CN114550198A - Home design generation method, device and system based on effect diagram - Google Patents
Home design generation method, device and system based on effect diagram Download PDFInfo
- Publication number
- CN114550198A CN114550198A CN202210128536.6A CN202210128536A CN114550198A CN 114550198 A CN114550198 A CN 114550198A CN 202210128536 A CN202210128536 A CN 202210128536A CN 114550198 A CN114550198 A CN 114550198A
- Authority
- CN
- China
- Prior art keywords
- goods
- hard
- similar
- soft
- home design
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Computational Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Medical Informatics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a home furnishing design generation method, device and system based on an effect graph, and belongs to the technical field of home furnishing design and image recognition. According to the invention, soft goods and hard goods in the picture are identified through the image identification technology through the home design scheme picture input by the user, similar or identical soft goods and hard goods are retrieved based on the soft goods and hard goods, and then the home design scheme meeting the user requirements is obtained according to the similar or identical soft goods and hard goods, so that the diversified requirements of the user can be met. Meanwhile, the efficiency of the user can be effectively improved under various scenes, so that the user experience is improved, and the use and familiarity costs of the design tool are reduced.
Description
Technical Field
The invention relates to the technical field of home design and image recognition, in particular to a home design generation method, device and system based on an effect graph.
Background
In daily life and work, people often see favorite decoration styles, whether home design high-definition effect pictures seen from the internet or photos shot on site, people have the requirement of moving the design effect on the photos to own new homes.
However, based on an effect diagram, the effect is restored by manually using a design software tool, the soft package layout is manually performed, the commodity model is selected, the hard package paving method is designed, the hard package material is selected, and the like, so that the time and labor are consumed, the efficiency is low, and the user experience is reduced.
Disclosure of Invention
In order to solve the problems in the prior art, the embodiment of the invention provides a household design generation method, a household design generation device and a household design generation system based on an effect diagram. The technical scheme is as follows:
on one hand, a household design generation method based on an effect diagram is provided, and the method comprises the following steps:
identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
retrieving to obtain a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and generating a household design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
Optionally, the recognizing the home design drawing input by the user to obtain the plurality of soft goods included in the home design drawing includes:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
identifying a plurality of soft goods in the soft goods sub-area and a location and an orientation of the plurality of soft goods.
Optionally, the identifying the home furnishing design drawing input by the user, and obtaining the hard-packed goods contained in the home furnishing design drawing and the laying scheme of the hard-packed goods includes:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
identifying a plurality of hard-goods in the hard-goods sub-area and a layup scheme for the plurality of hard-goods.
Optionally, the generating a home design scheme according to the user type, the paving scheme, the plurality of similar soft goods and the plurality of similar hard goods comprises:
obtaining the position, size and orientation of the furniture according to the house type, and dividing a plurality of functional areas;
the plurality of similar soft goods and the laying scheme are distributed in the house type according to the position, the size and the orientation of the furniture and a plurality of functional areas;
the plurality of similar hard goods and the laying scheme are laid in the house type according to the plurality of functional areas;
and obtaining the household design scheme after the layout is completed.
Optionally, recognizing the home design drawing input by the user, and obtaining the soft-package sub-area and the hard-package sub-area included in the home design drawing includes:
and obtaining the soft sub-area and the hard sub-area through target detection and example segmentation.
Optionally, the retrieving to obtain a plurality of similar soft goods similar to or the same as the plurality of soft goods, and a plurality of similar hard goods similar to or the same as the plurality of hard goods includes:
carrying out image retrieval in a commodity library through the image of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-package commodity to obtain the plurality of similar hard-package commodities and laying schemes corresponding to the plurality of similar hard-package commodities.
Optionally, the obtaining of the position, size, and orientation of the furniture and the dividing of the plurality of functional areas according to the house type includes:
according to a layout algorithm, on the basis of the house type, obtaining the position, the size and the orientation of furniture, and dividing a plurality of functional areas;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result graph comprises the position, the size and the orientation of the furniture and is divided into a plurality of functional areas.
In another aspect, an effect graph-based home design generation apparatus is provided, the apparatus including:
the system comprises an identification module, a data processing module and a data processing module, wherein the identification module is used for identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
the retrieval module is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout module is used for generating a home design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
Optionally, the identification module is specifically configured to:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
identifying a plurality of soft goods in the soft goods sub-area and a location and an orientation of the plurality of soft goods.
Optionally, the identification module is specifically configured to:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
identifying a plurality of hard-goods in the hard-goods sub-area and a layup scheme for the plurality of hard-goods.
Optionally, the layout module is specifically configured to:
obtaining the position, size and orientation of the furniture according to the house type, and dividing a plurality of functional areas;
the plurality of similar soft goods and the laying scheme are distributed in the house type according to the position, the size and the orientation of the furniture and a plurality of functional areas;
the plurality of similar hard goods and the laying scheme are distributed in the house type according to the plurality of functional areas;
and obtaining the household design scheme after the layout is completed.
Optionally, the identification module is specifically configured to:
and obtaining the soft sub-area and the hard sub-area through target detection and example segmentation.
Optionally, the retrieval module is specifically configured to:
carrying out image retrieval in a commodity library through the image of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-package commodity to obtain the plurality of similar hard-package commodities and laying schemes corresponding to the plurality of similar hard-package commodities.
Optionally, the layout module is specifically configured to:
according to a layout algorithm, on the basis of the house type, obtaining the position, the size and the orientation of furniture, and dividing a plurality of functional areas;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result graph comprises the position, the size and the orientation of the furniture and is divided into a plurality of functional areas.
In another aspect, a home design generation system based on an effect graph is provided, the system including:
the system comprises an identification device, a data processing device and a data processing device, wherein the identification device is used for identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
the retrieval device is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout device is used for generating a home design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
Optionally, the identification device is specifically configured to:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
identifying a plurality of soft goods in the soft goods sub-area and a location and an orientation of the plurality of soft goods.
Optionally, the identification device is specifically configured to:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
identifying a plurality of hard-goods in the hard-goods sub-area and a layup scheme for the plurality of hard-goods.
Optionally, the layout apparatus is specifically configured to:
obtaining the position, size and orientation of the furniture according to the house type, and dividing a plurality of functional areas;
the plurality of similar soft goods and the laying scheme are distributed in the house type according to the position, the size and the orientation of the furniture and a plurality of functional areas;
the plurality of similar hard goods and the laying scheme are distributed in the house type according to the plurality of functional areas;
and obtaining the household design scheme after the layout is completed.
Optionally, the identification device is specifically configured to:
and obtaining the soft sub-area and the hard sub-area through target detection and example segmentation.
Optionally, the retrieval apparatus is specifically configured to:
carrying out image retrieval in a commodity library through the image of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-package commodity to obtain the plurality of similar hard-package commodities and laying schemes corresponding to the plurality of similar hard-package commodities.
Optionally, the layout apparatus is specifically configured to:
according to a layout algorithm, on the basis of the house type, obtaining the position, the size and the orientation of furniture, and dividing a plurality of functional areas;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result graph comprises the position, the size and the orientation of the furniture and is divided into a plurality of functional areas.
In another aspect, an effect graph-based home design generation apparatus is provided, where the apparatus includes a memory and a processor, where the memory is used to store a set of program codes, and the processor calls the program codes stored in the memory to execute the method according to any one of the first aspect.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the soft goods and the hard goods which are similar or identical are searched out based on the soft goods and the hard goods, and then the home design scheme meeting the user requirements is obtained according to the similar or identical soft goods and hard goods, so that the diversified requirements of the user can be met. Meanwhile, the efficiency of the user can be effectively improved under various scenes, so that the user experience is improved, and the use and familiarity costs of the design tool are reduced.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a home design generation method based on an effect diagram according to an embodiment of the present invention;
FIG. 2 is a network structure and loss diagram of a layout algorithm provided by an embodiment of the present invention;
FIG. 3 is a home design drawing provided by an embodiment of the invention;
FIG. 4 is an intermediate layout provided by an embodiment of the present invention;
fig. 5 is a schematic diagram of a home design scheme provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a household design generation method based on an effect diagram is provided, and the method includes:
101. identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and laying schemes of the hard goods contained in the home design drawing;
102. searching to obtain a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
103. and generating a household design scheme according to the house type, the laying scheme, the approximate soft goods and the approximate hard goods of the user.
Optionally, recognizing the home design drawing input by the user to obtain a plurality of soft goods included in the home design drawing includes:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
a plurality of soft goods in the soft goods sub-area is identified, as well as a location and an orientation of the plurality of soft goods.
Optionally, recognizing the home design drawing input by the user to obtain the hard goods contained in the home design drawing and the laying scheme of the hard goods includes:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
a plurality of hard-goods in the hard-goods sub-area and a laying scheme of the plurality of hard-goods are identified.
Optionally, generating a home design scheme according to the house type of the user, the laying scheme, the plurality of similar soft goods and the plurality of similar hard goods comprises:
obtaining the position, size and orientation of furniture according to the house type, and dividing a plurality of functional areas;
a plurality of similar soft goods and laying schemes are distributed in the house type according to the position, the size and the orientation of furniture and a plurality of functional areas;
a plurality of similar hard goods and laying schemes are arranged in a house type according to a plurality of functional areas;
and obtaining a household design scheme after the layout is completed.
Optionally, recognizing the home design drawing input by the user, and obtaining the soft-package sub-area and the hard-package sub-area included in the home design drawing includes:
and obtaining a soft sub-area and a hard sub-area through target detection and example segmentation.
In the above steps, the target detection process may be implemented by using a target detection algorithm centret of anchor free, so as to avoid the influence of the non-maximum suppression NMS on the target detection effect and efficiency, and the process specifically includes:
the center point of the target is predicted, and then the length, width and offset of the detection frame are regressed. And C categories of target detection tasks, wherein the output size of the model is as follows: (C +4) × H/R × W/R, where R is the ratio of the down-sampling of the image, such as the input map 512 × 512 and the output map 128 × 128, then R × 4 and H, W represent the length and width of the input image, respectively. The output of C H/R W/R is the heatmap of the center point of each category, when predicting, the maximum value point (more than 8 points in the neighborhood) of top100 is selected, then the center position of each category object is obtained by screening with the threshold, the two-dimensional output of the remaining 4H/R W/R is the length and width of the detection frame, and the two-dimensional output is the offset of the output center point mapping back to the input image.
In this process, the backbone used was Hourglass.
The instance segmentation process can be realized through an instance segmentation algorithm K-net, the algorithm realizes semantic segmentation, instance segmentation and panoramic segmentation by using a unified frame, is also of Anchor Free, and solves the problem that a common network structure is difficult to converge due to high training difficulty under the Anchor Free condition by using a learnable kernel update strategy.
Optionally, the retrieving a plurality of similar soft goods similar to or the same as the plurality of soft goods and a plurality of similar hard goods similar to or the same as the plurality of hard goods includes:
carrying out image retrieval in a commodity library through the images of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-packed commodity to obtain a plurality of similar hard-packed commodities and laying schemes corresponding to the similar hard-packed commodities.
Optionally, obtaining the position, size and orientation of the furniture according to the house type, and dividing the functional areas comprises:
according to a layout algorithm, on the basis of the house type, the position, the size and the orientation of furniture are obtained, and a plurality of functional areas are divided;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result chart comprises the position, the size and the orientation of the furniture and divides a plurality of functional areas.
The layout algorithm specifically comprises the following steps:
using a large amount of actual design data, an intermediate result graph of the layout is generated, the room floor plan is used as input, the layout is used as a label to generate training data, a model of the C-GAN is trained, and the network structure and loss of the C-GAN are shown in fig. 2.
The C-GAN model is confronted with a generator through a discriminator for confrontation loss, so that the generation result of the generator is ensured to be fitted with the distribution of a training set as much as possible, and in order to ensure that an output intermediate result graph is closer to a label, besides the confrontation loss, pixel loss is added to constrain model training.
The embodiment of the invention also provides a home furnishing design generation device based on the effect graph, which comprises the following components:
the identification module is used for identifying the home design drawing input by the user to obtain a plurality of soft goods, hard goods and laying schemes of the hard goods contained in the home design drawing;
the retrieval module is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout module is used for generating a household design scheme according to the house type, the laying scheme, the approximate soft goods and the approximate hard goods of the user.
Optionally, the identification module is specifically configured to:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
a plurality of soft goods in the soft goods sub-area is identified, as well as a location and an orientation of the plurality of soft goods.
Optionally, the identification module is specifically configured to:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
a plurality of hard-goods in the hard-goods sub-area and a laying scheme of the plurality of hard-goods are identified.
Optionally, the layout module is specifically configured to:
obtaining the position, size and orientation of furniture according to the house type, and dividing a plurality of functional areas;
a plurality of similar soft goods and laying schemes are distributed in the house type according to the position, the size and the orientation of furniture and a plurality of functional areas;
a plurality of similar hard goods and laying schemes are arranged in a house type according to a plurality of functional areas;
and obtaining a household design scheme after the layout is completed.
Optionally, the identification module is specifically configured to:
and obtaining a soft sub-area and a hard sub-area through target detection and example segmentation.
Optionally, the retrieval module is specifically configured to:
carrying out image retrieval in a commodity library through the images of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-packed commodity to obtain a plurality of similar hard-packed commodities and laying schemes corresponding to the similar hard-packed commodities.
Optionally, the layout module is specifically configured to:
according to a layout algorithm, on the basis of the house type, the position, the size and the orientation of furniture are obtained, and a plurality of functional areas are divided;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result chart comprises the position, the size and the orientation of the furniture and divides a plurality of functional areas.
The embodiment of the invention also provides a home design generation system based on the effect graph, which comprises the following steps:
the identification device is used for identifying the home design drawing input by the user to obtain a plurality of soft goods, hard goods and laying schemes of the hard goods contained in the home design drawing;
the retrieval device is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout device is used for generating a household design scheme according to the house type, the laying scheme, the approximate soft goods and the approximate hard goods of the user.
Optionally, the identification device is specifically configured to:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
a plurality of soft goods in the soft goods sub-area is identified, as well as a location and an orientation of the plurality of soft goods.
Optionally, the identification device is specifically configured to:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
a plurality of hard-goods in the hard-goods sub-area and a laying scheme of the plurality of hard-goods are identified.
Optionally, the layout apparatus is specifically configured to:
obtaining the position, size and orientation of furniture according to the house type, and dividing a plurality of functional areas;
a plurality of similar soft goods and laying schemes are distributed in the house type according to the position, the size and the orientation of furniture and a plurality of functional areas;
a plurality of similar hard goods and laying schemes are arranged in a house type according to a plurality of functional areas;
and obtaining a household design scheme after the layout is completed.
Optionally, the identification device is specifically configured to:
and obtaining a soft sub-area and a hard sub-area through target detection and example segmentation.
Optionally, the retrieval apparatus is specifically configured to:
carrying out image retrieval in a commodity library through the images of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-packed commodity to obtain a plurality of similar hard-packed commodities and laying schemes corresponding to the similar hard-packed commodities.
Optionally, the layout apparatus is specifically configured to:
according to a layout algorithm, on the basis of the house type, the position, the size and the orientation of furniture are obtained, and a plurality of functional areas are divided;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result chart comprises the position, the size and the orientation of the furniture and divides a plurality of functional areas.
The embodiment of the invention also provides a home design generating device based on the effect graph, which comprises a memory and a processor, wherein the memory is used for storing a group of program codes, and the processor calls the program codes stored in the memory to execute the method in any one of the embodiments.
In order to make those skilled in the art further understand the effects achieved by the technical solutions provided in the present invention, the technical solutions provided in the present invention will be further described below with reference to the accompanying drawings.
The home design drawing input by the user may be as shown in fig. 3, in the process of executing the technical method according to the embodiment of the present invention, the middle layout drawing generated by the layout algorithm may be as shown in fig. 4, and the finally generated home design scheme may be as shown in fig. 4.
Therefore, soft goods and hard goods in the picture are identified through the image identification technology through the home design scheme picture input by the user, similar or identical soft goods and hard goods are searched out based on the soft goods and hard goods, and then the home design scheme meeting the user requirements is obtained according to the similar or identical soft goods and hard goods, so that the diversified requirements of the user can be met. Meanwhile, the efficiency of a user can be effectively improved under various scenes, and the use and familiarity cost of a design tool is reduced.
In addition, in a marketing scene, marketing personnel can quickly select commodities of their own according to the home design style pictures provided by the customers, so that the customers can see the decorated effect, and the marketing efficiency is improved; secondly, the system can help a designer to quickly generate a manuscript of a design scheme and adjust the manuscript again on the basis, so that the design efficiency is improved.
All the above-mentioned optional technical solutions can be combined arbitrarily to form the optional embodiments of the present invention, and are not described herein again.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, where the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A home design generation method based on an effect graph is characterized by comprising the following steps:
identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
retrieving to obtain a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and generating a household design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
2. The method according to claim 1, wherein the recognizing the home design drawing input by the user to obtain a plurality of soft goods included in the home design drawing comprises:
identifying a home design drawing input by a user to obtain a soft package subarea contained in the home design drawing;
identifying a plurality of soft goods in the soft goods sub-area and a location and an orientation of the plurality of soft goods.
3. The method according to claim 1, wherein the recognizing the home design drawing input by the user to obtain the hard-packed goods contained in the home design drawing and the laying scheme of the hard-packed goods comprises:
identifying a home design drawing input by a user to obtain a hard-ware subarea contained in the home design drawing;
identifying a plurality of hard-goods in the hard-goods sub-area and a layup scheme for the plurality of hard-goods.
4. The method of claim 2 or 3, wherein the generating a home design plan based on the user's house type, the paving plan, the plurality of near soft goods and the plurality of near hard goods comprises:
obtaining the position, size and orientation of the furniture according to the house type, and dividing a plurality of functional areas;
the plurality of similar soft goods and the laying scheme are distributed in the house type according to the position, the size and the orientation of the furniture and a plurality of functional areas;
the plurality of similar hard goods and the laying scheme are distributed in the house type according to the plurality of functional areas;
and obtaining the household design scheme after the layout is completed.
5. The method according to claim 2 or 3, wherein the step of recognizing the home design drawing input by the user to obtain the soft-clothing sub-area and the hard-clothing sub-area included in the home design drawing comprises the following steps:
and obtaining the soft sub-area and the hard sub-area through target detection and example segmentation.
6. The method of claim 5, wherein the retrieving a plurality of similar soft goods similar to or the same as the plurality of soft goods and a plurality of similar hard goods similar to or the same as the plurality of hard goods comprises:
carrying out image retrieval in a commodity library through the image of the soft goods to obtain a plurality of similar soft goods;
and performing image retrieval in the commodity library through the image of the hard-package commodity to obtain the plurality of similar hard-package commodities and laying schemes corresponding to the plurality of similar hard-package commodities.
7. The method of claim 4, wherein the obtaining of the position, size and orientation of the furniture and the dividing of the plurality of functional areas according to the house type comprises:
according to a layout algorithm, on the basis of the house type, obtaining the position, the size and the orientation of furniture, and dividing a plurality of functional areas;
the layout algorithm is obtained by training a plurality of design schemes, the input of the layout algorithm is a house type, the output of the layout algorithm is an intermediate result graph, and the label is a layout graph of the design schemes; wherein the intermediate result graph comprises the position, the size and the orientation of the furniture and is divided into a plurality of functional areas.
8. An effect graph-based home design generation device, the device comprising:
the system comprises an identification module, a data processing module and a data processing module, wherein the identification module is used for identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
the retrieval module is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout module is used for generating a home design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
9. A home design generation system based on an effect graph, the system comprising:
the system comprises an identification device, a data processing device and a data processing device, wherein the identification device is used for identifying a home design drawing input by a user to obtain a plurality of soft goods, hard goods and a laying scheme of the hard goods contained in the home design drawing;
the retrieval device is used for retrieving a plurality of similar soft goods similar to or the same as the soft goods and a plurality of similar hard goods similar to or the same as the hard goods;
and the layout device is used for generating a home design scheme according to the house type of the user, the laying scheme, the approximate soft goods and the approximate hard goods.
10. An effect-graph-based home design generation device, comprising a memory and a processor, wherein the memory is used for storing a set of program codes, and the processor calls the program codes stored in the memory to execute the method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210128536.6A CN114550198A (en) | 2022-02-11 | 2022-02-11 | Home design generation method, device and system based on effect diagram |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210128536.6A CN114550198A (en) | 2022-02-11 | 2022-02-11 | Home design generation method, device and system based on effect diagram |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114550198A true CN114550198A (en) | 2022-05-27 |
Family
ID=81673640
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210128536.6A Pending CN114550198A (en) | 2022-02-11 | 2022-02-11 | Home design generation method, device and system based on effect diagram |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114550198A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117934690A (en) * | 2024-03-25 | 2024-04-26 | 全屋优品科技(深圳)有限公司 | Household soft management method, device, equipment and storage medium |
-
2022
- 2022-02-11 CN CN202210128536.6A patent/CN114550198A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117934690A (en) * | 2024-03-25 | 2024-04-26 | 全屋优品科技(深圳)有限公司 | Household soft management method, device, equipment and storage medium |
CN117934690B (en) * | 2024-03-25 | 2024-06-07 | 全屋优品科技(深圳)有限公司 | Household soft management method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9262441B2 (en) | Wildcard color searching | |
US20190362152A1 (en) | Tagging virtualized content | |
US10073861B2 (en) | Story albums | |
CN102334118B (en) | Promoting method and system for personalized advertisement based on interested learning of user | |
US9020183B2 (en) | Tagging images with labels | |
CN101689394B (en) | Method and system for video indexing and video synopsis | |
CN102930523B (en) | Picture processing system and picture splicing implementation method | |
CN109086439A (en) | Information recommendation method and device | |
US20080298689A1 (en) | Storing Information for Access Using a Captured Image | |
JP2010512607A (en) | Image processing system for digital collage | |
CN110097616B (en) | Combined drawing method and device, terminal equipment and readable storage medium | |
JPWO2020240809A1 (en) | Learning device, classification device, learning method, classification method, learning program, and classification program | |
CN112270736A (en) | Augmented reality processing method and device, storage medium and electronic equipment | |
CN116934907A (en) | Image generation method, device and storage medium | |
WO2024131565A1 (en) | Garment image extraction method and apparatus, and device, medium and product | |
CN114550198A (en) | Home design generation method, device and system based on effect diagram | |
US8407575B1 (en) | Video content summary | |
US20230353701A1 (en) | Removing objects at image capture time | |
CN110049180A (en) | Shoot posture method for pushing and device, intelligent terminal | |
CN111798549A (en) | Dance editing method and device and computer storage medium | |
CN117635760A (en) | Image generation method, device and storage medium | |
CN113596574A (en) | Video processing method, video processing apparatus, electronic device, and readable storage medium | |
JP2010245983A (en) | Image structuring device, image structure method, and image structuring program | |
US9224069B2 (en) | Program, method and apparatus for accumulating images that have associated text information | |
KR102252135B1 (en) | Self-interior Service Method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |