CN110175355B - Building matching method and device based on machine learning - Google Patents
Building matching method and device based on machine learning Download PDFInfo
- Publication number
- CN110175355B CN110175355B CN201910319116.4A CN201910319116A CN110175355B CN 110175355 B CN110175355 B CN 110175355B CN 201910319116 A CN201910319116 A CN 201910319116A CN 110175355 B CN110175355 B CN 110175355B
- Authority
- CN
- China
- Prior art keywords
- home
- household
- matching
- machine learning
- building
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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 application provides a building matching method and device based on machine learning. The method comprises the following steps: constructing a household multi-dimensional characteristic set through household characteristic data; the home furnishing comprises furniture and household appliances; quantitatively extracting the user family member structure and household function demand characteristics to form a user demand limiting set; establishing a machine learning network based on a matching case for placing the indoor home of the building, and training; and importing the household multi-dimensional feature set into a machine learning network, and matching the placement position of the household in the building room by combining the user requirement limiting set for constraint. According to the building matching method and device based on machine learning, the household placing design efficiency is improved by combining the household placing method and the machine learning characteristics.
Description
Technical Field
The application relates to the field of home design, in particular to a building matching method and device based on machine learning.
Background
The household design refers to the overall display style and ornament design collocation of the family living environment, the office, the public space or the commercial space. With the improvement of living standard of people, the requirements of people on household design are higher and higher. At the same time, the rising of the house price also makes the living area more and more tense. How to utilize limited space to reasonably place furniture, household appliances and other household equipment, the functional requirements of the whole family members are met, meanwhile, the purpose of meeting the traditional aesthetic experience is also achieved, and the method becomes a difficult point of the current household design.
The motivation of machine learning lies in the establishment and simulation of neural networks for human brain analysis and learning. Machine learning mimics the mechanism of the human brain to interpret data, and forms abstract high-level representation attribute categories or features by combining low-level features, thereby realizing general artificial intelligence. At present, deep learning is widely applied to the fields of machine translation, semantic mining, image recognition, face recognition, voice recognition and the like. Therefore, the machine learning technology and the home design practice can be combined, so that the efficiency of home design is improved, and the accuracy of space utilization is improved.
Disclosure of Invention
In view of this, an object of the present application is to provide a building matching method and device based on machine learning, so as to improve the utilization level of building space and solve the technical problems of low intelligence and low efficiency in the current home design process.
Based on the above purpose, the present application provides a building matching method based on machine learning, including:
constructing a household multi-dimensional characteristic set through household characteristic data; the home furnishing comprises furniture and household appliances;
quantitatively extracting the user family member structure and household function demand characteristics to form a user demand limiting set;
establishing a machine learning network based on a matching case for placing the indoor home of the building, and training;
and importing the household multi-dimensional feature set into the machine learning network, and combining the user demand limiting set to carry out constraint to match the placing position of the household in the building room.
In some embodiments, the building a household multidimensional feature set from household feature data includes:
the household multi-dimensional feature set is formed by carrying out multi-dimensional data extraction on the size, shape, material, color and function of a household, and carrying out standardization and quantification processing.
In some embodiments, the normalization and quantization process comprises:
the method comprises the steps of classifying the home according to the shape, material, color and function of the home, so that the shape, material, color and function of the home are described through unified measurement respectively, and the standardized processing of the home is realized;
and coding the shape, material, color and function of the home, thereby realizing the quantitative processing of the home.
In some embodiments, the quantitatively extracting the user family member structure and the household function requirement characteristics to form a user requirement definition set includes:
the family members are coded according to different living combination types, and the family structure requirement limitation is determined according to the different living combination types.
In some embodiments, the quantitatively extracting the user family member structure and the household function requirement characteristics to form a user requirement limiting set further includes:
and decomposing the household function requirements, sequencing and coding according to the requirement strength, and combining the household structure requirement limitation to form a quantitative user requirement limitation set.
In some embodiments, the building indoor home placement matching case based machine learning network is constructed and trained, including the following steps:
establishing a home furnishing sample set, obtaining an n-dimensional home furnishing characteristic value of each sample furniture, and forming a plurality of n-dimensional home furnishing characteristic vectors, wherein n is a positive integer;
decomposing the suite in the indoor home furnishing placement matching case of the building into a plurality of independent rooms, obtaining the placement matching position of the home furnishing in each independent room, and forming an s-dimensional matching position feature vector, wherein s is the number of home furnishing in the independent room;
taking the n-dimensional home characteristic vector in the home sample set as the input of a machine learning network, taking the s-dimensional matching position characteristic vector as the output, and carrying out neural network training;
and setting a steady state threshold value epsilon, wherein delta is the current home furnishing matching position, and delta 'is the home furnishing matching position in the last training result, after the neural network is iteratively trained for multiple times, when the | delta-delta' | < epsilon, the training process enters a steady state, and the training is stopped.
In some embodiments, the matching the placement position of the home in the building room by combining the constraint of the user requirement definition set includes:
and coding the user requirement strength into the front m bits of the limited set, and calculating the home placement position capable of maximally meeting the user requirement by adopting a matching or matching mode.
Based on the above-mentioned purpose, this application has still provided a building matching device based on machine learning, includes:
the feature extraction module is used for constructing a household multi-dimensional feature set through household feature data; the home furnishing comprises furniture and household appliances;
the demand extraction module is used for quantitatively extracting the demand characteristics of the family member structure and the household function of the user to form a user demand limiting set;
the machine learning module is used for establishing a machine learning network based on the matching cases of the indoor home arrangement of the building and carrying out training;
and the result matching module is used for importing the household multi-dimensional feature set into the machine learning network, combining the user requirement limiting set for constraint, and matching the placing position of the household in the building room.
In some embodiments, the feature extraction module comprises:
the furniture feature extraction unit is used for performing multi-dimensional data extraction on the size, shape, material, color and function of the home, and performing standardization and quantification processing to form a furniture multi-dimensional feature set;
and the household appliance characteristic extraction unit is used for extracting multi-dimensional data of the size, shape, material, color and function of the household appliance, and carrying out standardization and quantification processing to form a household appliance multi-dimensional characteristic set.
In some embodiments, the demand extraction module includes:
the family demand extraction unit is used for coding family members according to different living combination types and determining family structure demand limitation according to the different living combination types;
and the function requirement extraction unit is used for decomposing the household function requirements by taking the household as a unit, coding the household function requirements, and combining the household structure requirement limitation to form a quantized user requirement limitation set.
Drawings
In the drawings, like reference numerals refer to the same or similar parts or elements throughout the several views unless otherwise specified. The figures are not necessarily to scale. It is appreciated that these drawings depict only some embodiments in accordance with the disclosure and are therefore not to be considered limiting of its scope.
Fig. 1 shows a flowchart of a building matching method based on machine learning according to an embodiment of the present invention.
Fig. 2 shows a constitutional view of a machine learning-based building matching apparatus according to an embodiment of the present invention.
Fig. 3 shows a feature extraction module configuration diagram according to an embodiment of the present invention.
FIG. 4 illustrates a demand extraction module configuration diagram according to an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows a flowchart of a building matching method based on machine learning according to an embodiment of the present invention. As shown in fig. 1, the building matching method based on machine learning includes:
s11, constructing a household multi-dimensional feature set through household feature data; the home furnishing comprises furniture and household appliances.
In an embodiment, the building a home multidimensional feature set from home feature data includes:
the household multi-dimensional feature set is formed by carrying out multi-dimensional data extraction on the size, shape, material, color and function of a household, and carrying out standardization and quantification processing.
In one embodiment, the normalization and quantization process comprises:
the method comprises the steps of classifying the home according to the shape, material, color and function of the home, so that the shape, material, color and function of the home are described through unified measurement respectively, and the standardized processing of the home is realized;
and coding the shape, material, color and function of the home, thereby realizing the quantitative processing of the home.
Particularly, in the process of considering the placement and positioning of a home, the factors such as the size, shape and characteristics, color matching, convenience in function and the like of the home are comprehensively considered, so that when the work is handed to machine learning, the factors also need to be comprehensively analyzed. Because machine learning can only accurately process and calculate quantized data, the first step of machine learning is to standardize and quantize various household characteristic data.
For the size of a home, the data is quantized data, further quantization processing is not needed, but the data of three dimensions of length, width and height of the home needs to be collected, and the data are matched according to the actual size of the building interior.
For the shape characteristics, since the shape itself is not quantized data, it is necessary to encode the shape of the house, and for example, a rectangle can be encoded as 001, and a circle can be encoded as 002. It is noted that people often consider the combination of shape and size in the process of laying a home, for example, it may be appropriate to match an inscribed square table or a round table in a round area of one square meter. Therefore, in the process of machine learning, the shape and the size are taken as input features independently, and simultaneously, the joint features of the shape and the size can be taken as input features to be introduced into the machine learning process.
For color, the encoding quantization process is also required. People often need to match home colors into similar or similar styles in the home matching design process, so that the color matching measurement can be quickly realized by adopting a code matching algorithm in combination with the home aesthetic matching rule in the machine learning process.
It is also a feature of the function that the encoding quantization process needs to be performed. Different households have different functions, and the matched placement positions also need certain rules, for example, kitchen and bathroom appliances can be placed in a designated area of a kitchen or a bathroom regardless of the size, the dimension and the color. Therefore, when the function quantization coding is carried out, the area limitation can be carried out by adopting a hierarchical coding mode, so that the technical effect that the specified function area is matched with the specified function home is achieved. For example, in the case of function coding, the primary code is a function area code, such as 1 for living room, 2 for kitchen; the secondary code is a code for a specific person, such as 1 for the old and 2 for the child; the tertiary code is a specific function, such as 001 for reading, 002 for cooking, and 21002 when representing a kitchen home for elderly cooking. Certainly, the functional code can be further refined in grading granularity according to the specific home matching requirement, so that the accuracy of functional matching is improved.
And S12, quantitatively extracting the user family member structure and the household function requirement characteristics to form a user requirement limiting set.
In one embodiment, the quantitatively extracting the characteristics of the family member structure and the household function requirement of the user to form a user requirement definition set includes:
the family members are coded according to different living combination types, and the family structure requirement limitation is determined according to the different living combination types.
Specifically, in the current chinese family, there appear different home living structures such as 4-2-1 inverted pyramid type (i.e. 4 old people, 2 middle-aged people, 1 child), 2-1 inverted pyramid type (i.e. 2 middle-aged people, 1 child), and the world of a newly married couple, and in the process of matching and placing the home, it is necessary to determine a limited set of user requirements according to the combination type of the different home living structures.
For example, in the 4-2-1 family type, the needs of the elderly, children and middle-aged people need to be coded, and a comprehensive demand limit set taking the family as a unit is formed after intersection.
In an embodiment, the quantitatively extracting the characteristics of the family member structure and the household function requirement of the user to form a user requirement limiting set further includes:
and decomposing the household function requirements, sequencing and coding according to the requirement strength, and combining the household structure requirement limitation to form a quantitative user requirement limitation set.
Particularly, the limited building space often cannot fully meet all user requirements when facing infinite living requirements, so that in the process of matching machine learning, in order to avoid a final calculation result without solution, coding can be carried out on the home matching requirements of the user according to the urgency degree, and in the process of machine learning, the urgency requirements of most users can be met, namely effective solving can be realized. For example, the need for security protection of the elderly and children is often more urgent than the need for entertainment, and the urgency level of security protection of the elderly and children may be encoded to be prioritized over the entertainment function.
And S13, constructing a machine learning network based on the matching cases of the indoor home arrangement of the building, and training.
In one embodiment, the building indoor home placement matching case based machine learning network is constructed and trained, and the method includes the following steps:
establishing a home furnishing sample set, obtaining an n-dimensional home furnishing characteristic value of each sample furniture, and forming a plurality of n-dimensional home furnishing characteristic vectors, wherein n is a positive integer;
decomposing the suite in the indoor home furnishing placement matching case of the building into a plurality of independent rooms, obtaining the placement matching position of the home furnishing in each independent room, and forming an s-dimensional matching position feature vector, wherein s is the number of home furnishing in the independent room;
taking the n-dimensional home characteristic vector in the home sample set as the input of a machine learning network, taking the s-dimensional matching position characteristic vector as the output, and carrying out neural network training;
and setting a steady state threshold value epsilon, wherein delta is the current home furnishing matching position, and delta 'is the home furnishing matching position in the last training result, after the neural network is iteratively trained for multiple times, when the | delta-delta' | < epsilon, the training process enters a steady state, and the training is stopped.
And S14, importing the household multi-dimensional feature set into the machine learning network, and matching the placement position of the household in the building room by combining the user requirement limiting set for constraint.
In one embodiment, the matching the placement position of the home in the building room with the constraint combining the user requirement definition set includes:
and coding the user requirement strength into the front m bits of the limited set, and calculating the home placement position capable of maximally meeting the user requirement by adopting a matching or matching mode.
For example, when the requirement strength is coded, the 1 st bit of the limited set is coded as a requirement strength coding bit, 0 is required to be met, 1 is as much as possible, and 2 is optional, if the scheme of the calculation result matching "0 and 1and 2" is less, the requirement can be released, and more home placement matching schemes can be released by adopting the matching standard of "0 and 1" or "0".
Fig. 2 shows a constitutional view of a machine learning-based building matching apparatus according to an embodiment of the present invention. As shown in fig. 2, the building matching device based on machine learning may be divided into:
the feature extraction module 21 is configured to construct a household multi-dimensional feature set through household feature data; the home furnishing comprises furniture and household appliances;
the requirement extraction module 22 is used for quantitatively extracting the requirement characteristics of the family member structure and the household function of the user to form a user requirement limiting set;
the machine learning module 23 is used for constructing a machine learning network based on the matching cases of the indoor home arrangement of the building and training;
and the result matching module 24 is used for importing the household multi-dimensional feature set into the machine learning network, performing constraint by combining the user requirement limiting set, and matching the placing position of the household in the building room.
Fig. 3 shows a configuration diagram of a machine learning-based building matching apparatus according to an embodiment of the present invention.
As can be seen from fig. 3, the feature extraction module 21 includes:
the furniture feature extraction unit 211 is configured to perform multi-dimensional data extraction on the size, shape, material, color and function of a home, and perform standardization and quantization processing to form a furniture multi-dimensional feature set;
the household appliance feature extraction unit 212 is configured to perform multi-dimensional data extraction on the size, shape, material, color, and function of the household appliance, and perform standardization and quantization processing to form a household appliance multi-dimensional feature set.
FIG. 4 illustrates a demand extraction module configuration diagram according to an embodiment of the present invention.
As can be seen from fig. 4, the demand extraction module 22 includes:
the family demand extraction unit 221 is used for encoding the family members according to different living combination types and determining the family structure demand limitation according to the different living combination types;
and the function requirement extracting unit 222 is configured to decompose and encode the home function requirements in units of home, and form a quantized user requirement limiting set by combining the home structure requirement limitation.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer readable storage medium. The storage medium may be a read-only memory, a magnetic or optical disk, or the like.
The above description is only for the specific embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various changes or substitutions within the technical scope of the present invention, and these should be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (6)
1. A building matching method based on machine learning is characterized by comprising the following steps:
constructing a household multi-dimensional characteristic set through household characteristic data; the home furnishing comprises furniture and household appliances;
quantitatively extracting the user family member structure and household function demand characteristics to form a user demand limiting set;
establishing a machine learning network based on a matching case for placing the indoor home of the building, and training;
importing the household multi-dimensional feature set into the machine learning network, and combining the user requirement limiting set to carry out constraint to match the placement position of the household in the building room;
the method comprises the following steps of establishing a machine learning network based on a matching case for placing the indoor home of the building, and training the machine learning network, wherein the method comprises the following steps:
establishing a home furnishing sample set, obtaining an n-dimensional home furnishing characteristic value of each sample home furnishing to form a plurality of n-dimensional home furnishing characteristic vectors, wherein n is a positive integer;
decomposing the suite in the indoor home furnishing placement matching case of the building into a plurality of independent rooms, obtaining the placement matching position of the home furnishing in each independent room, and forming an s-dimensional matching position feature vector, wherein s is the number of home furnishing in the independent room;
taking the n-dimensional home characteristic vector in the home sample set as the input of a machine learning network, taking the s-dimensional matching position characteristic vector as the output, and carrying out neural network training;
and setting a steady state threshold value epsilon, wherein delta is the current home furnishing matching position, and delta 'is the home furnishing matching position in the last training result, after the neural network is iteratively trained for multiple times, when the absolute value delta-delta' | is less, the training process enters a steady state, and the training is stopped.
2. The method according to claim 1, wherein the building of the household multi-dimensional feature set from the household feature data comprises:
the household multi-dimensional feature set is formed by carrying out multi-dimensional data extraction on the size, shape, material, color and function of a household, and carrying out standardization and quantification processing.
3. The method of claim 2, wherein the normalization and quantization process comprises:
the method comprises the steps of classifying the home according to the shape, material, color and function of the home, so that the shape, material, color and function of the home are described through unified measurement respectively, and the standardized processing of the home is realized;
and coding the shape, material, color and function of the home, thereby realizing the quantitative processing of the home.
4. The method according to claim 1, wherein the quantitatively extracting the user family member structure and the household function requirement characteristics to form a user requirement limiting set comprises:
the family members are coded according to different living combination types, and the family structure requirement limitation is determined according to the different living combination types.
5. The method according to claim 4, wherein the quantitatively extracting the user family member structure and the household function requirement characteristics to form a user requirement limiting set further comprises:
and decomposing the household function requirements, sequencing and coding according to the requirement strength, and combining the household structure requirement limitation to form a quantitative user requirement limitation set.
6. The method of claim 1, wherein said matching the home's placement within the building with the constraints of the user demand definition set comprises:
and coding the user requirement strength into the front m bits of the limited set, and calculating the home placement position capable of maximally meeting the user requirement by adopting a matching or matching mode.
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 CN110175355A (en) | 2019-08-27 |
| CN110175355B true 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) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN112052507B (en) * | 2020-09-16 | 2022-08-26 | 同济大学 | House waist line design system |
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 |
|---|
| Example-based Synthesis of 3D Object Arrangements;Matthew Fisher 等;《ACM Transactions on Graphics》;20121231;第31卷(第6期);第1-11页 * |
| 基于案例库的室内区域自动布局方法;刘米兰 等;《计算机辅助设计与图形学学报》;20170115;第29卷(第1期);第90-100页 * |
| 面向虚实融合的卧室箱体建模与布局算法;王超 等;《计算机科学与探索》;20180209;第4卷(第12期);第511-524页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110175355A (en) | 2019-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110175355B (en) | Building matching method and device based on machine learning | |
| Tervonen | JSMAA: open source software for SMAA computations | |
| CN107391505B (en) | Image processing method and system | |
| Rigau et al. | Informational aesthetics measures | |
| Stiny et al. | The palladian grammar | |
| CN110197225A (en) | House type spatial match method and system based on deep learning | |
| EP3474192A1 (en) | Classifying data | |
| CN111046478B (en) | Custom hard-fitting design method and design device | |
| Malz et al. | Approximating photo-z PDFs for large surveys | |
| CN112733246B (en) | Automatic building design method, device, terminal, storage medium and processor | |
| CN104077590A (en) | Video fingerprint extraction method and system | |
| García-Honrado et al. | An essay on the linguistic roots of fuzzy sets | |
| RU2687085C1 (en) | Simplified texture comparison system | |
| Landsheer | The specification of causal models with Tetrad IV: A review | |
| CN113505583B (en) | Emotion reason clause pair extraction method based on semantic decision graph neural network | |
| CN113779674A (en) | Method, device, equipment and storage medium for designing customized household three-dimensional model scheme | |
| CN111400519B (en) | Efficient customized massive similar house type searching method | |
| CN113743969A (en) | Method, device, equipment and storage medium for sales data prediction | |
| CN116431827A (en) | Information processing method, information processing device, storage medium and computer equipment | |
| CN108734761B (en) | Scene visualization method and device, electronic equipment and storage medium | |
| CN115169322A (en) | Natural language data mining statement solving method and device based on knowledge graph | |
| Wang et al. | A survey of personalized interior design | |
| CN114758788A (en) | Abnormal place identification method, device, equipment and storage medium | |
| CN105446959B (en) | Log content audits optimization method and device | |
| CN112818432A (en) | Method and device for generating tile laying design, 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 |