CN110175355A - A kind of building matching process and device based on machine learning - Google Patents
A kind of building matching process and device based on machine learning Download PDFInfo
- Publication number
- CN110175355A CN110175355A CN201910319116.4A CN201910319116A CN110175355A CN 110175355 A CN110175355 A CN 110175355A CN 201910319116 A CN201910319116 A CN 201910319116A CN 110175355 A CN110175355 A CN 110175355A
- Authority
- CN
- China
- Prior art keywords
- household
- collection
- machine learning
- demand
- matching
- 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
Abstract
The embodiment of the present application provides a kind of building matching process and device based on machine learning.This method comprises: constructing household multidimensional characteristic collection by household characteristic;Household includes furniture, household electrical appliances;Subscriber household member structure, household functional requirement feature are extracted in quantization, form user demand restriction collection;Matching case is put based on architecture indoor household, constructs machine learning network, and be trained;Household multidimensional characteristic collection is imported into machine learning network, is constrained in conjunction with user demand restriction collection, matches household in the placement position of architecture indoor.A kind of building matching process and device based on machine learning of the embodiment of the present application improves household and puts design efficiency by combining household arrangement method and machine learning feature.
Description
Technical field
This application involves Home Fashion & Design Shanghai field more particularly to a kind of building matching process and device based on machine learning.
Background technique
Home Fashion & Design Shanghai refers to the whole furnishings wind of living circumstance, office space, public space either commercial space
Lattice and ornaments design collocation.As people's living standard improves, requirement of the people to Home Fashion & Design Shanghai is also higher and higher.It is same with this
When, room rate it is surging but also living space is more and more nervous.How limited space is utilized, reasonably set the furniture, household electrical appliances
Equal home equipments, while meeting entire kinsfolk's functional requirement, also achieve the purpose that meet traditional Aesthetic experience, become and work as
The difficult point of preceding Home Fashion & Design Shanghai.
The motivation of machine learning is to establish, simulate the neural network that human brain carries out analytic learning.People is imitated in machine learning
The mechanism of brain explains data, by combine low-level feature formed it is abstract it is high-rise indicate attribute classification or feature, to realize
General artificial intelligence.At present deep learning be widely used in machine translation, semantic excavation, image recognition, recognition of face,
The fields such as speech recognition.It therefore, can be by the way that machine learning techniques be combined with Home Fashion & Design Shanghai practice, to both improve house
The efficiency of design is occupied, and improves the accuracy of space utilization.
Summary of the invention
In view of this, the purpose of the application is to propose a kind of building matching process and device based on machine learning, mention
High building space utilization is horizontal, during solving current Home Fashion & Design Shanghai, the technical issues of intelligent low, low efficiency.
Based on above-mentioned purpose, present applicant proposes a kind of building matching process based on machine learning, comprising:
Household multidimensional characteristic collection is constructed by household characteristic;The household includes furniture, household electrical appliances;
Subscriber household member structure, household functional requirement feature are extracted in quantization, form user demand restriction collection;
Matching case is put based on architecture indoor household, constructs machine learning network, and be trained;
The household multidimensional characteristic collection is imported into the machine learning network, is carried out about in conjunction with the user demand restriction collection
Beam matches household in the placement position of architecture indoor.
It is in some embodiments, described that household multidimensional characteristic collection is constructed by household characteristic, comprising:
Multidimensional data extraction is carried out, and is standardized and measures by size, shape, material, color, the function to household
Change processing, forms household multidimensional characteristic collection.
In some embodiments, the standardization and quantification treatment, comprising:
Classify by the shape of household, material, color, function to household, so that the shape of household, material, color, function
It can be described respectively by unified metric, to realize the standardization of household;
The shape of household, material, color, function are encoded, to realize the quantification treatment of household.
In some embodiments, subscriber household member structure, household functional requirement feature are extracted in the quantization, form user
Demand restriction collection, comprising:
Kinsfolk is encoded by different inhabitation composite types, determines family structure according to different inhabitation composite types
Demand limits.
In some embodiments, subscriber household member structure, household functional requirement feature are extracted in the quantization, form user
Demand restriction collection, further includes:
Household functional requirement is decomposed, and intensity is ranked up coding as desired, is needed in conjunction with the family structure
Restriction is asked, quantization user demand restriction collection is formed.
