CN110096768A - A kind of method and system fast implementing kitchen autoplacement - Google Patents
A kind of method and system fast implementing kitchen autoplacement Download PDFInfo
- Publication number
- CN110096768A CN110096768A CN201910301857.XA CN201910301857A CN110096768A CN 110096768 A CN110096768 A CN 110096768A CN 201910301857 A CN201910301857 A CN 201910301857A CN 110096768 A CN110096768 A CN 110096768A
- Authority
- CN
- China
- Prior art keywords
- kitchen
- region
- free space
- autoplacement
- furniture
- 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.)
- Granted
Links
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Civil Engineering (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Architecture (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Instructional Devices (AREA)
Abstract
The invention discloses a kind of methods for fast implementing kitchen autoplacement, go out the space that can be laid out according to kitchen layout rule preliminary screening first；Then reasonable parametrization placement model is established using the relationship between spatial information and space and furniture, furniture and furniture；Finally by the furniture placement scheme that the parameter of the layout style acquisition model of learning user input is final with determination.For the difference of kitchen layout and other function space layout, the present invention can generate reasonable kitchen layout scheme according to different space characteristics and specified layout style.
Description
Technical field
The present invention relates to a kind of method and system for fast implementing kitchen autoplacement, belong to Computer-aided Design Technology
Field.
Background technique
With the continuous growth of decoration requirements and finishing upsurge, entangled by designer according to house type and decoration style to be each
The room layout of room design adaptation becomes to take time and effort.Kitchen is necessary region in each living space, and is lived empty
Between the middle highest space of frequency of use.It needs to put the tinkling of jades food materials met the eye on every side and flavoring agent in the lesser kitchen in space and makes for people
With this requires the layout in kitchen that must consider functional and practicability as far as possible.Since existing automatic layout algorithm cannot fit completely
The requirement of kitchen layout is answered, the realization of kitchen autoplacement method is particularly important.
Such as: prior art CN106484940A discloses a kind of home decoration Intelligentized design method, needs in this method
A large amount of design sample is obtained, and domestic layout design result is obtained by intelligent algorithm, but this method is for kitchen
Space as room is small, furniture position is put for the design objective for needing strict control, and it is ineffective that there is machine learning
The problem of；In another example CN107256434A discloses a kind of method of household autoplacement, comprising: need to be laid out in input chamber
Furniture；The furniture of input is ranged into sitting and lying furniture, sitting and lying adjacent furniture, optic centre furniture, comfort furniture respectively
One type in totally four class furniture；It is carried out using the optic centre furniture as core according to the furniture of the classification to input
Combination；The furniture after combination is laid out using tabu search algorithm, needs to use tabu search algorithm in this method, because
This needs to preset more critical parameter, and intelligent effect is bad, and under condition of small sample, layout designs result is not
It is able to satisfy the requirement of design of kitchen.
Summary of the invention
The present invention has designed and developed a kind of method for fast implementing kitchen autoplacement.The present invention is according to the base of kitchen layout
This rule screens arrangement space, obtains the candidate region that can be laid out.Then, the present invention is by the information of kitchen layout feature
It is converted to a parametrization placement model, the layout effect with different-style is obtained by the parameter set and changed in model
Figure.Importantly, the present invention can learn the parameter in placement model according to the style that user specifies, so that user
Oneself desired layout effect can be seen in time.
A method of kitchen autoplacement is fast implemented, is included the following steps:
Step 1 obtains the position of door and window in kitchen floor plan and figure；
Step 2 is determined in the floor plan of kitchen for placing the freeboard region of article of furniture；
Step 3 designs needs by the placement model or machine learning method of setup parameter in freeboard region
The position of the object of layout.
In one embodiment, the freeboard region is continuous and is distributed along wall.
In one embodiment, the opening and closing space of freeboard region with the door is not overlapped.
In one embodiment, the ratio that the area of the freeboard region accounts for kitchen area is no more than setting threshold
Value.
In one embodiment, two parallel the distance between rectangles in the freeboard region are greater than
Given threshold.
In one embodiment, it is set as the longest rectangle of length in freeboard region to be used for the area of cloth object storage component
Domain.
In one embodiment, in the freeboard region it needs to be determined that position of hearth and pond out.
In one embodiment, hearth and pond are located in the region for cloth object storage component.
In one embodiment, hearth is located at one end of the separate window in the region for cloth object storage component.
In one embodiment, machine learning method includes but is not limited to: genetic algorithm, neural network algorithm, support
Vector machine algorithm etc..
In one embodiment, machine learning method includes the following steps:
S1 reads in kitchen floor plan sample data, obtains the object in sample data；
S2 calculates the distance between each object and wall, and each object is belonged to the nearest face wall of the object distance
On body；
S3 makes minimum circumscribed rectangle for the corresponding object of each face wall body；And by the minimum circumscribed rectangle near
The side of wall side extends to line segment where wall, and other three sides of the minimum circumscribed rectangle are expanded to suitable position
It sets, the region that each minimum circumscribed rectangle obtains after expansion is determined as sample free space；
S4, using object as input value, using object in the relative position of sample free space as output valve, model is trained,
Obtain prediction model；
S5 obtains the object for needing to be laid out, and exports the free space that object is obtained in step 2 by above-mentioned prediction model
Position in region.
In one embodiment, the placement model of parametrization be refer to quantitatively representation space and furniture, furniture with
The rule of positional relationship between furniture.
A kind of system fast implementing kitchen autoplacement, comprising:
Floor plan identification module, for obtaining the position of door and window in kitchen floor plan and figure；
Free space generation module, for determining in the floor plan of kitchen for placing the freeboard region of article of furniture；
Layout modules, for being designed in freeboard region by the placement model or machine learning method of setup parameter
The position for the object for needing to be laid out out.
In one embodiment, the free space generation module executes following judgement: the free space region
Domain is continuous and is distributed along wall；The opening and closing space of freeboard region with the door is not overlapped；The free space
The ratio that the area in region accounts for kitchen area is no more than given threshold；Two parallel squares in the freeboard region
The distance between shape is greater than given threshold.
In one embodiment, the free space generation module is by the longest square of length in freeboard region
Shape is set as the region for cloth object storage component.
In one embodiment, the free space generation module determines stove in the freeboard region
The position of platform and pond.
In one embodiment, hearth and pond are set to the region of cloth object storage component by the free space generation module
In；Hearth is located at one end of the separate window in the region for cloth object storage component.
In one embodiment, machine learning method includes but is not limited to: genetic algorithm, neural network algorithm, support
Vector machine algorithm etc..
It in one embodiment, include machine learning module in layout modules, the machine learning module includes:
Object read module obtains the object in sample data for reading in kitchen floor plan sample data；
Object belongs to determination module and each object is belonged to the object for calculating the distance between each object and wall
On the nearest face wall of part distance；
Sample free space determining module makes minimum circumscribed rectangle for being directed to the corresponding object of each face wall body；And by institute
The minimum circumscribed rectangle stated extends to line segment where wall near the side of wall side, and by the minimum circumscribed rectangle
Other three sides are expanded to suitable position, and the region that each minimum circumscribed rectangle obtains after expansion is determined as sample freedom
Region；
Sample training module, for using object as input value, using object in the relative position of sample free space as output valve, it is right
Model is trained, and obtains prediction model；
Layout modules export object in free space by the prediction model for obtaining the object for needing to be laid out
Position in region.
It is a kind of to record the computer-readable of the program that run the above-mentioned method for fast implementing kitchen autoplacement
Medium.
Beneficial effect
The present invention filters out the candidate region that can be laid out using kitchen layout rule to given space, by establishing furniture and sky
Between, the correlation between different furniture construct a parametrization placement model, the layout style of user's requirement is learnt
Layout parameter is obtained, finally determines placement scheme.When user selects different layout styles, placement model can be rapidly to it
Learnt and obtains reasonable placement scheme under the space.
Detailed description of the invention
Fig. 1 is the flow diagram of the method for the invention.
Fig. 2 be the method for the invention in screening can layout areas flow diagram.
Fig. 3 is to obtain the flow diagram of furniture placement scheme in the method for the invention.
Fig. 4 be the method for the invention in filter out can arrangement space schematic diagram.
Fig. 5 is in machine learning algorithm to the schematic diagram of training sample processing.
Fig. 6 is the schematic three dimensional views that kitchen autoplacement is realized in the method for the invention.
Specific embodiment
In order to illustrate more clearly of the technical solution of embodiments herein, will make below to required in embodiment description
Attached drawing is briefly described.It should be evident that the accompanying drawings in the following description is only some examples or implementation of the application
Example, for those of ordinary skill in the art, without creative efforts, can also be according to these attached drawings
The application is applied to other similar scene.It should be appreciated that providing these exemplary embodiments merely to making related fields
Technical staff better understood when and then realize the present invention, be not intended to limit the scope of the invention in any way.
As shown in the application and claims, unless context clearly prompts exceptional situation, " one ", "one", " one
The words such as kind " and/or "the" not refer in particular to odd number, may also comprise plural number.It is, in general, that term " includes " only prompts to wrap with "comprising"
Include clearly identify the step of and element, and these steps and element do not constitute one it is exclusive enumerate, method or apparatus
The step of may also including other or element.
Although the application is made that certain systems, module or the unit in system according to an embodiment of the present application various
Reference, however, any amount of disparate modules can be used and be operated on client and/or server.The module is only
It is illustrative, and disparate modules can be used in the different aspect of the system and method.
Meanwhile the application has used particular words to describe embodiments herein.Such as " one embodiment ", " one implements
Example ", and/or " some embodiments " mean a certain feature relevant at least one embodiment of the application, structure or feature.Cause
This, it should be highlighted that and it is noted that " embodiment " or " an implementation referred to twice or repeatedly in this specification in different location
Example " or " alternate embodiment " are not necessarily meant to refer to the same embodiment.In addition, in one or more embodiments of the application
Certain features, structure or feature can carry out combination appropriate.
Since kitchen space is narrow, the furniture type for needing to be added is more, if directly adopt machine learning exports cloth again
When the mode of office's result, the rule in readily understood some layouts out is not allowed in machine learning, leads to learning effect and output result all
And there are deviations for actual demand.Therefore, during the present invention introduces autoplacement by priori, first passing through introducing " can
Such a concept of the free space of layout ", and in the concept be embedded in kitchen in Basic Design rule, i.e., " pond " and
" hearth ", then can be obtained by the free space of a preliminary basic use habit, then again in the free space of generation
It is middle that autoplacement space is generated using machine learning and method, so that it may preferably to allow cloth of algorithm under the conditions of one restricted
Office's rule, is converted to a parametrization placement model for the information of kitchen layout feature, by setting and changing the ginseng in model
Number obtains the layout effect picture with different-style, it will be able to more targetedly carry out certainly under the premise of meeting living habit
Dynamic layout, improves the accuracy of algorithm output.The present invention can learn in placement model according to the style that user specifies
Parameter, so that user can see oneself desired layout effect in time.
Although the layout designs in kitchen have the characteristics that different according to different space structures, there are certain general character.Kitchen
Room and other function space are distinct: kitchen space area is small, complicated for operation, functional, thus kitchen lie in be not
Size, but functional planning.The functional areas in kitchen are generally divided into cooking area, Storage and scrubbing section, the arrangement of each functional areas
It need to be determined by people in the operating process in kitchen, it is necessary to meet harmony and fluency.Particularly, empty for enclosed kitchen
Between, cabinet generally arranges along wall and has certain continuity, with guarantor by enough operating spaces.
The present invention provides a kind of method for fast implementing kitchen autoplacement comprising:
Step 1) goes out the free space that can be laid out based on the kitchen layouts rule preliminary screening such as door, space utilization rate；
For the particular kitchen space of input, furniture, and the type and quantity of furniture are not present in the front space of initial designs
Indefinite (hearth and pond are essential for kitchen).Other furniture be the division for completing free space it
Afterwards, it is introduced further according to the habit of user.
Next it needs to generate a free space according to artificially determining use habit, to the layout principles of free space
Including but not limited to: free space along wall be distributed and it is continuously distributed；Region is opened an account and closed in the region of door cannot be by free space
It blocks and (can not be blocked by other objects), and the distance of furniture to the two sides of door and door cannot be excessively close；Guarantee to close between cabinet body
Suitable distance avoids impacting discrepancy；Reasonable space utilization rate guarantees there are enough operating spaces using the people in kitchen.
For the wall in space, determine whether the wall can put furniture according to the wall where door first, if cannot put
When furniture, free space should not be divided on the wall where door, it, can if the wall where door is sufficiently wide when can place furniture
Free space is included in vacant wall space, and the layout range for the wall being adjacent, such as Fig. 4, door to its place
No. 1 wall both ends distance be less than threshold value, it is too short to put furniture；The range that is laid out of No. 4 walls is whole face wall.
Wall (No. 2 of such as Fig. 4 and No. 4 walls) parallel for two sides works as passage in order to which guarantor has enough passage spaces
Width be less than people front walking apart from when；In addition, it is good to can choose longer in parallel wall and continuity under optimum condition
Wall as the specific preferable layout region in free space, furniture article emphasis places (4 in Fig. 4 in this region
Number wall)；It is of course also possible to arrange in whole free spaces.
For space utilization rate, the area utilization in general kitchen is usually no more than 60%.When area utilization is greater than threshold value
When, then it cannot be guaranteed that enough operating spaces, need to consider in the utilization rate limit it is best can layout areas；Sky mentioned here
Between utilization rate refer to that free space accounts for the percentage of entire kitchen area.
After basic free space has been determined, it is also necessary to wherein the region in hearth and pond is being determined, due to
The two furniture are the most important objects in kitchen, therefore, it can be first arranged in free space.In the floor plan of acquisition
In, obtain the position of window, due to hearth should not directly with window it is neighbouring, be otherwise easy to appear the knot that stove fire is gone out by wind
Therefore fruit in the free space of determination above, chooses the position far from window and determines hearth, in addition, due to being washed
Biggish area is needed when washing operation, therefore, is also provided with discharge bay on the above-mentioned longer area of space of line segment.
Based on above step, the determination of free space in kitchen, and the house type based on kitchen are realized, in free zone
The region in hearth and pond is defined in domain.It on this basis, can be more targeted by subsequent design means
In limited conditions to the study of sample and output.
Step 2, the placement model for determining other articles in kitchen.
In this step, this placement model is also possible to based on artificial warp either what machine learning algorithm generated
It tests specified.
By taking artificial experience is specified as an example:
Reasonable ginseng is formulated using the relationship between spatial information (door, window, shape etc.) and space and furniture, furniture and furniture
Shuo Hua placement model；It is that layout rules be limited to type of item all to be in freely empty when formulating model rule
Between inside in so that meeting the status requirement for the free space that above-mentioned steps obtain by the result that parameter model obtains.
Parametrization placement model refers to by the way that lay down a regulation can be quantitatively between representation space and furniture, furniture and furniture
Positional relationship.Parameterized model will consider to put sequence and relative distance between different functionalities furniture, to guarantee to grasp
The fluency and harmony of work.
Basket is drawn in the angled cabinet of the classification of other cabinets, seasoning, and drawer etc. formulates different classes of cabinet different plans
Slightly, such as seasoning draws basket that should should be placed on the corner etc. of layout areas close to hearth, angular counter.
By taking machine learning algorithm as an example:
The machine learning algorithm that can be used includes but does not limit: genetic algorithm, neural network algorithm, algorithm of support vector machine
Deng.
Firstly, obtaining the type of other articles in kitchen by input data sample；For example, being obtained in Fig. 5
Six articles of A/B/C/D/E/F are arrived.In addition, if the preliminary in step 1 pond determined in free space and
Behind the position of hearth, it can also no longer need to be laid out processing to the position in pond and hearth again, it in this case, can
To select the object in the training sample that will identify that not include pond and hearth.
Next, being belonged to this six articles from the positional distance of four sides wall to different metopes according to them；
For example, A article, it is closer with the position of wall above in figure, and farther out with the left side and following wall displacement, therefore, by A object
Product belong to that face wall above；Similarly, C/D belongs to the wall on the left side, and E/F belongs to following wall；
Then, then by the article for belonging to each face wall determine that maximum boundary rectangle belongs to the A/B of abutment wall as shown in Figure 5
Article can determine maximum boundary rectangle 1, and the C/D article for belonging to leftwall can determine maximum boundary rectangle 2, ownership
Maximum boundary rectangle 3 can be determined in the E/F article of lower abutment wall；
Again by each boundary rectangle it is opposite with wall beyond extend to the side where wall, and again by be stretched with this face this
Adjacent both sides are extended to two sides on one side, this boundary rectangle is made to be extended to region appropriate, just raw after completing extension
At a new region, the region after this is extended is defined as free space, just makes itself and previous step 1) in freedom
Space is corresponding；Similarly, maximum boundary rectangle 2 and 3 can be extended respectively and generates two free spaces.
Then, according to the data in sample, the relative position of these articles respectively in free space is obtained.Again by article
Type as input value, the relative position of article in free space as output valve, using machine learning algorithm to sample into
Row study, obtains empirical law therein, finds the placement location of different articles in excellent design, and formation designs a model.
Finally, by the specified type of goods for needing to be added in new layout of user, according to generated in previous step 1 from
By space, the relative position of article in free space is exported by model, the kitchen layout of generation can be obtained.
In above scheme, a virtual freedom is constructed in the position by then passing through the object in training sample itself
Space, and the arrangement of object is based on the relative position in this Virtual Space, therefore, machine learning algorithm
Data dimension is significantly reduced, without the concern for the absolute space size width in kitchen, so that input vector is reduced；Meanwhile again
Due to being data sample to be directly constrained in the free space of one artificial settings, avoid conventional machine learning algorithm not
It can effectively identify the intrinsic placement rule in kitchen, therefore, also improve the learning efficiency of machine learning, avoid sample
The bad problem of learning effect under this quantity.Therefore, the pre-treatment of data and subsequent feature extraction handle two steps
Between mutually cooperate with, complete jointly dimensionality reduction overall technology design.
Due in the methods described above, by constructing a preparatory free space, and by sample data
As soon as article position marked off a corresponding freeboard region, then algorithm is during study, it is easier to which ground is right
The rule in kitchen is determined, and reduces the dimension of algorithm, improves the accuracy of computational efficiency and result output.
The parameter of placement model can rule of thumb be manually specified, the layout style that can also be inputted according to user
It practises, to reach the requirement of user.
Referring to fig. 4, the present invention goes out the region that can be laid out according to spatial information and above-mentioned kitchen layout rule preliminary screening,
Shadow representation is used in Fig. 4；When given layout style or layout requirements, water is determined according to the parameter for calculating placement model first
The position in pond and hearth: in fenestrate space, pond keeps certain relative distance generally proximate to window, hearth and pond；Most
Determine the position of other cabinets again afterwards.It is the kitchen schematic diagram being laid out such as Fig. 6.
Based on above method, the present invention also provides a kind of systems for fast implementing kitchen autoplacement, comprising:
Floor plan identification module, for obtaining the position of door and window in kitchen floor plan and figure；
Free space generation module, for determining in the floor plan of kitchen for placing the freeboard region of article of furniture；
Layout modules, for being designed in freeboard region by the placement model or machine learning method of setup parameter
The position for the object for needing to be laid out out.
In one embodiment, the free space generation module executes following judgement: the free space region
Domain is continuous and is distributed along wall；The opening and closing space of freeboard region with the door is not overlapped；The free space
The ratio that the area in region accounts for kitchen area is no more than given threshold；Two parallel squares in the freeboard region
The distance between shape is greater than given threshold.
In one embodiment, the free space generation module is by the longest square of length in freeboard region
Shape is set as the region for cloth object storage component.
In one embodiment, the free space generation module determines stove in the freeboard region
The position of platform and pond.
In one embodiment, hearth and pond are set to the region of cloth object storage component by the free space generation module
In；Hearth is located at one end of the separate window in the region for cloth object storage component.
In one embodiment, machine learning method includes but is not limited to: genetic algorithm, neural network algorithm, support
Vector machine algorithm etc..
It in one embodiment, include machine learning module in layout modules, the machine learning module includes:
Object read module obtains the object in sample data for reading in kitchen floor plan sample data；
Object belongs to determination module and each object is belonged to the object for calculating the distance between each object and wall
On the nearest face wall of part distance；
Sample free space determining module makes minimum circumscribed rectangle for being directed to the corresponding object of each face wall body；And by institute
The minimum circumscribed rectangle stated extends to line segment where wall near the side of wall side, and by the minimum circumscribed rectangle
Other three sides are expanded to suitable position, and the region that each minimum circumscribed rectangle obtains after expansion is determined as sample freedom
Region；
Sample training module, for using object as input value, using object in the relative position of sample free space as output valve, it is right
Model is trained, and obtains prediction model；
Layout modules export object in free space by the prediction model for obtaining the object for needing to be laid out
Position in region.
The present invention also provides a kind of record can run the journey of the above-mentioned method for fast implementing kitchen autoplacement
The computer-readable medium of sequence.
In addition, it will be understood by those skilled in the art that the various aspects of the application can be by several with patentability
Type or situation are illustrated and described, the combination or right including any new and useful process, machine, product or substance
Their any new and useful improvement.Correspondingly, the various aspects of the application can completely by hardware execute, can be complete
It is executed, can also be executed by combination of hardware by software (including firmware, resident software, microcode etc.).Hardware above is soft
Part is referred to alternatively as " data block ", " module ", " engine ", " unit ", " component " or " system ".In addition, the various aspects of the application
The computer product being located in one or more computer-readable mediums may be shown as, which includes computer-readable program
Coding.
Computer-readable signal media may include the propagation data signal containing computer program code in one, such as
A part in base band or as carrier wave.The transmitting signal may there are many forms of expression, including electromagnetic form, light form etc.
Deng or suitable combining form.Computer-readable signal media can be any meter in addition to computer readable storage medium
Calculation machine readable medium, the medium can be realized by being connected to an instruction execution system, device or equipment communication, propagate or
Transmit the program for using.Program coding in computer-readable signal media can be carried out by any suitable medium
It propagates, the combination including radio, cable, fiber optic cables, radiofrequency signal or similar mediums or any of above medium.
Computer program code needed for the operation of the application each section can use any one or more programming language,
Including Object-Oriented Programming Language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET,
Python etc., conventional procedural programming language for example C language, Visual Basic, 2003 Fortran, Perl, COBOL 2002,
PHP, ABAP, dynamic programming language such as Python, Ruby and Groovy or other programming languages etc..The program coding can be complete
Entirely on the user computer run run on the user computer as independent software package or partially in subscriber computer
Upper operation part runs in remote computer or runs on a remote computer or server completely.In the latter cases, remotely
Computer can be connect by any latticed form with subscriber computer, such as local area network (LAN) or wide area network (WAN), or even
It is connected to outer computer (such as passing through internet), or in cloud computing environment, or is serviced as service using such as software
(SaaS)。
In addition, except clearly stating in non-claimed, the sequence of herein described processing element and sequence, digital alphabet
Using or other titles use, be not intended to limit the sequence of the application process and method.Although by each in above-mentioned disclosure
Kind of example discuss it is some it is now recognized that useful inventive embodiments, but it is to be understood that, such details only plays explanation
Purpose, appended claims are not limited in the embodiment disclosed, on the contrary, claim is intended to cover and all meets the application
The amendment and equivalent combinations of embodiment spirit and scope.For example, although system component described above can be set by hardware
It is standby to realize, but can also be only achieved by the solution of software, such as pacify on existing server or mobile device
Fill described system.
Claims (10)
1. a kind of method for fast implementing kitchen autoplacement, which comprises the steps of: step 1 obtains kitchen family
The position of door and window in type figure and figure；Step 2 is determined in the floor plan of kitchen for placing the free space region of article of furniture
Domain；Step 3 is designed in freeboard region by the placement model or machine learning method of setup parameter and needs cloth
The position of the object of office.
2. the method according to claim 1 for fast implementing kitchen autoplacement, which is characterized in that in an embodiment
In, the freeboard region is continuous and is distributed along wall.
3. the method according to claim 1 for fast implementing kitchen autoplacement, which is characterized in that in an embodiment
In, the freeboard region is not overlapped with the opening and closing space of door.
4. the method according to claim 1 for fast implementing kitchen autoplacement, which is characterized in that the free space
The ratio that the area in region accounts for kitchen area is no more than given threshold；Two parallel squares in the freeboard region
The distance between shape is greater than given threshold；It is set as the longest rectangle of length in freeboard region to be used for the area of cloth object storage component
Domain.
5. the method according to claim 1 for fast implementing kitchen autoplacement, which is characterized in that the free space
In the region it needs to be determined that position of hearth and pond out；Hearth and pond are located in the region for cloth object storage component；Hearth is located at
One end for the separate window in the region of cloth object storage component；Machine learning method includes but is not limited to: genetic algorithm, nerve net
Network algorithm, algorithm of support vector machine etc..
6. the method according to claim 1 for fast implementing kitchen autoplacement, which is characterized in that machine learning method packet
Include following steps:
S1 reads in kitchen floor plan sample data, obtains the object in sample data；
S2 calculates the distance between each object and wall, and each object is belonged to the nearest face wall of the object distance
On body；
S3 makes minimum circumscribed rectangle for the corresponding object of each face wall body；And by the minimum circumscribed rectangle near
The side of wall side extends to line segment where wall, and other three sides of the minimum circumscribed rectangle are expanded to suitable position
It sets, the region that each minimum circumscribed rectangle obtains after expansion is determined as sample free space；
S4, using object as input value, using object in the relative position of sample free space as output valve, model is trained,
Obtain prediction model；
S5 obtains the object for needing to be laid out, and exports the free space that object is obtained in step 2 by above-mentioned prediction model
Position in region；The placement model of parametrization is the position referred between quantitatively representation space and furniture, furniture and furniture
Set the rule of relationship.
7. a kind of system for fast implementing kitchen autoplacement characterized by comprising
Floor plan identification module, for obtaining the position of door and window in kitchen floor plan and figure；
Free space generation module, for determining in the floor plan of kitchen for placing the freeboard region of article of furniture；
Layout modules, for being designed in freeboard region by the placement model or machine learning method of setup parameter
The position for the object for needing to be laid out out.
8. the system according to claim 7 for fast implementing kitchen autoplacement, which is characterized in that the free space
Generation module executes following judgement: the freeboard region is continuous and is distributed along wall；The free space region
Domain is not overlapped with the opening and closing space of door；The ratio that the area of the freeboard region accounts for kitchen area is no more than setting threshold
Value；The distance between two parallel rectangles in the freeboard region are greater than given threshold；The free zone
Domain generation module is set as the longest rectangle of length in freeboard region to be used for the region of cloth object storage component；The free zone
Domain generation module determines the position in hearth and pond in the freeboard region；The free space generation module
Hearth and pond are set in the region of cloth object storage component；Hearth is located at one of the separate window in the region for cloth object storage component
End；Machine learning method includes but is not limited to: genetic algorithm, neural network algorithm, algorithm of support vector machine etc..
9. the system according to claim 7 for fast implementing kitchen autoplacement, which is characterized in that include in layout modules
Machine learning module, the machine learning module include:
Object read module obtains the object in sample data for reading in kitchen floor plan sample data；
Object belongs to determination module and each object is belonged to the object for calculating the distance between each object and wall
On the nearest face wall of part distance；
Sample free space determining module makes minimum circumscribed rectangle for being directed to the corresponding object of each face wall body；And by institute
The minimum circumscribed rectangle stated extends to line segment where wall near the side of wall side, and by the minimum circumscribed rectangle
Other three sides are expanded to suitable position, and the region that each minimum circumscribed rectangle obtains after expansion is determined as sample freedom
Region；
Sample training module, for using object as input value, using object in the relative position of sample free space as output valve, it is right
Model is trained, and obtains prediction model；
Layout modules export object in free space by the prediction model for obtaining the object for needing to be laid out
Position in region.
10. a kind of record the meter that can run the program of the method described in claim 1 for fast implementing kitchen autoplacement
Calculation machine readable medium.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910301857.XA CN110096768B (en) | 2019-04-16 | 2019-04-16 | Method and system for quickly realizing automatic layout of kitchen |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910301857.XA CN110096768B (en) | 2019-04-16 | 2019-04-16 | Method and system for quickly realizing automatic layout of kitchen |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110096768A true CN110096768A (en) | 2019-08-06 |
| CN110096768B CN110096768B (en) | 2022-07-08 |
Family
ID=67444976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910301857.XA Active CN110096768B (en) | 2019-04-16 | 2019-04-16 | Method and system for quickly realizing automatic layout of kitchen |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110096768B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555284A (en) * | 2019-09-12 | 2019-12-10 | 杭州群核信息技术有限公司 | Cloud rapid modeling and design method based on spatial position |
| CN110737963A (en) * | 2019-12-20 | 2020-01-31 | 广东博智林机器人有限公司 | Poster element layout method, poster element layout system, computer equipment and storage medium |
| CN110874496A (en) * | 2020-01-20 | 2020-03-10 | 广东博智林机器人有限公司 | Building placement method and device based on reinforcement learning, storage medium and computer equipment |
| CN111104704A (en) * | 2019-12-10 | 2020-05-05 | 杭州群核信息技术有限公司 | Cabinet internal layout design method, device and system and storage medium |
| CN111161379A (en) * | 2019-12-13 | 2020-05-15 | 江苏艾佳家居用品有限公司 | Indoor home automatic layout algorithm based on deep learning and empty house type feature detection |
| CN111882644A (en) * | 2020-06-23 | 2020-11-03 | 北京城市网邻信息技术有限公司 | Furniture display method and device |
| CN112163308A (en) * | 2020-10-13 | 2021-01-01 | 西安理工大学 | Adaptive guide design layout method |
| CN113360981A (en) * | 2021-06-04 | 2021-09-07 | 深圳须弥云图空间科技有限公司 | Automatic furniture layout method and device, storage medium and electronic equipment |
| CN113434934A (en) * | 2021-06-28 | 2021-09-24 | 杭州群核信息技术有限公司 | Household layout placing method and device and storage medium |
| CN113742996A (en) * | 2021-07-28 | 2021-12-03 | 杭州群核信息技术有限公司 | Processing method and device for cabinet layout |
| CN114935994A (en) * | 2022-05-10 | 2022-08-23 | 阿里巴巴（中国）有限公司 | Article data processing method, device and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595768A (en) * | 2018-03-28 | 2018-09-28 | 杭州群核信息技术有限公司 | A kind of the autoplacement system and device of kitchen space |
| CN109033652A (en) * | 2018-08-02 | 2018-12-18 | 江苏艾佳家居用品有限公司 | A kind of indoor autoplacement method based on sliding window feature and regression forecasting |
-
2019
- 2019-04-16 CN CN201910301857.XA patent/CN110096768B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595768A (en) * | 2018-03-28 | 2018-09-28 | 杭州群核信息技术有限公司 | A kind of the autoplacement system and device of kitchen space |
| CN109033652A (en) * | 2018-08-02 | 2018-12-18 | 江苏艾佳家居用品有限公司 | A kind of indoor autoplacement method based on sliding window feature and regression forecasting |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555284A (en) * | 2019-09-12 | 2019-12-10 | 杭州群核信息技术有限公司 | Cloud rapid modeling and design method based on spatial position |
| CN111104704A (en) * | 2019-12-10 | 2020-05-05 | 杭州群核信息技术有限公司 | Cabinet internal layout design method, device and system and storage medium |
| CN111104704B (en) * | 2019-12-10 | 2023-08-18 | 杭州群核信息技术有限公司 | Cabinet internal layout design method, device and system and storage medium |
| CN111161379B (en) * | 2019-12-13 | 2022-07-08 | 江苏艾佳家居用品有限公司 | Indoor home automatic layout method based on deep learning empty house type feature detection |
