CN109299386A - A kind of furniture industry designer resource intelligent search matching method and system - Google Patents
A kind of furniture industry designer resource intelligent search matching method and system Download PDFInfo
- Publication number
- CN109299386A CN109299386A CN201811340173.2A CN201811340173A CN109299386A CN 109299386 A CN109299386 A CN 109299386A CN 201811340173 A CN201811340173 A CN 201811340173A CN 109299386 A CN109299386 A CN 109299386A
- Authority
- CN
- China
- Prior art keywords
- design
- information
- designer
- matching
- furniture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000013461 design Methods 0.000 claims abstract description 185
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000012550 audit Methods 0.000 claims abstract description 4
- 230000008520 organization Effects 0.000 claims abstract description 4
- 238000007726 management method Methods 0.000 claims description 26
- 230000008569 process Effects 0.000 claims description 16
- 230000003044 adaptive effect Effects 0.000 claims description 10
- 230000001537 neural effect Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 238000013439 planning Methods 0.000 claims description 5
- 238000012986 modification Methods 0.000 claims description 4
- 230000004048 modification Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000005284 excitation Effects 0.000 description 4
- 230000010365 information processing Effects 0.000 description 4
- 210000005036 nerve Anatomy 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 239000004744 fabric Substances 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
Abstract
The present invention relates to a kind of furniture industry designer resource intelligent search matching method and systems.This method comprises: user, designer and design organization issue design requirement information or designed capacity information by furniture design service platform；Furniture design service platform audits information, determines that information format, content meet platform rule, to guarantee to carry out retrieval matching according to platform rule；Design requirement information, designed capacity information are stored in the database of cloud server, storage mode is using keyword, classification, attribute as foundation；Beyond the clouds in server, the matching of the automatically retrieval based on fuzzy neural network is carried out to design requirement information and designed capacity information, and according to matching degree descending assortment from high to low, matching result Intelligence Feedback to user.The present invention can be improved furniture design resource retrieval efficiency, promotes furniture design supply and demand and docks matching precision, can be realized intelligent retrieval and the Optimized Matching of design requirement description and design resource.
Description
Technical field
The invention belongs to information technologies, technical field of furniture design, and in particular to a kind of furniture industry designer resource intelligence
It can search matching method and system.
Background technique
Fuzzy theory (Fuzzy Theory) grows up on the basis of Fuzzy Set Theory, including fuzzy mathematics, fuzzy
Five branches such as system, uncertainty and information, fuzzy decision, fuzzy logic and artificial intelligence.In fuzzy set, given range
Interior element is not necessarily the only two kinds of situations of "Yes" or "No" to its membership, but with the real number between 0 and 1 come table
Show subjection degree, there is also intermediate states.
Artificial neural network (Artificial Neural Networks, be abbreviated as ANNs) is referred to as neural network
(NNs) or make link model (Connection Model), it is a kind of imitation animal nerve network behavior feature, is divided
The algorithm mathematics model of cloth parallel information processing.This network relies on the complexity of system, by adjusting internal a large amount of sections
Relationship interconnected between point, to achieve the purpose that handle information.
Fuzzy neural network is the blurring of neural network.I.e. based on fuzzy set, fuzzy logic, in conjunction with NN method, benefit
With the self-organization of NN, achieve the purpose that flexible information processing.At present, FS is theoretical and NN is combined and is mainly used in business and economy
Estimation, automatic detection and monitoring, robot and automatic control, computer vision, expert system, speech processes, optimization problem, doctor
Application etc. is treated, furniture design transactional services field is not yet applied to.
During current furniture design service transacting, using traditional search method, the designer that user searches often with
Desired design requirement is not inconsistent.Furniture industry internet platform converges magnanimity designer, design resource and works, sets in numerous
It counts in category, user is difficult to quick-searching, identification and design requirement design resource the most matched.Thus, design transaction supply and demand
The period of docking is longer, and Design Works quality is difficult to ensure, affects user to the degree of belief of platform.
Summary of the invention
During current furniture design service transacting, it is difficult to quick, quasi- according to the task description of furniture design project
Really retrieve suitable design resource, designer and design requirement matching degree is lower, retrieval service period longer problem, this
Invention proposes a kind of automatic search matching method in furniture design qualified teachers source based on fuzzy neural network technology, improves furniture design
Resource retrieval efficiency promotes furniture design supply and demand and docks matching precision.
The present invention is based on fuzzy theorys, artificial nerve network model, using fuzzy neural network technology, multi-tag data mould
Paste set, artificial network's distributed algorithm model have well solved furniture design resource and have solved search cycle length, precision deficiency
Problem.Platform by by furniture design standard process, Design Works, design requirement structuring, labeling, using fuzzy set,
The self-organization of fuzzy logic, NN method reaches the handling flexibly of furniture design information, realizes that design requirement description is provided with design
The intelligent retrieval in source and Optimized Matching.
The technical solution adopted by the invention is as follows:
A kind of furniture industry designer resource intelligent search matching method, comprising the following steps:
User, designer and design organization issue design requirement information or designed capacity letter by furniture design service platform
Breath；
Furniture design service platform audits information, determines that information format, content meet platform rule, to guarantee
It is enough to carry out retrieval matching according to platform rule；
Design requirement information, designed capacity information are stored in the database of cloud server, storage mode is with key
Word, classification, attribute are foundation；
Beyond the clouds in server, design requirement information and designed capacity information are carried out based on the automatic of fuzzy neural network
Retrieval matching, and according to matching degree descending assortment from high to low, matching result is fed back to user.
Further, the design requirement information includes: demand coding, demand title, demand classification, issued state, hair
The cloth time；The demand classification includes use environment, three design field, design style dimensions；The issued state is covered
Publication, it is pending, do not pass through, undercarriage.
Further, in use environment dimension, the label of design requirement information is covered: bedroom, parlor, dining room, children, book
Room, office, hotel, other furniture；In design field dimension, the label of design requirement information includes: designing and consuftng, intelligent plant
Planning, the design of soft dress display and design, furniture design, family product, Brand Design；In design style dimension, design requirement information
Label include: Korean style, it is Southeast Asia, modern brief, American, Chinese style, European, Japanese.
Further, shown designed capacity information includes: designer's essential information and professional technique information；The designer
Essential information includes: designer's name, head portrait, telephone number, E-mail address；The professional technique information includes: inaugural position,
Design experiences are good at field, design, personal brief introduction, prize-winning situation.
Further, the field of being good at includes: that designing and consuftng, intelligent plant planning, soft dress display and design, furniture are set
Meter, family product design, Brand Design；The design includes the design style that designer is good at and design environment two dimensions
Degree, design style dimension includes: Korean style, Southeast Asia, modern brief, American, Chinese style, European, Japanese, design environment dimension packet
Contain: bedroom, parlor, dining room, children, study, office, hotel, other furniture.
Further, the automatically retrieval based on fuzzy neural network is carried out using Adaptive Neuro-fuzzy Inference
Matching, the Adaptive Neuro-fuzzy Inference is a Multi-layered Feedforward Networks comprising:
First layer: for the membership function layer of input variable, it is responsible for the blurring of input signal；
The second layer: for the intensity releasing layer of rule, the node of this layer is responsible for for input signal being multiplied, each node it is defeated
The confidence level of the rule is represented out；
Third layer: for the normalization layer of strictly all rules intensity, i-th of node calculates the unitized confidence level of the i-th rule；
4th layer: calculating the output of fuzzy rule；
Layer 5: for a stationary nodes, total output of all input signals is calculated.
Further, the Adaptive Neuro-fuzzy Inference passes through BP algorithm or BP algorithm and least squares estimate
Hybrid algorithm learnt, adjusting the former piece and consequent parameter of system；In hybrid algorithm, the forward direction stage is calculated to the
Four layers, consequent parameter then is recognized with LSE method；Reversal phase error signal back transfer updates former piece parameter with BP method.
Further, it in forward direction learning process, using the input value of n group training data, acquires consequent parameter and obscures
The output valve of neural inference system, output valve calculate calculated value and training data original expected error value by least square method principle,
And reversely pass this error amount back, premise parameter is corrected by maximum gradient search method, is constantly realized during changing these parameters
Modification to membership function figure, to reach the smallest purpose of output error value in the cyclic process of setting.
A kind of furniture design Service Matching background management system using method described above, including user management subsystem
Subsystem is managed with designer；
The user management subsystem includes:
User log-in block is used for typing user information, subscriber identity information is sent to platform engine and is authenticated,
Certification allows user to log in after passing through；
Design requirement release module, for inquiring, adding design requirement, typing design requirement information；
Design object askes bidding management module, for providing a user design object inquiry, the typing of quotation information and looking into
Ask management；
Order management module, for providing a user furniture design project matched design Shi Guanli；
The designer manages subsystem:
Designer's log-in module is used for typing designer identity information, is sent to platform engine and is authenticated, logical in certification
Allow designer to log in later；
Designer's Capability promulgation module issues personal designed capacity information for designer；
Design Works management module, for managing, inquiring, adding Design Works, typing work title, brief introduction, description letter
Breath；
Matching module is used for matched design teacher and design requirement；
Ordering Module sends inquiry information to designer, forwards to user for receiving the design requirement information
Quotation information.
Further, after designer and user confirm cooperative relationship, the Ordering Module is by order management information
It is sent to designer and user's subsystem, when supply and demand information mismatches, ends processing process.
Beneficial effects of the present invention are as follows:
1, technical solution, furniture enterprise can quickly search out suitable designer, realize demander through the invention
Best match improves the efficiency of design transactional services.
2. designer can carry out remote design service, form setting for cross-region by furniture design service transacting platform
Service mode is counted, the problem of existing design is by limited space is changed.
3. platform carries out intelligent Matching to designer, descending arrangement is carried out according to matching degree, is provided for user more abundant
Designer's resource, enterprise customer can according to recommend designer's resource effectively be managed.
4. the present invention can be applied to the fields such as engineering, science and technology, information technology and economy, design requirement and design are formed
The accurate intelligent Matching in qualified teachers source, according to cases of otherwise standard design demand information, intelligently parsing and matched design teacher, Design Works are provided
Source, the information such as intelligent recommendation designer contact method, main works and historical quotes, so that optimization design transaction flow, is promoted
Design the efficiency and quality of transactional services.
Detailed description of the invention
Fig. 1 is the step flow chart of furniture industry designer's resource automatically retrieval matching process of the invention.
Fig. 2 is the resource matched illustraton of model of furniture industry designer.
Fig. 3 is fuzzy controller schematic diagram.
Fig. 4 is corresponding adaptive neuro-fuzzy inference system structure diagram.
Specific embodiment
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below by specific embodiment and
Attached drawing is described in further details the present invention.
A kind of furniture industry designer resource automatically retrieval matching process is present embodiments provided, as shown in Figure 1, the side
Method includes:
User and designer, design organization issue design requirement information or designed capacity by furniture design service platform
Information；
Furniture design service platform audits information, determines that information format, content meet in plateform system interface and explains
State rule (such as: issue size, the precision of picture, issue text number of words limitation, issue date require etc.), it is ensured that platform
Retrieval matching can be carried out by rule；
Data storage is carried out, design requirement information, designed capacity information are stored in the database of cloud server, deposited
Storage mode, for foundation, creates information form with keyword, classification, attribute etc.；
Beyond the clouds in server, the intelligence based on fuzzy neural network is carried out to design requirement information and designed capacity information
Retrieval matching, and according to matching degree descending assortment from high to low, matching result is fed back to user.
The design requirement information includes: demand coding, demand title, demand classification, issued state, issuing time.Its
In, demand classification information includes use environment, three design field, design style dimensions.In use environment dimension, design requirement
The label of information is covered: bedroom, parlor, dining room, children, study, office, hotel, other furniture.In design field dimension, if
The label of meter demand information includes: that designing and consuftng, intelligent plant planning, soft dress display and design, furniture design, family product are set
Meter, Brand Design.In design style dimension, the label of design requirement information include: Korean style, Southeast Asia, it is modern it is brief, American,
It is Chinese style, European, Japanese.Issued state information cover issued, be pending, not passed through, undercarriage.
Shown designed capacity information includes: designer's essential information and professional technique information.Designer's essential information includes:
Designer's name, head portrait, telephone number, E-mail address.Professional technique information includes: inaugural position, design experiences are good at neck
Domain, design, personal brief introduction, prize-winning situation.Wherein, be good at field label include: designing and consuftng, intelligent plant planning, it is soft
Fill display and design, furniture design, family product design, Brand Design.Design include the design style be good at of designer and
Two dimensions of design environment, design style dimension includes: Korean style, Southeast Asia, modern brief, American, Chinese style, European, Japanese；If
Meter environment dimension includes: bedroom, parlor, dining room, children, study, office, hotel, other furniture.
Furniture design Intelligent Service Matching Platform of the invention also includes furniture design Service Matching background management system,
For the background management system of unitized overall development, (portal entrance, user authentication, platform architecture, information standard, security system, credit are commented
Estimate system), including user management subsystem and designer's management subsystem.
The user management subsystem includes:
User log-in block is used for typing user information (such as enterprise user information), subscriber identity information is sent to flat
Platform engine is authenticated, and allows user to log in after certification passes through.
Design requirement release module, for inquiring, adding design requirement, typing design requirement title, classification, issuing time
Etc. information.By design requirement release management list, list and searching and managing are carried out to designer's demand.
Design object askes bidding management module, for providing a user design object inquiry, the typing of quotation information and looking into
Ask management.
Order management module, for providing a user furniture design project matched design Shi Guanli.
The designer manages subsystem:
Designer's log-in module is used for typing designer identity information, is sent to platform engine and is authenticated, logical in certification
Allow designer to log in later.
Designer's Capability promulgation module issues personal designed capacity information for designer.
Design Works management module, for managing, inquiring, adding Design Works, typing work title, brief introduction, description letter
Breath.
Matching module: matched design teacher and design requirement are used for；
Ordering Module sends inquiry information to designer, forwards to user for receiving the design requirement information
Quotation information.After designer and user confirm cooperative relationship, order management information is sent to designer and user's subsystem,
When supply and demand information mismatches, process is ended processing.
Following Tables 1 and 2 is respectively design requirement list of fields and designed capacity list of fields.It can join when specific implementation
Examine two table typing design requirement information and designed capacity information.
1. design requirement field of table
2. designed capacity field of table
The present invention is based on the accurate intelligent Matchings that fuzzy neural network forms design requirement and designer's resource.Fig. 2 is family
Has industry design qualified teachers source Matching Model figure.The automatically retrieval matching process based on fuzzy neural network is specifically described below.
Fuzzy theory (Fuzzy Theory, be abbreviated as FT): the theory to grow up on the basis of Fuzzy Set Theory, packet
Include five branches such as fuzzy mathematics, fuzzy system, uncertainty and information, fuzzy decision, fuzzy logic and artificial intelligence；It is fuzzy
In set, given range interior element is not necessarily the only two kinds of situations of "Yes" or "No" to its membership, but between 0 He
Real number between 1 indicates subjection degree, and there is also intermediate states.
Artificial neural network (Artificial Neural Networks, be abbreviated as ANNs): referred to as neural network
(NNs) or make link model (Connection Model), it is a kind of imitation animal nerve network behavior feature, is divided
The algorithm mathematics model of cloth parallel information processing；This network relies on the complexity of system, by adjusting internal a large amount of sections
Relationship interconnected between point, to achieve the purpose that handle information.
Fuzzy neural network is the blurring of neural network.I.e. based on fuzzy set, fuzzy logic, in conjunction with NN method, benefit
With the self-organization of NN, achieve the purpose that flexible information processing.Currently, FT is theoretical and NN is combined and is mainly used in business and economy
Estimation, automatic detection and monitoring, robot and automatic control, computer vision, expert system, speech processes, optimization problem, doctor
Application etc. is treated, and extends to the fields such as engineering, science and technology, information technology and economy.
The learning process for realizing T-S fuzzy model, is generally translated into a network, i.e. fuzzy neural inference system,
Fuzzy controller schematic diagram as shown in Figure 3.Fig. 4 is corresponding adaptive neuro-fuzzy inference system structure diagram.The net
Network is a Multi-layered Feedforward Networks, totally five layers (Layer1~Layer5), and square nodes therein need to carry out parameter learning.
First layer: first layer is the membership function layer of input variable, is responsible for the blurring of input signal, and node i has defeated
Function out:
Or
Or
Wherein x, y, z are the inputs of node i, respectively represent design requirement in use environment, design field, design style dimension
The information input of degree, Ai、Bi、CiIt is use environment dimension (comprising 8 characteristic parameters), design field dimension (comprising 6 features
Parameter), the auxiliary variable of design style dimension (include 7 characteristic parameters).It is Ai、Bi、CiMembership function value, indicate x,
Y, z belongs to Ai、Bi、CiDegree.Subordinating degree functionWithShape determined completely by some parameters, these parameters
Referred to as former piece parameter.
The second layer: the second layer is the intensity releasing layer of rule, and the node of this layer is responsible for for input signal being multiplied:
The output of each node represents the confidence level of the rule.
Third layer: third layer is the normalization layer of strictly all rules intensity, and i-th of node calculates the unitized of the i-th rule
Confidence level:
The output of 4th layer: the 4th layer of calculating fuzzy rule, each node i of this layer are adaptive node, output
Are as follows:
HereFor the output of third layer, { pi,qi,ri,siBe the node parameter set, referred to as consequent parameter.
Layer 5: layer 5 is a stationary nodes, calculates total output of all input signals:
After given former piece parameter, the output of fuzzy neural inference system can be expressed as the linear combination of consequent parameter:
Therefore ANFIS (Adaptive Neuro-fuzzy Inference) can pass through BP algorithm (back propagation learning algorithm) or BP
The hybrid algorithm of algorithm and least squares estimate is learnt, adjusting the former piece and consequent parameter of system.Such as following table 3
Shown, in hybrid algorithm, the forward direction stage is calculated to the 4th layer, then recognizes consequent parameter with LSE method (least square method).Instead
To truncation errors signal back transfer, former piece parameter is updated with BP method.
Two stages of the mixing calligraphy learning of table 3.
| The forward direction stage | Reversal phase | |
| Former piece parameter | It is fixed | The adjustment of BP method |
| Consequent parameter | The adjustment of LSE method | It is fixed |
| Signal | Node output | Error signal |
It is optimal with the consequent parameter that LSE method recognizes when former piece parameter is fixed.BP method can be reduced using mixing method
Search space scale, to improve the training speed of ANFIS.
In the forward direction learning process of network, using the input value of n group training data, parameter p is acquiredi,qi,ri,siValue
And output valveNValue calculates calculated value and training data original expected error value by least square method principle, and this is missed
Difference is reversely passed back, corrects former piece parameter by maximum gradient search method, and constantly realization is to being subordinate to letter during changing these parameters
The modification of number figure, to reach the smallest purpose of output error value in the cyclic process of setting.
Key problem in technology point of the invention is:
1, based on neural network algorithm, search for theory generally, using multi-tag data, fuzzy set technology, establish artificial
Network distribution type algorithm model.From multiple relatively dimensions, the matching degree of COMPREHENSIVE CALCULATING designer and project demands.
Specifically, using neural network algorithm, the 4th layer of each neuron of output output as a result, formed three dimensions,
The output neuron of 21 characteristic parametersSome neuron output value in first dimension, eight neurons> is set
Determine standard value, represent the neuronal excitation, system judges that designer's resource matches in terms of this feature.When second dimension six
Some neuron output value in neuron> established standards value, represents the neuronal excitation, and system judges designer's resource
It is matched in terms of this feature.Some neuron output value in seven neurons of third dimension> established standards value, generation
The table neuronal excitation, system judge designer's resource matched in terms of this feature (established standards value according to specific design objective,
It is determined by expert by industry experience).The 4th layer of the neural network judgement generated whether each neuronal excitation, use environment and design
Environments match, the matching of project style and the characteristic style of works, the matching of project fields and designer's fields.In nerve net
Network algorithm layer 5, according to the quantity of the 4th layer of excitor nerve member and the weights of importance of each neuron, calculate generate it is final
Export result.Define three kinds of weight types: use environment (100), design field (100), design style (80).Score 100
For necessary condition, score < 100 are subsidiary conditions, and radix is the sum that can be divided exactly by 100.
2, to the intelligent recommendation of designer's resource.According to the matching degree and designer of design object and designer's resource
Credit, quote situations, intelligent Matching is carried out to designer and according to the sequence of comprehensive score from high to low user is set
Teacher is counted to recommend.
The present invention can also complete Auto-matching using expert algorithm, and rate is faster than fuzzy neural network algorithm, but searches
Hitch fruit is relatively single.
The present invention uses matching unit mode.Further include personal matching unit mode in addition to this mode, is used for user and list
One designer's is resource matched, and group matches mode is used for the matching of user and multiple designers.Personal matching unit can basis
User instruction selects specific single designer such as designer's name.Group matches unit can select more according to user instructions
A designer with instructions match.But both the above method, it all cannot achieve design object and the intelligent Matching of designer.This
Invention is using talent's matching unit mode, it can be achieved that the intelligent Matching of design object and designer, promotes the effective of design service
Property.
The above embodiments are merely illustrative of the technical solutions of the present invention rather than is limited, the ordinary skill of this field
Personnel can be with modification or equivalent replacement of the technical solution of the present invention are made, without departing from the spirit and scope of the present invention, this
The protection scope of invention should be subject to described in claims.
Claims (10)
1. a kind of furniture industry designer resource intelligent search matching method, which comprises the following steps:
User, designer and design organization issue design requirement information or designed capacity information by furniture design service platform；
Furniture design service platform audits information, determine information format, content meet platform rule, with guarantee by
Retrieval matching is carried out according to platform rule；
Design requirement information, designed capacity information are stored in the database of cloud server, storage mode with keyword, point
Class, attribute are foundation；
Beyond the clouds in server, the automatically retrieval based on fuzzy neural network is carried out to design requirement information and designed capacity information
Matching, and according to matching degree descending assortment from high to low, matching result is fed back to user.
2. the method according to claim 1, wherein the design requirement information includes: demand coding, demand name
Title, demand classification, issued state, issuing time；The demand classification includes use environment, design field, design style three
Dimension；The issued state cover issued, be pending, not passed through, undercarriage.
3. according to the method described in claim 2, it is characterized in that, the label of design requirement information is contained in use environment dimension
Lid: bedroom, parlor, dining room, children, study, office, hotel, other furniture；In design field dimension, design requirement information
Label includes: designing and consuftng, intelligent plant planning, the design of soft dress display and design, furniture design, family product, Brand Design；?
Design style dimension, the label of design requirement information includes: Korean style, Southeast Asia, modern brief, American, Chinese style, European, Japanese.
4. the method according to claim 1, wherein shown designed capacity information includes: designer's essential information
With professional technique information；Designer's essential information includes: designer's name, head portrait, telephone number, E-mail address；It is described
Professional technique information includes: inaugural position, design experiences are good at field, design, personal brief introduction, prize-winning situation.
5. according to the method described in claim 4, it is characterized in that, the field of being good at includes: designing and consuftng, intelligent plant rule
It draws, the design of soft dress display and design, furniture design, family product, Brand Design；The design is set comprising what designer was good at
Two dimensions of style and design environment are counted, design style dimension includes: Korean style, Southeast Asia, modern brief, American, Chinese style, Europe
Formula, Japanese, design environment dimension includes: bedroom, parlor, dining room, children, study, office, hotel, other furniture.
6. the method according to claim 1, wherein carrying out the base using Adaptive Neuro-fuzzy Inference
It being matched in the automatically retrieval of fuzzy neural network, the Adaptive Neuro-fuzzy Inference is a Multi-layered Feedforward Networks,
Include:
First layer: for the membership function layer of input variable, it is responsible for the blurring of input signal；
The second layer: for the intensity releasing layer of rule, the node of this layer is responsible for for input signal being multiplied, the output generation of each node
The confidence level of the table rule；
Third layer: for the normalization layer of strictly all rules intensity, i-th of node calculates the unitized confidence level of the i-th rule；
4th layer: calculating the output of fuzzy rule；
Layer 5: for a stationary nodes, total output of all input signals is calculated.
7. according to the method described in claim 6, it is characterized in that, the Adaptive Neuro-fuzzy Inference passes through BP algorithm
Or the hybrid algorithm of BP algorithm and least squares estimate is learnt, to adjust the former piece and consequent parameter of system；Mixed
In hop algorithm, the forward direction stage is calculated to the 4th layer, then recognizes consequent parameter with LSE method；Reversal phase error signal reversely passes
It passs, updates former piece parameter with BP method.
8. the method according to the description of claim 7 is characterized in that in forward direction learning process, using the defeated of n group training data
Enter value, acquire the output valve of consequent parameter and fuzzy neural inference system, output valve calculates calculated value by least square method principle
With training data original expected error value, and this error amount is reversely passed back, correct premise parameter by maximum gradient search method, is changing this
The modification to membership function figure is realized during a little parameters, constantly to reach output error in the cyclic process of setting
It is worth the smallest purpose.
9. a kind of furniture design Service Matching background management system using claim 1 the method, which is characterized in that including
User management subsystem and designer manage subsystem；
The user management subsystem includes:
User log-in block is used for typing user information, subscriber identity information is sent to platform engine and is authenticated, is being authenticated
It is logged in by rear permission user；
Design requirement release module, for inquiring, adding design requirement, typing design requirement information；
Design object askes bidding management module, for providing a user design object inquiry, the typing of quotation information and inquiry pipe
Reason；
Order management module, for providing a user furniture design project matched design Shi Guanli；
The designer manages subsystem:
Designer's log-in module is used for typing designer identity information, is sent to platform engine and is authenticated, after certification passes through
Designer is allowed to log in；
Designer's Capability promulgation module issues personal designed capacity information for designer；
Design Works management module, for managing, inquiring, adding Design Works, typing work title, brief introduction, description information；
Matching module is used for matched design teacher and design requirement；
Ordering Module sends inquiry information to designer, forwards and offer to user for receiving the design requirement information
Information.
10. system according to claim 9, which is characterized in that described to order after designer and user confirm cooperative relationship
Order management information is sent to designer and user's subsystem by single processing module, when supply and demand information mismatches, is ended processing
Process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340173.2A CN109299386A (en) | 2018-11-12 | 2018-11-12 | A kind of furniture industry designer resource intelligent search matching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811340173.2A CN109299386A (en) | 2018-11-12 | 2018-11-12 | A kind of furniture industry designer resource intelligent search matching method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109299386A true CN109299386A (en) | 2019-02-01 |
Family
ID=65146467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811340173.2A Pending CN109299386A (en) | 2018-11-12 | 2018-11-12 | A kind of furniture industry designer resource intelligent search matching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109299386A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872065A (en) * | 2019-02-15 | 2019-06-11 | 深圳易至科技有限公司 | A kind of method of the preferred house ornamentation personnel of intelligence |
| CN111143920A (en) * | 2019-12-06 | 2020-05-12 | 江苏艾佳家居用品有限公司 | Full-space top automatic design method in home decoration design |
| CN112650878A (en) * | 2019-10-11 | 2021-04-13 | 北京声智科技有限公司 | Retrieval method, system, device and medium |
| CN112700213A (en) * | 2020-12-29 | 2021-04-23 | 苏州京航工业设计有限公司 | Networking industrial design platform |
| CN112907333A (en) * | 2021-03-17 | 2021-06-04 | 北京太火红鸟科技有限公司 | Intelligent matching method, device and equipment based on block chain and storage medium |
| CN113379270A (en) * | 2021-06-22 | 2021-09-10 | 特赞（上海）信息科技有限公司 | Label-based customer demand management method and device and storage medium |
| WO2021217340A1 (en) * | 2020-04-27 | 2021-11-04 | Li Jianjun | Ai-based automatic design method and apparatus for universal smart home scheme |
| CN113610587A (en) * | 2020-12-17 | 2021-11-05 | 江苏锁安科技有限公司 | Distribution method and device of intelligent household order service platform |
| TWI787566B (en) * | 2019-12-20 | 2022-12-21 | 遠東科技大學 | Search platform with pastry tips corresponding squeezed flowers |
| CN116089502A (en) * | 2023-04-11 | 2023-05-09 | 北京泽桥医疗科技股份有限公司 | Order retrieval analysis system and method based on self-adaptive model |
| CN117689450A (en) * | 2024-01-29 | 2024-03-12 | 北京一起网科技股份有限公司 | Digital marketing system based on big data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160364651A1 (en) * | 2011-03-29 | 2016-12-15 | Manyworlds, Inc. | Inferential-based Communications Method and System |
| CN106682878A (en) * | 2016-12-29 | 2017-05-17 | 特赞（上海）信息科技有限公司 | Designer matching platform and method |
| US20180268015A1 (en) * | 2015-09-02 | 2018-09-20 | Sasha Sugaberry | Method and apparatus for locating errors in documents via database queries, similarity-based information retrieval and modeling the errors for error resolution |
-
2018
- 2018-11-12 CN CN201811340173.2A patent/CN109299386A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160364651A1 (en) * | 2011-03-29 | 2016-12-15 | Manyworlds, Inc. | Inferential-based Communications Method and System |
| US20180268015A1 (en) * | 2015-09-02 | 2018-09-20 | Sasha Sugaberry | Method and apparatus for locating errors in documents via database queries, similarity-based information retrieval and modeling the errors for error resolution |
| CN106682878A (en) * | 2016-12-29 | 2017-05-17 | 特赞（上海）信息科技有限公司 | Designer matching platform and method |
Non-Patent Citations (1)
| Title |
|---|
| 东苗 等: ""基于模糊神经网络的服装号型推荐专家***"", 《微型电脑应用》, vol. 26, no. 03, pages 317 - 322 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872065A (en) * | 2019-02-15 | 2019-06-11 | 深圳易至科技有限公司 | A kind of method of the preferred house ornamentation personnel of intelligence |
| CN112650878A (en) * | 2019-10-11 | 2021-04-13 | 北京声智科技有限公司 | Retrieval method, system, device and medium |
| CN111143920A (en) * | 2019-12-06 | 2020-05-12 | 江苏艾佳家居用品有限公司 | Full-space top automatic design method in home decoration design |
| CN111143920B (en) * | 2019-12-06 | 2022-07-26 | 江苏艾佳家居用品有限公司 | Full-space top automatic design method in home decoration design |
| TWI787566B (en) * | 2019-12-20 | 2022-12-21 | 遠東科技大學 | Search platform with pastry tips corresponding squeezed flowers |
| WO2021217340A1 (en) * | 2020-04-27 | 2021-11-04 | Li Jianjun | Ai-based automatic design method and apparatus for universal smart home scheme |
| CN113610587A (en) * | 2020-12-17 | 2021-11-05 | 江苏锁安科技有限公司 | Distribution method and device of intelligent household order service platform |
| CN113610587B (en) * | 2020-12-17 | 2024-01-23 | 江苏锁安科技有限公司 | Distribution method of intelligent home order service platform |
| CN112700213A (en) * | 2020-12-29 | 2021-04-23 | 苏州京航工业设计有限公司 | Networking industrial design platform |
| CN112907333B (en) * | 2021-03-17 | 2022-04-22 | 北京太火红鸟科技有限公司 | Intelligent matching method, device and equipment based on block chain and storage medium |
| CN112907333A (en) * | 2021-03-17 | 2021-06-04 | 北京太火红鸟科技有限公司 | Intelligent matching method, device and equipment based on block chain and storage medium |
| CN113379270A (en) * | 2021-06-22 | 2021-09-10 | 特赞（上海）信息科技有限公司 | Label-based customer demand management method and device and storage medium |
| CN116089502A (en) * | 2023-04-11 | 2023-05-09 | 北京泽桥医疗科技股份有限公司 | Order retrieval analysis system and method based on self-adaptive model |
| CN117689450A (en) * | 2024-01-29 | 2024-03-12 | 北京一起网科技股份有限公司 | Digital marketing system based on big data |
| CN117689450B (en) * | 2024-01-29 | 2024-04-19 | 北京一起网科技股份有限公司 | Digital marketing system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109299386A (en) | A kind of furniture industry designer resource intelligent search matching method and system | |
| Wang et al. | A linguistic large group decision making method based on the cloud model | |
| Liang et al. | Consensus reaching with time constraints and minimum adjustments in group with bounded confidence effects | |
| Pan et al. | A dynamic programming algorithm based clustering model and its application to interval type-2 fuzzy large-scale group decision-making problem | |
| Dorfeshan et al. | A group TOPSIS-COPRAS methodology with Pythagorean fuzzy sets considering weights of experts for project critical path problem | |
| Yu et al. | Social optimal mean field control problem for population growth model | |
| WO2022252014A1 (en) | Method for intelligently matching supply and demand in innovation and entrepreneurship services | |
| Zhao et al. | Bounded confidence-based opinion formation for opinion leaders and opinion followers on social networks | |
| AU2021102006A4 (en) | A system and method for identifying online rumors based on propagation influence | |
| CN107705227A (en) | A kind of network system for being used to provide law financial service | |
| Wei et al. | TODIM method for probabilistic linguistic multiple attribute group decision making based on the similarity measures and entropy | |
| Wu et al. | A fuzzy ANP with interval type-2 fuzzy sets approach to evaluate enterprise technological innovation ability | |
| Song et al. | Cloud edge collaborative service composition optimization for intelligent manufacturing | |
| CN113128667A (en) | Cross-domain self-adaptive graph convolution balance migration learning method and system | |
| He et al. | SRSH: a social recommender system based on Hadoop | |
| Liu et al. | A decision-making method based on a two-stage regularized generalized canonical correlation analysis for complex multi-attribute large-group decision making problems | |
| Azadfallah | A New Aggregation Rule for Ranking Suppliers in Group Decision Making under Multiple Criteria. | |
| Silva Filho et al. | Group decision model based on ordered weighted distance to aid decisions on logistics | |
| Yin | Sharing economy and new business model development based on internet of things big data | |
| Sakawa et al. | Interactive fuzzy multiobjective stochastic programming with simple recourse | |
| Lee et al. | Using fuzzy-based association rule mining to improve production systems for chemical product development | |
| Hu et al. | SMS-based mobile recommendation system for campus recruitment in China | |
| JP4224002B2 (en) | Supply and demand mediation system, supply and demand mediation method, and program for supporting supply and demand mediation | |
| Chen et al. | Performance evaluation of online recruitment enterprises based on intuitionistic fuzzy set and TOPSIS | |
| Kopp et al. | Enterprise Architecture Tools Assessment for Smart Cities Governance using Fuzzy Logic Techniques |
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 |