In some embodiments, described that matching case is put based on architecture indoor household, machine learning network is constructed, is gone forward side by side
Row training, comprising the following steps:
Household sample set is established, the n dimension household characteristic value of each sample furniture is obtained, constitutes multiple n dimension household features
Vector, wherein n is positive integer;
The architecture indoor household is put into the inner room in matching case and is decomposed into multiple independent rooms, obtains each independence
Household puts matching position in room, constitutes s and ties up matching position feature vector, wherein s is the household quantity in independent room;
Using the n dimension household feature vector in the household sample set as the input of machine learning network, the s dimension
With position feature vector as exporting, neural metwork training is carried out;
Stable state threshold epsilon is set, δ is current household matching position, and δ ' is the household matching position in last training result,
After successive ignition training neural network, when | δ-δ ' | training process enters stable state, deconditioning when < ε.
In some embodiments, user demand restriction collection described in the combination is constrained, and matches household in building room
Interior placement position, comprising:
Be preceding m of restriction collection by user demand intensity coding, using with or matched mode calculate and maximum can expire
The household placement position of sufficient user demand.
Based on above-mentioned purpose, the application also proposed a kind of building coalignment based on machine learning, comprising:
Feature extraction module, for constructing household multidimensional characteristic collection by household characteristic;The household include furniture,
Household electrical appliances;
Demand abstraction module extracts subscriber household member structure, household functional requirement feature for quantifying, and forming user needs
Seek restriction collection;
Machine learning module constructs machine learning network, and carry out for putting matching case based on architecture indoor household
Training;
As a result matching module, for the household multidimensional characteristic collection to be imported the machine learning network, in conjunction with the use
Family demand restriction collection is constrained, and matches household in the placement position of architecture indoor.
In some embodiments, the feature extraction module, comprising:
Furniture feature extraction unit, for carrying out multidimensional data by size, shape, material, color, the function to household
It extracts, and is standardized and quantification treatment, form furniture multidimensional characteristic collection;
Household electrical appliances feature extraction unit, for carrying out multidimensional data by size, shape, material, color, the function to household electrical appliances
It extracts, and is standardized and quantification treatment, form household electrical appliances multidimensional characteristic collection.
In some embodiments, the demand abstraction module, comprising:
Household demand extracting unit, for encoding kinsfolk by different inhabitation composite types, according to not living together
Firmly composite type determines that family structure demand limits;
Functional requirement extracting unit, for household functional requirement being decomposed, and is encoded as unit of household,
It is limited in conjunction with the family structure demand, forms the user demand restriction collection of quantization.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 shows the flow chart of the building matching process according to an embodiment of the present invention based on machine learning.
The composition figure for the building coalignment that Fig. 2 shows according to an embodiment of the present invention based on machine learning.
Fig. 3 shows feature extraction module composition figure according to an embodiment of the present invention.
Fig. 4 shows demand abstraction module composition figure according to an embodiment of the present invention.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is only used for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to just
Part relevant to related invention is illustrated only in description, attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The application is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 shows the flow chart of the building matching process according to an embodiment of the present invention based on machine learning.Such as Fig. 1 institute
Show, being somebody's turn to do the building matching process based on machine learning includes:
Step S11, household multidimensional characteristic collection is constructed by household characteristic;The household includes furniture, household electrical appliances.
It is in one embodiment, described that household multidimensional characteristic collection is constructed by household characteristic, comprising:
Multidimensional data extraction is carried out, and is standardized and measures by size, shape, material, color, the function to household
Change processing, forms household multidimensional characteristic collection.
In one embodiment, standardization and quantification treatment include:
Classify by the shape of household, material, color, function to household, so that the shape of household, material, color, function
It can be described respectively by unified metric, to realize the standardization of household;
The shape of household, material, color, function are encoded, to realize the quantification treatment of household.
Specifically, people carry out household put positioning the considerations of during, can comprehensively consider household size,
The factors such as features of shape, colour match, function be convenient, therefore, when giving this work to machine learning and carry out, it is also desirable to
Comprehensive analysis is carried out to these factors.It is calculated since machine learning can only carry out accurate processing to quantized data, engineering
The first step of habit is to be standardized all kinds of household characteristics and quantification treatment.
For the size of household, the data inherently quantified without carrying out further quantization processing, but are needed
Will the data of three dimensions of length to household be acquired, matched for architecture indoor actual size.
For features of shape, since shape itself is not quantized data, it is therefore necessary to the shape of household into
Row coded treatment, for example, rectangle can be encoded to 001, circle can be encoded to 002 etc..It is worth noting that, people into
During expert puts in residence, often shape is often combined with size and is accounted for, for example, appearing in a square meter
Border circular areas in, be that the inscribed square teapoy of matching one is suitable, or matching one round teapoy is suitable.Therefore, into
It, can also be by the union feature of the two while shape and size are separately as input feature vector during row machine learning
It is imported in machine-learning process as input feature vector.
For color, also need to carry out coded quantization processing.People often need in household Matching design
It is close or similar style by the colour match of household, it therefore, can be in conjunction with household aesthetics during machine learning
Collocating rule fast implements the metering of colour match by using codes match algorithm.
For function, and need to carry out a feature of coded quantization processing.Different households has different
Function, matched placement position are also required to certain rule, such as kitchen and bath's electric appliance, whether great or small, size, color how, also only
The specified region of kitchen or toilet can be placed in.Therefore, when carrying out product function quantification coding, it may be considered that use hierarchical coding
Mode carry out region restriction, to realize that specified functional area matches the technical effect of specified function household.For example, function is compiled
When code, level encoder is functional area coding, and such as 1 indicates parlor, and 2 indicate kitchen;Second level is encoded to specific people's coding, such as 1
Indicate old man, 2 indicate children;Three-level is encoded to concrete function, and if 001 is reads, 002 is culinary art, when expression is cooked for old man
When the kitchen household prepared food, that is, it may be encoded as 21002.Certainly, function coding can be carried out according to the matched needs of specific household into
The partition size of one step refines, to improve the accuracy of function match.
Step S12, subscriber household member structure, household functional requirement feature are extracted in quantization, form user demand restriction collection.
In one embodiment, subscriber household member structure, household functional requirement feature are extracted in the quantization, are formed and are used
Family demand restriction collection, comprising:
Kinsfolk is encoded by different inhabitation composite types, determines family structure according to different inhabitation composite types
Demand limits.
Specifically, at present in Chinese family, there are inverted pyramid type (i.e. 4 old men, 2 a middle-aged persons, 1 of 4-2-1
Child), there are also the different household resident structures such as newly-married couple's two people's word by 2-1 (i.e. 2 a middle-aged persons, 1 child), in household
During matching is put, need to be combined the restriction collection that type determines user demand for different home residential construction.
For example, needing to encode old man, child, middle aged Man's Demands, after taking intersection in 4-2-1 family type
Form the integration requirement restriction collection as unit of family.
In one embodiment, subscriber household member structure, household functional requirement feature are extracted in the quantization, are formed and are used
Family demand restriction collection, further includes:
Household functional requirement is decomposed, and intensity is ranked up coding as desired, is needed in conjunction with the family structure
Restriction is asked, quantization user demand restriction collection is formed.
Specifically, limited space cannot often meet all users in face of unlimited residential needs comprehensively
Demand, therefore, during carrying out matching machine learning, in order to avoid finally there is the calculated result of no solution, it may be considered that
The household matching demand of user is encoded according to pressing degree, in machine-learning process, it is urgent to be able to satisfy most of user
Demand can be considered effective solution.For example, the security protection demand of old man and child are often more more urgent than entertainment requirements, then may be used
The urgent degree coding of the security protection of old man and child first to be come on amusement function.
Step S13, matching case is put based on architecture indoor household, constructs machine learning network, and be trained.
In one embodiment, described that matching case is put based on architecture indoor household, machine learning network is constructed, and
It is trained, comprising the following steps:
Household sample set is established, the n dimension household characteristic value of each sample furniture is obtained, constitutes multiple n dimension household features
Vector, wherein n is positive integer;
The architecture indoor household is put into the inner room in matching case and is decomposed into multiple independent rooms, obtains each independence
Household puts matching position in room, constitutes s and ties up matching position feature vector, wherein s is the household quantity in independent room;
Using the n dimension household feature vector in the household sample set as the input of machine learning network, the s dimension
With position feature vector as exporting, neural metwork training is carried out;
Stable state threshold epsilon is set, δ is current household matching position, and δ ' is the household matching position in last training result,
After successive ignition training neural network, when | δ-δ ' | training process enters stable state, deconditioning when < ε.
Step S14, the household multidimensional characteristic collection is imported into the machine learning network, is limited in conjunction with the user demand
Collection is constrained, and matches household in the placement position of architecture indoor.
In one embodiment, user demand restriction collection described in the combination is constrained, and is matched household and is being built
Indoor placement position, comprising:
Be preceding m of restriction collection by user demand intensity coding, using with or matched mode calculate and maximum can expire
The household placement position of sufficient user demand.
For example, compiling the 1st of restriction collection for demand intensity bits of coded, 0 is that must expire when carrying out demand intensity coding
Foot, 1 is meets as far as possible, and 2 be that optional satisfaction can be decontroled if the calculated result scheme of matching " 0and 1and 2 " is less
It is required that releasing more households using " 0and1 " or the matching criteria of " 0 " and putting matching scheme.
The composition figure for the building coalignment that Fig. 2 shows according to an embodiment of the present invention based on machine learning.Such as Fig. 2 institute
Show, being somebody's turn to do the building coalignment based on machine learning can integrally be divided into:
Feature extraction module 21, for constructing household multidimensional characteristic collection by household characteristic;The household includes family
Tool, household electrical appliances;
Demand abstraction module 22 extracts subscriber household member structure, household functional requirement feature for quantifying, forms user
Demand restriction collection;
Machine learning module 23 constructs machine learning network, goes forward side by side for putting matching case based on architecture indoor household
Row training;
As a result matching module 24, for the household multidimensional characteristic collection to be imported the machine learning network, in conjunction with described
User demand restriction collection is constrained, and matches household in the placement position of architecture indoor.
Fig. 3 shows the composition figure of the building coalignment according to an embodiment of the present invention based on machine learning.
From figure 3, it can be seen that feature extraction module 21, comprising:
Furniture feature extraction unit 211, for carrying out multidimensional by size, shape, material, color, the function to household
Data are extracted, and are standardized and quantification treatment, and furniture multidimensional characteristic collection is formed;
Household electrical appliances feature extraction unit 212, for carrying out multidimensional by size, shape, material, color, the function to household electrical appliances
Data are extracted, and are standardized and quantification treatment, and household electrical appliances multidimensional characteristic collection is formed.
Fig. 4 shows demand abstraction module composition figure according to an embodiment of the present invention.
From fig. 4, it can be seen that demand abstraction module 22 includes:
Household demand extracting unit 221, for encoding kinsfolk by different inhabitation composite types, according to difference
Inhabitation composite type determines that family structure demand limits;
Functional requirement extracting unit 222, for household functional requirement being decomposed, and is compiled as unit of household
Code limits in conjunction with the family structure demand, forms the user demand restriction collection of quantization.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.The more specific example (non-exhaustive list) of computer-readable medium include the following: there is the electricity of one or more wirings
Interconnecting piece (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable read-only memory
(CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other suitable Jie
Matter, because can then be edited, be interpreted or when necessary with other for example by carrying out optical scanner to paper or other media
Suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is that relevant hardware can be instructed to complete by program, the program can store in a kind of computer-readable storage medium
In matter, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized and when sold or used as an independent product in the form of software function module, also can store in a computer
In readable storage medium storing program for executing.The storage medium can be read-only memory, disk or CD etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement,
These should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the guarantor of the claim
It protects subject to range.
Claims (10)
1. a kind of building matching process based on machine learning characterized by comprising
Household multidimensional characteristic collection is constructed by household characteristic;The household includes furniture, household electrical appliances;
Subscriber household member structure, household functional requirement feature are extracted in quantization, form user demand restriction collection;
Matching case is put based on architecture indoor household, constructs machine learning network, and be trained;
The household multidimensional characteristic collection is imported into the machine learning network, is constrained in conjunction with the user demand restriction collection,
Household is matched in the placement position of architecture indoor.
2. the method according to claim 1, wherein described construct household multidimensional characteristic by household characteristic
Collection, comprising:
Carry out multidimensional data extraction by size to household, shape, material, color, function, and be standardized and quantization at
Reason forms household multidimensional characteristic collection.
3. according to the method described in claim 2, it is characterized in that, the standardization and quantification treatment, comprising:
Classify by the shape of household, material, color, function to household, so that the shape of household, material, color, function point
It is not described by unified metric, to realize the standardization of household;
The shape of household, material, color, function are encoded, to realize the quantification treatment of household.
4. the method according to claim 1, wherein subscriber household member structure is extracted in the quantization, family claims credit for oneself
Energy demand characteristic, forms user demand restriction collection, comprising:
Kinsfolk is encoded by different inhabitation composite types, determines family structure demand according to different inhabitation composite types
It limits.
5. according to the method described in claim 4, it is characterized in that, subscriber household member structure is extracted in the quantization, family claims credit for oneself
Energy demand characteristic, forms user demand restriction collection, further includes:
Household functional requirement is decomposed, and intensity is ranked up coding as desired, is limited in conjunction with the family structure demand
It is fixed, form quantization user demand restriction collection.
6. the method according to claim 1, wherein described put matching case, structure based on architecture indoor household
Machine learning network is built, and is trained, comprising the following steps:
Household sample set is established, the n dimension household characteristic value of each sample furniture is obtained, constitutes multiple n dimension household feature vectors,
Wherein n is positive integer;
The architecture indoor household is put into the inner room in matching case and is decomposed into multiple independent rooms, obtains each independent room
Middle household puts matching position, constitutes s and ties up matching position feature vector, and wherein s is the household quantity in independent room;
Using the n dimension household feature vector in the household sample set as the input of machine learning network, the s ties up match bit
Feature vector is set as output, carries out neural metwork training;
Stable state threshold epsilon is set, δ is current household matching position, and δ ' is the household matching position in last training result, repeatedly
After repetitive exercise neural network, when | δ-δ ' | training process enters stable state, deconditioning when ε.
7. the method according to claim 1, wherein user demand restriction collection described in the combination is constrained,
Household is matched in the placement position of architecture indoor, comprising:
Be preceding m of restriction collection by user demand intensity coding, using with or matched mode calculate and maximum can meet use
The household placement position of family demand.
8. a kind of building coalignment based on machine learning characterized by comprising
Feature extraction module, for constructing household multidimensional characteristic collection by household characteristic;The household includes furniture, family
Electricity;
Demand abstraction module extracts subscriber household member structure, household functional requirement feature for quantifying, forms user demand limit
Fixed collection;
Machine learning module constructs machine learning network, and instructed for putting matching case based on architecture indoor household
Practice;
As a result matching module is needed for the household multidimensional characteristic collection to be imported the machine learning network in conjunction with the user
It asks restriction collection to be constrained, matches household in the placement position of architecture indoor.
9. system according to claim 8, which is characterized in that the feature extraction module, comprising:
Furniture feature extraction unit is mentioned for carrying out multidimensional data by size, shape, material, color, the function to household
It takes, and is standardized and quantification treatment, form furniture multidimensional characteristic collection;
Household electrical appliances feature extraction unit is mentioned for carrying out multidimensional data by size, shape, material, color, the function to household electrical appliances
It takes, and is standardized and quantification treatment, form household electrical appliances multidimensional characteristic collection.
