation, and labeling of the original floor plan, and quickly complete the acquisition of the target floor plan from the original floor plan. The training of the above specific artificial intelligence model can use the blank floor plans in the public building field such as public rental housing and the floor plan functional area segmentation diagrams corresponding to the manual functional area labeling of the blank floor plans as training samples, so that the specific artificial intelligence model can be trained to obtain a model that can realize the functional area recognition, segmentation, and labeling of the blank floor plan. The specific artificial intelligence model of this embodiment includes deep learning models, convolutional neural networks (CNNs), etc.

[0037] Furthermore, in a possible embodiment, the process of the above embodiment for functional area recognition and segmentation of the original floor plan to obtain a functional area segmentation diagram can also be: first, identify the walls of the original floor plan to obtain wall features; then, segment and identify the functional areas enclosed by the wall features to obtain a floor plan functional area segmentation diagram. It can be understood that the process of identifying the walls of the original floor plan in this embodiment can also be carried out through artificial intelligence technology. For example, use a trained first specific artificial intelligence model to identify the walls (walls, windows, doors, fences, etc.) of the floor plan to obtain wall features (i.e., specific wall features, window features, door features, fence features, etc.), as shown in Figure 7The wall features in the target floor plan are marked with color bars of different color values for different types of wall features; the trained second specific artificial intelligence model is used to identify and segment the functional areas (bedrooms, living and dining rooms, balconies, bathrooms, kitchens, etc.) formed by the wall features to obtain the floor plan of the functional area segmentation of this floor plan. The training of the first specific artificial intelligence model can use the blank floor plans in the public building field such as public rental housing and the floor plans with the wall feature type markings by artificial for the corresponding blank floor plans as training samples, so that the first specific artificial intelligence model can be trained to obtain a trained model that can identify the wall features of the original floor plan; the training of the second specific artificial intelligence model can use the floor plans with wall feature markings (such as the floor plans output by the first specific artificial intelligence model) and the floor plan of the functional area segmentation of the floor plan with the functional area markings by artificial for the corresponding floor plan as training samples, so that the second specific artificial intelligence model can be trained to obtain a trained model that can identify and segment the functional areas of the floor plan with wall feature markings. In this embodiment, the first specific artificial intelligence model and the first specific artificial intelligence model can be deep learning models, convolutional neural networks (CNNs), etc. Since the process of training the artificial intelligence model is a relatively mature existing technology, this embodiment will not be described in too much detail.

[0038] 202. Input the target floor plan into a preset artificial intelligence model for furniture layout processing to obtain the furniture layout color block diagram of the target floor plan.

[0039] The execution of this step is similar to the operation performed in step 102 in the foregoing Figure 1 embodiment and will not be elaborated.

[0040] 203. Determine the target furniture model corresponding to the target color block in the furniture layout color block diagram.

[0041] The execution of this step is similar to the operation performed in step 103 in the foregoing Figure 1 embodiment and will not be elaborated.

[0042] 204. Adaptively place the target furniture model at the target position in the furniture layout color block diagram to obtain the furniture layout effect diagram of the target floor plan.

[0043] The execution of this step is similar to the operation performed in step 104 in the foregoing Figure 1 embodiment and will not be elaborated.

[0044] Specifically, to better conform to the human viewing perspective and more accurately place the target furniture model obtained in step 203 at the target position in the furniture layout color block diagram, this step can identify the regional contour of the target color block at the target position in the furniture layout color block diagram to obtain the target color block contour shape, that is, to know the outer contour boundary of the entire target color block. To reduce the amount of calculation, the shape of the target color block is usually a rectangle. To improve the accuracy, the shape of the target color block can also be other polygons, such as pentagons, hexagons, etc.; then perform size transformation processing on the target furniture model obtained in step 203 (i.e., proportionally reducing or enlarging the size) until the target furniture model can be fully and properly placed into the target color block contour shape to obtain the target furniture model with adjusted size; determine the placement angle of the target furniture model with adjusted size according to the furniture placement rules of the functional area corresponding to the target position; place the target furniture model with adjusted size at the target position according to the placement angle.

[0045] It should be noted that the furniture placement rules of the functional area corresponding to the target position can support users to set according to actual needs. For example: when the functional area corresponding to the target position is the living room, the backrest (in the length direction) of the sofa leans against the wall, and the seating of the sofa faces the coffee table, etc.; when the functional area corresponding to the target position is the bedroom, the backrest of the bed leans against the wall, etc. It can be seen that based on the principle that the backrest of the furniture leans against the wall, furniture such as sofas and beds can quickly and accurately determine the placement angle to avoid the problem that the furniture placement angle does not conform to people's usage habits, making the furniture layout effect drawing of the target house type more realistic and improving the user's visual experience of the furniture layout effect drawing of the target house type.