| CN111161379A (en) * | 2019-12-13 | 2020-05-15 | 江苏艾佳家居用品有限公司 | Indoor home automatic layout algorithm based on deep learning and empty house type feature detection |
| CN110737963A (en) * | 2019-12-20 | 2020-01-31 | 广东博智林机器人有限公司 | Poster element layout method, poster element layout system, computer equipment and storage medium |
| CN110737963B (en) * | 2019-12-20 | 2020-03-31 | 广东博智林机器人有限公司 | Poster element layout method, system and computer readable storage medium |
| CN110874496A (en) * | 2020-01-20 | 2020-03-10 | 广东博智林机器人有限公司 | Building placement method and device based on reinforcement learning, storage medium and computer equipment |
| CN111882644A (en) * | 2020-06-23 | 2020-11-03 | 北京城市网邻信息技术有限公司 | Furniture display method and device |
| CN112163308A (en) * | 2020-10-13 | 2021-01-01 | 西安理工大学 | Adaptive guide design layout method |
| CN113360981A (en) * | 2021-06-04 | 2021-09-07 | 深圳须弥云图空间科技有限公司 | Automatic furniture layout method and device, storage medium and electronic equipment |
| CN113360981B (en) * | 2021-06-04 | 2024-04-16 | 深圳须弥云图空间科技有限公司 | Furniture automatic layout method and device, storage medium and electronic equipment |
| CN113434934A (en) * | 2021-06-28 | 2021-09-24 | 杭州群核信息技术有限公司 | Household layout placing method and device and storage medium |
| CN113742996A (en) * | 2021-07-28 | 2021-12-03 | 杭州群核信息技术有限公司 | Processing method and device for cabinet layout |
| CN114935994A (en) * | 2022-05-10 | 2022-08-23 | 阿里巴巴（中国）有限公司 | Article data processing method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110096768B (en) | 2022-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110096768A (en) | A kind of method and system fast implementing kitchen autoplacement | |
| CN109740243A (en) | A kind of furniture layout method and system based on bulk-breaking intensified learning technology | |
| CN109670264A (en) | A kind of intensified learning domestic layout optimization method and system | |
| CN101930627B (en) | Three-dimensional dwelling size modeling method based on two-dimensional dwelling size diagram | |
| US11270034B1 (en) | Method and system for kitchen cabinet layout | |
| CN108694266A (en) | intelligent decoration design method and system based on machine learning | |
| CN109697653A (en) | Generate the method and system of individual microdata | |
| US10430525B2 (en) | Reconfigurable spaces | |
| CN111274627B (en) | Automatic kitchen layout method and device based on nonlinear optimization and computer equipment | |
| CN110084293A (en) | A kind of determination method and apparatus in complete bright pattern house | |
| CN109698777A (en) | Smart home mode configuration method, device and equipment | |
| CN111400960A (en) | Furniture active customization method and active customization device | |
| Ougolnitsky et al. | Solution algorithms for differential models of hierarchical control systems | |
| CN113988989A (en) | Intelligent recommendation method and system suitable for imported furniture and storage medium | |
| CN109063827B (en) | Method, system, storage medium and terminal for automatically taking specific luggage in limited space | |
| Zhang et al. | Federated Markov Logic Network for indoor activity recognition in Internet of Things | |
| Rahimi-Vahed et al. | A hybrid multi-objective particle swarm algorithm for a mixed-model assembly line sequencing problem | |
| CN106066928A (en) | A kind of health data based reminding method based on mobile terminal and mobile terminal | |
| KR102443166B1 (en) | Apparatus and method for recommending object on adjacent trunk line based on data structure of trunk line connection generated from big data of interior service | |
| CN109815551A (en) | Architectural design method, device, readable storage medium storing program for executing and mixed reality equipment | |
| CN114781724A (en) | Intelligent replenishment decision-making method based on reinforcement learning and simulated learning and storage medium | |
| KR20220072381A (en) | Apparatus and method for recommending object on adjacent trunk line based on data structure of trunk line connection generated from big data of interior service | |
| Akbari et al. | Gakh: A new evolutionary algorithm for graph clustering problem | |
| KR102524780B1 (en) | System for designing kitchen drawing based on 2d/3d | |
| KR102549980B1 (en) | Apparatus and method for providing model for arrangement of object of interior service based on reinforcement learning |
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 | ||
| CB02 | Change of applicant information |
Address after: 211100 floor 5, block a, China Merchants high speed rail Plaza project, No. 9, Jiangnan Road, Jiangning District, Nanjing, Jiangsu (South Station area) Applicant after: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. Address before: 211100 No. 18 Zhilan Road, Science Park, Jiangning District, Nanjing City, Jiangsu Province Applicant before: JIANGSU AIJIA HOUSEHOLD PRODUCTS Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |