Method, apparatus, electronic device and storage medium for constructing a home decoration design knowledge graph

Abstract

An embodiment of the present application provides a method, device, electronic device, and storage medium for constructing a home decoration design knowledge graph, which relates to the technical field of home decoration. The method includes obtaining a top view of existing design data; identifying the top view to obtain spatial data; using a preset target detection algorithm to identify the object categories and coordinates in the top view, as well as the positional relationships between objects; formatting and storing the positional relationship data and the spatial data to generate the knowledge graph, obtaining the spatial types, areas, and shapes in a large number of existing design schemes, the types, position coordinates of furniture, and the positional relationships between furniture, thereby realizing the construction of the knowledge graph, with a wider range of use, and solving the problem of large limitations in existing methods.

Description

Technical Field

[0001] This application relates to the field of home improvement technologies, and more particularly, to a method, apparatus, electronic device, and storage medium for constructing a knowledge graph of home improvement design. Background Art

[0002] The existing home improvement knowledge graph is based on crawling some home improvement knowledge on the Internet. This knowledge is relatively scattered, without systematicness and logic, and there is no systematic knowledge construction for the layout of furniture positions and the style and color matching between furniture in home improvement design, having great limitations. Summary of the Invention

[0003] The purpose of the embodiments of this application is to provide a method, apparatus, electronic device, and storage medium for constructing a knowledge graph of home improvement design, which can obtain the space type, area, and shape in a large number of existing design schemes, the type, position coordinates of furniture, and the positional relationship between furniture, so as to realize the construction of the knowledge graph, with a wider range of use, and solve the problem of great limitations in existing methods.

[0004] The embodiments of this application provide a method for constructing a knowledge graph of home improvement design, and the method includes:

[0005] Obtain a top view of existing design data;

[0006] Identify the top view to obtain spatial data;

[0007] Use a preset object detection algorithm to identify the object categories and coordinates in the top view, as well as the positional relationship between objects;

[0008] Format and store the positional relationship data and the spatial data to generate the knowledge graph.

[0009] In the above implementation process, since a lot of professional design concepts are included in the existing design schemes, as well as which furniture needs to be arranged in each space and the relative layout relationship between furniture, and the style matching relationship between furniture, a large number of existing design schemes can be used to obtain the space type, area, and shape therein, the type, position coordinates of furniture, and the positional relationship between furniture, so as to realize the construction of the knowledge graph, with a wider range of use, and solve the problem of great limitations in existing methods.

[0010] Further, the identifying the top view to obtain spatial data includes:

[0011] Use an object detection algorithm to frame the space name and area in the top view;

[0012] Use an optical character recognition algorithm to recognize the text corresponding to the space name and area to obtain the category and area of the space.

[0013] In the above implementation process, the top view of the apartment layout is recognized to obtain the category and area data of the space.

[0014] Further, the recognition of the object categories and coordinates in the top view by using the preset object detection algorithm includes:

[0015] Using the pre-trained open-source yolo-v5 algorithm to recognize the top view to obtain the categories of walls, doors, windows and various furniture and the corresponding rectangular box coordinates.

[0016] In the above implementation process, the open-source yolo-v5 algorithm can be used to recognize the categories of walls, doors, windows and various furniture and the corresponding rectangular box coordinates.

[0017] Further, the recognition of the positional relationship between objects in the top view by using the preset object detection algorithm includes:

[0018] Calculating the orientation of the wall using the rectangular box coordinates of the wall;

[0019] Based on the orientation of the wall, calculating the relationship between the wall and the furniture and the orientation of the furniture;

[0020] Calculating the positional relationship and orientation between furniture using the orientation of the furniture and the rectangular box coordinates of the furniture.

[0021] In the above implementation process, the orientation of the wall and the orientation of the furniture and the positional relationship between various objects can be calculated using the rectangular box coordinates of the wall.

[0022] Further, the calculation of the orientation of the wall using the rectangular box coordinates of the wall includes:

[0023] Based on the rectangular box coordinates, obtaining the four coordinates of the wall, which are (x1, y1), (x2, y2), (x3, y3), (x4, y4) respectively;

[0024] Obtaining the end coordinates at both ends of the wall, and the end coordinates are expressed as [(x1, y1), (x2, y2)] and [(x3, y3), (x4, y4)];

[0025] Calculating the center line coordinates [(a1, b1), (a2, b2)] of the wall based on the end coordinates;

[0026] where, a1 = (x1 + x2) / 2, b1 = (y1 + y2) / 2;

[0027] a2 = (x3 + x4) / 2, b2 = (y3 + y4) / 2;

[0028] Calculate the minimum distance of each end coordinate, and obtain the coordinates corresponding to the walls connected end to end to generate a closed wall polygon;

[0029] Obtain the center point coordinates of the minimum circumscribed rectangle of the wall polygon;

[0030] Compare the center point coordinate values with the center line coordinate values to determine the orientation of the wall.

[0031] In the above implementation process, the center point coordinate values and the center line coordinate values are obtained using the rectangle frame coordinates, so that the orientation of the wall can be determined by comparing the magnitudes.

[0032] Further, the comparing the center point coordinate values with the center line coordinate values to determine the orientation of the wall includes:

[0033] If a1 = a2, the wall is vertical;

[0034] If a1 < x, the orientation of the wall is to the right;

[0035] If a1 > x, the wall faces left;

[0036] If b1 = b2, the wall is horizontal;

[0037] If b1 < y, the wall faces up;

[0038] If b1 > y, the wall faces down.

[0039] In the above implementation process, the orientation of the wall such as left, right, horizontal and vertical can be determined by comparing the center point coordinate values with the center line coordinate values.

[0040] The embodiment of the present application also provides a device for constructing a home improvement design knowledge graph, and the device includes:

[0041] A data acquisition module for acquiring the top view of the existing design data;

[0042] A first recognition module for recognizing the top view to obtain spatial data;

[0043] A second recognition module for using a preset target detection algorithm to recognize the object categories and coordinates in the top view, as well as the positional relationships between objects;

[0044] A storage module for formatting and storing the positional relationship data and the spatial data to generate the knowledge graph.

[0045] In the above implementation process, since the existing design solutions include many professional design concepts, as well as which furniture needs to be arranged in each space, the relative arrangement relationship between the furniture, and the style matching relationship between the furniture, a large number of existing design solutions can be utilized to obtain the space type, area, and shape, the type of furniture, the position coordinates, and the positional relationship between the furniture, thereby realizing the construction of the knowledge graph, with a wider range of applications and solving the problem of large limitations in existing methods.

[0046] Further, the first recognition module includes:

[0047] A space recognition module, configured to use an object detection algorithm to frame the space name and area in the top view;

[0048] A text recognition module, configured to use an optical character recognition algorithm to recognize the text corresponding to the space name and area, so as to obtain the category and area of the space.

[0049] In the above implementation process, the top view of the house type drawing is recognized to obtain the category and area data of the space.

[0050] The embodiment of the present application further provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the computer device to execute the above-mentioned method for constructing a home decoration design knowledge graph.

[0051] The embodiment of the present application further provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the above-mentioned method for constructing a home decoration design knowledge graph is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments of the present application. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0053] Figure 1 It is a flowchart of a method for constructing a home decoration design knowledge graph provided by an embodiment of the present application;

[0054] Figure 2 It is a flowchart of constructing a home decoration design knowledge graph provided by an embodiment of the present application;

[0055] Figure 3 It is a schematic diagram of the specific process of obtaining space data provided by an embodiment of the present application;

[0056] Figure 4 Schematic diagram of the recognition result of the household type space provided by the embodiment of the present application;

[0057] Figure 5 Flow chart of the recognition of the positional relationship between objects provided by the embodiment of the present application;

[0058] Figure 6 Flow chart of the calculation of the wall orientation provided by the embodiment of the present application;

[0059] Figure 7 Schematic diagram of the four coordinates of the wall provided by the embodiment of the present application;

[0060] Figure 8 Schematic diagram of the bed and bedside table recognized by the target detection provided by the embodiment of the present application;

[0061] Figure 9 Structure block diagram of a device for constructing a home improvement design knowledge graph provided by the embodiment of the present application;

[0062] Figure 10 Structure block diagram of another device for constructing a home improvement design knowledge graph provided by the embodiment of the present application.

[0063] Icon:

[0064] 100 - Data acquisition module; 200 - First recognition module; 201 - Space recognition module; 202 - Character recognition module; 300 - Second recognition module; 301 - Wall orientation calculation module; 302 - Furniture orientation calculation module; 303 - Positional relationship calculation module; 400 - Storage module. Detailed implementation manners

[0065] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings in the embodiments of the present application.

[0066] It should be noted that: similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0067] Please refer to Figure 1 , Figure 1The flowchart of a method for constructing a home improvement design knowledge graph provided by an embodiment of this application. A large number of designed indoor decoration design schemes have been accumulated on existing design platforms or the Internet. These schemes include space types, areas, and shapes, types of furniture, position coordinates, and the positional relationships between furniture. By extracting and formatting this information, a home improvement design knowledge graph can be generated, and the coverage is more extensive, meeting the personalized needs of different users.

[0068] As Figure 2 shown, it is the flowchart for constructing a home improvement design knowledge graph. The method specifically includes the following steps:

[0069] Step S100: Obtain the top view of the existing design data;

[0070] Step S200: Identify the top view to obtain spatial data;

[0071] Among them, as Figure 3 shown, it is the schematic diagram of the specific process for obtaining spatial data. Specifically:

[0072] Step S201: Use the target detection algorithm to frame the space name and area in the top view;

[0073] Step S202: Use the text recognition algorithm to recognize the text corresponding to the space name and area to obtain the category and area of the space.

[0074] Exemplarily, the space name and area text are framed by the target detection algorithm, and then the text recognition algorithm is used to recognize the category and area of the current space. For example: Bedroom, 20.48m 2 As Figure 4 shown, it is the schematic diagram of the recognition result of the house type space.

[0075] Among them, the target detection algorithm can use the pre-trained open-source yolo-v5 algorithm. The input is the top view of the design scheme obtained above, and the output is the rectangular box coordinates of the house type space name and area text, and then the framed picture is cropped.

[0076] The text recognition algorithm is not limited here. For example, because the space name and area text are relatively simple, the open OCR recognition interface of Baidu can be directly used. The input is the picture containing the space name and area text cropped above, and the output is the corresponding space name and area text.

[0077] Step S300: Use a preset target detection algorithm to recognize the object categories and coordinates in the top view, as well as the positional relationships between objects;

[0078] Specifically:

[0079] The top view is recognized using the pre-trained open-source YOLO-v5 algorithm to obtain the categories of walls, doors, windows, and various furniture, as well as the corresponding rectangular box coordinates.

[0080] As Figure 5 shown, it is a flowchart for recognizing the positional relationship between objects. Specifically:

[0081] Step S310: Calculate the orientation of the wall using the rectangular box coordinates of the wall;

[0082] Among them, as Figure 6 shown, it is a flowchart for calculating the orientation of the wall. Step S310 specifically includes:

[0083] Step S311: Based on the rectangular box coordinates, obtain the four coordinates of the wall, which are (x1, y1), (x2, y2), (x3, y3), and (x4, y4) respectively;

[0084] Step S312: Obtain the end coordinates at both ends of the wall. The end coordinates are expressed as [(x1, y1), (x2, y2)] and [(x3, y3), (x4, y4)];

[0085] Step S313: Calculate the center line coordinates [(a1, b1), (a2, b2)] of the wall based on the end coordinates;

[0086] Among them, a1 = (x1 + x2) / 2, b1 = (y1 + y2) / 2;

[0087] a2 = (x3 + x4) / 2, b2 = (y3 + y4) / 2;

[0088] Step S314: Calculate the minimum distance of each end coordinate and obtain the coordinates corresponding to the walls connected end to end to generate a closed wall polygon;

[0089] Step S315: Obtain the center point coordinates (x, y) of the minimum circumscribed rectangle of the wall polygon;

[0090] Step S316: Compare the magnitudes of the center point coordinate values and the center line coordinate values to determine the orientation of the wall.

[0091] If a1 = a2, the wall is vertical;

[0092] If a1 < x, the orientation of the wall is to the right;

[0093] If a1 > x, the wall faces left;

[0094] If b1 = b2, the wall is horizontal;

[0095] If b1 < y, the wall faces up;

[0096] If b1 > y, then the wall faces downward.

[0097] Specifically, first calculate the orientation of the wall: Define four orientations: up, down, left, and right. The y-axis coordinate is positive upward, and the x-axis coordinate is positive to the right. For the wall coordinates identified in step S300, since the coordinates of each wall are independent and it is possible that the coordinates of adjacent walls do not connect end to end, post-processing of the coordinates is required to make all the wall coordinates form a closed frame. First, take out the four coordinates of each identified wall. As Figure 7 shown, it is a schematic diagram of the four coordinates of the wall. According to the slender characteristics of the wall, the coordinates of the two ends of the wall [(x1, y1), (x2, y2)] and [(x3, y3), (x4, y4)] can be obtained, and then the centerline coordinates [(a1, b1), (a2, b2)] of the wall are calculated as follows:

[0098] a1 = (x1 + x2) / 2, b1 = (y1 + y2) / 2;

[0099] a2 = (x3 + x4) / 2, b2 = (y3 + y4) / 2;

[0100] Calculate the centerline coordinates of other walls in the same way, and then calculate the minimum distance between the coordinates of each end point according to these coordinates. The coordinates of the walls connected end to end form a closed wall polygon. Use the minAreaRect method of opencv to obtain the center point coordinates (x, y) of the minimum circumscribed rectangle of the wall polygon. Since most walls are horizontal and vertical, when a1 = a2, it is vertical; when a1 < x, the orientation of the wall is to the right; when a1 > x, the wall faces left; when b1 = b2, it is horizontal; when b1 < y, the wall faces upward; when b1 > y, then the wall faces downward.

[0101] Step S320: Based on the orientation of the wall, calculate the relationship between the wall and the furniture and the orientation of the furniture;

[0102] Calculate the relationship between the wall and the furniture and the orientation of the furniture: Define that when the wall rectangle and the furniture rectangle intersect, it is the furniture against the wall relationship, and the orientation of the furniture is the same as that of the wall. To calculate whether the polygons intersect, the calculation can be performed using polygon1.intersects(polygon2) of the open-source shapely library.

[0103] Step S330: Use the orientation of the furniture and the rectangular frame coordinates of the furniture to calculate the positional relationship and orientation between the furniture.

[0104] Based on the category and rectangular coordinate information identified in the above steps, the positional relationship between two categories can be calculated, such as Figure 8As shown, it is a schematic diagram of a bed and a bedside table detected and recognized by object detection. Calculate the distance between one side of the bedside table [(x21, y21), (x24, y24)] and one side of the bed [(x12, y12), (x13, y13)]. We define that when the distance is less than 20 mm, it is an adjacent relationship.

[0105] Step S400: Format and store the position relationship data and the spatial data to generate the knowledge graph.

[0106] Format the data and store it in a graph database, such as the Neo4j graph database.

[0107] By obtaining the spatial types, areas, and shapes in a large number of existing design solutions, the types of furniture, the position coordinates of the furniture, and the position relationships between the furniture, the construction of the knowledge graph is realized, with a wider range of applications, and the problem of large limitations in existing methods is solved.

[0108] The embodiment of the present application also provides a device for constructing a home improvement design knowledge graph, as Figure 9 shown, which is a structural block diagram of the device for constructing a home improvement design knowledge graph. The device includes:

[0109] A data acquisition module 100, configured to acquire a top view of existing design data;

[0110] A first recognition module 200, configured to recognize the top view to obtain spatial data;

[0111] A second recognition module 300, configured to use a preset object detection algorithm to recognize the object categories and coordinates in the top view, as well as the position relationships between the objects;

[0112] A storage module 400, configured to format and store the position relationship data and the spatial data to generate the knowledge graph.

[0113] As Figure 10 shown, which is a structural block diagram of another device for constructing a home improvement design knowledge graph. Among them, the first recognition module 200 includes:

[0114] A space recognition module 201, configured to use an object detection algorithm to frame the space name and area in the top view;

[0115] A text recognition module 202, configured to use a text recognition algorithm to recognize the text corresponding to the space name and area to obtain the category and area of the space.

[0116] The second recognition module 300 includes:

[0117] A wall orientation calculation module 301, configured to calculate the orientation of the wall using the rectangular frame coordinates of the wall;

[0118] A furniture orientation calculation module 302, configured to calculate the relationship between a wall and furniture and the orientation of the furniture based on the orientation of the wall;

[0119] A positional relationship calculation module 303, configured to calculate the positional relationship and orientation between furniture by using the orientation of the furniture and the rectangular frame coordinates of the furniture.

[0120] For the specific calculation process, it has been specifically described in the method embodiments and will not be elaborated here.

[0121] The embodiment of the present application further provides an electronic device, which includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the computer device to execute the above-mentioned home improvement design knowledge graph construction method.

[0122] The embodiment of the present application further provides a readable storage medium, in which computer program instructions are stored. When the computer program instructions are read and run by a processor, the above-mentioned home improvement design knowledge graph construction method is executed.

[0123] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are only illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0124] In addition, in each embodiment of the present application, the various functional modules may be integrated together to form an independent part, or each module may exist alone, or two or more modules may be integrated to form an independent part.

[0125] When the above-mentioned functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This 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 described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0126] The above are only the embodiments of this application and are not used to limit the protection scope of this application. For those skilled in the art, this application can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of this application shall be included in the protection scope of this application. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0127] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by this application and should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0128] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

Claims

1. A method for constructing a home decoration design knowledge graph, characterized in that The method includes: Obtaining a top view of the existing design data; Identifying the top view to obtain spatial data. Specifically: Using an object detection algorithm to frame the spatial names and areas in the top view; Using an optical character recognition algorithm to recognize the text corresponding to the spatial names and areas to obtain the category and area of the space; Using a preset object detection algorithm to identify the object categories and coordinates in the top view, as well as the positional relationships between objects. Among them, using the preset object detection algorithm to identify the positional relationships between objects in the top view includes: Calculating the orientation of the wall using the rectangular frame coordinates of the wall; Calculating the relationship between the wall and the furniture and the orientation of the furniture based on the orientation of the wall; Calculating the positional relationships and orientations between the furniture using the orientation of the furniture and the rectangular frame coordinates of the furniture; Formatting and storing the positional relationship data and the spatial data to generate the knowledge graph.

2. The method for constructing a home improvement design knowledge graph according to claim 1, wherein The using the preset object detection algorithm to identify the object categories and coordinates in the top view includes: Using the pre-trained open-source yolo-v5 algorithm to identify the top view to obtain the categories of the wall, door, window, and each piece of furniture and the corresponding rectangular frame coordinates.

3. The method for constructing a home improvement design knowledge graph according to claim 1, wherein The calculating the orientation of the wall using the rectangular frame coordinates of the wall includes: Based on the rectangular frame coordinates, obtaining the four coordinates of the wall, which are (x1, y1), (x2, y2), (x3, y3), and (x4, y4) respectively; Obtaining the end coordinates at both ends of the wall, and the end coordinates are expressed as [(x1, y1), (x2, y2)] and [(x3, y3), (x4, y4)]; Calculating the center line coordinates [(a1, b1), (a2, b2)] of the wall based on the end coordinates; Among them, a1 = (x1 + x2) / 2, b1 = (y1 + y2) / 2; a2 = (x3 + x4) / 2, b2 = (y3 + y4) / 2; Calculating the minimum distance of each end coordinate and obtaining the coordinates corresponding to the walls connected end to end to generate a closed wall polygon; Obtaining the center point coordinates (x, y) of the minimum circumscribed rectangle of the wall polygon; Comparing the magnitude of the center point coordinate values and the center line coordinate values to determine the orientation of the wall.

4. The method for constructing a home improvement design knowledge graph according to claim 3, wherein The comparing the magnitude of the center point coordinate values and the center line coordinate values to determine the orientation of the wall includes: If a1 = a2, the wall is vertical; If a1 < x, the orientation of the wall is to the right; If a1 > x, the wall faces left; If b1 = b2, the wall is horizontal; If b1 < y, the wall faces up; If b1 > y, the wall faces down.

5. A device for constructing a home decoration design knowledge graph, characterized in that, The device includes: A data acquisition module for obtaining a top view of the existing design data; A first identification module for identifying the top view to obtain spatial data; A second identification module for using a preset object detection algorithm to identify the object categories and coordinates in the top view, as well as the positional relationships between objects. Among them, using the preset object detection algorithm to identify the positional relationships between objects in the top view includes: Calculating the orientation of the wall using the rectangular frame coordinates of the wall; Calculating the relationship between the wall and the furniture and the orientation of the furniture based on the orientation of the wall; Calculate the positional relationship and orientation between furniture using the orientation of the furniture and the rectangular frame coordinates of the furniture; A storage module for formatting and storing the positional relationship data and the spatial data to generate the knowledge graph; The first recognition module includes: A spatial recognition module for using an object detection algorithm to frame the spatial name and area in the top view; A text recognition module for using an optical character recognition algorithm to recognize the text corresponding to the spatial name and area to obtain the category and area of the space.

6. An electronic device, characterized in that, The electronic device includes a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to cause the computer device to execute the home improvement design knowledge graph construction method according to any one of claims 1 to 4.

7. A readable storage medium, characterized in that, Computer program instructions are stored in the readable storage medium. When the computer program instructions are read and run by a processor, the home improvement design knowledge graph construction method according to any one of claims 1 to 4 is executed.

Images