CN108694266A - intelligent decoration design method and system based on machine learning - Google Patents
intelligent decoration design method and system based on machine learning Download PDFInfo
- Publication number
- CN108694266A CN108694266A CN201710739955.2A CN201710739955A CN108694266A CN 108694266 A CN108694266 A CN 108694266A CN 201710739955 A CN201710739955 A CN 201710739955A CN 108694266 A CN108694266 A CN 108694266A
- Authority
- CN
- China
- Prior art keywords
- room
- study
- furniture
- user
- finishing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Theoretical Computer Science (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Architecture (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a kind of intelligent Decoration Design method and system based on machine learning.Decoration Design method (400) according to the present invention based on machine learning, including:With the method for machine learning, study finishing is regular (S401) in advance from existing Decoration Design scheme;It inputs floor plan and user requires (S403);It is required according to the floor plan of input and user, function is determined for each room, and according to the size and function in each room, according to the finishing rule of study automatically to room selection furniture (S405);It is each selected furniture of room automatic putting (S407) according to the finishing rule of study;And the finishing rule according to study, several limited design schemes are chosen from the multiple design schemes for being well placed selected furniture to be presented to the user (S409).
Description
Technical field
The present invention relates to machine learning and artificial intelligence, it is more particularly to the intelligent Decoration Design method based on machine learning
With system.
Background technology
In current Decoration Design industry, it is common to use Decoration Design teacher adds the mode of professional Decoration Design software to be to have
The consumer of Decoration Design wish provides Decoration Design scheme.
In the software of existing Decoration Design, some software needs do design manually and put, be from mock-up funiture library
Article pendulum is hauled out in floor plan, doing so a design will take an undesirably long time.In the case, user oneself will learn
Practise how deep operations software, user wants oneself to go for furniture to model library, and furniture is put into some room of floor plan,
The even longer time 2 hours is usually spent to complete a design.
Software also provides a series of rendering effect figure of model room templates and they, allows user to select model room, then
House type according to model room to user generates design scheme.In the case, the number of model room template is typically limited, no
Centainly meet the needs of users.If the house type of user and the house type gap of model room are larger, sample is applied mechanically again in this case
Design between plate can be barely satisfactory, it is difficult to meet the needs of users, it is also difficult to which the desired design for reaching user is horizontal.
In addition, a kind of common mode is, designer listens to the demand of user and draws floor plan according to practical house type,
It is presented to the user after being finished in design software.Such mode or such software have that real-time is bad, Yong Huyao
Etc. longer times.In addition, the level of designer is irregular, so the scheme provided is not necessarily met the needs of users.
Therefore, it is necessary to a kind of design and the fast automatic intelligence for generating design scheme of energy are done for the specific floor plan of user
Decoration Design product.
Invention content
In order to overcome the defect of prior art mentioned above, the present invention to propose a kind of intelligence dress based on machine learning
Repair design method and system.The present invention determines room type according to house type and subscriber household situation and hobby, according to room class
Type size and the brand style etc. of user's selection select the furniture that each room will be put to user.The present invention can intelligently be drawn
Divide functional area, is put not to different types of room using along wall sampling and tree-shaped search strategy on the basis of rule module
Same furniture.Evaluation system according to the present invention can select best Decoration Design scheme.
According to the first aspect of the invention, a kind of intelligent Decoration Design method based on machine learning is provided, including:Use machine
Study finishing is regular in advance from existing Decoration Design scheme for the method for device study;It inputs floor plan and user requires;According to
The floor plan of input and user require, and function are determined for each room, and according to the size and function in each room, according to study
Finishing rule automatically give room select furniture;It is each selected family of room automatic putting according to the finishing rule of study
Tool;And the finishing rule according to study, it is chosen from the multiple design schemes for being well placed selected furniture limited several
A design scheme is presented to the user.
Preferably for public space region, Intelligent partition algorithm may be used, intelligently divide and define different functions
Area;According to the division and definition of functional areas, each functional areas are given to select furniture automatically.
Preferably, in furniture selected for each room automatic putting, the strategy sampled along wall may be used, along
Wall samples limited several key points, the selected furniture of automatic putting in these key points.
Preferably, it during automatic putting furniture is to form multiple design schemes, can be carried out by tree
Search, directly removes bad design scheme.
Preferably, series of rules is created for each element of design decorating scheme according to the finishing of study rule,
To constitute Evaluation subsystem;Each Evaluation subsystem can make each element evaluation, all evaluation subsystems of weighted comprehensive
The evaluation united to all elements, obtains the overall merit of all elements;It can be with above-mentioned steps to being well placed selected furniture
Multiple design schemes are evaluated one by one, obtain weighted synthetical evaluation;The weighted synthetical evaluation of more above-mentioned multiple design schemes,
Several highest limited design schemes of evaluation are therefrom chosen to be presented to the user.
Preferably, several described limited design schemes are five or less design scheme.
According to the second aspect of the invention, a kind of intelligent Decoration Design system based on machine learning is provided, including:Machine
Learn extracting rule module, for rule to be fitted up in study in advance from existing Decoration Design scheme with the method for machine learning;
Interactive module is required for inputting floor plan and user;Primary election module, for according to the floor plan of input and user's requirement, being
Each room determines function, and according to the size and function in each room, is selected automatically to room according to the finishing rule of study
Furniture;Module is put, is each selected furniture of room automatic putting for the finishing rule according to study;And it is selected
Module, for the finishing rule according to study, if being chosen from the multiple design schemes for being well placed selected furniture limited
Dry design scheme.The interactive module is additionally operable to several limited design schemes that selected module selects being presented to use
Family.
According to the third aspect of the invention we, a kind of computer-readable medium is provided, can be executed by processor for recording
Instruction, described instruction is when being executed by processor so that processor executes the intelligent Decoration Design method based on machine learning, packet
It includes:With the method for machine learning, study finishing is regular in advance from existing Decoration Design scheme;Input floor plan and user want
It asks;It is required according to the floor plan of input and user, function is determined for each room, and according to the size and function in each room,
According to the finishing rule of study furniture is selected to room automatically;According to the finishing rule of study, for each room automatic putting institute
The furniture of selection;And the finishing rule according to study, being chosen from the multiple design schemes for be well placed selected furniture has
Several design schemes of limit are presented to the user.
The purpose of the present invention is according to the specific house type of user and personal preference, once quickly can generate several set automatically
Meter scheme, such as 5 kinds of design schemes.To these design schemes, user can make an amendment.The present invention quickly generates design side automatically
Case can be presented design scheme to user in 10 seconds, need few foolproof interactive operation, overcome the time-consuming expense of the prior art
The shortcomings that thing;The present invention generates design scheme for the specific house type of user, avoids the prior art and is unsatisfactory for user's house type need
The shortcomings that asking;The present invention quickly generates design scheme automatically, and real-time is fine, in addition can generate kinds of schemes, solves existing
The shortcomings that real-time is poor in technology, scheme cannot be satisfied user demand.
Description of the drawings
Below with reference to the accompanying drawings it is described in conjunction with the embodiments the present invention.In the accompanying drawings:
Fig. 1 is the schematic block diagram of the intelligent Decoration Design system according to an embodiment of the invention based on machine learning.
Fig. 2 is the schematic diagram for explaining the strategy sampled along wall in the present invention.
Fig. 3 is the schematic diagram of the strategy for explaining the tree-shaped search in the present invention.
Fig. 4 is the flow chart of the intelligent Decoration Design method according to an embodiment of the invention based on machine learning.
Fig. 5 is an example of user's floor plan.
Fig. 6 is the subregion signal for the public space of user's floor plan of Fig. 5.
Fig. 7 A-7E are 5 schemes for for user's floor plan of Fig. 5 provide after intelligent Decoration Design.
Specific implementation mode
Attached drawing is given for example only explanation, should not be understood as the limitation to this patent;With reference to the accompanying drawings and examples to this
The technical solution of invention is described further.
Fig. 1 is the schematic block diagram of the intelligent Decoration Design system according to an embodiment of the invention based on machine learning.Such as
Shown in Fig. 1, the intelligent Decoration Design system 100 according to the present invention based on machine learning includes:Machine learning extracting rule
Module 101, for study finishing to be regular in advance from existing Decoration Design scheme with the method for machine learning;Interactive module
102, it is required for inputting floor plan and user;Primary election module 103 is every for being required according to the floor plan of input and user
A room determines function, and according to the size and function in each room, and house is selected to room automatically according to the finishing rule of study
Tool;Module 104 is put, is each selected furniture of room automatic putting for the finishing rule according to study;And it is selected
Module 105 is chosen limited for the finishing rule according to study from the multiple design schemes for being well placed selected furniture
Several design schemes.The interactive module 105 is additionally operable to
Now give user.
The operation principle of other several modules in addition to interactive module 105 is introduced in detail below.
Machine learning extracting rule module 101
We obtain finishing rule with the method for machine learning from good design decorating scheme.Specifically, we can be with
It extracts placement position of furniture etc. in the shape in room, the position of door and window, the area in room, room and is used as sample characteristics.One
A designed decorating scheme is exactly a sample, and many decorating schemes form our training set.Because in machine learning
Random forests algorithm have training and predetermined speed it is fast, higher-dimension degrees of data can be handled, it is strong to the fault-tolerant ability of data, do not allow
Easily there is the features such as overfitting, so we train the phase between different furniture and wall door and window using random forests algorithm
Mutual relation, the correlation between different furniture.Extract finishing rule of these correlations as us.Entirely trained
Journey is full-automatic, and to training result, we use enlarged sample collection, and by verification collection, the methods of separation carries out from test set
Multiple tuning.
Primary election module 102
According to subscriber household demand information, such as the size of population, age, hobby, 102 intelligence of primary election module determines each room
Between function.Further, according to the size in each room, in conjunction with the function in room, intelligence selects suitable furniture to room.
For public space region, we are divided by intelligent algorithm and defined function area, then select to close to them again
Suitable furniture.Here the strategy that we use is to use Intelligent partition algorithm to public space, intelligently divides and defines and is different
Functional areas.For multiple dimensions such as efficiency, beauty, practicability, we construct the evaluation function of a subregion.In order to obtain almost
Each possible partition conbination, we devise a kind of approximate search algorithm to obtain candidate solution.Using approximate search algorithm,
All candidate solutions are evaluated and sorted, optimal solution can be obtained.It is used again in functional areas hereinafter in putting module 103
The strategy sampled along wall and scanned for by tree mentioned.
Put module 103
For interior decoration design, when setting the furniture, there are many positions can select for each family.Assuming that we have it is N number of
Furniture, each family have M selection, then our scheme has the M powers of N, this number is extremely huge.If to every
A scheme is all evaluated, it would be desirable to for quite a long time, cannot thus meet the work(that design scheme is quickly presented to user
Energy demand, so having to reach quickly to set the furniture, we use two strategies simultaneously thus.
First strategy is the strategy sampled along wall, this strategy is that we sample several key points along wall.
Fig. 2 is the schematic diagram for explaining the strategy sampled along wall in the present invention.As shown in Fig. 2, the line of black overstriking
Segment table shows a face wall, and the point on black line segment that the filament on vertical direction is directed toward is optional (furniture is put) position.When along wall
When setting the furniture, there are many points (position) it can be selected that as shown in upper figure in Fig. 2, we there can be 21 positions that can select.
But if doing so, calculation amount can be huge, cannot achieve the effect that quickly to generate design scheme.According to 5 in Fig. 2 figure below
Sampled point, calculation amount can greatly reduce, can quickly generate design scheme, and design scheme puts effect also without what
Difference.
That is, when putting module 103 using along the strategy that wall samples, adopted only with several along a face wall
Sampling point as furniture placement position, and and without considering that all practical optional positions progress furniture along the wall are put.
Second strategy is scanned for by tree, is directly removed bad design scheme, is also saved in this way
It is a large amount of to calculate the time.
When we set the furniture, often puts a furniture and just form a node, thus form multiple nodes
One tree.Fig. 3 is the schematic diagram of the strategy for explaining the tree-shaped search in the present invention.As shown in Figure 3, we have put
4 furniture to have been put, there are 4 kinds to put scheme, each scheme is exactly from root node to leaf node, they are scheme 1 respectively, scheme 2,
Scheme 3 and scheme 4.It is exactly one new node of increase in currently existing scheme, in this way when increasing when putting of furniture
Just there are many selections, according to our evaluation system, each scheme has corresponding scoring score value, we are direct according to score value
Remove those low route schemes that score.In figure 3, we exactly can only be put on the basis of scheme 1 with reservation scheme 1
Other furniture remove scheme 2 and arrive scheme 4, in this way when putting the 5th furniture, only consider the further branch of scheme 1
(without considering further that branch caused by scheme 2,3,4), to save a large amount of calculating times.
In addition, mentioning the algorithm policy of Intelligent partition when discussing public space before.By using these three plans
Slightly, we, which can realize, quickly sets the furniture, and indoor design decorating scheme is presented to user.
Selected module 104
For interior decoration design, there are many kinds of design schemes for we, different design schemes how are evaluated, to select
Best indoor design decorating schemeWe specific way are the finishings learnt according to machine learning extracting rule module 101
Rule, for each element of Decoration Design scheme, we can be that it creates series of rules, and these rules constitute one and comment
Valence subsystem, each Evaluation subsystem can make each element evaluation, and all Evaluation subsystems of weighted comprehensive are to all members
The evaluation of element, just obtains the overall merit of all elements, is evaluated one by one design decorating scheme, is just weighted in this approach
Overall merit compares the final evaluation of different designs decorating scheme, to several Decoration Design schemes that selection is best.
According to the present invention, selected module 104 will be chosen limited from the multiple design schemes for being well placed selected furniture
Several design schemes.Preferably, 5 or less design scheme are selected, is presented to the user by interactive module 105.With
Family may browse through, select, further changing these design schemes.
In conclusion the key point of the present invention is to obtain rule by machine learning, intelligent selection furniture is adopted using along wall
Sample and tree-shaped search strategy quickly set the furniture automatically, finally pick out best several design sides using overall evaluation system
Case is presented to the user.
Compared with present product, this product is designed for the specific floor plan of user, can fast automatic generation design
Scheme.
Fig. 4 is the flow chart of the intelligent Decoration Design method according to an embodiment of the invention based on machine learning.
As shown in Figure 4, the stream of the intelligent Decoration Design method 400 according to an embodiment of the invention based on machine learning
Journey figure starts from step S401, and in this step, with the method for machine learning, study fills in advance from existing Decoration Design scheme
Repair rule.
When Decoration Design scheme is presented in actual needs, first, in step S403, inputs floor plan and user requires.
Next, in step S405, required according to the floor plan of input and user, function, and root are determined for each room
According to the size and function in each room, furniture is selected to room automatically according to the finishing rule of study.For public space region,
Using Intelligent partition algorithm, different functional areas are intelligently divided and defined;According to the division and definition of functional areas, give automatically each
Functional areas select furniture.
Then, it is each selected furniture of room automatic putting according to the finishing rule of study in step S407.Tool
Body, using the strategy sampled along wall, limited several key points are sampled along wall, in these key points selected by automatic putting
The furniture selected.In addition, during automatic putting furniture is to form multiple design schemes, scanned for by tree,
Directly remove bad design scheme.
Finally, in step S409, according to the finishing rule of study, from the multiple design schemes for being well placed selected furniture
Middle several limited design schemes of selection are presented to the user.Specifically, according to the finishing rule of study, fitted up for design
Each element of scheme creates series of rules, to constitute Evaluation subsystem;Each Evaluation subsystem can be to each element
Evaluation is made, evaluation of all Evaluation subsystems of weighted comprehensive to all elements obtains the overall merit of all elements;With above-mentioned step
Suddenly the multiple design schemes for being well placed selected furniture are evaluated one by one, obtains weighted synthetical evaluation;It is more above-mentioned more
The weighted synthetical evaluation of a design scheme is therefrom chosen several highest limited design schemes of evaluation and is presented to the user.
Several described limited design schemes can be five or less design scheme.
Method 400 terminates after step S409 is completed.
Example
The concrete instance of an application present invention is provided below by Fig. 5,6,7A-7E.
Fig. 5 is an example of user's floor plan.We use the signal floor plan of Fig. 5 as an example, to illustrate this
Invention is if carrying out intelligent Decoration Design for such floor plan.
By machine learning, in primary election module, intelligent algorithm of the invention has to the furniture type that parlor is selected:Sofa,
Tea table, air-conditioning, cabinet for TV, book, fruit tray, vase hang picture, green plant, TV, dining table, dining chair.On the other hand, intelligence of the invention
The family that algorithm is selected to bedroom has:Bed, nightstand hang picture, and hat rack, carpet, cabinet for TV, TV, wardrobe, struggle against cabinet, desk lamp, etc.
Deng.
For public space region, intelligent algorithm according to the present invention divides and defined function area.Fig. 6 is for Fig. 5
The subregion of the public space of user's floor plan is illustrated.As shown in Figure 6, dining room area and parlor area are shown in public space,
They are exactly subregion of the algorithm to public space of the present invention.According to the size in dining room area and parlor area, intelligence of the invention is calculated
Method is on the basis of the furniture type of selection, the sizeable furniture of intelligent selection.
In putting module, placement position is sampled according to trained model, then using tree-shaped search to sample bits
It sets and carries out assessment search, directly remove and assess bad sampled point.Such as when putting bed, each wall in room can have 4
Sampled point (two, the both ends point of wall, 2 points apart from two 1/4 walls of endpoint of wall length).
In selected module, our weighted synthetical evaluation system assesses numerous schemes, then selects best
5 kinds of schemes to user.Fig. 7 A-7E are five schemes for for user's floor plan of Fig. 5 provide after intelligent Decoration Design.
In the scheme of Fig. 7 A-7E, floor plan 90 degree are rotated clockwise, so that the case where furniture is put more easily is presented.User
It can select to be suitble to the scheme of oneself from this five schemes, some adjustment can also be done since a certain scheme therein,
To ultimately form the scheme of oneself.
It will be appreciated by one of ordinary skill in the art that the method and system of the present invention can be implemented as computer program.
As above in conjunction with described in Fig. 1 and 4, one or more programs, including instruction can be executed according to the method and system of above-described embodiment
To make computer or processor execute the algorithm in conjunction with described in attached drawing.These programs can use various types of non-instantaneous meters
Calculation machine readable medium is stored and provided to computer or processor.Non-transitory computer-readable medium includes various types of tangible
Storage medium.The example of non-transitory computer-readable medium includes magnetic recording medium (such as floppy disk, tape and hard drive
Device), Magnetooptic recording medium (such as magneto-optic disk), CD-ROM (compact disk read-only memory), CD-R, CD-R/W and semiconductor deposit
Reservoir (such as ROM, PROM (programming ROM), EPROM (erasable PROM), flash rom and RAM (random access memory)).
Further, these programs can be supplied to computer by using various types of instantaneous computer-readable mediums.Chronoscope
The example of calculation machine readable medium includes electric signal, optical signal and electromagnetic wave.Instantaneous computer-readable medium can be used for by all
As the wired communication path or wireless communications path of electric wire and optical fiber provide program to computer.
Therefore, according to the invention, it is further possible to propose a kind of computer program or a kind of computer-readable medium, for recording
The instruction that can be executed by processor, described instruction is when being executed by processor so that processor executes the intelligence based on machine learning
Energy Decoration Design method, including:With the method for machine learning, study finishing is regular in advance from existing Decoration Design scheme;It is defeated
Enter floor plan and user requires;It is required according to the floor plan of input and user, determines function for each room, and according to each room
Between size and function, according to study finishing rule automatically give room select furniture;It is each according to the finishing rule of study
The selected furniture of room automatic putting;And the finishing rule according to study, it is set from the multiple of selected furniture are well placed
Several limited design schemes are chosen in meter scheme to be presented to the user.
Various embodiments of the present invention and implementation situation are described above.But the spirit and scope of the present invention are not
It is limited to this.Those skilled in the art will it is according to the present invention introduction and make more applications, and these application all this
Within the scope of invention.
That is, the above embodiment of the present invention is only examples of the invention to clearly illustrate, rather than to this
The restriction of invention embodiment.For those of ordinary skill in the art, it can also do on the basis of the above description
Go out other various forms of variations or variation.There is no necessity and possibility to exhaust all the enbodiments.It is all in the present invention
Spirit and principle within made by it is any modification, replace or improve etc., should be included in the protection model of the claims in the present invention
Within enclosing.
Claims (8)
1. a kind of intelligent Decoration Design method based on machine learning, including:
With the method for machine learning, study finishing is regular in advance from existing Decoration Design scheme;
It inputs floor plan and user requires;
It is required according to the floor plan of input and user, function is determined for each room, and according to the size and function in each room,
According to the finishing rule of study furniture is selected to room automatically;
It is each selected furniture of room automatic putting according to the finishing rule of study;And
According to the finishing rule of study, limited several are chosen from the multiple design schemes for being well placed selected furniture and are set
Meter scheme is presented to the user.
It is each room 2. being required according to the floor plan of input and user described in the method for claim 1, wherein
It determines function, and according to the size and function in each room, furniture is selected to room automatically according to the finishing rule of study, into one
Step includes:
For public space region, using Intelligent partition algorithm, different functional areas are intelligently divided and defined;
According to the division and definition of functional areas, each functional areas are given to select furniture automatically.
3. the method for claim 1, wherein finishing rule according to study, is each room automatic putting
Selected furniture, further comprises:
Using the strategy sampled along wall, limited several key points are sampled along wall, in these key points selected by automatic putting
The furniture selected.
4. the method for claim 1, wherein finishing rule according to study, is each room automatic putting
Selected furniture, further comprises:
It during automatic putting furniture is to form multiple design schemes, is scanned for, is directly removed not by tree
Good design scheme.
5. the method for claim 1, wherein finishing rule according to study, from being well placed selected family
Tool multiple design schemes in choose several limited design schemes be presented to the user including:
Series of rules is created for each element of design decorating scheme according to the finishing rule of study, to constitute evaluation
Subsystem;
Each Evaluation subsystem can make each element evaluation, and all Evaluation subsystems of weighted comprehensive comment all elements
Valence obtains the overall merit of all elements;
The multiple design schemes for being well placed selected furniture are evaluated one by one with above-mentioned steps, weighted comprehensive is obtained and comments
Valence;
The weighted synthetical evaluation of more above-mentioned multiple design schemes is therefrom chosen and evaluates several highest limited design schemes
It is presented to the user.
6. the method as described in claim 1 or 5, wherein several described limited design schemes are five or less
Design scheme.
7. a kind of intelligent Decoration Design system based on machine learning, including:
Machine learning extracting rule module, for study to fill in advance from existing Decoration Design scheme with the method for machine learning
Repair rule;
Interactive module is required for inputting floor plan and user;
Primary election module determines function, and according to each room for being required according to the floor plan of input and user for each room
Size and function, according to study finishing rule automatically give room select furniture;
Module is put, is each selected furniture of room automatic putting for the finishing rule according to study;And
Selected module is chosen for the finishing rule according to study from the multiple design schemes for being well placed selected furniture
Several limited design schemes,
The interactive module is additionally operable to several limited design schemes that selected module selects being presented to the user.
8. a kind of computer-readable medium, for recording the instruction that can be executed by processor, described instruction is being executed by processor
When so that processor executes the intelligent Decoration Design method based on machine learning, including:
With the method for machine learning, study finishing is regular in advance from existing Decoration Design scheme;
It inputs floor plan and user requires;
It is required according to the floor plan of input and user, function is determined for each room, and according to the size and function in each room,
According to the finishing rule of study furniture is selected to room automatically;
It is each selected furniture of room automatic putting according to the finishing rule of study;And
According to the finishing rule of study, limited several are chosen from the multiple design schemes for being well placed selected furniture and are set
Meter scheme is presented to the user.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2017102231485 | 2017-04-07 | ||
| CN201710223148 | 2017-04-07 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108694266A true CN108694266A (en) | 2018-10-23 |
Family
ID=63843734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710739955.2A Pending CN108694266A (en) | 2017-04-07 | 2017-08-23 | intelligent decoration design method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108694266A (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109886418A (en) * | 2019-03-12 | 2019-06-14 | 深圳微品致远信息科技有限公司 | A kind of method, system and storage medium intelligently generating Design Works based on machine learning |
| CN109887049A (en) * | 2019-01-31 | 2019-06-14 | 浙江工商大学 | Hierarchical dependency-based furniture scene generation method |
| CN109961178A (en) * | 2019-03-12 | 2019-07-02 | 中国电子工程设计院有限公司 | The acquisition methods and device of house type transformation information |
| CN109961319A (en) * | 2019-03-12 | 2019-07-02 | 中国电子工程设计院有限公司 | A kind of acquisition methods and device of house type transformation information |
| CN110175355A (en) * | 2019-04-19 | 2019-08-27 | 特斯联（北京）科技有限公司 | A kind of building matching process and device based on machine learning |
| CN110414100A (en) * | 2019-07-15 | 2019-11-05 | 杭州群核信息技术有限公司 | A kind of house ornamentation automated design system with design effect feedback closed loop |
| CN110442976A (en) * | 2019-08-07 | 2019-11-12 | 广州神蛋网络科技有限公司 | A kind of Novel decoration scheme auto acquisition system and method |
| CN111199100A (en) * | 2018-12-29 | 2020-05-26 | 美宅科技（北京）有限公司 | Hard-set customized design method and design device |
| CN111400960A (en) * | 2018-12-29 | 2020-07-10 | 美宅科技（北京）有限公司 | Furniture active customization method and active customization device |
| CN111837122A (en) * | 2020-06-17 | 2020-10-27 | 上海亦我信息技术有限公司 | Virtual decoration method, device and system |
| WO2020238022A1 (en) * | 2019-05-28 | 2020-12-03 | 贝壳找房(北京)科技有限公司 | Three-dimensional space view display method, apparatus, and storage medium |
| CN112131645A (en) * | 2020-09-23 | 2020-12-25 | 贝壳技术有限公司 | Indoor article placement completion method, device and equipment, and storage medium |
| WO2021008566A1 (en) * | 2019-07-15 | 2021-01-21 | Ke.Com (Beijing) Technology Co., Ltd. | Artificial intelligence systems and methods for interior design |
| WO2021096393A1 (en) * | 2019-11-12 | 2021-05-20 | Елена Владимировна ХЛАПИНА | Module for the automatic placement of room elements |
| CN113486436A (en) * | 2021-09-08 | 2021-10-08 | 深圳须弥云图空间科技有限公司 | Soft installation design method, device, equipment and storage medium based on tree structure |
| CN113505429A (en) * | 2021-09-09 | 2021-10-15 | 深圳须弥云图空间科技有限公司 | Indoor design scheme acquisition method and device, computer equipment and storage medium |
| CN113779674A (en) * | 2021-09-01 | 2021-12-10 | 广州市圆方计算机软件工程有限公司 | Method, device, equipment and storage medium for designing customized household three-dimensional model scheme |
| CN118427945A (en) * | 2024-05-31 | 2024-08-02 | 中景创维(北京)科技有限公司 | Indoor design method and system based on machine learning |
| US12086861B1 (en) | 2020-04-27 | 2024-09-10 | State Farm Mutual Automobile Insurance Company | Systems and methods for commercial inventory mapping including a lidar-based virtual map |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140278274A1 (en) * | 2012-07-24 | 2014-09-18 | Stanley J. Osher | Automatic optimization of scene configuration |
| CN104778756A (en) * | 2015-04-10 | 2015-07-15 | 北京明兰网络科技有限公司 | Intelligent home decoration design system |
| CN106033547A (en) * | 2015-03-12 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Color matching evaluation method and device, and dress collocation recommendation method and device |
| CN106202352A (en) * | 2016-07-05 | 2016-12-07 | 华南理工大学 | The method that indoor furniture style based on Bayesian network designs with colour match |
| CN106447046A (en) * | 2016-10-17 | 2017-02-22 | 深圳市彬讯科技有限公司 | House type design scheme evaluation method based on machine learning |
| CN106484940A (en) * | 2016-07-09 | 2017-03-08 | 陈志静 | A kind of home decoration Intelligentized design method and system |
-
2017
- 2017-08-23 CN CN201710739955.2A patent/CN108694266A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140278274A1 (en) * | 2012-07-24 | 2014-09-18 | Stanley J. Osher | Automatic optimization of scene configuration |
| CN106033547A (en) * | 2015-03-12 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Color matching evaluation method and device, and dress collocation recommendation method and device |
| CN104778756A (en) * | 2015-04-10 | 2015-07-15 | 北京明兰网络科技有限公司 | Intelligent home decoration design system |
| CN106202352A (en) * | 2016-07-05 | 2016-12-07 | 华南理工大学 | The method that indoor furniture style based on Bayesian network designs with colour match |
| CN106484940A (en) * | 2016-07-09 | 2017-03-08 | 陈志静 | A kind of home decoration Intelligentized design method and system |
| CN106447046A (en) * | 2016-10-17 | 2017-02-22 | 深圳市彬讯科技有限公司 | House type design scheme evaluation method based on machine learning |
Non-Patent Citations (2)
| Title |
|---|
| WENZHUO XU ET AL.: "Wall grid structure for interior scene synthesis", 《COMPUTERS & GRAPHICS》 * |
| 刘米兰 等: "基于案例库的室内区域自动布局方法", 《计算机辅助设计与图形学学报》 * |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN109670264A (en) * | 2018-12-28 | 2019-04-23 | 江苏艾佳家居用品有限公司 | A kind of intensified learning domestic layout optimization method and system |
| CN109670262B (en) * | 2018-12-28 | 2021-04-27 | 江苏艾佳家居用品有限公司 | Computer-aided home layout optimization method and system |
| CN109670264B (en) * | 2018-12-28 | 2022-07-08 | 江苏艾佳家居用品有限公司 | Method and system for optimizing layout of reinforcement learning home |
| CN111400960A (en) * | 2018-12-29 | 2020-07-10 | 美宅科技（北京）有限公司 | Furniture active customization method and active customization device |
| CN111199100A (en) * | 2018-12-29 | 2020-05-26 | 美宅科技（北京）有限公司 | Hard-set customized design method and design device |
| CN109887049A (en) * | 2019-01-31 | 2019-06-14 | 浙江工商大学 | Hierarchical dependency-based furniture scene generation method |
| CN109961178A (en) * | 2019-03-12 | 2019-07-02 | 中国电子工程设计院有限公司 | The acquisition methods and device of house type transformation information |
| CN109961319A (en) * | 2019-03-12 | 2019-07-02 | 中国电子工程设计院有限公司 | A kind of acquisition methods and device of house type transformation information |
| CN109961178B (en) * | 2019-03-12 | 2020-12-08 | 中国电子工程设计院有限公司 | Method and device for acquiring house type transformation information |
| CN109886418A (en) * | 2019-03-12 | 2019-06-14 | 深圳微品致远信息科技有限公司 | A kind of method, system and storage medium intelligently generating Design Works based on machine learning |
| CN110175355B (en) * | 2019-04-19 | 2020-02-04 | 特斯联（北京）科技有限公司 | Building matching method and device based on machine learning |
| CN110175355A (en) * | 2019-04-19 | 2019-08-27 | 特斯联（北京）科技有限公司 | A kind of building matching process and device based on machine learning |
| US11875460B2 (en) | 2019-05-28 | 2024-01-16 | Ke.Com (Beijing) Technology Co., Ltd. | Method, apparatus and storage medium for displaying three-dimensional space view |
| WO2020238022A1 (en) * | 2019-05-28 | 2020-12-03 | 贝壳找房(北京)科技有限公司 | Three-dimensional space view display method, apparatus, and storage medium |
| US11158134B2 (en) | 2019-05-28 | 2021-10-26 | Ke.Com (Beijing) Technology Co., Ltd. | Method, apparatus and storage medium for displaying three-dimensional space view |
| CN110414100A (en) * | 2019-07-15 | 2019-11-05 | 杭州群核信息技术有限公司 | A kind of house ornamentation automated design system with design effect feedback closed loop |
| WO2021008566A1 (en) * | 2019-07-15 | 2021-01-21 | Ke.Com (Beijing) Technology Co., Ltd. | Artificial intelligence systems and methods for interior design |
| CN110442976A (en) * | 2019-08-07 | 2019-11-12 | 广州神蛋网络科技有限公司 | A kind of Novel decoration scheme auto acquisition system and method |
| WO2021096393A1 (en) * | 2019-11-12 | 2021-05-20 | Елена Владимировна ХЛАПИНА | Module for the automatic placement of room elements |
| US12198428B2 (en) | 2020-04-27 | 2025-01-14 | State Farm Mutual Automobile Insurance Company | Systems and methods for a 3D home model for representation of property |
| US12148209B2 (en) | 2020-04-27 | 2024-11-19 | State Farm Mutual Automobile Insurance Company | Systems and methods for a 3D home model for visualizing proposed changes to home |
| US12086861B1 (en) | 2020-04-27 | 2024-09-10 | State Farm Mutual Automobile Insurance Company | Systems and methods for commercial inventory mapping including a lidar-based virtual map |
| CN111837122B (en) * | 2020-06-17 | 2021-08-24 | 上海亦我信息技术有限公司 | Virtual decoration method, device and system |
| CN111837122A (en) * | 2020-06-17 | 2020-10-27 | 上海亦我信息技术有限公司 | Virtual decoration method, device and system |
| CN112131645A (en) * | 2020-09-23 | 2020-12-25 | 贝壳技术有限公司 | Indoor article placement completion method, device and equipment, and storage medium |
| CN113779674A (en) * | 2021-09-01 | 2021-12-10 | 广州市圆方计算机软件工程有限公司 | Method, device, equipment and storage medium for designing customized household three-dimensional model scheme |
| CN113486436A (en) * | 2021-09-08 | 2021-10-08 | 深圳须弥云图空间科技有限公司 | Soft installation design method, device, equipment and storage medium based on tree structure |
| WO2023035592A1 (en) * | 2021-09-09 | 2023-03-16 | 深圳须弥云图空间科技有限公司 | Interior design solution acquisition method and apparatus, computer device, and storage medium |
| CN113505429B (en) * | 2021-09-09 | 2021-12-07 | 深圳须弥云图空间科技有限公司 | Indoor design scheme acquisition method and device, computer equipment and storage medium |
| US12086510B2 (en) | 2021-09-09 | 2024-09-10 | Shenzhen Xumi Yuntu Space Technology Co., Ltd. | Indoor design scheme acquisition method and apparatus, computer device and storage medium |
| CN113505429A (en) * | 2021-09-09 | 2021-10-15 | 深圳须弥云图空间科技有限公司 | Indoor design scheme acquisition method and device, computer equipment and storage medium |
| CN118427945A (en) * | 2024-05-31 | 2024-08-02 | 中景创维(北京)科技有限公司 | Indoor design method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694266A (en) | intelligent decoration design method and system based on machine learning | |
| CN107369203B (en) | Indoor three-dimensional scene self-adaptive construction method and device | |
| WO2021009389A1 (en) | Method and system for generating artificial intelligence-aided design solutions and method and system for training same | |
| CN106936127B (en) | A kind of line load regression analysis and prediction technique and system | |
| CN110287626A (en) | Automatically generate method, medium, equipment and the device of interior decoration design scheme | |
| CN109344532A (en) | A kind of indoor design method and device applied to real estate | |
| CN110750567A (en) | Wearing and matching data generation method and system based on intelligent wardrobe | |
| CN107368911A (en) | A kind of furniture layout method based on placement regulation | |
| CN113486436B (en) | Soft installation design method, device, equipment and storage medium based on tree structure | |
| Wang et al. | SSIEA: a hybrid evolutionary algorithm for supporting conceptual architectural design | |
| CN109166004A (en) | The product customization method of case-based reasioning | |
| CN106599230A (en) | Method and system for evaluating distributed data mining model | |
| CN109408954A (en) | A kind of indoor design method and device applied to electric business | |
| CN109033652B (en) | A kind of indoor autoplacement method based on sliding window feature and regression forecasting | |
| CN113886911A (en) | Household design scheme generation method and device and computer readable storage medium | |
| CN106776995A (en) | A kind of tree-like acquisition technique of structural data based on MDA | |
| CN109241580A (en) | A kind of plot design method, device, computer equipment and storage medium | |
| CN106156844A (en) | For building Space-time Neural Network and utilizing its method and apparatus being predicted | |
| Sun | Design and optimization of indoor space layout based on deep learning | |
| CN106649776B (en) | A kind of method of semi-automation synthetic vector polygon | |
| CN111062074B (en) | Building space quality virtual simulation and intelligent evaluation method | |
| CN103150685B (en) | A kind of intelligence Maintenance Schedule Optimization workout system | |
| CN104703059B (en) | A kind of method and device for planning of broadband access network | |
| CN114626886A (en) | Questionnaire data analysis method and system | |
| CN108764118A (en) | A kind of room layout method, apparatus, terminal and computer-readable medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181023 |
|
| RJ01 | Rejection of invention patent application after publication |