CN114298308B - Furniture personalized customization system and method based on interactive genetic algorithm - Google Patents
Furniture personalized customization system and method based on interactive genetic algorithmInfo
- Publication number
- CN114298308B CN114298308B CN202111493197.3A CN202111493197A CN114298308B CN 114298308 B CN114298308 B CN 114298308B CN 202111493197 A CN202111493197 A CN 202111493197A CN 114298308 B CN114298308 B CN 114298308B
- Authority
- CN
- China
- Prior art keywords
- furniture
- genetic algorithm
- phenotype
- method based
- interactive genetic
- 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
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
本发明涉及一种基于交互遗传算法的家具个性化定制方法，旨在帮助小空间住户合理规划家具储存空间布局，以衣柜储存空间布局为主。技术方案及其主要用途包括以下几点：1)将衣柜内部储存功能模块进行划分并归纳各功能模块的空间尺寸范围，基于卡诺模型结合“Better‑worse满意度系数”筛选出必备功能模块；2)采用交互遗传算法,针对用户视觉化获取最优储存布局方案,解决用户偏好模糊和与设计师之间沟通成本高效率低的问题；3)引入惩罚函数引导方案生成方向,以较少评价次数获取最终优化结果,缓解用户在方案评价时产生的疲劳，同时保证储存布局方案均具备可行性及合理性。
This invention relates to a method for personalized furniture customization based on an interactive genetic algorithm, aiming to help residents in small spaces rationally plan the layout of furniture storage space, focusing on wardrobe storage space. The technical solution and its main uses include the following: 1) Dividing the internal storage functional modules of the wardrobe and summarizing the spatial size range of each module, using a Kano model combined with a "Better-worse satisfaction coefficient" to select essential functional modules; 2) Employing an interactive genetic algorithm to visually obtain the optimal storage layout scheme for users, solving the problems of ambiguous user preferences and high communication costs and low efficiency between users and designers; 3) Introducing a penalty function to guide the direction of scheme generation, obtaining the final optimized result with fewer evaluations, alleviating user fatigue during scheme evaluation, and ensuring that all storage layout schemes are feasible and reasonable.
Description
Technical Field
The invention relates to the field of personalized customization of furniture, in particular to a personalized customization system and method of furniture based on an interactive genetic algorithm.
Background
More and more people select small family type home or Loft apartment residence, the use requirement of the user on furniture is not limited to single function use of traditional furniture, and a layout scheme which accords with individuation and diversification of space storage is designed through understanding the living environment, living habit and storage requirement of the user. The customized furniture is also an essential important component in modern home decoration, and has the characteristics of being custom-made, environment-friendly, fashionable, professional and the like, however, for the customized furniture, the personalized customization scheme of the furniture is limited in the aspect of aesthetic appearance, no unified standard is formulated in the layout market aiming at the storage space of the furniture, and the customized furniture is custom-made by relying on the experience of users and designers, so that the operation mode not only leads the finished furniture to be disjointed with the actual demands of the users, but also increases the cost of manpower and material resources of the users and the designers.
The interactive genetic algorithm is used as a computer intelligent algorithm for expanding the application field of the traditional genetic algorithm, is mainly applied to the design fields of buildings, music, industry, clothing and the like at present, takes influence factors which cannot be edited into specific objective functions such as psychology, emotion, hobbies and the like of people as important indexes in the evolution process to be embedded into an algorithm system, and guides the population evolution direction, but the design research of furniture storage function layout by applying the interactive genetic algorithm does not appear in the furniture design field, so that the introduction of the interactive genetic algorithm in the furniture storage function layout field design has pioneering significance.
Disclosure of Invention
The invention aims to provide a furniture personalized customization system and method based on an interactive genetic algorithm, which solve the problems.
The invention realizes the aim through the following technical scheme that the furniture personalized customization system and the furniture personalized customization method based on the interactive genetic algorithm are characterized by comprising the following steps:
1) Dividing the function modules of the appointed furniture according to the A1 standard;
2) Performing region positioning on different functional modules, and setting a size range;
3) Constructing a mathematical model for the functional module area by adopting a grid method, and sequentially marking the functional module area with a-y according to the longitudinal axis direction and from left to right by combining a letter symbol method;
4) The unit modulus, the growth direction and the level variable are set for the furniture module and are respectively used as a gene position of a furniture chromosome to control the phenotype of each functional area of the furniture;
5) Sequentially decoding all the gene information contained in the chromosome according to a-y order from small to large until all the gene information is decoded, wherein the whole furniture storage space layout is fully paved by the dominant phenotype;
6) Setting four limit rules of different functional areas, and adding punishment items for the objective function;
7) And selecting the initial population scale as M=60P 55, acquiring the initial population P54, performing fitness evaluation, selecting M=60 as the initial population scale number, and performing fitness evaluation on the initial population.
8) Performing gene crossover mutation operation by using a single-point crossover method, and setting the population crossover rate and the mutation rate to be Pc=0.8 and Pm=0.1 respectively;
9) Outputting the optimal scheme or the visualized furniture scheme when the user evaluation times reach forty-five times.
As a preferred aspect of the present invention, the A1 standard is an optimum standard, which is to divide furniture into a plurality of functional areas, and to correspondingly set the storage contents of each functional area and the common accessories.
In the present invention, it is preferable that the interior space of the furniture is divided into five areas (A-E), wherein the area A is a space height set in a range of 600 to 1400mm, the area B is a space height set in a range of 1400 to 180mm, the area C is a space height set in a range of 1800mm or more, and the area D, E is a space height set in a range of 600mm or less.
As a preferred aspect of the present invention, the corresponding spatial dimension ranges are set according to different functional modules, so as to conform to the usage scenario of the articles in the area in real life.
As a preferred mode of the present invention, the cells are numbered with a code n, wherein the functional module phenotype gene information of the n-number cell n=i [ a≤i≤y ] as the initial growth point is represented by the form of a ternary array (Ai, bi, ci), wherein A represents a cell modulus variable, B represents a growth direction variable, and C represents a level variable.
As the optimization of the invention, the length of the complete chromosome genotype is 25 times 3=75 bits, and the acquisition method is to sequentially connect the genetic bit information in the a-y number unit cells end to end.
Preferably, the expression patterns of the eight functional modules are expressed in the form of triplets in the chromosomal individual gene, whereby the functional module translation rules are tabulated.
As the optimization of the invention, the phenotypes are divided into two types of recessive phenotypes or explicit phenotypes, wherein the recessive phenotypes are that genes contained in the recessive phenotypes are hidden and invisible in the process of participating in an interactive genetic algorithm by a user, the explicit phenotypes are expressed as visible, decoding priorities are used as the basis of eight modules of recessive or explicit phenotypes, in a-y number of cells, the earlier the cell letter numbers in an English alphabetical table are the more preferentially the decoding orders, and only the furniture whole storage layout scheme generated by the explicit phenotypes is presented to the user for scoring by a visual effect.
As the optimization of the invention, a punishment function is introduced, a punishment mechanism is formulated, and except for one dominant phenotype which is selected, the system sets the individual adaptation of the chromosomes with the same dominant phenotype to 0 and conceals the individual adaptation, so that the participation in the user interaction evaluation process is avoided.
In the system screening process, chromosome individuals conforming to a punishment mechanism are set to be low-score and are regarded as invalid individuals, the rest are regarded as valid individuals, and the visualized storage layout scheme phenotype is given to a user for selection evaluation through decoding of the valid individuals.
As the optimization of the invention, the crossing rate of the single-point crossing method determines the convergence performance of the population, and the excessive or insufficient crossing rate can influence the genotypes of the individuals with excellent population, and a mutation operator is introduced, namely, random mutation operation is carried out on a certain genetic locus of a parent chromosome, so that new individuals are generated, thereby improving the global searching capability of the algorithm. .
Compared with the prior art, the method has the beneficial effects that the method is designed by introducing the interactive genetic algorithm to carry out visualization scheme design aiming at furniture storage layout in the field of furniture design, users and designers can break through the traditional communication mode to carry out demand visualized extraction, the cost of manpower and material resources is reduced, the design efficiency and enterprise side customized service experience are greatly improved, meanwhile, a punishment function is introduced on the basis of the interactive genetic algorithm, namely punishment rule constraint is carried out on selected population individuals in the system operation process, and the rationality and feasibility of the storage layout scheme which is participated in selection and evaluation by the users are ensured. And introducing a mutation operator into the algorithm system, carrying out random mutation operation on a certain gene position of a parent chromosome to generate a new individual, and improving the global searching capability of the algorithm when the population iteration is nearly converged and the solving space is overlarge and the optimal solution of the objective function still does not exist.
Drawings
FIG. 1 is a schematic flow diagram of an interactive genetic algorithm according to an embodiment of the present invention;
FIG. 2 is a schematic view of a customized wardrobe interior storage space grid in accordance with an embodiment of the invention;
FIG. 3 is a schematic representation of chromosome coding according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a translation rule of a functional module according to an embodiment of the present invention;
FIG. 5 is a schematic representation of a single point crossover operation of a parent chromosome according to an embodiment of the present invention;
FIG. 6 is a schematic representation of a paternal chromosomal variation manipulation according to an embodiment of the invention;
FIG. 7 is a histogram of optimal fitness values for an optimal storage layout scheme according to an embodiment of the present invention;
FIG. 8 is a graph showing the trend of the optimal fitness value per generation according to the preferred embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings:
Furniture personalized customization system and method based on interactive genetic algorithm, as shown in figures 1-8, comprises the following steps:
1) And dividing the function modules of the appointed furniture according to the optimal standards.
2) Performing region positioning on different functional modules, and setting a size range;
3) Constructing a mathematical model for the functional module area by adopting a grid method, and sequentially marking the functional module area with a-y according to the longitudinal axis direction and from left to right by combining a letter symbol method;
4) The unit modulus, the growth direction and the level variable are set for the furniture module and are respectively used as a gene position of a furniture chromosome to control the phenotype of each functional area of the furniture;
5) Sequentially decoding all the gene information contained in the chromosome according to a-y order from small to large until all the gene information is decoded, wherein the whole furniture storage space layout is fully paved by the dominant phenotype;
6) Setting four limit rules of different functional areas, and adding punishment items for the objective function;
7) And selecting the initial population scale as M=60P 55, acquiring the initial population P54, performing fitness evaluation, selecting M=60 as the initial population scale number, and performing fitness evaluation on the initial population.
8) Performing gene crossover mutation operation by using a single-point crossover method, and setting the population crossover rate and the mutation rate to be Pc=0.8 and Pm=0.1 respectively;
9) Outputting the optimal scheme or the visualized furniture scheme when the user evaluation times reach forty-five times.
The A1 standard is an optimal standard, wherein the optimal standard is to divide furniture into a plurality of functional areas, and the storage content and common accessories of each functional area are correspondingly set.
The interior space of the furniture is divided into five areas (A-E), wherein the area A is set to have a space height in the range of 600-1400 mm, the area B is set to have a space height in the range of 1400-1500 mm, the area C is set to have a space height in the range of 1800mm or more, and the area D, E is set to have a space height in the range of 600mm or less.
And setting a corresponding space size range according to different functional modules so as to accord with the use scene of the articles in the area in actual life.
The cells are numbered, the code is n, wherein the functional module phenotype gene information taking n number of the cells n=i [ a≤i≤y ] as an initial growth point is represented by a form of a ternary array (Ai, bi, ci), wherein A represents a unit modulus variable, B represents a growth direction variable, and C represents a level variable. The length of the complete chromosome genotype is 25 times 3=75 bits, and the acquisition method is to sequentially connect the genetic bit information in the a-y number unit cells end to end. The phenotypes of the eight functional modules are represented in the chromosome individual genes in the form of a ternary array, so that the functional module translation rules are tabulated.
The method comprises the steps of dividing the phenotypes into two types of recessive phenotypes or explicit phenotypes, wherein the recessive phenotypes are that genes contained in the recessive phenotypes are hidden and invisible in the process of participating in an interactive genetic algorithm by a user, the explicit phenotypes are visible, decoding priorities are used as the basis of eight modules of recessive or explicit phenotypes, in a-y number cell, the earlier the cell letter numbers in an English alphabetical table are, the more preferential the decoding orders are, and only the furniture whole storage layout scheme generated by the explicit phenotypes is presented to the user for scoring by a visual effect.
And introducing a punishment function, formulating a punishment mechanism, and setting all chromosome individual adaptations of the other same dominant phenotype to 0 and hiding except for one dominant phenotype selected by the system so as to avoid participating in the user interaction evaluation process.
In the system screening process, chromosome individuals conforming to a punishment mechanism are set as low scores and are regarded as invalid individuals, the rest are regarded as valid individuals, and the visualized storage layout scheme phenotype is given to a user for selection evaluation through decoding of the valid individuals.
The crossing rate of the single-point crossing method determines the convergence performance of the population, and the excessive or insufficient crossing rate can influence the genotypes of the excellent individuals of the population, and a mutation operator is introduced, namely, random mutation operation is performed on a certain genetic locus of a parent chromosome, so that new individuals are generated, and the global searching capability of an algorithm is improved. .
When the customized wardrobe is used, the wardrobe is taken as an example, as the storage layout requirements of the mass population on the customized wardrobe are wider, compared with the mass population, the customized wardrobe has specificity for the old people and children, and special rule limitations exist in the design process of the customized wardrobe, so that the mass population is selected as a main tested population, the age and sex distribution of the mass population are uniform, namely, the users from 20 years old to 55 years old are set as the main tested population of the customized wardrobe, the number of tested personnel is 6, and the specific information is as follows:
| Age range | Sex (sex) | Numbering device |
| Age 20-29 | Man's body | No. 1 |
| Age 20-29 | Female | No. 2 |
| Age of 30-39 years | Man's body | No. 3 |
| Age of 30-39 years | Female | No. 4 |
| Age of 40-55 years | Man's body | No. 5 |
| Age of 40-55 years | Female | No. 6 |
The tested group adopts a Rickett five-level scale as a scoring standard, wherein 0-20 points represent very dissatisfaction, 20-40 points represent dissatisfaction, 40-60 points represent general satisfaction, 60-80 points represent satisfaction, and 80-100 points represent very satisfaction, wherein when a user scores over 95 points for a storage layout scheme, the system automatically judges the scheme as an optimal scheme and simultaneously terminates an algorithm and outputs the optimal scheme, and when the number of times of user participation in selection evaluation reaches forty-five times, the system screens out the current optimal scheme according to the evaluation result of the user and simultaneously the algorithm is automatically terminated.
And adopting elite selection method in algorithm operation system to make population interactive genetic evolution, in the course of user participation selection and evaluation, the individual can be automatically excluded when the score is less than 20min, when the score is between 20-80 min, the system can introduce mutation operator to make cross mutation operation, and when the score is greater than 80 min, the individual can be retained.
The selected 6 testees participate in the evaluation for about 40 to 45 times, wherein the highest fitness value is 95 minutes, the average fitness value is 89.7 minutes (shown in fig. 7), the rationality and feasibility of the interactive genetic algorithm for the internal storage layout design of furniture in the field of furniture design can be known through data analysis, and a user can intuitively and efficiently obtain a satisfaction scheme in the process of selecting and evaluating fewer times through the algorithm.
The data of the number 1 tested person is selected for example analysis, in the process of selecting and evaluating the scheme, the optimal fitness value of each generation of individuals has certain fluctuation, but as the evaluation times are more, the backward evaluation fitness value is more stable, which proves that when the number of the evaluation selected by the user is more and more, the scheme output by the system through the algorithm is more and more consistent with the requirement of the user.
The method has the advantages that the method is designed by introducing the interactive genetic algorithm to the furniture storage layout in the field of furniture design, users and designers can break through the traditional communication mode to carry out demand visualized extraction, the cost of manpower and material resources is reduced, the design efficiency and enterprise customized service experience are greatly improved, meanwhile, a punishment function is introduced on the basis of the interactive genetic algorithm, namely punishment rule constraint is carried out on selected population individuals in the system operation process, and the rationality and feasibility of the storage layout scheme which is participated in selection and evaluation by the users are ensured. And introducing a mutation operator into the algorithm system, carrying out random mutation operation on a certain gene position of a parent chromosome to generate a new individual, and improving the global searching capability of the algorithm when the population iteration is nearly converged and the solving space is overlarge and the optimal solution of the objective function still does not exist.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims.
Claims (11)
1. The furniture personalized customization method based on the interactive genetic algorithm is characterized by comprising the following steps of:
dividing the function modules of the appointed furniture according to the A1 standard;
Performing region positioning on different functional modules, and setting a size range;
constructing a mathematical model for the functional module area by adopting a grid method, and sequentially marking the functional module area with a-y according to the longitudinal axis direction and from left to right by combining a letter symbol method;
The unit modulus, the growth direction and the level variable are set for the furniture module and are respectively used as a gene position of a furniture chromosome to control the phenotype of each functional area of the furniture;
sequentially decoding all the gene information contained in the chromosome according to a-y order from small to large until all the gene information is decoded, wherein the whole furniture storage space layout is fully paved by the dominant phenotype;
Setting four limit rules of different functional areas, and adding punishment items for the objective function;
selecting M=60 as the scale quantity of the initial population, and evaluating the fitness of the initial population;
Performing gene crossover mutation operation by using a single-point crossover method, and setting the population crossover rate and the mutation rate to be Pc=0.8 and Pm=0.1 respectively;
When the user scores more than 95 points for the storage layout scheme, the system automatically judges the scheme as the optimal scheme, and simultaneously terminates the algorithm and outputs the optimal scheme, wherein when the number of times of user participation in selection evaluation reaches forty-five times, the system screens out the current optimal scheme according to the user evaluation result, and the algorithm is automatically terminated.
2. The furniture personalized customization method based on the interactive genetic algorithm according to claim 1, wherein the A1 standard is an optimal standard, the optimal standard is to divide furniture into a plurality of functional areas, and the storage content and common accessories of each functional area are correspondingly set.
3. The furniture personalized customization method based on the interactive genetic algorithm according to claim 1 is characterized in that the furniture internal space is divided into five areas, wherein the area A is a space height which is set in a range of 600-1400 mm, the area B is a space height which is set in a range of 1400-630 mm, the area C is a space height which is set in a range of more than 1800mm, and the area D, E is a space height which is set in a range of less than 600 mm.
4. A furniture personalization method based on an interactive genetic algorithm according to claim 3, wherein the corresponding spatial size ranges are set according to different functional modules to conform to the use scenario of the articles in the area in real life.
5. The furniture personalized customization method based on the interactive genetic algorithm according to claim 4, wherein the number of the cells is n, the code is n, the functional module phenotype gene information taking n number of the cells n=i [ a≤i≤y ] as an initial growth point is represented by a form of a ternary array (Ai, bi, ci), wherein Ai represents a unit modulus variable, bi represents a growth direction variable, and Ci represents a level variable.
6. The furniture personalized customization method based on the interactive genetic algorithm according to claim 1, wherein the length of the complete chromosome genotype is 25 x 3 = 75 bits, and the acquisition method is to sequentially connect the genetic bit information in the a-y number unit cells end to end.
7. The method for customizing furniture according to claim 6, wherein the phenotypes of the eight functional modules are represented in the form of triplets in the individual chromosome genes, thereby tabulating the functional module translation rules.
8. The furniture personalized customization method based on interactive genetic algorithm according to claim 7, wherein the phenotype is classified into a recessive phenotype or a manifestation phenotype, the recessive phenotype is that a gene contained in the phenotype is hidden and invisible in the process of participating in the interactive genetic algorithm by a user, and the dominant phenotype is visible, and decoding priority is taken as eight modules for hiding
And according to the basis of the explicit or explicit phenotype, in the cells a-y, the earlier the cell letter number is in the English alphabetical list, the more the decoding order is, and only the furniture whole storage layout scheme generated by the explicit phenotype is presented to a user for scoring by a visual effect.
9. The furniture personalized customization method based on the interactive genetic algorithm according to claim 8, wherein a punishment function is introduced to formulate a punishment mechanism, and the system sets all chromosome individual adaptations of the same dominant phenotype to 0 and conceals except for the selected dominant phenotype, so as to avoid participating in the user interactive evaluation process.
10. The furniture personalized customization method based on the interactive genetic algorithm according to claim 9, wherein in the system screening process, chromosome individuals conforming to the punishment mechanism are set as low scores and are regarded as invalid individuals, the rest are regarded as valid individuals, and the visualized storage layout scheme phenotype is given to a user for selection evaluation through decoding of the valid individuals.
11. The furniture personalized customization method based on the interactive genetic algorithm according to claim 1, wherein the crossing rate of the single-point crossing method determines the convergence performance of the population, and the excessive or insufficient crossing rate can affect the genotypes of the excellent individuals of the population, and a mutation operator is introduced, namely, random mutation operation is performed on a certain genetic locus of a parent chromosome, so that new individuals are generated, and the global searching capability of the algorithm is improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111493197.3A CN114298308B (en) | 2021-12-08 | 2021-12-08 | Furniture personalized customization system and method based on interactive genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111493197.3A CN114298308B (en) | 2021-12-08 | 2021-12-08 | Furniture personalized customization system and method based on interactive genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114298308A CN114298308A (en) | 2022-04-08 |
| CN114298308B true CN114298308B (en) | 2025-11-21 |
Family
ID=80966470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111493197.3A Active CN114298308B (en) | 2021-12-08 | 2021-12-08 | Furniture personalized customization system and method based on interactive genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114298308B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2236015A1 (en) * | 1995-10-31 | 1997-05-09 | Frederick S. M. Herz | System for customized electronic identification of desirable objects |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6067409A (en) * | 1996-06-28 | 2000-05-23 | Lsi Logic Corporation | Advanced modular cell placement system |
| CN103500255A (en) * | 2013-10-16 | 2014-01-08 | 南通大学 | Intelligent layout method used for rectangular part |
| CN107330214B (en) * | 2017-07-11 | 2021-06-01 | 哈尔滨工业大学（威海） | Spatial Layout Optimization Method Based on Discretization and Heuristic Evolutionary Algorithm |
| CN111079273A (en) * | 2019-12-03 | 2020-04-28 | 北京新学堂网络科技有限公司 | Automatic layout design method and device |
| CN113688322A (en) * | 2021-09-03 | 2021-11-23 | 德华兔宝宝装饰新材股份有限公司 | Wardrobe customizing method based on customer preferences |
-
2021
- 2021-12-08 CN CN202111493197.3A patent/CN114298308B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2236015A1 (en) * | 1995-10-31 | 1997-05-09 | Frederick S. M. Herz | System for customized electronic identification of desirable objects |
| CN109740243A (en) * | 2018-12-29 | 2019-05-10 | 江苏艾佳家居用品有限公司 | A kind of furniture layout method and system based on bulk-breaking intensified learning technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114298308A (en) | 2022-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779084B (en) | Machine learning system and method | |
| Christin et al. | Anatomical enablers and the evolution of C4 photosynthesis in grasses | |
| US7730002B2 (en) | Method for iterative design of products | |
| Dou et al. | Multi-stage interactive genetic algorithm for collaborative product customization | |
| CN103488714B (en) | Book recommendation method and system based on social networking | |
| JP2008500660A (en) | Determining group design preferences | |
| CN108564117A (en) | A kind of poor student's auxiliary identification based on SVM | |
| CN112862217A (en) | Bilateral matching method for supply and demand parties of high-end equipment cloud manufacturing platform | |
| CN102799741B (en) | Initially baked tobacco formula threshing optimized design method based on genetic algorithm | |
| CN114298308B (en) | Furniture personalized customization system and method based on interactive genetic algorithm | |
| Ramasubramanian et al. | Strategies to assure optimal trade-offs among competing objectives for the genetic improvement of soybean | |
| Greenwood et al. | Evolutionary games and the study of cooperation: Why has so little progress been made? | |
| CN118709920A (en) | A landscape planning scheme intelligent matching method and system | |
| Cai | User preference adaptive fitness of interactive genetic algorithm based ceramic disk pattern generation method | |
| CN112817959B (en) | Construction method of ancient biomorphic phylogenetic tree based on multi-metric index weight | |
| CN108985854A (en) | A kind of personalized product conceptual design method that user participates in | |
| Wanga et al. | The Problem of" Multi-person Multi-object Exchange Strategy | |
| Yamauchi et al. | Relaxation of selection, niche construction, and the Baldwin effect in language evolution | |
| Yang et al. | An Intelligent Designing Approach for Personalized Products Using Product Gene | |
| Misri et al. | Design DNA: Theory Reviewing Behind the Behavioral Aspect in the Levels of Design | |
| Nowak et al. | No need for speed: Modeling trend adoption in a heterogeneous population | |
| Tang et al. | Research on web association rules mining structure with genetic algorithm | |
| CN117829671A (en) | Performance evaluation method based on self-adaptive weighting | |
| CN115374690A (en) | House indoor design selection method, terminal equipment and storage medium | |
| Jerinabi et al. | Empowerment of women through convergence technology |
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 |