CN113792358B - Automatic interactive layout method and device for three-dimensional furniture and electronic equipment - Google Patents
Automatic interactive layout method and device for three-dimensional furniture and electronic equipment Download PDFInfo
- Publication number
- CN113792358B CN113792358B CN202111108052.7A CN202111108052A CN113792358B CN 113792358 B CN113792358 B CN 113792358B CN 202111108052 A CN202111108052 A CN 202111108052A CN 113792358 B CN113792358 B CN 113792358B
- Authority
- CN
- China
- Prior art keywords
- furniture
- room
- information
- moving
- dimensional
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 11
- 238000010586 diagram Methods 0.000 claims abstract description 19
- 238000013461 design Methods 0.000 claims description 46
- 238000004088 simulation Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 10
- 239000003795 chemical substances by application Substances 0.000 description 23
- 238000012549 training Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000005034 decoration Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Hardware Design (AREA)
- Computer Graphics (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a method, a device and electronic equipment for automatic interactive layout of three-dimensional furniture, which comprises the following steps: responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture; and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information. Therefore, when the furniture needs to be moved or replaced, firstly, the furniture which is not selected by a user is adjusted, and then all the furniture is adjusted, so that a new furniture layout diagram can be directly generated, and the efficiency is improved.
Description
Technical Field
The invention relates to the field of household layout, in particular to an automatic interactive layout method and device for three-dimensional furniture and electronic equipment.
Background
Before house decoration, a designer is usually required to give a design scheme, wherein the design scheme comprises hard-wearing equipment and soft-wearing equipment, but because the requirements of users can be changed continuously, the design diagram is also required to be modified continuously, for example, the users may need to adjust the layout of furniture or the furniture in the design diagram may be replaced.
In the prior art, if the layout of the furniture is required to be adjusted or the furniture is required to be replaced, the user needs to communicate with a designer and modify the design by the designer, in this way, the timeliness is poor, and if the designer does not have the intention of the user completely, a small change can be modified for many times, so that the efficiency is low.
Disclosure of Invention
In view of the above, the embodiment of the invention discloses a method, a device and electronic equipment for automatically and interactively laying out three-dimensional furniture, which solve the problems of poor timeliness and low efficiency of furniture layout adjustment in the prior art.
The embodiment of the invention discloses a method for automatically and interactively laying out three-dimensional furniture, which comprises the following steps:
Generating a three-dimensional simulation environment through a two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
Determining an initial layout state of a room according to the three-dimensional simulation environment;
responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture;
and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information.
Optionally, the generating a three-dimensional simulation environment through the two-dimensional furniture design drawing includes:
identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design diagram;
generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
Processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
Identifying key points of each civil engineering element from the civil engineering language intention, and constructing outlines of each civil engineering element according to the key points of each civil engineering element;
calculating the house type size of each room through the outline of each civil engineering element;
Based on the house type size of each room and the three-dimensional outline of each furniture, the position relationship between each furniture and the room is determined.
Optionally, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information, which includes:
If the first room state information obtained at present is changed from the first room state information obtained by moving the furniture last time, taking the first room state information obtained at present as the current room state information, and executing the following steps:
Determining a first probability value of moving in different directions when the first furniture and the second furniture move simultaneously based on a preset first furniture cooperation intelligent network and current room state information; the current room state and the initial room state in the initial state;
determining the probability of the second furniture moving in different directions according to a preset first furniture cooperation intelligent network and the current room state;
Determining a first target direction and a moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions;
and moving the second furniture according to the moving step length of the second furniture in the first target direction to obtain the first room state information.
Optionally, the determining the first target direction and the moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions includes:
Calculating a product value of a second probability value of the second furniture moving in each direction and the first probability value in the direction;
And taking the direction corresponding to the maximum product value as a first target direction.
Optionally, the determining movement information of the plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture, to obtain second room layout information, includes:
If the second room state obtained at present is different from the second room state obtained by the last furniture movement, the second room state obtained at present is expressed as the current room state, and the following steps are executed:
Determining a third probability value of movement in different directions when a plurality of furniture move cooperatively according to the current room state and a preset second furniture cooperation intelligent agent network;
Determining a fourth probability value of furniture moving in different directions in the plurality of furniture respectively according to the current room state and a preset second furniture moving intelligent agent network;
determining a second direction in which each piece of furniture moves and a second movement step by a third probability value that each piece of furniture moves in different directions and a fourth probability value that each piece of furniture moves in different directions when the pieces of furniture move cooperatively;
and moving each piece of furniture according to the second direction of movement of each piece of furniture and the movement step length.
Optionally, the determining the second direction of movement of each piece of furniture by the third probability value of movement in different directions when the pieces of furniture cooperatively move and the fourth probability value of movement of each piece of furniture in different directions includes:
calculating, for any piece of furniture, a product of a fourth probability of the piece of furniture in each direction and a third probability value when a plurality of pieces of furniture move cooperatively in the corresponding direction;
And taking the direction corresponding to the maximum product value as a second target direction.
Optionally, the method further comprises:
Changing the second furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture.
The embodiment of the invention discloses a device for automatically and interactively laying out three-dimensional furniture, which comprises the following components:
The generating unit is used for generating a three-dimensional simulation environment through the two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
A determining subunit, configured to determine an initial layout state of a room according to the three-dimensional simulation environment;
the first moving unit is used for responding to the adjustment instruction of the first furniture, determining the moving information of the second furniture according to the initial layout state of the room, the first furniture information, the preset first layout network and the information of the second furniture, and moving the second furniture according to the moving information of the second furniture to obtain the state information of the first room; the second furniture is any one or more pieces of furniture except the first furniture;
The second moving unit is used for determining moving information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the moving information of the plurality of pieces of furniture to obtain layout information of a second room.
Optionally, the generating unit includes:
the first identification subunit is used for identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design drawing;
The generation subunit is used for generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
the processing subunit is used for processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
The second recognition subunit is used for recognizing key points of each civil engineering element from the civil engineering language intention and constructing the outline of each civil engineering element according to the key points of each civil engineering element;
The calculating subunit is used for calculating the house type size of each room through the outline of each civil engineering element;
and the determining subunit is used for determining the position relation between each furniture and each room based on the house type size of each room and the three-dimensional outline of each furniture.
The embodiment of the invention discloses an electronic device, which comprises:
A memory and a processor;
The memory is used for storing a program, and the processor is used for executing the method for automatically and interactively laying out the three-dimensional furniture when executing the program of the memory.
The embodiment of the invention discloses a method and a device for automatic interactive layout of three-dimensional furniture and electronic equipment, wherein the method comprises the following steps: responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture; and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information, wherein the initial layout state of the room is determined according to a three-dimensional simulation environment which is determined through a two-dimensional furniture design diagram. Therefore, when the furniture needs to be moved or replaced, firstly, the furniture which is not selected by a user is adjusted, and then all the furniture is adjusted, so that when the user needs to adjust a certain furniture, a new furniture layout diagram can be directly generated, and the efficiency is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for automatic interactive layout of three-dimensional furniture according to an embodiment of the present invention;
fig. 2 shows a schematic structural diagram of an automatic interactive layout device for three-dimensional furniture according to an embodiment of the present invention;
fig. 3 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the prior art, if the layout of the furniture in the design drawing is required to be adjusted or the furniture is required to be replaced, under the normal condition, a user needs to communicate with a designer, and then the designer modifies the scheme, but in the mode, the timeliness is poor, the efficiency is low, and the satisfaction of the user is not easy to achieve in some cases.
In order to improve efficiency, the embodiment of the invention discloses an automatic interactive layout method of three-dimensional furniture, which is based on a two-dimensional furniture design diagram to generate a three-dimensional simulation environment, wherein the three-dimensional simulation environment comprises the house type size of each room, the three-dimensional outline of each furniture and the position relation between each furniture and the room, the initial layout state of the room is determined according to the three-dimensional simulation environment, then the layout of the furniture is adjusted through two layers, firstly, the movement information of a first furniture (the furniture which is not selected to be adjusted by a user) is determined through a preset first layout network, and the second furniture is moved according to the movement information of the second furniture, so that the state information of the first room is obtained; and then determining the movement information of a plurality of pieces of furniture through a preset second layout network, so as to obtain second furniture layout information. Therefore, when a user needs to adjust a certain furniture, the design scheme of the adjusted furniture can be directly generated, and the efficiency is improved.
And the furniture can be adjusted according to the needs of the user, and a plurality of different layout schemes are generated for the user to select.
The following will describe the present technical solution in detail:
Example 1
Referring to fig. 1, a flow chart of a method for automatic interactive layout of three-dimensional furniture according to an embodiment of the present invention is shown, where in this embodiment, the method includes:
S101: generating a three-dimensional simulation environment through a two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
in this embodiment, the two-dimensional furniture design drawing may be designed in any manner, for example, may be a CAD drawing, where the two-dimensional furniture drawing includes elements of soft-packs and hard-packs and attribute information of the elements (the attribute information includes at least a size and a category).
The generated three-dimensional simulation environment comprises the house type size of each room and the three-dimensional outline of each furniture, optionally, each piece of information required by the three-dimensional simulation environment can be obtained by identifying the two-dimensional furniture design drawing and calculating each piece of identified information, and optionally, the S101 comprises:
identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design diagram;
generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
Processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
Identifying key points of each civil engineering element from the civil engineering language intention, and constructing outlines of each civil engineering element according to the key points of each civil engineering element;
calculating the house type size of each room through the outline of each civil engineering element;
Based on the house type size of each room and the three-dimensional outline of each furniture, the position relationship between each furniture and the room is determined.
In this embodiment, each furniture element and attribute information of each furniture element may be identified from the two-dimensional design chart in various manners, for example, each furniture element and attribute information of each furniture element may be identified from the two-dimensional design chart by an SSD (Single Shot Multi-Box Detector) model or by a FASTERRCNN model.
The attribute information of each element includes at least: the dimensions and the class of the individual furniture elements, wherein the class represents different furniture categories, such as living room sofas, bedrooms, etc.
In this embodiment, the civil language is intended to include a structure that is hard-wired to a room, for example, including: walls, doors, windows, roofs, floors, etc. Also, the semantic recognition model may be any convolutional neural network model or other machine learning model, and optionally, the semantic recognition model may include: an encoder and a decoder, wherein the encoder comprises: 4 CNN (convolutional) layers, the parameters of the encoder include, for example: 160×128,80×80×256,40×40×512,20×20×512, wherein the two-dimensional image can be encoded into 10×10×512 vectors by the encoder; the decoder comprises two CNN (convolution) layers, and the parameters respectively comprise: 20 x 512,40 x 256, wherein 128 x 3 vectors can be decoded by a decoder.
In this embodiment, the key points of each civil engineering element may be represented as inflection points of each civil engineering element, and the outline of each civil engineering element may be constructed through the inflection points of each civil engineering element. Wherein the outline of each civil element represents the composition and size of each civil element.
In this embodiment, the house type size of each room is calculated through the outline of each civil engineering element, where the house type size of each room includes: length, width, height, etc. of each room.
S102: determining an initial layout state of a room according to the three-dimensional simulation environment;
In this embodiment, as can be seen from the above description, the three-dimensional simulation environment includes: the house type size of each room, the three-dimensional contour of each furniture, and the positional relationship of each furniture and room, which can represent the initial layout state of the room.
S103: responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture;
In this embodiment, the adjustment command of the first furniture may be triggered by the user, wherein the adjustment command may be to replace the position of the first furniture or to replace the first furniture.
In this embodiment, the first layout network is obtained after training in advance, where the trained first layout network has a capability of adjusting a furniture layout, specifically, when a user replaces a certain furniture in a room, the first layout network can adjust the capability of other furniture except for the furniture to be replaced, and optionally, S102 includes:
If the first room state information obtained at present is changed from the first room state information obtained by moving the furniture last time, taking the first room state information obtained at present as the current room state information, and executing the following steps:
Determining a first probability value of moving in different directions when the first furniture and the second furniture move simultaneously based on a preset first furniture cooperation intelligent network and current room state information; the current room state and the initial room state in the initial state;
determining the probability of the second furniture moving in different directions according to a preset first furniture cooperation intelligent network and the current room state;
Determining a first target direction and a moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions;
and moving the second furniture according to the moving step length of the second furniture in the first target direction to obtain the first room state information.
In this embodiment, the first furniture cooperated intelligent agent network may be pre-trained, and the first furniture cooperated intelligent agent network may be trained by using room status information as a training sample, so that the first furniture cooperated intelligent agent network has probabilities of moving in different directions when outputting different furniture cooperated movements.
Illustrating: the direction of the cooperative movement of the furniture includes, for example: the probability of different furniture moving cooperatively in each direction can be predicted by the first furniture agent network, up, down, left, right, forward and backward.
Wherein the first furniture partner network may be any convolutional neural network or any machine learning model, and optionally, the first furniture partner network includes:
Three convolutional layers and two fully-connected layers, wherein parameters of the three convolutional layers include, for example: (512*512*512*64,256*256*256*128,128*128*128*256.
In this embodiment, the first furniture moving agent network may be obtained through pre-training, where the training sample is room status information and information of the selected furniture to be replaced, and the trained second furniture moving agent network has a probability of predicting that the user does not select furniture (second furniture) to move in different directions.
Wherein the first furniture mobile agent network may be any convolutional neural network or any machine learning model, and optionally, the first furniture mobile agent network includes:
Three convolutional layers and two fully-connected layers, wherein parameters of the three convolutional layers include, for example: (512*512*512*64,256*256*256*128,128*128*128*256.
In this embodiment, the first target direction of movement of each second piece of furniture is determined by the first probability that the first piece of furniture and the second piece of furniture cooperatively move in different directions and the probability that the second piece of furniture unselected by the user moves in different directions, and optionally, the direction with the largest probability value may be selected as the first target direction of movement of the second piece of furniture, including:
Calculating a product value of a second probability value of the second furniture moving in each direction and the first probability value in the direction;
And taking the direction corresponding to the maximum product value as a first target direction.
In this embodiment, when a piece of furniture needs to be moved, for example, when a bed or a moving bed needs to be replaced, a bedside table may need to be moved, or a cabinet may need to be moved, then different furniture layout diagrams may be obtained when different pieces of furniture are moved, and in order to give a user more choices, different furniture different diagrams may be obtained by selecting different second pieces of furniture, which specifically further includes:
Changing the second furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture.
In this embodiment, the step size of moving in the first target direction may be preset or may be actually calculated.
S104: and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information.
In this embodiment, after a certain piece of furniture moves, the layout of a plurality of pieces of furniture in a room may be affected, so in order to implement the overall layout of the room, the plurality of pieces of furniture need to be moved and adjusted, specifically, S104 includes:
If the second room state obtained at present is different from the second room state obtained by the last furniture movement, the second room state obtained at present is expressed as the current room state, and the following steps are executed:
Determining a third probability value of movement in different directions when a plurality of furniture move cooperatively according to the current room state and a preset second furniture cooperation intelligent agent network;
determining a fourth probability value of each furniture moving in different directions according to the current room state and a preset second furniture moving intelligent network;
determining a second direction in which each piece of furniture moves and a second movement step length through a third probability value that each piece of furniture moves in different directions when the pieces of furniture move cooperatively and a fourth probability value that each piece of furniture moves in different directions;
and moving each piece of furniture according to the second direction of movement of each piece of furniture and the movement step length.
In this embodiment, the second furniture cooperative agent network is obtained through pre-training, and the second furniture cooperative agent network is trained by taking the current room state as a training sample, so that the trained second furniture cooperative agent network has a third probability value of moving in different directions when a plurality of pieces of furniture cooperatively move.
The second furniture cooperator agent network may be any convolutional neural network or any network of machine learning models.
Illustrating: the second furniture collaboration agent network may be composed of a 3-layer convolution layer and two fully-connected layers, wherein parameters of the 3-layer convolution layer may include:
512*512*512x64,256*256*256*128,128*128*128*256。
in this embodiment, the second furniture mobile agent network may be any convolutional neural network or any machine learning model, and optionally, the second furniture mobile agent network includes: the parameters of the three convolutional layers and the two fully-connected layers, for example, may include:
512*512*512*64,256*256*256*128,128*128*128*256。
In this embodiment, the determining the second direction of movement of each piece of furniture and the second movement step length by the probability of movement in different directions and the probability of movement in different directions when the pieces of furniture cooperatively move includes:
calculating, for any piece of furniture, a product of a fourth probability of the piece of furniture in each direction and a third probability value when a plurality of pieces of furniture move cooperatively in the corresponding direction;
And taking the direction corresponding to the maximum product value as a second target direction.
In this embodiment, as can be seen from the above description, in order to give the user more choices, different furniture layout diagrams can be obtained by selecting different second furniture, that is, different first room status information can be obtained, and in the case of different first room status information, different second room layout information can be obtained finally through the step of S104, so as to obtain different design schemes.
Example 2:
Referring to fig. 2, a schematic structural diagram of an automatic interactive layout device for three-dimensional furniture according to an embodiment of the present invention is shown, where in this embodiment, the device includes:
A generating unit 201, configured to generate a three-dimensional simulation environment through a two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
a determining subunit 202, configured to determine an initial layout state of a room according to the three-dimensional simulation environment;
The first moving unit 203 is configured to determine movement information of the second furniture according to an initial layout state of the room, first furniture information, a preset first layout network, and information of the second furniture in response to an adjustment instruction of the first furniture, and move the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture;
The second moving unit 204 is configured to determine movement information of a plurality of pieces of furniture based on the first room status information and a preset second layout network, and move the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture, so as to obtain second room layout information.
Optionally, the generating unit includes:
the first identification subunit is used for identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design drawing;
The generation subunit is used for generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
the processing subunit is used for processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
The second recognition subunit is used for recognizing key points of each civil engineering element from the civil engineering language intention and constructing the outline of each civil engineering element according to the key points of each civil engineering element;
the first calculating subunit is used for calculating the house type size of each room through the outline of each civil engineering element;
and the determining subunit is used for determining the position relation between each furniture and each room based on the house type size of each room and the three-dimensional outline of each furniture.
Optionally, the first mobile unit includes:
the first detection subunit is configured to take the first room state information obtained at present as the current room state information if the first room state information obtained at present and the first room state information obtained at last time of moving the furniture change, and execute the following steps:
The first determining subunit is used for determining a first probability value of moving in different directions when the first furniture and the second furniture move simultaneously based on a preset first furniture cooperation intelligent agent network and current room state information; the current room state and the initial room state in the initial state;
The second determining subunit is used for determining the probability of the second furniture moving in different directions according to the preset first furniture cooperative agent network and the current room state;
A third determining subunit, configured to determine a first target direction and a movement step size that the second furniture needs to be moved according to the second probability of moving in the different directions and the first probability of moving in the different directions;
the first moving subunit is used for moving the second furniture according to the moving step length of the second furniture in the first target direction to obtain first room state information.
Optionally, the third determining subunit includes:
A second calculation subunit for calculating a product value of a second probability value of the second furniture moving in each direction and the first probability value in the direction;
and the fourth determining subunit is used for taking the direction corresponding to the maximum product value as the first target direction.
Optionally, the second mobile unit includes:
the second detecting subunit is configured to, if the second room state obtained at present is different from the second room state obtained by the previous furniture movement, represent the second room state obtained at present as the current room state, and execute the following steps:
A fifth determining subunit, configured to determine a third probability value of movement in different directions when the plurality of furniture cooperatively move according to the current room state and a preset second furniture cooperatively intelligent agent network;
A sixth determining subunit, configured to determine a fourth probability value that each piece of furniture in the plurality of pieces of furniture moves in different directions according to the current room state and a preset second furniture moving agent network;
A seventh determining subunit configured to determine a second direction in which each piece of furniture moves, and a second movement step size, by the third probability value that each piece of furniture moves in different directions and the fourth probability value that each piece of furniture moves in different directions when the pieces of furniture move cooperatively;
And the second moving subunit is used for moving each piece of furniture according to the second direction and the moving step length of the movement of each piece of furniture.
Optionally, the seventh determining subunit is configured to:
A third calculation subunit, configured to calculate, for any piece of furniture, a product of a fourth probability of the piece of furniture in each direction and a third probability value when a plurality of pieces of furniture move cooperatively in the corresponding direction;
And an eighth determining subunit, configured to take the direction corresponding to the maximum product value as the second target direction.
Optionally, the method further comprises:
Changing the second furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture.
The device of the embodiment responds to an adjustment instruction of the first furniture, determines movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moves the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture; and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information, wherein the initial layout state of the room is determined according to a three-dimensional simulation environment which is determined through a two-dimensional furniture design diagram. Therefore, when the furniture needs to be moved or replaced, firstly, the furniture which is not selected by a user is adjusted, and then all the furniture is adjusted, so that a new furniture layout diagram can be directly generated under the condition of furniture adjustment, and the efficiency is improved.
Example 3:
referring to fig. 3, a schematic structural diagram of an electronic device according to an embodiment of the present invention is shown, where in this embodiment, the electronic device includes:
A memory 301 and a processor 302;
The memory 301 is configured to store a program, and the processor 302 is configured to execute, when executing the program in the memory, a method for automatically and interactively laying out three-dimensional furniture, where the method is as follows:
Generating a three-dimensional simulation environment through a two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
Determining an initial layout state of a room according to the three-dimensional simulation environment;
responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture;
and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information.
Optionally, the generating a three-dimensional simulation environment through the two-dimensional furniture design drawing includes:
identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design diagram;
generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
Processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
Identifying key points of each civil engineering element from the civil engineering language intention, and constructing outlines of each civil engineering element according to the key points of each civil engineering element;
calculating the house type size of each room through the outline of each civil engineering element;
Based on the house type size of each room and the three-dimensional outline of each furniture, the position relationship between each furniture and the room is determined.
Optionally, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information, which includes:
If the first room state information obtained at present is changed from the first room state information obtained by moving the furniture last time, taking the first room state information obtained at present as the current room state information, and executing the following steps:
Determining a first probability value of moving in different directions when the first furniture and the second furniture move simultaneously based on a preset first furniture cooperation intelligent network and current room state information; the current room state and the initial room state in the initial state;
determining the probability of the second furniture moving in different directions according to a preset first furniture cooperation intelligent network and the current room state;
Determining a first target direction and a moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions;
and moving the second furniture according to the moving step length of the second furniture in the first target direction to obtain the first room state information.
Optionally, the determining the first target direction and the moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions includes:
Calculating a product value of a second probability value of the second furniture moving in each direction and the first probability value in the direction;
And taking the direction corresponding to the maximum product value as a first target direction.
Optionally, the determining movement information of the plurality of pieces of furniture based on the first room state information and the preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture, to obtain second room layout information, includes:
If the second room state obtained at present is different from the second room state obtained by the last furniture movement, the second room state obtained at present is expressed as the current room state, and the following steps are executed:
Determining a third probability value of movement in different directions when a plurality of furniture move cooperatively according to the current room state and a preset second furniture cooperation intelligent agent network;
determining a fourth probability value of each furniture moving in different directions according to the current room state and a preset second furniture moving intelligent network;
determining a second direction in which each piece of furniture moves and a second movement step length through a third probability value that each piece of furniture moves in different directions when the pieces of furniture move cooperatively and a fourth probability value that each piece of furniture moves in different directions;
and moving each piece of furniture according to the second direction of movement of each piece of furniture and the movement step length.
Optionally, the determining the second direction of each furniture movement by the third probability value of the furniture moving in different directions when the furniture cooperatively moves and the fourth probability value of each furniture moving in different directions includes:
calculating, for any piece of furniture, a product of a fourth probability of the piece of furniture in each direction and a third probability value when a plurality of pieces of furniture move cooperatively in the corresponding direction;
And taking the direction corresponding to the maximum product value as a second target direction.
Optionally, the method further comprises:
Changing the second furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture.
It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for automatically interacting with a layout of a three-dimensional piece of furniture, comprising:
Generating a three-dimensional simulation environment through a two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
Determining an initial layout state of a room according to the three-dimensional simulation environment;
Responding to an adjustment instruction of the first furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture, and the first layout network has the capability of adjusting the layout of the furniture;
and determining movement information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture to obtain second room layout information.
2. The method of claim 1, wherein generating a three-dimensional simulation environment from a two-dimensional furniture design drawing comprises:
identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design diagram;
generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
Processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
Identifying key points of each civil engineering element from the civil engineering language intention, and constructing outlines of each civil engineering element according to the key points of each civil engineering element;
calculating the house type size of each room through the outline of each civil engineering element;
Based on the house type size of each room and the three-dimensional outline of each furniture, the position relationship between each furniture and the room is determined.
3. The method of claim 1, wherein determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, the preset first layout network, and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture, to obtain the first room state information, comprises:
If the first room state information obtained at present is changed from the first room state information obtained by moving the furniture last time, taking the first room state information obtained at present as the current room state information, and executing the following steps:
Determining a first probability value of moving in different directions when the first furniture and the second furniture move simultaneously based on a preset first furniture cooperation intelligent network and current room state information; the current room state and the initial room state in the initial state;
determining the probability of the second furniture moving in different directions according to a preset first furniture cooperation intelligent network and the current room state;
Determining a first target direction and a moving step length of the second furniture to be moved according to the second probability of moving in different directions and the first probability of moving in different directions;
and moving the second furniture according to the moving step length of the second furniture in the first target direction to obtain the first room state information.
4. A method according to claim 3, wherein determining the first target direction and movement step size in which the second furniture needs to be moved based on the second probability of movement in the different direction and the first probability of movement in the different direction comprises:
Calculating a product value of a second probability value of the second furniture moving in each direction and the first probability value in the direction;
And taking the direction corresponding to the maximum product value as a first target direction.
5. The method of claim 1, wherein determining movement information of a plurality of pieces of furniture based on the first room status information and a preset second layout network, and moving the plurality of pieces of furniture according to the movement information of the plurality of pieces of furniture, to obtain the second room layout information, comprises:
If the second room state obtained at present is different from the second room state obtained by the last furniture movement, the second room state obtained at present is expressed as the current room state, and the following steps are executed:
Determining a third probability value of movement in different directions when a plurality of furniture move cooperatively according to the current room state and a preset second furniture cooperation intelligent agent network;
Determining a fourth probability value of each furniture in the plurality of furniture moving in different directions according to the current room state and a preset second furniture moving intelligent network;
determining a second direction in which each piece of furniture moves and a second movement step by a third probability value that each piece of furniture moves in different directions and a fourth probability value that each piece of furniture moves in different directions when the pieces of furniture move cooperatively;
and moving each piece of furniture according to the second direction of movement of each piece of furniture and the movement step length.
6. The method of claim 5, wherein determining the second direction of movement of each piece of furniture from the third probability value of movement in a different direction and the fourth probability value of movement of each piece of furniture in a different direction when the pieces of furniture move cooperatively comprises:
calculating, for any piece of furniture, a product of a fourth probability of the piece of furniture in each direction and a third probability value when a plurality of pieces of furniture move cooperatively in the corresponding direction;
And taking the direction corresponding to the maximum product value as a second target direction.
7. The method as recited in claim 1, further comprising:
Changing the second furniture, determining movement information of the second furniture according to the initial layout state of the room, the first furniture information, a preset first layout network and the information of the second furniture, and moving the second furniture according to the movement information of the second furniture to obtain first room state information; the second furniture is any one or more pieces of furniture except the first furniture.
8. An apparatus for automatic interactive placement of three-dimensional furniture, comprising:
The generating unit is used for generating a three-dimensional simulation environment through the two-dimensional furniture design drawing; the three-dimensional simulation environment comprises: the house type size of each room, the three-dimensional outline of each furniture and the position relationship between each furniture and the room;
A determining subunit, configured to determine an initial layout state of a room according to the three-dimensional simulation environment;
The first moving unit is used for responding to the adjustment instruction of the first furniture, determining the moving information of the second furniture according to the initial layout state of the room, the first furniture information, the preset first layout network and the information of the second furniture, and moving the second furniture according to the moving information of the second furniture to obtain the state information of the first room; the second furniture is any one or more pieces of furniture except the first furniture, and the first layout network has the capability of adjusting the layout of the furniture;
The second moving unit is used for determining moving information of a plurality of pieces of furniture based on the first room state information and a preset second layout network, and moving the plurality of pieces of furniture according to the moving information of the plurality of pieces of furniture to obtain layout information of a second room.
9. The apparatus of claim 8, wherein the generating unit comprises:
the first identification subunit is used for identifying each furniture element and attribute information of each furniture element from the two-dimensional furniture design drawing;
The generation subunit is used for generating three-dimensional outlines of all furniture elements through attribute information of all furniture elements in the two-dimensional furniture design drawing;
the processing subunit is used for processing the two-dimensional furniture design drawing through a pre-trained language recognition model to obtain civil engineering language intention;
The second recognition subunit is used for recognizing key points of each civil engineering element from the civil engineering language intention and constructing the outline of each civil engineering element according to the key points of each civil engineering element;
The calculating subunit is used for calculating the house type size of each room through the outline of each civil engineering element;
and the determining subunit is used for determining the position relation between each furniture and each room based on the house type size of each room and the three-dimensional outline of each furniture.
10. An electronic device, comprising:
A memory and a processor;
The memory is used for storing a program, and the processor is used for executing the method for automatically and interactively laying out the three-dimensional furniture according to the claims 1-7 when executing the program of the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111108052.7A CN113792358B (en) | 2021-09-22 | 2021-09-22 | Automatic interactive layout method and device for three-dimensional furniture and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111108052.7A CN113792358B (en) | 2021-09-22 | 2021-09-22 | Automatic interactive layout method and device for three-dimensional furniture and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792358A CN113792358A (en) | 2021-12-14 |
| CN113792358B true CN113792358B (en) | 2024-06-04 |
Family
ID=78879064
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111108052.7A Active CN113792358B (en) | 2021-09-22 | 2021-09-22 | Automatic interactive layout method and device for three-dimensional furniture and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792358B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004195217A (en) * | 2002-12-04 | 2004-07-15 | Matsushita Electric Ind Co Ltd | Automatic arrangement device of furniture |
| CN109670262A (en) * | 2018-12-28 | 2019-04-23 | 江苏艾佳家居用品有限公司 | A kind of area of computer aided domestic layout optimization method and system |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
| CN110751721A (en) * | 2019-12-24 | 2020-02-04 | 广东博智林机器人有限公司 | Furniture layout drawing generation method and device, computer equipment and storage medium |
| CN111177826A (en) * | 2019-12-12 | 2020-05-19 | 江苏艾佳家居用品有限公司 | Indoor home automatic layout method based on deep convolutional network |
| CN113221225A (en) * | 2021-05-27 | 2021-08-06 | 北京有竹居网络技术有限公司 | Article layout method, article layout device, storage medium and electronic equipment |
| JP6932821B1 (en) * | 2020-07-03 | 2021-09-08 | 株式会社ベガコーポレーション | Information processing systems, methods and programs |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11004270B2 (en) * | 2018-09-11 | 2021-05-11 | Houzz, Inc. | Virtual item placement system |
-
2021
- 2021-09-22 CN CN202111108052.7A patent/CN113792358B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004195217A (en) * | 2002-12-04 | 2004-07-15 | Matsushita Electric Ind Co Ltd | Automatic arrangement device of furniture |
| CN109670262A (en) * | 2018-12-28 | 2019-04-23 | 江苏艾佳家居用品有限公司 | A kind of area of computer aided domestic layout optimization method and system |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
| CN111177826A (en) * | 2019-12-12 | 2020-05-19 | 江苏艾佳家居用品有限公司 | Indoor home automatic layout method based on deep convolutional network |
| CN110751721A (en) * | 2019-12-24 | 2020-02-04 | 广东博智林机器人有限公司 | Furniture layout drawing generation method and device, computer equipment and storage medium |
| JP6932821B1 (en) * | 2020-07-03 | 2021-09-08 | 株式会社ベガコーポレーション | Information processing systems, methods and programs |
| CN113221225A (en) * | 2021-05-27 | 2021-08-06 | 北京有竹居网络技术有限公司 | Article layout method, article layout device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792358A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Young et al. | Pomdp-based statistical spoken dialog systems: A review | |
| CN104662491B (en) | Automatic gesture for sensing system is recognized | |
| CN111260764B (en) | Method, device and storage medium for making animation | |
| EP4383115A1 (en) | Interior design solution acquisition method and apparatus, computer device, and storage medium | |
| CN107632987A (en) | One kind dialogue generation method and device | |
| Cruz et al. | Multi-modal integration of dynamic audiovisual patterns for an interactive reinforcement learning scenario | |
| WO2023103581A1 (en) | Skeleton-skinning method and apparatus, computer device and storage medium | |
| CN114241100B (en) | Skinning method, skinning device, skinning apparatus, skinning medium, and program product for virtual object | |
| KR20190105403A (en) | An external device capable of being combined with an electronic device, and a display method thereof. | |
| CN112720453A (en) | Method and apparatus for training manipulation skills of a robotic system | |
| CN115115846A (en) | Automatic generation method and device of house type layout, computer equipment and storage medium | |
| Thabet et al. | Sample-efficient deep reinforcement learning with imaginary rollouts for human-robot interaction | |
| CN103218663A (en) | Information processing apparatus, information processing method, and program | |
| CN113792358B (en) | Automatic interactive layout method and device for three-dimensional furniture and electronic equipment | |
| Leino et al. | RL-KLM: Automating keystroke-level modeling with reinforcement learning | |
| CN107256434B (en) | Automatic household layout method | |
| CN117132864A (en) | Multi-mode input digital character generation method, device, equipment and storage medium | |
| Di et al. | Multi-agent reinforcement learning of 3d furniture layout simulation in indoor graphics scenes | |
| CN113449356B (en) | Indoor automatic layout method, indoor automatic layout device, computer equipment and computer-readable storage medium | |
| Henschke et al. | Touchless gestural interaction with wizard-of-oz: Analysing user behaviour | |
| Takano et al. | Construction of a space of motion labels from their mapping to full-body motion symbols | |
| CN115542759A (en) | Intelligent household control method, system and storage medium based on multi-mode recognition | |
| CN114065353A (en) | Indoor arrangement method and device, electronic equipment and storage medium | |
| US20140316757A1 (en) | Motion-Based Design of Mechanical Objects | |
| CN115993783A (en) | Method executed by intelligent device and related device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |