Functional area wall processing method of house type image and related device

Abstract

The invention is suitable for the technical field of graphic processing, provides a functional area wall processing method of a house type image and a related device, and realizes completion of wall feature recognition missing parts of functional areas in the house type image. The method mainly comprises the steps of obtaining wall features of a target house type image, wherein the target house type image is a wall feature image obtained by performing wall feature recognition on an original house type image through an artificial intelligence model; performing mean value calculation on the color values of the pixel blocks at the positions corresponding to the wall features in the original house type image to obtain a target color value; identifying the pixel blocks falling into the target color value in the original house type image to obtain identification features; performing intersection operation on the recognition features and the wall body features to obtain intersection features; carrying out difference set operation on the identification features and the wall body features to obtain difference set features; determining a target difference set feature in direct contact with the intersection feature from the difference set features; and supplementing the target difference set features into the wall features to obtain new wall features of the target house type image.

Description

Technical Field

[0001] The present application belongs to the field of graphics processing technology, and in particular relates to a method for processing walls in functional areas of a floor plan and related devices. Background Art

[0002] In the field of building decoration, in order to enable users to display the decoration effects that are in line with their own floor plans on the online platform, it is a prerequisite to accurately identify the various functional areas of the floor plans uploaded by users.

[0003] With the rapid development and maturity of artificial intelligence (AI), AI technology has also been introduced into the process of feature recognition in floor plans. However, since there are many wall features that need to be recognized in floor plans (such as walls, windows, doors, etc.), in order to accurately identify the characteristics of each wall type, the AI model will be trained to recognize the characteristics of different wall types. However, this also results in the AI model often being able to accurately recognize the wall features of floor plans, but often missing the recognition of wall features in floor plans. In other words, the current AI model cannot achieve both accurate and comprehensive recognition of wall features in floor plans. Summary of the Invention

[0004] The present application provides a method and related device for processing walls of functional areas in a floor plan, so as to complete the missing parts of the wall feature recognition of the functional areas in the floor plan.

[0005] In a first aspect, the present application provides a method for processing walls in functional areas of a floor plan, comprising:

[0006] Obtaining wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan;

[0007] Calculate the average color value of the pixel blocks at the corresponding positions of the wall features in the original floor plan to obtain a target color value;

[0008] Identify pixel blocks in the original floor plan that fall within the target color value to obtain identification features;

[0009] Performing an intersection operation on the recognition feature and the wall feature to obtain an intersection feature;

[0010] Performing a difference operation on the recognition feature and the wall feature to obtain a difference feature;

[0011] Determining a target difference feature that is in direct contact with the intersection feature from among the difference features;

[0012] The target difference set features are added to the wall features to obtain new wall features of the target floor plan.

[0013] Optionally, identifying pixel blocks in the original floor plan that fall within the target color value to obtain identification features includes:

[0014] Determine the target color range value with the target color value as the middle value;

[0015] The pixel blocks in the original floor plan that fall within the target color range are identified to obtain the identification features.

[0016] Optionally, after obtaining the intersection feature and before determining, in the identification features, a target difference feature that directly contacts the intersection feature, the method further includes:

[0017] Determine whether the intersection feature is empty;

[0018] If the intersection feature is empty, then executing the step of obtaining the wall feature of the target floor plan;

[0019] If the intersection feature is not empty, it is ignored.

[0020] Optionally, after determining, in the identification features, a target difference feature that is in direct contact with the intersection feature, the method further includes:

[0021] Determine whether the target difference set feature is empty;

[0022] If the target difference set feature is empty, it is determined that the wall feature of the target floor plan is in a non-missing state, and a reminder is issued that the functional area wall is not missing;

[0023] If the target difference set feature is not empty, it is determined that the wall feature of the target floor plan is in a wall missing state, and a reminder of missing walls in the functional area is issued.

[0024] Optionally, the method further includes:

[0025] Functional area identification and segmentation are performed on the target floor plan according to the new wall features to obtain a floor plan functional area segmentation diagram.

[0026] Optionally, the wall features include: one or more of walls, windows, doors, fences, and screens.

[0027] In a second aspect, the present application provides a device for processing walls in functional areas of a floor plan, comprising:

[0028] an acquisition unit, configured to acquire wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan;

[0029] A calculation unit, configured to calculate the average color value of the pixel blocks at the positions corresponding to the wall features in the original floor plan to obtain a target color value;

[0030] An identification unit, configured to identify pixel blocks in the original floor plan that fall within the target color value to obtain identification features;

[0031] The calculation unit is further configured to perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature;

[0032] The calculation unit is further configured to perform a difference operation on the recognition feature and the wall feature to obtain a difference feature;

[0033] a determining unit, configured to determine, from the difference features, a target difference feature that is in direct contact with the intersection feature;

[0034] A supplementing unit is used to supplement the target difference set features into the wall features to obtain new wall features of the target floor plan.

[0035] Optionally, the recognition unit identifies pixel blocks in the original floor plan that fall within the target color value, and when obtaining the recognition feature, is specifically used to:

[0036] Determine the target color range value with the target color value as the middle value;

[0037] The pixel blocks in the original floor plan that fall within the target color range are identified to obtain the identification features.

[0038] Optionally, the device further includes:

[0039] A judging unit, configured to judge whether the intersection feature is empty;

[0040] an execution unit, configured to execute the step of obtaining the wall features of the target floor plan if the intersection feature is empty;

[0041] The ignoring unit is used to ignore if the intersection feature is not empty.

[0042] Optionally, the device further includes:

[0043] The judging unit is configured to judge whether the target difference set feature is empty;

[0044] a reminder unit, configured to, if the target difference set feature is empty, determine that the wall feature of the target floor plan is in a non-missing state, and issue a reminder that the functional area wall is not missing;

[0045] The reminder unit is further configured to, if the target difference set feature is not empty, determine that the wall feature of the target floor plan is in a wall missing state, and issue a reminder that a functional area wall is missing.

[0046] Optionally, the device further includes:

[0047] The segmentation unit is used to identify and segment the functional areas of the target floor plan according to the new wall features to obtain a floor plan functional area segmentation diagram.

[0048] Optionally, the wall features include: one or more of walls, windows, doors, fences, and screens.

[0049] In a third aspect, the present application provides a computer device, comprising:

[0050] Processor, memory, bus, input and output interface, network interface;

[0051] The processor is connected to the memory, the input / output interface, and the network interface via a bus;

[0052] The memory stores a program;

[0053] When the processor executes the program stored in the memory, the method for processing the functional area walls of the floor plan described in any one of the first aspects above is implemented.

[0054] In a fourth aspect, the present application provides a computer storage medium, wherein the computer storage medium stores instructions, and when the instructions are executed on a computer, the computer executes the functional area wall processing method of the floor plan described in any one of the first aspects above.

[0055] In a fifth aspect, the present application provides a computer program product, which, when executed on a computer, enables the computer to execute the functional area wall processing method of the floor plan described in any one of the first aspects above.

[0056] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0057] The functional area wall processing method of the floor plan of this embodiment obtains the wall features of the target floor plan to learn a wall type whose wall features need to be completed, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on the original floor plan by an artificial intelligence model, and the wall features are the same wall type features in the target floor plan; the color values of the pixel blocks at the corresponding positions of the wall features in the original floor plan are averaged to obtain the target color value; the pixel blocks falling into the target color value in the original floor plan are identified to obtain an identification feature; the identification feature is intersected with the wall feature to obtain an intersection feature; the identification feature is differenced with the feature to obtain a difference feature; the target difference feature is determined in the difference feature that is directly in contact with the intersection feature; the target difference feature is added to the wall feature to obtain a new wall feature of the target floor plan, so as to complete the missing parts of the wall feature recognition of the functional area in the floor plan when the artificial intelligence model accurately recognizes the wall features in the original floor plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of an embodiment of a method for processing walls in functional areas of a floor plan of this application;

[0059] Figure 2 This is a flow chart of another embodiment of the method for processing walls in functional areas of the floor plan of this application;

[0060] Figure 3 This is a schematic structural diagram of an embodiment of a wall processing device for a functional area of a floor plan of this application;

[0061] Figure 4 This is a schematic structural diagram of an embodiment of a wall processing device for a functional area of a floor plan of this application;

[0062] Figure 5 This is a schematic diagram of the structure of an embodiment of the computer device of the present application;

[0063] Figure 6 This is a schematic diagram of an embodiment of the original floor plan of this application;

[0064] Figure 7 This is a schematic diagram of an embodiment of the target floor plan of this application;

[0065] Figure 8 for Figure 7 A schematic diagram of an embodiment of a middle wall;

[0066] Figure 9 for Figure 7 A schematic diagram of an embodiment after the target floor plan is completed with wall features. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is 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 this application and are not intended to limit this application.

[0068] It should be noted that the so-called floor plan in this embodiment refers to a floor plan layout diagram of a house, i.e., a graphic depicting the function, location, and size of each independent space within the house. The floor plan allows users to intuitively understand the layout of the house. In this embodiment, the functional areas of the floor plan refer to the independent spaces within the floor plan, such as the kitchen, living room, bedroom, bathroom, balcony, and other functional areas. The functional area walls refer to the wall features that enclose the kitchen, living room, bedroom, bathroom, balcony, and other functional areas. For example, wall features include one or more of walls, windows, doors, fences, and screens. Currently, with the rapid development and maturity of artificial intelligence (AI), AI technology has also been introduced into the process of feature recognition of floor plans. A trained AI model (e.g., the yolov8 model) is used to perform graphic recognition on the floor plan to accurately identify and extract wall features such as walls, windows, doors, fences, and screens within the floor plan. The process of training an AI model is a relatively mature prior art and will not be described in detail here.

[0069] The functional area wall processing method of the floor plan of the present application is run in the functional area wall processing system of the floor plan, and the functional area wall processing system of the floor plan includes: a central processing unit module, a memory module, an artificial intelligence chip module, a communication module, a power supply module, etc., through a printed circuit board (PCB) The above modules are connected to a computer PCB (PCB) to obtain a functional area wall processing system for the floor plan; wherein the central processing unit is mainly used to comprehensively dispatch the various component modules connected to it to implement the functional area wall processing method for the floor plan mentioned in this embodiment; the power module is mainly used to provide a suitable operating voltage to the central processing unit module, the memory module, the artificial intelligence chip module, the communication module, etc. The power module can be powered by a built-in battery or a mains power supply mode, and the power source of the power module is not limited here; the memory module mainly stores a program for implementing the relevant steps of this embodiment, and the memory also stores a preset trained artificial intelligence model, which can recognize wall features of the original floor plan; the artificial intelligence chip module is used to quickly load and run the artificial intelligence model stored in the memory module, and perform wall feature recognition and analysis on the original floor plan, and obtain the desired recognition and analysis results (for example, a wall feature map for wall feature recognition of the original floor plan) and store them in the memory module; the communication module is mainly used to communicate with the outside world (mobile phones, tablets, computers and other electronic devices) (for example, obtaining floor plans, outputting reminder information, etc.).

[0070] Based on the above understanding, please refer to Figure 1 An embodiment of the method for processing the walls of the functional areas of the floor plan of the present application includes:

[0071] 101. Obtain wall features of a target floor plan. The target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model. The wall features are features of the same wall type as in the target floor plan.

[0072] It should be noted that the target floor plan in this step is the wall feature map obtained by the artificial intelligence model to identify the wall features of the original floor plan. Figure 6 As shown, the target floor plan is as follows Figure 7 As shown, the first color (gray) part of the target floor plan is the mark of the wall recognized by the artificial intelligence model from the original floor plan, the second color (orange) part of the target floor plan is the mark of the window recognized by the artificial intelligence model from the original floor plan, the third color (white) part of the target floor plan is the mark of the door recognized by the artificial intelligence model from the original floor plan, and the fourth color (green) part of the target floor plan is the mark of the sliding door recognized by the artificial intelligence model from the original floor plan; for example Figure 7 The target floor plan shown is from Figure 6The wall feature map obtained by wall feature recognition of the original floor plan, Figure 7 The target floor plan shown is missing the wall feature M of the balcony in the upper left corner. This is only used as an example. In the actual process of using an artificial intelligence model to identify wall features of the original floor plan, the missing wall features may be one or more of walls, windows, doors, fences (fences), screens, etc. In this embodiment, the wall features obtained in the target floor plan should refer to the same wall type features among walls, windows, doors, fences, screens, etc., that is, the same color identification type (for example, gray walls, orange windows, white doors, green sliding doors, etc.) identified by the artificial intelligence model from the original floor plan.

[0073] 102. Calculate the average color value of the pixel blocks at the corresponding positions of the wall features in the original floor plan to obtain the target color value.

[0074] It can be understood that this embodiment is to identify all wall features from the original floor plan. Therefore, under the premise that the wall features of the target floor plan obtained in step 101 are missing, in order to further accurately identify the missing wall features from the original floor plan, this step needs to identify the missing wall features in the original floor plan (for example, Figure 6 ) in the wall feature (such as a wall, window, door, fence, screen, etc.) is averaged to obtain the target color value. Figure 6 In the original floor plan, the color value of the white pixel block corresponding to the wall feature (this embodiment uses the white color value of the wall as an example for illustration; the color value corresponding to the wall in other floor plans can also be other colors) is (255, 255, 255) in the RGB color mode. Some white pixel blocks may also have color values of (245, 245, 245) in the RGB color mode. That is, the color values of the white pixel blocks on the wall in the original floor plan are displayed differently. To improve the accuracy of identifying the wall feature as a wall, the color values of the pixel blocks that have been identified as part of the wall in the original floor plan are averaged. For example, the color value of the white pixel blocks on the wall is obtained as (250, 250, 250) in the RGB color mode, striving to balance recognition accuracy and comprehensiveness. Of course, if the color values of the white pixel blocks on the wall in the original floor plan are consistent in the RGB color mode, the target color value obtained after the average calculation in this step is still its original color value.

[0075] 103. Identify the pixel blocks falling into the target color value in the original floor plan to obtain identification features.

[0076] Specifically, this embodiment can directly identify the pixel blocks in the original floor plan using the target color value to obtain identification features. For relatively standard original floor plans, the color values of wall features of the same type are the same. Even if the average of the color values is calculated in step 102, it is equal to the original value of the color value. The wall features missing from the target floor plan can be directly identified and included in the identification features. However, for some original floor plans that are not very standard, in order to improve the adaptability of the embodiment of the present application, this embodiment can use the target color value as the middle value to determine the target color range value. For example, the target color value in the RGB color mode is (250, 250, 250) as the middle value, and the difference between the front and back is 5 values (set according to actual needs, or 10 values, etc.) as the fault tolerance range. All white pixel blocks in the original floor plan that fall within the range of (245, 245, 245) to (255, 255, 255) in the RGB color mode are identified to obtain identification features, and strive to identify the wall features missing from the target floor plan from the original floor plan and include them in the identification features.

[0077] 104. Perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature.

[0078] It is understandable that since the wall feature recognition in step 101 is assumed to be accurate, only the missing Figure 6 The wall on the upper left corner of the balcony in the original floor plan, Figure 6 The color value of the wall in the upper left corner of the balcony in the original floor plan is the same as or not much different from the color values of other walls; then the recognition features in step 103 will include all the wall features in step 101, of course, it may also include Figure 6 Other non-wall features in the original floor plan that meet the target color value (or fall within the target color value range) (such as Figure 6 (e.g., white fonts in the original floor plan, item N in the restaurant, etc.) Assume that the recognition features in step 103 have been included. Figure 6 All walls including the wall at the upper left corner of the balcony in the original floor plan are identified, and the intersection operation in this step obtains the wall features in step 101.

[0079] 105. Perform a difference operation on the recognition feature and the wall feature to obtain the difference feature.

[0080] For example, the difference feature of this step can be obtained Figure 6 Other non-wall features in the original floor plan that meet the target color value (or fall within the target color value range) (such as Figure 6 White fonts in the original floor plan, item N in the restaurant, etc.), and Figure 6 The wall in the upper left corner of the balcony in the original floor plan.

[0081] 106. Determine the target difference feature that is in direct contact with the intersection feature in the difference feature.

[0082] It is understandable that other non-wall features (such as Figure 6 The white font in the original floor plan, the item N in the restaurant, etc.) usually do not have direct contact with the wall feature in the intersection feature. The target difference feature that is in direct contact with the intersection feature is determined in the difference feature, that is, the target difference feature can be filtered out from the difference feature. Figure 6 The wall features corresponding to the wall in the upper left corner of the balcony in the original floor plan.

[0083] 107. Add the target difference set features to the wall features to obtain the new wall features of the target floor plan.

[0084] Specifically, the step 106 is obtained Figure 6 The wall features corresponding to the wall in the upper left corner of the balcony in the original floor plan are added to the wall features in step 101, so that the missing parts of the wall feature recognition of the functional area in the floor plan can be completed when the artificial intelligence model accurately recognizes the wall features in the original floor plan.

[0085] See also Figure 2 An embodiment of the method for processing the walls of the functional areas of the floor plan of the present application includes:

[0086] 201. Obtain wall features of a target floor plan. The target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model. The wall features are features of the same wall type in the target floor plan.

[0087] The execution of this step is the same as the above Figure 1 The execution of step 101 in the embodiment is similar and will not be repeated here.

[0088] 202. Calculate the average color value of the pixel blocks at the corresponding positions of the wall features in the original floor plan to obtain the target color value.

[0089] The execution of this step is the same as the above Figure 1 The execution of step 102 in the embodiment is similar and will not be repeated here.

[0090] It is understandable that in order to determine the corresponding position of the wall feature in the original floor plan, only the wall feature in the target floor plan can be displayed. For example, if the wall feature only refers to the wall, then only the first color (gray) part of the target floor plan is displayed, such as Figure 8 As shown, then Figure 8 The shape of the first color (gray) part is shown Figure 6 The wall feature matching and recognition of the original floor plan shown in Figure 8The first color (gray) part shown is the same as Figure 6 When the wall features of the original floor plan are matched successfully, the shape of the first color (gray) part is Figure 6 The intersecting portion of the wall features in the original floor plan is the so-called "corresponding position of the wall features determined in the original floor plan."

[0091] 203. Identify pixel blocks falling into the target color value in the original floor plan to obtain identification features.

[0092] The execution of this step is the same as the above Figure 1 The execution of step 103 in the embodiment is similar and will not be repeated here.

[0093] 204. Perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature.

[0094] The execution of this step is the same as the above Figure 1 The execution of step 104 in the embodiment is similar and will not be repeated here.

[0095] 205. Determine whether the intersection feature is empty. If the intersection feature is empty, execute step 201; if the intersection feature is not empty, execute step 206.

[0096] It can be understood that this step is used to verify the accuracy of the recognition feature. Assuming that the wall feature recognition in step 101 is accurate, the recognition feature in step 203 should include some or all of the wall features in step 201, that is, the intersection feature obtained by performing the intersection operation of the recognition feature and the wall feature is not empty; if the intersection feature is empty, it proves that the recognition feature obtained by step 203 has too large a deviation, and the target color value needs to be adjusted to re-identify the original floor plan; if the intersection feature is not empty, it proves that the recognition feature obtained by step 203 is acceptable and can be ignored.

[0097] 206. Ignore.

[0098] 207. Perform a difference operation on the recognition feature and the wall feature to obtain a difference feature.

[0099] The execution of this step is the same as the above Figure 1 The execution of step 105 in the embodiment is similar and will not be repeated here.

[0100] 208. Determine whether the difference set feature is empty. If the difference set feature is empty, execute step 209; if the difference set feature is not empty, execute step 210.

[0101] It can be understood that this step is used to verify the comprehensiveness of the identification features. Assuming that the wall feature identification in step 101 is one-sided and does not fully identify the wall features in the original floor plan, then the identification features in step 203 should include other identification features not included in step 201, that is, the difference feature obtained by performing a difference operation between the identification feature and the wall feature is not empty; if the difference feature is empty, it proves that the wall features of the target floor plan are not missing; if the difference feature is not empty, it proves that the wall features of the target floor plan are missing.

[0102] 209. Ensure that the wall features of the target floor plan are intact and issue a reminder that the walls of the functional area are intact.

[0103] When step 208 determines that the wall features of the target floor plan are not missing, there is no need to execute the functional area wall processing solution of the floor plan of this embodiment, and a reminder that the functional area walls are not missing is issued so that the user can stop the execution of the solution of this embodiment in time.

[0104] 210. Determine that the wall features of the target floor plan are in a missing state, and issue a missing wall reminder for the functional area.

[0105] When step 208 determines that the wall feature of the target floor plan is in a wall missing state, it is necessary to execute the functional area wall processing solution of the floor plan of this embodiment, and issue a reminder that the functional area wall is missing so that the user does not prevent the execution of the solution of this embodiment, for example, the user triggers the continuation of step 211.

[0106] 211. Determine the target difference feature that is in direct contact with the intersection feature in the difference feature.

[0107] The execution of this step is the same as the above Figure 1 The execution of step 106 in the embodiment is similar and will not be repeated here.

[0108] In another embodiment, this step can further determine whether the target difference set feature is empty. If the target difference set feature is empty, it proves that the missing feature screening of the wall feature is wrong, resulting in the loss of the missing feature, and reminds the user to pre-process the original floor plan. The pre-processing includes: manually marking the wall features that are missing in the target floor plan in the original floor plan with the other identified wall features using the same color value as the identified wall features to connect and contact them; and marking and isolating the non-wall features in the original floor plan with the same color value as the identified wall features with other color values; so as to improve the recognition accuracy of this embodiment.

[0109] 212. Add the target difference set features to the wall features to obtain the new wall features of the target floor plan.

[0110] The execution of this step is the same as the above Figure 1 The execution of step 107 in the embodiment is similar and will not be repeated here. This embodiment is a remedy for the lack of wall features recognized by the artificial intelligence model in the original floor plan, which can effectively make up for the shortcomings of the artificial intelligence model in recognizing accuracy and comprehensiveness.

[0111] 213. Identify and segment the functional areas of the target floor plan based on the new wall features to obtain a floor plan functional area segmentation diagram.

[0112] After the wall features of the original floor plan are accurately and comprehensively identified and completed in step 212, a wall feature map corresponding to the original floor plan can be obtained, such as Figure 9 This embodiment can further identify and segment the target floor plan based on the new wall features to obtain a floor plan segmentation diagram. Figure 9 Based on the above, the independent spaces in the floor plan can be identified, such as the kitchen, living room, bedroom, bathroom, balcony and other functional areas. This step can be achieved using a trained artificial intelligence model and will not be described in detail here.

[0113] The above describes the embodiment of the method for processing the wall of the functional area of the floor plan of this application. The following describes the device for processing the wall of the functional area of the floor plan of this application. Please refer to Figure 3 An embodiment of the functional area wall processing device of the floor plan of the present application includes:

[0114] An acquisition unit 301 is configured to acquire wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan;

[0115] A calculation unit 302 is configured to calculate the average color value of the pixel blocks at the positions corresponding to the wall features in the original floor plan to obtain a target color value;

[0116] The recognition unit 303 is configured to recognize pixel blocks in the original floor plan that fall within the target color value to obtain recognition features;

[0117] The calculation unit 302 is further configured to perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature;

[0118] The calculation unit 302 is further configured to perform a difference operation on the recognition feature and the wall feature to obtain a difference feature;

[0119] A determining unit 304 is configured to determine, from the difference features, a target difference feature that is in direct contact with the intersection feature;

[0120] The supplementing unit 305 is configured to supplement the target difference set features into the wall features to obtain new wall features of the target floor plan.

[0121] The operation performed by the functional area wall processing device of the floor plan of this application is the same as the above Figure 1 The operations described in the embodiment are similar and will not be repeated here.

[0122] See also Figure 4 Another embodiment of the functional area wall processing device of the floor plan of the present application includes:

[0123] An acquisition unit 401 is configured to acquire wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan;

[0124] A calculation unit 402 is configured to calculate the average color value of the pixel blocks at the positions corresponding to the wall features in the original floor plan to obtain a target color value;

[0125] The recognition unit 403 is configured to recognize pixel blocks in the original floor plan that fall within the target color value to obtain recognition features;

[0126] The calculation unit 402 is further configured to perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature;

[0127] The calculation unit 402 is further configured to perform a difference operation on the recognition feature and the wall feature to obtain a difference feature;

[0128] A determining unit 404 is configured to determine, from the difference features, a target difference feature that is in direct contact with the intersection feature;

[0129] The supplementing unit 405 is configured to supplement the target difference set features into the wall features to obtain new wall features of the target floor plan.

[0130] Optionally, the recognition unit 403 recognizes pixel blocks in the original floor plan that fall within the target color value, and obtains recognition features, which are specifically used to:

[0131] Determine the target color range value with the target color value as the middle value;

[0132] The pixel blocks in the original floor plan that fall within the target color range are identified to obtain the identification features.

[0133] Optionally, the device further includes:

[0134] A judging unit 406 is used to judge whether the intersection feature is empty;

[0135] An execution unit 407 is configured to execute a step of obtaining wall features of a target floor plan if the intersection feature is empty;

[0136] The ignoring unit 408 is configured to ignore the intersection feature if it is not empty.

[0137] Optionally, the device further includes:

[0138] The judging unit 406 is configured to judge whether the target difference set feature is empty;

[0139] The reminder unit 409 is configured to determine that the wall feature of the target floor plan is in a non-missing state if the target difference set feature is empty, and issue a reminder that the functional area wall is not missing;

[0140] The reminder unit 409 is further configured to, if the target difference set feature is not empty, determine that the wall feature of the target floor plan is in a wall missing state, and issue a reminder indicating that a functional area wall is missing.

[0141] Optionally, the device further includes:

[0142] The segmentation unit 410 is configured to identify and segment the target floor plan into functional areas according to the new wall features, thereby obtaining a floor plan functional area segmentation diagram.

[0143] Optionally, the wall features include: one or more of walls, windows, doors, fences, and screens.

[0144] The operation performed by the functional area wall processing device of the floor plan of this application is the same as the above Figure 2 The operations described in the embodiment are similar and will not be repeated here.

[0145] The computer device in the embodiment of the present application is described below. Figure 5 , an embodiment of the computer device in the embodiment of the present application includes:

[0146] The computer device 500 may include one or more processors (central processing units, CPU) 501 and a memory 502, in which one or more applications or data are stored. The memory 502 is a volatile storage or a 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 in the computer device. Furthermore, 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 also include: one or more network interfaces 503, one or more input and output interfaces 504, and / or one or more operating systems, such as HarmonyOS, Windows Server, Mac OS, Unix, Linux, FreeBSD, etc. The processor 501 may execute the aforementioned Figure 1 ,to Figure 2 The operations performed in any of the illustrated embodiments will not be described in detail here.

[0147] In the several embodiments provided in the embodiments of the present application, those skilled in the art should understand that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the unit is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0148] In addition, the functional units in the various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically separately, 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 this understanding, the technical solution of the present application is essentially 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, which 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 of the various embodiments of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0149] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements or improvements made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A method for processing the walls of functional areas of a floor plan, characterized in that: include: Obtaining wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan; Calculate the average color value of the pixel blocks at the corresponding positions of the wall features in the original floor plan to obtain a target color value; Identify pixel blocks in the original floor plan that fall within the target color value to obtain identification features; Performing an intersection operation on the recognition feature and the wall feature to obtain an intersection feature; Performing a difference operation on the recognition feature and the wall feature to obtain a difference feature; Determining a target difference feature that is in direct contact with the intersection feature from among the difference features; The target difference set features are added to the wall features to obtain new wall features of the target floor plan.

2. The method for processing the functional area walls of a floor plan according to claim 1, characterized in that: Identify the pixel blocks in the original floor plan that fall within the target color value, and obtain the identification features including: Determine the target color range value with the target color value as the middle value; The pixel blocks in the original floor plan that fall within the target color range are identified to obtain the identification features.

3. The method for processing walls in functional areas of a floor plan according to claim 1, characterized in that: After obtaining the intersection feature and before determining the target difference feature that is in direct contact with the intersection feature in the recognition feature, the method further includes: Determine whether the intersection feature is empty; If the intersection feature is empty, then executing the step of obtaining the wall feature of the target floor plan; If the intersection feature is not empty, it is ignored.

4. The method for processing walls in functional areas of a floor plan according to claim 1, characterized in that: After determining, in the identification features, a target difference feature that is in direct contact with the intersection feature, the method further includes: Determine whether the target difference set feature is empty; If the target difference set feature is empty, it is determined that the wall feature of the target floor plan is in a non-missing state, and a reminder is issued that the functional area wall is not missing; If the target difference set feature is not empty, it is determined that the wall feature of the target floor plan is in a wall missing state, and a reminder of missing walls in the functional area is issued.

5. The method for processing walls in functional areas of a floor plan according to claim 1, characterized in that: The method further comprises: Functional area identification and segmentation are performed on the target floor plan according to the new wall features to obtain a floor plan functional area segmentation diagram.

6. The method for processing walls in functional areas of a floor plan according to claim 1, characterized in that: The wall features include: one or more of walls, windows, doors, railings, and screens.

7. A device for processing the wall of a functional area of a floor plan, characterized in that: include: an acquisition unit, configured to acquire wall features of a target floor plan, wherein the target floor plan is a wall feature map obtained by performing wall feature recognition on an original floor plan using an artificial intelligence model, and the wall features are features of the same wall type in the target floor plan; A calculation unit, configured to calculate the average color value of the pixel blocks at the positions corresponding to the wall features in the original floor plan to obtain a target color value; An identification unit, configured to identify pixel blocks in the original floor plan that fall within the target color value to obtain identification features; The calculation unit is further configured to perform an intersection operation on the recognition feature and the wall feature to obtain an intersection feature; The calculation unit is further configured to perform a difference operation on the recognition feature and the wall feature to obtain a difference feature; a determining unit, configured to determine, from the difference features, a target difference feature that is in direct contact with the intersection feature; A supplementing unit is used to supplement the target difference set features into the wall features to obtain new wall features of the target floor plan.

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 the functional area walls of the floor plan 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 functional area wall processing method of the floor plan 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 functional area wall processing method of the floor plan according to any one of claims 1 to 6.

Images