[0046] 205. Do not display the specific color represented by the target position.

[0047] It should be noted that the target house type diagram with identified and marked different functional areas is actually formed by covering specific color value color block layers and color bar layers on different functional areas and different wall features on the basis of the original house type diagram; similarly, the target color blocks representing furniture in the furniture layout color block diagram are also added on the upper layer of the target house type diagram in the form of layer covering. When placing the target furniture model at the target position according to the placement angle, it is equivalent to adding the target furniture model on the upper layer of the target color block position in the furniture layout color block diagram in the form of layer covering, that is, when placing the target furniture model at the target position of the furniture layout color block diagram, it is also placed at the target position corresponding to the functional area of the target house type diagram (original house type diagram); when this step selects not to display the specific color (target color block) represented by the target position, it is equivalent to adding the target furniture model to replace the target color block in the target house type diagram; when selecting not to display the color block layer and color bar layer with specific color values for the functional area and wall features corresponding to the target house type diagram, it is equivalent to adding the target furniture model to the original house type diagram, such asFigure 9 As shown Figure 9 The visual effect of the furniture layout rendering of the target house type shown has hidden the target color blocks, color block layers, and color bar layers, and the visual effect of the furniture layout rendering of the target house type is better.

[0048] Furthermore, in another embodiment, the furniture layout rendering of the target house type in this embodiment can be further converted into a 3D furniture layout rendering of the target house type, such as Figure 10 As shown Figure 10 For Figure 9 FIG. is a schematic diagram of an embodiment of a 3D furniture layout rendering of a target house type corresponding to the furniture layout rendering of the target house type. The 3D furniture layout rendering of the target house type can provide users with more furniture layout details and better user experience. The process of converting the furniture layout rendering of the target house type into the 3D furniture layout rendering of the target house type can also be obtained by inputting the furniture layout rendering of the target house type into a trained target artificial intelligence model; the target artificial intelligence model can output a 3D furniture layout rendering of the target house type with 3D effect according to the furniture layout rendering of the target house type. The training of the target artificial intelligence model can collect furniture layout renderings of a large number of house types and 3D furniture layout renderings of the corresponding house types at specific viewing angles as training samples, and combine the data such as furniture names, furniture positions, and furniture sizes in the 3D furniture layout renderings at specific viewing angles manually to perform one-to-one annotation classification with the data such as furniture names, furniture positions, and furniture sizes in the corresponding furniture layout renderings of the house type, so as to train the artificial intelligence model to obtain a trained model that can output 3D furniture layout renderings of specific viewing angles with 3D effect according to the furniture layout renderings of the house type. It can be understood that the preset artificial intelligence model in this embodiment includes a deep learning model, a convolutional neural network (CNN), etc.

[0049] The above embodiments have described the embodiments of the method for processing the furniture layout of a house type diagram based on artificial intelligence in this application. Next, the device for processing the furniture layout of a house type diagram based on artificial intelligence in this application will be described. Please refer to Figure 3 , an embodiment of the device for processing the furniture layout of a house type diagram based on artificial intelligence in this application, includes: An acquisition unit 301, configured to acquire a target house type diagram, and different functional areas in the target house type diagram have been identified and marked; The processing unit 302 is configured to input the target floor plan into a preset artificial intelligence model for furniture layout processing, so as to obtain a furniture layout color block diagram corresponding to the target floor plan. In the furniture layout color block diagram, color blocks of specific colors marked at target positions in corresponding functional areas of the target floor plan represent specific types of furniture, and the sizes of the color blocks of specific colors represent the space occupied by specific types of furniture at the target positions. The preset artificial intelligence model is a trained model that can generate color blocks representing the colors of appropriate specific types of furniture corresponding to the corresponding functional areas of the floor plan; The determination unit 303 is configured to determine a target furniture model corresponding to a target color block in the furniture layout color block diagram, where the target color block is a color block of a specific color represented by the target position; The placement unit 304 is configured to adaptively place the target furniture model at the target position in the furniture layout color block diagram to obtain an effect diagram of the furniture layout of the target floor plan.

[0050] The operations performed by the device for processing the furniture layout of the floor plan based on artificial intelligence in this application are similar to those described in the foregoing Figure 1 embodiment and will not be elaborated here.

[0051] Please refer to Figure 4 , another embodiment of the device for processing the furniture layout of the floor plan based on artificial intelligence in this application, includes: The acquisition unit 401 is configured to acquire a target floor plan, where different functional areas in the target floor plan have been identified and marked; The processing unit 402 is configured to input the target floor plan into a preset artificial intelligence model for furniture layout processing, so as to obtain a furniture layout color block diagram corresponding to the target floor plan. In the furniture layout color block diagram, color blocks of specific colors marked at target positions in corresponding functional areas of the target floor plan represent specific types of furniture, and the sizes of the color blocks of specific colors represent the space occupied by specific types of furniture at the target positions. The preset artificial intelligence model is a trained model that can generate color blocks representing the colors of appropriate specific types of furniture corresponding to the corresponding functional areas of the floor plan; The determination unit 403 is configured to determine a target furniture model corresponding to a target color block in the furniture layout color block diagram, where the target color block is a color block of a specific color represented by the target position; The placement unit 404 is configured to adaptively place the target furniture model at the target position in the furniture layout color block diagram to obtain an effect diagram of the furniture layout of the target floor plan.

[0052] Optionally, when the acquisition unit 401 acquires the target floor plan, it is specifically configured to: acquire an original floor plan, where the original floor plan is an empty floor plan without furniture configured; Perform functional area recognition and segmentation on the original floor plan to obtain a floor plan functional area segmentation diagram; Label the same functional areas in the floor plan functional area segmentation diagram with the same color value, and label different functional areas in the floor plan functional area segmentation diagram with different color values to obtain the target floor plan. The color value used to label the functional areas in the floor plan functional area segmentation diagram is different from the color value of the specific color represented by the target position.

[0053] Optionally, when the obtaining unit 401 performs functional area recognition and segmentation on the original floor plan to obtain a floor plan functional area segmentation diagram, it is specifically used for: Identify the walls of the original floor plan to obtain wall features; Segment and identify the functional areas enclosed by the wall features to obtain the floor plan functional area segmentation diagram.

[0054] Optionally, when the determining unit 403 determines the target furniture model corresponding to the target color block in the furniture layout color block diagram, it is specifically used for: Determine the target color value of the target color block; Determine the target furniture name corresponding to the target color value in the preset furniture model and color value comparison table; Determine the target furniture model in the preset furniture model database according to the target furniture name.

[0055] Optionally, when the placing unit 404 adaptively places the target furniture model at the target position in the furniture layout color block diagram, it is specifically used for: Identify the regional outline of the target color block to obtain the target color block outline shape; Perform size transformation processing on the target furniture model until the target furniture model can be appropriately placed into the target color block outline shape to obtain a target furniture model with adjusted size; Determine the placement angle of the target furniture model with adjusted size according to the furniture placement rules of the functional area corresponding to the target position; Place the target furniture model with adjusted size at the target position according to the placement angle.

[0056] Optionally, the device further includes: A display unit 405 for not displaying the specific color represented by the target position.

[0057] The operations performed by the floor plan furniture layout processing device based on artificial intelligence in this application are similar to those described in the foregoing Figure 2 embodiment and will not be elaborated here.

[0058] The computer device in the embodiments of the present application will be described below. Please refer to Figure 5 , an embodiment of the computer device in the embodiments of the present application includes: The computer device 500 may include one or more processors (central processing units, CPUs) 501 and a memory 502, and one or more applications or data are stored in the memory 502. Among them, the memory 502 is volatile storage or persistent storage. The program stored in the memory 502 may include one or more modules, and each module may include a series of instruction operations on the computer device. Further, the processor 501 may be configured to communicate with the memory 502 and execute a series of instruction operations in the memory 502 on the computer device 500. The computer device 500 may further include: one or more wireless network interfaces 503, one or more input / output interfaces 504, and / or one or more operating systems, such as Harmony OS, Windows Server, Mac OS, Unix, Linux, FreeBSD, etc. The processor 501 may execute the foregoing Figure 1 or Figure 2 any of the operations performed in the illustrated embodiments, which will not be specifically described here.

[0059] In several embodiments provided by the embodiments of the present application, those skilled in the art should understand that the disclosed systems, devices, and methods may be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other may be through some interfaces, and the indirect coupling or communication connection of the device or unit may be in an electrical, mechanical or other form.