10. system according to claim 8, which is characterized in that the demand abstraction module, comprising:
Household demand extracting unit, for encoding kinsfolk by different inhabitation composite types, according to different inhabitation groups
It closes type and determines that family structure demand limits;
Functional requirement extracting unit, for household functional requirement being decomposed, and is encoded as unit of household, in conjunction with
The family structure demand limits, and forms the user demand restriction collection of quantization.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910319116.4A CN110175355B (en) | 2019-04-19 | 2019-04-19 | Building matching method and device based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910319116.4A CN110175355B (en) | 2019-04-19 | 2019-04-19 | Building matching method and device based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110175355A true CN110175355A (en) | 2019-08-27 |
CN110175355B CN110175355B (en) | 2020-02-04 |
Family
ID=67689745
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910319116.4A Active CN110175355B (en) | 2019-04-19 | 2019-04-19 | Building matching method and device based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110175355B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111191145A (en) * | 2019-11-26 | 2020-05-22 | 重庆特斯联智慧科技股份有限公司 | Community traffic sharing method and system based on neural network algorithm |
CN112052507A (en) * | 2020-09-16 | 2020-12-08 | 同济大学 | House waist line design system |
WO2021217340A1 (en) * | 2020-04-27 | 2021-11-04 | Li Jianjun | Ai-based automatic design method and apparatus for universal smart home scheme |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106484940A (en) * | 2016-07-09 | 2017-03-08 | 陈志静 | A kind of home decoration Intelligentized design method and system |
CN108694266A (en) * | 2017-04-07 | 2018-10-23 | 美宅科技(北京)有限公司 | intelligent decoration design method and system based on machine learning |
-
2019
- 2019-04-19 CN CN201910319116.4A patent/CN110175355B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106484940A (en) * | 2016-07-09 | 2017-03-08 | 陈志静 | A kind of home decoration Intelligentized design method and system |
CN108694266A (en) * | 2017-04-07 | 2018-10-23 | 美宅科技(北京)有限公司 | intelligent decoration design method and system based on machine learning |
Non-Patent Citations (3)
Title |
---|
MATTHEW FISHER 等: "Example-based Synthesis of 3D Object Arrangements", 《ACM TRANSACTIONS ON 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》 * |
王超 等: "面向虚实融合的卧室箱体建模与布局算法", 《计算机科学与探索》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111191145A (en) * | 2019-11-26 | 2020-05-22 | 重庆特斯联智慧科技股份有限公司 | Community traffic sharing method and system based on neural network algorithm |
CN111191145B (en) * | 2019-11-26 | 2023-07-07 | 重庆特斯联智慧科技股份有限公司 | Community traffic sharing method and system based on neural network algorithm |
WO2021217340A1 (en) * | 2020-04-27 | 2021-11-04 | Li Jianjun | Ai-based automatic design method and apparatus for universal smart home scheme |
CN112052507A (en) * | 2020-09-16 | 2020-12-08 | 同济大学 | House waist line design system |
CN112052507B (en) * | 2020-09-16 | 2022-08-26 | 同济大学 | House waist line design system |
Also Published As
Publication number | Publication date |
---|---|
CN110175355B (en) | 2020-02-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110175355A (en) | A kind of building matching process and device based on machine learning | |
CN104156464A (en) | Micro-video retrieval method and device based on micro-video feature database | |
CN102819858A (en) | Method for organizing and applying cartoon material | |
Emmons et al. | Architectural handbooks and the user experience | |
Zhu et al. | A hybrid multiple-attribute decision-making model for evaluating the esthetic expression of environmental design schemes | |
CN106489114A (en) | A kind of generation method of robot interactive content, system and robot | |
Kallus et al. | Neighborhood—The metamorphosis of an idea | |
Poldma | Transforming interior spaces: Enriching subjective experiences through design research | |
Naz | Interactive living space for neo-nomads: an anticipatory approach | |
CN111506940A (en) | Furniture, ornament and lamp integrated intelligent local method based on 3D structured light | |
CN107590852B (en) | Behavior-constrained automatic indoor three-dimensional scene construction method | |
Chen et al. | Toward Affordable and Practical Home Context Recognition:—Framework and Implementation with Image-based Cognitive API— | |
Törnberg | Innovation in complex adaptive systems | |
Chen et al. | Recognizing fine-grained home contexts using multiple cognitive APIs | |
Winther | Urban compact living: Making home in the city: An ethnographic case study of compact living in an urban Danish context | |
Jiuqiang et al. | Design and management methods of smart home human-computer relationship | |
Guy | Pragmatic ecologies | |
De Deyne et al. | Graded structure in adjective categories | |
CN112836276A (en) | Method, device, equipment and storage medium for file broadcasting based on household design | |
Boylan | ICOM at fifty | |
Wang et al. | Applying shape grammar and BIM for generating the mass modular housing design in ShanLiChenJia village, ZhaoYuan, China | |
Ma et al. | Embodiment and Technical Application of Biophilia in Private Space | |
Vasilski | Sense of simplicity as a model of meaning in cultural landscape. Case study: minimalism in Architecture | |
Zhang | A Knowledge-based Framework for Human-Centered Residential Built Environment Design | |
CN117095082A (en) | Decoration effect graph generation method and device, electronic equipment and storage 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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |