Application method, device and medium for matching home products based on floor plan

Abstract

The present invention discloses an application method, device and medium for matching household products based on a house plan, and relates to the field of computer technology. The method comprises: identifying the subspace category of a residential house plan and obtaining the structural data of the subspace; obtaining the household product category and the space to which the user belongs, and matching them with the subspace in the house plan, distributing multiple household products around the house plan through an algorithm, and automatically drawing a display map and returning it to the user; at the same time, judging whether all subspaces are matched with household products, and reminding the user to increase the selection through an interactive method until all subspaces are matched with household products.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method for displaying the distribution of selected household products on a floor plan to a user in a what-you-see-is-what-you-get manner. Background Art

[0002] Selecting home furnishing products such as sofas and beds is an important part of soft furnishing design. During the home furnishing product sales process, we should ensure that the home furnishing products selected by users are sufficient to meet the needs of the users, that is, we should ensure that home furnishing products have been selected for the sub-spaces (bedrooms, living rooms, etc.) in the user's house.

[0003] This process usually requires multiple confirmations and communications between the designer and the user or is completed by the user himself. It lacks timely feedback and accuracy, and is time-consuming and laborious for users in the entire home product purchasing process.

[0004] In the sales process of home furnishing products, it is necessary to help users more intuitively check whether the home furnishing products they choose meet their needs. At the same time, timely feedback should be given to users to remind them which sub-spaces in the house should continue to choose home furnishing products. Combining artificial intelligence methods to automate the entire process and add timely interaction with users can promote the sales progress of home furnishing products and enhance users' experience in purchasing home furnishing products. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides an application method, device and medium for matching household products based on a floor plan, which intuitively presents the distribution of selected household products on the floor plan to the user in a what-you-see-is-what-you-get manner.

[0006] An aspect of an embodiment of the present invention provides an application method for matching home products based on a floor plan, including: Identify the subspace category of the residential floor plan uploaded by the user and obtain the structural data of the subspace; Interactively remind users to select home products, and match subspaces in the floor plan according to the spaces and categories to which multiple home products selected by the user belong; Arrange all the household products around the floor plan through an algorithm, and connect the center point of the subspace with the center point of the household product through a broken line to generate a result display diagram; The degree of completion of the subspace matching the home furnishing products in the floor plan is determined, and the user is interactively reminded to add new home furnishing products until the degree of completion reaches 100%.

[0007] Optionally, the method further comprises the step of identifying the subspace category of the residential floor plan uploaded by the user and obtaining structural data of the subspace, the step comprising: Defining the category of the subspace in the floor plan and creating a floor plan dataset; Based on the semantic segmentation algorithm, the AI ​​model is trained using the floor plan dataset; Based on the trained AI model, the subspace category of the floor plan uploaded by the user is identified and the key structural data is extracted.

[0008] Optionally, the method further includes a step of identifying subspace categories and extracting key structural data from the floor plan uploaded by the user based on the trained AI model, the step comprising: Use the trained AI model to identify all subspace categories and segmentation result images in the floor plan uploaded by the user; Each subspace region is extracted based on the segmentation result map, and the coordinates of the center point of each subspace are obtained.

[0009] Optionally, the method further includes a step of arranging all the household products around the floor plan by an algorithm, and connecting the subspace center point and the household product center point by a broken line to generate a result display diagram, which step includes: Arranging the coordinates of the center points of all subspaces in the floor plan, and counting the subspaces in the same row and column, that is, a distribution feature of the subspaces in the floor plan; Match the subspaces corresponding to all the household products according to the categories, and obtain the number of household products in each subspace; According to the distribution characteristics of the subspace, combined with the number of home furnishing products in the subspace, and combined with an algorithm, the home furnishing products are distributed around the floor plan; Use the broken line method to connect the center point of the subspace with the corresponding center points of all home products.

[0010] Optionally, the method further includes arranging the coordinates of the center points of all subspaces in the floor plan and counting the subspaces in the same row and column, that is, a distribution feature of the subspaces in the floor plan, the step including: Based on the horizontal coordinates of the subspace, counting multiple groups of subspaces in the same or nearly same line in the subspace; Based on the ordinate of the subspace, counting a plurality of groups of subspaces in the same column or nearly in the same column in the subspace; By combining the above-mentioned subspace distribution characteristics of the same row and column, the row coordinates and column coordinates of each subspace in the floor plan are obtained, and finally a matrix distribution characteristic of the floor plan subspace is obtained.

[0011] Optionally, the method further comprises the step of distributing the household products around the floor plan according to the distribution characteristics of the subspace, the number of household products in the subspace, and an algorithm, the step comprising: Based on certain rules and algorithms, combined with the distribution characteristics of the subspaces in the floor plan, the home products in each subspace are arranged around the floor plan; Based on the rules and algorithms, the center point of the subspace and the center point of the corresponding home product are connected by a broken line method. By calculating and reasonably distributing the inflection points of the broken lines, the intersection of different broken lines and the situation where the broken line of a subspace passes through another subspace are avoided.

[0012] Another aspect of an embodiment of the present invention further provides an electronic device, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method described above.

[0013] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the method described above.

[0014] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0015] The embodiment of the present invention trains an AI model by making a house plan data set, identifies the subspace category and structural data in the house plan uploaded by the user based on the AI ​​model; interactively reminds the user to select home products, and matches the multiple home products selected by the user to the subspace in the house plan; arranges multiple home products around the house plan based on certain rules and algorithms, and designs multiple groups of broken lines with the starting point and the end point being the subspace center point and the home product center point respectively, to ensure that there is no intersection between the broken lines and that the broken lines of different subspaces do not cross each other; draws a home product distribution map in combination with the house plan and displays it to the user; at the same time, interactively reminds the user whether there is a subspace without selecting a home product, until all subspaces have selected home products. The present invention includes the identification of the subspace type and structural data of the house plan based on the AI ​​model, and more importantly, designs algorithms and rules to design how multiple home products are distributed around the house plan and connect the subspace and home products by means of a broken line graph, and displays the distribution scheme of home products in the user's house plan to the user in a WYSIWYG manner, which is a method obtained by the process processing of all steps of the present invention, and can assist users in completing the selection of home products more efficiently in the home product sales link. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 is a flowchart of the overall steps of an embodiment of the present invention; Figure 2 This is a household product distribution display example mentioned in an embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0019] By collecting common floor plans on the market, we create a floor plan dataset for semantic segmentation algorithms and train AI models. After the AI ​​model is trained, the floor plan uploaded by the user is used as input to obtain the segmentation result of the floor plan using the model, and the structural data of the category of each subspace is obtained based on the segmentation result. Remind users to select home products in an interactive way, and match the home products selected by the user to the corresponding subspace. All home products are arranged around the floor plan through algorithms and certain rules, and the center point of the subspace is connected with the center point of the home product by a broken line, and the result display diagram is generated and returned to the user for viewing. At the same time, interactively remind users to continue to select home products until all subspaces are matched with enough home products.

[0020] Specifically, this example describes an application method for matching home products based on a floor plan. The method flow chart is as follows: Figure 1 As shown. First, collect common floor plans on the market, define subspace categories, annotate floor plans to build a data set, and train AI models. Then identify the floor plans uploaded by users to obtain the categories and structural data of subspaces in the floor plans. Then interactively remind users to select multiple home products and match them with the subspaces in the floor plan. Then, based on certain rules and algorithms, distribute home products around the floor plan, connect the subspaces and home products with a line graph, draw a display graph and return it to the user, and determine whether all subspaces are matched to home products. If there is a subspace that has not matched a home product, interactively remind the user to continue selecting home products until all subspaces are matched to home products. Specifically, the following steps are included: 1. Collect common floor plans on the market, define subspace categories, annotate floor plans to build a data set, and train AI models.

[0021] I. Define the subspace categories in the floor plan as balcony, living room, dining room, kitchen, second bedroom, master bedroom, second bathroom, master bathroom, cloakroom, entrance, corridor, other areas, door, window and wall. Annotate the floor plan to create a dataset.

[0022] II. Train AI models based on semantic segmentation algorithms and datasets.

[0023] 2. Identify the floor plan uploaded by the user and obtain the category and structural data of the subspace in the floor plan.

[0024] I. Based on the trained semantic segmentation AI model, identify the floor plan uploaded by the user and obtain the segmentation result map.

[0025] II. Process the segmentation result graph to obtain the category and structure data of each subspace in the floor plan.

[0026] a. Based on the rule that different categories have different colors in the segmentation result image, the segmentation result image is converted into an HSV image, and the HSV image is processed according to the HSV values ​​of different categories in turn to obtain binary mask images of different categories.

[0027] b. Process the MASK area in the binary mask image and calculate the minimum enclosing rectangle of the area.

[0028] c. The length and width of the rectangle represent the length and width of the subspace represented by the original HSV color of the area. Calculate the coordinates of the center point of the rectangle as the coordinates of the center point of the subspace.

[0029] 3. Interactively remind users to select multiple home products and match them with subspaces in the floor plan.

[0030] I. The user selects multiple home products and collects the category and space of each home product.

[0031] II. Match each home product to the corresponding subspace according to its space, and record the number and pictures of home products that have been matched in each subspace.

[0032] 4. Based on certain rules and algorithms, the home furnishing products are distributed around the floor plan, and the subspaces and home furnishing products are connected with a line graph. A display graph is drawn and returned to the user, and at the same time, it is determined whether all subspaces are matched with home furnishing products.

[0033] I. Analyze the distribution characteristics of all subspaces and calculate the number of rows and columns of each subspace on the floor plan.

[0034] d. According to the horizontal coordinates of all subspaces, filter out subspaces that are in the same or close to the same line, and obtain multiple groups of subspaces in the same line. The specific steps are: a) The horizontal coordinate of the ith subspace is x(i), and the vertical coordinate is y(i). The rule is: the subspace with the smallest horizontal and vertical coordinates is the subspace in the upper left corner of the floor plan, and the subspace with the largest difference in horizontal and vertical coordinates is the subspace in the upper right corner of the floor plan. These two subspaces are regarded as the first and last of the first row of subspace arrangement in the floor plan.

[0035] b) Calculate the distance d from the center points of all remaining subspaces to the line segment connecting the center points of the two subspaces in step a) in turn. When d is less than the threshold we set, it can be considered that the subspace is in the same row as the two subspaces in step a).

[0036] c) After selecting all the subspaces of the first row, calculate the combination of the second row in the center points of the remaining subspaces, and so on, until the left and right subspaces are allocated according to the characteristics of the common rows.

[0037] e. Similarly, according to the ordinate of each subspace, subspaces in the same row or nearly in the same column are selected to obtain multiple groups of subspaces in the same column.

[0038] f. Combining the distribution characteristics of the subspaces in the same row and column above, calculate the number of rows and columns of each subspace in the floor plan, and get an m*n matrix, where m represents that all subspaces in the floor plan can be divided into m rows, and n represents that the subspaces in the floor plan can be divided into n columns. The row index value and column index value in the matrix represent the distribution characteristics of the subspace in the floor plan, that is, it can be summarized in the floor plan as the row and column. Not every block in the matrix has a corresponding subspace, because the distribution of subspaces in the floor plan is not saturated.

[0039] II. Based on certain rules and combined with the distribution characteristics of all subspaces, all home furnishing product images are distributed in appropriate locations on the floor plan.

[0040] g. Combining the distribution characteristics of subspaces in the floor plan, appropriate distribution rules can be summarized as follows: a) The home product images in the first row of subspaces should be distributed above the floor plan; b) The home product images in the subspace of the last row should be distributed below the floor plan; c) The home product images in the middle row of the subspace should be distributed on the left and right sides of the floor plan; d) The home product images in the subspace of the first column should be distributed on the left side of the floor plan; e) The home product images in the subspace of the last column should be distributed to the right of the floor plan; f) The home product images in the subspace of the middle column should be distributed above and below the floor plan.

[0041] h. According to the above rules, all home furnishing product images are evenly distributed around the floor plan to obtain a larger image.

[0042] III. Take the center point of the subspace as the starting point and the center point of the distributed home product image as the end point, and select the inflection point coordinates based on certain rules to draw the polyline.

[0043] i. The inflection points of the polyline are selected on the four boundaries of the larger image obtained in step II.

[0044] j. A polyline has multiple inflection points, that is, the polyline may cross multiple boundaries.

[0045] k. Based on the position of the home furnishing product image in the larger image obtained in step II, we can select which boundaries should be crossed, and ensure that the polylines do not intersect and do not cross another subspace.

[0046] 1. Finally, the broken line is drawn on the graph, and the household product distribution map is returned to the user for viewing.

[0047] 5. Determine whether all subspaces are assigned home products. If there is a subspace without home products, interactively remind the user to continue selecting home products. After the user adds a new home product, repeat step 4 until all subspaces are assigned home products.

[0048] In summary, the method of the present invention has the following characteristics: After applying this method, in the sales link of home furnishing products in soft furnishing design, the distribution plan of the selected home furnishing products on the floor plan can be interactively and automatically displayed to the user, and the types and quantities of home furnishing products in each subspace in the floor plan can be intuitively displayed, helping users to purchase home furnishing products more conveniently, greatly improving the user experience and improving the efficiency of the home furnishing product sales link.

[0049] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0050] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0051] If the functions are implemented in the form of software functional units 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 the present invention, or the part that contributes to the prior art or the 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, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0052] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0053] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0054] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0055] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0056] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0057] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. An application method for matching home products based on a floor plan, characterized in that: include: Identify the subspace category of the residential floor plan uploaded by the user and obtain the structural data of the subspace; Interactively remind users to select home products, and match subspaces in the floor plan according to the spaces and categories to which multiple home products selected by the user belong; All the household products are arranged around the floor plan by an algorithm, and the center point of the subspace is connected with the center point of the household product by a broken line to generate a result display diagram, including arranging the center point coordinates of all subspaces in the floor plan, and counting the subspaces in the same row and column, that is, a distribution feature of the subspaces in the floor plan; Matching the subspaces corresponding to all the household products according to the categories, and obtaining the number of household products in each subspace; According to the distribution characteristics of the subspace, combined with the number of home furnishing products in the subspace, and combined with an algorithm, the home furnishing products are distributed around the floor plan; Connect the center point of the subspace with the center points of all corresponding home products through the broken line method; The degree of completion of the subspace matching the home furnishing products in the floor plan is determined, and the user is interactively reminded to add new home furnishing products until the degree of completion reaches 100%.

2. The application method for matching home products based on floor plan according to claim 1, characterized in that: The identifying of the subspace category of the residential floor plan uploaded by the user and obtaining the structural data of the subspace includes: Defining the category of the subspace in the floor plan and creating a floor plan dataset; Based on the semantic segmentation algorithm, the AI ​​model is trained using the floor plan dataset; Based on the trained AI model, the subspace categories of the floor plan uploaded by the user are identified and the key structural data are extracted.

3. The application method for matching home products based on floor plan according to claim 2, characterized in that: The identifying of subspace categories and extracting key structural data of the floor plan uploaded by the user based on the trained AI model includes: Use the trained AI model to identify all subspace categories and segmentation result images in the floor plan uploaded by the user; Each subspace region is extracted based on the segmentation result map, and the coordinates of the center point of each subspace are obtained.

4. The application method for matching home products based on floor plan according to claim 1, characterized in that: Arranging the coordinates of the center points of all subspaces in the floor plan and counting the subspaces in the same row and column, i.e., a distribution feature of the subspaces in the floor plan, includes: Based on the horizontal coordinates of the subspace, counting multiple groups of subspaces in the same or nearly same line in the subspace; Based on the ordinate of the subspace, counting a plurality of groups of subspaces in the same column or nearly in the same column in the subspace; By combining the above-mentioned subspace distribution characteristics of the same row and the same column, the row coordinates and column coordinates of each subspace in the floor plan are obtained, and finally a matrix distribution characteristic of the floor plan subspace is obtained.

5. The application method for matching home products based on floor plan according to claim 1, characterized in that: The method of distributing the home furnishing products around the floor plan according to the distribution characteristics of the subspace and the number of home furnishing products in the subspace and an algorithm includes: Based on certain rules and algorithms, combined with the distribution characteristics of the subspaces in the floor plan, the home furnishing products in each subspace are arranged around the floor plan; Based on the rules and algorithms, the center point of the subspace and the center point of the corresponding home product are connected by a broken line method. By calculating and reasonably distributing the inflection points of the broken lines, the intersection of different broken lines and the situation where the broken line of a subspace passes through another subspace are avoided.

6. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 5.

Images