[0060] In addition, in each embodiment of the present application, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0061] The foregoing is only a preferred embodiment of the present application and is not intended to limit the present application. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for processing furniture layout of a floor plan based on artificial intelligence, characterized in that: include: Obtain a target floor plan, in which different functional areas have been identified and marked; Input the target floor plan into a preset artificial intelligence model to perform furniture layout processing, and obtain a furniture layout color block diagram corresponding to the target floor plan, wherein the furniture layout color block diagram marks a color block of a specific color at a target position in a functional area corresponding to the target floor plan to represent a specific type of furniture, and the size of the color block of the specific color represents the size of the space occupied by the specific type of furniture at the target position, wherein the preset artificial intelligence model is a trained model capable of generating color blocks of a color suitable for representing a specific type of furniture in a corresponding functional area of ​​the floor plan; Determine a target furniture model corresponding to a target color block in the furniture layout color block diagram, wherein the target color block is a color block of a specific color represented by the target position; The target furniture model is adapted and placed at the target position in the furniture layout color block diagram to obtain a target apartment furniture layout rendering.

2. The method for processing furniture layout in a floor plan based on artificial intelligence according to claim 1, characterized in that: The obtaining of the target floor plan comprises: Obtaining an original floor plan, where the original floor plan is an empty floor plan without any furniture; Identifying and segmenting the functional areas of the original floor plan to obtain a floor plan functional area segmentation diagram; The same functional areas in the functional area segmentation diagram of the apartment type are marked with the same color value, and different functional areas in the functional area segmentation diagram of the apartment type are marked with different color values ​​to obtain the target apartment type. The color value used to mark the functional area in the functional area segmentation diagram of the apartment type is different from the color value of the specific color represented by the target position.

3. The method for processing furniture layout in a floor plan based on artificial intelligence according to claim 2 is characterized in that: The functional area identification and segmentation of the original floor plan to obtain a floor plan functional area segmentation diagram includes: Identify the walls of the original floor plan to obtain wall features; The functional areas enclosed by the wall features are segmented and identified to obtain a functional area segmentation diagram of the apartment.

4. The method for processing furniture layout in a floor plan based on artificial intelligence according to claim 1, characterized in that: Determining the target furniture model corresponding to the target color block in the furniture layout color block image includes: Determine a target color value of the target color block; Determine the target furniture name corresponding to the target color value in a preset furniture model and color value comparison table; The target furniture model is determined in a preset furniture model database according to the target furniture name.

5. The method for processing furniture layout in a floor plan based on artificial intelligence according to claim 4 is characterized in that: Adapting and placing the target furniture model in the target position in the furniture layout color block diagram includes: Identifying the area contour of the target color block to obtain the contour shape of the target color block; Performing a size transformation process on the target furniture model until the target furniture model can be fit into the target color block contour shape, thereby obtaining a size-adjusted target furniture model; Determining a placement angle of the target furniture model after the size adjustment according to a furniture placement rule of a functional area corresponding to the target position; The target furniture model after the size adjustment is placed at the target position according to the placement angle.

6. The method for processing furniture layout in a floor plan based on artificial intelligence according to claim 5 is characterized in that: After placing the target furniture model after the size adjustment at the target position according to the placement angle, the method further includes: The specific color represented by the target location is not displayed.

7. An artificial intelligence-based floor plan furniture layout processing device, characterized in that: include: An acquisition unit, used for acquiring a target floor plan, wherein different functional areas in the target floor plan have been identified and marked; a processing unit, configured to input the target floor plan into a preset artificial intelligence model for furniture layout processing, and obtain a furniture layout color block diagram corresponding to the target floor plan, wherein the furniture layout color block diagram marks color blocks of specific colors at target positions in functional areas corresponding to the target floor plan to represent specific types of furniture, and the size of the color blocks of specific colors represents the size of space occupied by the specific type of furniture at the target position, wherein the preset artificial intelligence model is a trained model capable of generating color blocks of colors suitable for representing specific types of furniture in corresponding functional areas of the floor plan; A determination unit, configured to determine a target furniture model corresponding to a target color block in the furniture layout color block diagram, wherein the target color block is a color block of a specific color represented by the target position; A placement unit is used to adapt and place the target furniture model at the target position in the furniture layout color block diagram to obtain a target apartment furniture layout rendering.

8. A computer device, characterized in that: include: Processor, memory, bus, input and output interface, network interface; The processor is connected to the memory, the input / output interface, and the network interface via a bus; The memory stores a program; When the processor executes the program stored in the memory, the method for processing floor plan furniture layout based on artificial intelligence as described in any one of claims 1 to 6 is implemented.

9. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the artificial intelligence-based floor plan furniture layout processing method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that When the computer program product is executed on a computer, the computer is enabled to execute the artificial intelligence-based floor plan furniture layout processing method as described in any one of claims 1 to 6.

Images