CN110188414A - A kind of personalization capsule wardrobe creation method, device and capsule wardrobe - Google Patents
A kind of personalization capsule wardrobe creation method, device and capsule wardrobe Download PDFInfo
- Publication number
- CN110188414A CN110188414A CN201910394490.0A CN201910394490A CN110188414A CN 110188414 A CN110188414 A CN 110188414A CN 201910394490 A CN201910394490 A CN 201910394490A CN 110188414 A CN110188414 A CN 110188414A
- Authority
- CN
- China
- Prior art keywords
- wardrobe
- clothes
- user
- stature
- capsule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Abstract
The present disclosure discloses a kind of personalized capsule wardrobe creation method, device and capsule wardrobes, receive multi-modal data collection, are pre-processed;By pretreated sample according to the different multipath neural networks by opposite data input pre-training of mode;The characteristic for extracting different modalities respectively according to the neural network of pre-training and multi-layer perception (MLP), the level Hash for obtaining different modalities indicate;The Semantic Similarity between sample is evaluated and tested according to the inner product that every layer of similar matrix intermediate value training Hash indicates according to similar matrix of the sample in different levels after the building pretreatment of level label;Using varigrained level label, and the level of analysis compares neural network performance and influences, and determines best level ratio;It indicates to obtain Hash codes according to every layer of Hash;Training dual path neural network, and optimize training dual path neural network using SCD gradient descent method, the depth cross-module state Hash model based on level label is established, is searched for for cross-module state.
Description
Technical field
The disclosure belongs to the technical field of intelligent wardrobe, is related to a kind of personalized capsule wardrobe creation method, device and glue
Peel cupboard more particularly to a kind of personalized capsule wardrobe creation method, device and capsule wardrobe based on clothes and user model.
Background technique
Only there is provided background technical informations relevant to the disclosure for the statement of this part, it is not necessary to so constitute first skill
Art.
Capsule wardrobe is a kind of wardrobe simplified, it can be arranged in pairs or groups out with less clothes and is more set with.Possess one
Capsule wardrobe can save money of the people on the clothes how thinking wears the time costed and extra purchase redundancy, therefore,
It is played a crucial role in people's daily life.Based on this demand, some fashion experts are shared on network
Their capsule wardrobe is referred to for people;In order to mitigate cost of labor, visual signature and verbal description of the researcher to clothes
Modeling creates capsule wardrobe based on clothes compatibility.However, inventor has found in R&D process, either fashion expert is also
It is that can not all be related to the individual information of people, such as hobby, stature and the consumption of people by the capsule wardrobe of model creation
Habit etc., this not liking there are people or inappropriate clothes in the capsule wardrobe of creation.
Summary of the invention
For the deficiencies in the prior art, one or more other embodiments of the present disclosure provide a kind of personalized capsule
Wardrobe creation method, device and capsule wardrobe, in conjunction with dress form and user model, analyze compatibility between clothes and clothes and
Compatibility between user and clothes;Simultaneously by clothes that delete redundancy in original wardrobe or inappropriate, and add
Suitable clothes create the capsule wardrobe for completely meeting people's individual information, so that inside personalized capsule wardrobe
Clothes as much as possible can be combined into suit that is not only good-looking but also being suitble to this people.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of based on clothes and user model is provided
Property capsule wardrobe creation method.
A kind of personalized capsule wardrobe creation method based on clothes and user model, this method comprises:
Toggery in calling and obtaining user purchaser record, obtains the hobby and stature of user, and foundation likes user with it
With suitable stature toggery apart from small user model;
Using shot and long term memory network, the potential collocation rule of fashion community website collocation suit is excavated, clothes mould is established
Type;
Based on user model and dress form, by realizing that maximizing wardrobe user model and dress form gets optimization just
Beginning wardrobe creates personalized capsule wardrobe.
Further, in the method, the toggery in user's purchaser record includes visual information, text information
And sizing information, the visual information are toggery picture, the text information includes verbal description and type label, described
Visual information and text information indicate that user preferences product features, the sizing information indicate user's stature feature.
Further, in the method, it according to the hobby of user and stature, is constructed using Bayes's personalized ordering algorithm
The loss function of user preferences.
Further, in the method, user is expressed as by identity characteristic vector using stature classifier, according to user's
Hobby and stature establish the prediction stature matching degree of toggery and refer to stature matching degree, by minimizing mean square deviation loss
Function ensures to predict stature matching degree and the consistency with reference to stature matching degree.
Further, in the method, the dress form indicates the t+1 part clothes predicted by preceding t part clothes
With the model of the minimum difference of true t+1 part clothes.
Further, in the method, it is based on user model and dress form, by balance factor to user model and clothes
Scoring model is established in the weighted array of die-filling type, and the user and clothes and clothes and clothes compatibility to wardrobe carry out comprehensive visitor
The evaluation of sight.
Further, in the method, described by realizing that maximizing wardrobe user model and dress form gets optimization
Initially the specific steps of wardrobe include:
Judge whether the clothes number in the original wardrobe of user under each catalogue has reached preset range;
Increasing from candidate clothes in catalogue of the clothes number less than stated range minimum being capable of maximum lift wardrobe score
Clothes;
Least suitable clothes is deleted in catalogue of those clothes numbers more than range maximum value;
In the case that clothes number has reached preset range in wardrobe, judge in wardrobe with the presence or absence of unsuitable clothing
Clothes, and if it exists, then delete that part clothes, otherwise, current wardrobe is optimal, as personalized capsule wardrobe.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes a kind of personalized capsule wardrobe creation method based on clothes and user model.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction;Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed described one kind and is based on for storing a plurality of instruction, described instruction
The personalized capsule wardrobe creation method of clothes and user model.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of based on clothes and user model is provided
Property capsule wardrobe creating device.
A kind of personalized capsule wardrobe creating device based on clothes and user model is based on clothes based on described one kind
With the personalized capsule wardrobe creation method of user model, comprising:
User model establishes module, and the toggery being configured as in calling and obtaining user purchaser record obtains the hobby of user
And stature, foundation like user with it and are suitble to stature toggery apart from small user model;
Dress form establishes module, is configured as excavating fashion community website collocation suit using shot and long term memory network
Potential collocation rule, establishes dress form;
Capsule wardrobe creation module is configured as based on user model and dress form, by realizing that maximizing wardrobe uses
Family model and dress form get the initial wardrobe of optimization, create personalized capsule wardrobe.
According to the one aspect of one or more other embodiments of the present disclosure, a kind of personalized capsule wardrobe is provided.
A kind of personalization capsule wardrobe is created based on the kind based on clothes and the personalized capsule wardrobe of user model
Device.
The disclosure the utility model has the advantages that
A kind of personalized capsule wardrobe creation method, device and the capsule wardrobe that the disclosure provides, by user model and clothes
Die-filling type is integrated to during the creation of capsule wardrobe, proposes the personalized capsule wardrobe creation frame based on Combinatorial Optimization
Frame, the frame is in combination with user and dress form, and in user model, the present disclosure contemplates the hobbies of user and stature two
It is a that particularly important factor is matched for clothes, it is ensured that the clothes in the wardrobe of creation, which meets the hobby of user and highlights, (to be covered
Lid) user's stature advantage (disadvantage).In dress form, the disclosure is by shot and long term memory network, while to the picture of clothes
Feature, character express and catalogue modeling can excavate implicit garment coordination principle in all directions.The disclosure iteratively optimizes original
Beginning wardrobe, each iteration ensures that current wardrobe has higher user and clothes and clothes and clothes compatibility, so that finally
The capsule wardrobe of creation had not only been able to satisfy the customized information of user but also the suit for the more compatibility that can arrange in pairs or groups out.
Detailed description of the invention
The Figure of description for constituting a part of this disclosure is used to provide further understanding of the disclosure, and the disclosure is shown
Meaning property embodiment and its explanation do not constitute the improper restriction to the disclosure for explaining the disclosure.
Fig. 1 is to be created according to a kind of of one or more embodiments based on clothes and the personalized capsule wardrobe of user model
Method flow diagram;
Fig. 2 is to be created according to a kind of of one or more embodiments based on clothes and the personalized capsule wardrobe of user model
Method specific flow chart;
Specific embodiment:
Below in conjunction with the attached drawing in one or more other embodiments of the present disclosure, to one or more other embodiments of the present disclosure
In technical solution be clearly and completely described, it is clear that described embodiment is only disclosure a part of the embodiment,
Instead of all the embodiments.Based on one or more other embodiments of the present disclosure, those of ordinary skill in the art are not being made
Every other embodiment obtained under the premise of creative work belongs to the range of disclosure protection.
It is noted that following detailed description is all illustrative, it is intended to provide further instruction to the disclosure.Unless another
It indicates, all technical and scientific terms that the present embodiment uses have and disclosure person of an ordinary skill in the technical field
Normally understood identical meanings.
It should be noted that term used herein above is merely to describe specific embodiment, and be not intended to restricted root
According to the illustrative embodiments of the disclosure.As used herein, unless the context clearly indicates otherwise, otherwise singular
Also it is intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " packet
Include " when, indicate existing characteristics, step, operation, device, component and/or their combination.
It should be noted that flowcharts and block diagrams in the drawings show according to various embodiments of the present disclosure method and
The architecture, function and operation in the cards of system.It should be noted that each box in flowchart or block diagram can represent
A part of one module, program segment or code, a part of the module, program segment or code may include one or more
A executable instruction for realizing the logic function of defined in each embodiment.It should also be noted that some alternately
Realization in, function marked in the box can also occur according to the sequence that is marked in attached drawing is different from.For example, two connect
The box even indicated can actually be basically executed in parallel or they can also be executed in a reverse order sometimes,
This depends on related function.It should also be noted that each box and flow chart in flowchart and or block diagram
And/or the combination of the box in block diagram, the dedicated hardware based system that functions or operations as defined in executing can be used are come
It realizes, or the combination of specialized hardware and computer instruction can be used to realize.
In the absence of conflict, the feature in the embodiment and embodiment in the disclosure can be combined with each other, and tie below
It closes attached drawing and embodiment is described further the disclosure.
Embodiment one
According to the one aspect of one or more other embodiments of the present disclosure, a kind of based on clothes and user model is provided
Property capsule wardrobe creation method.
The present embodiment is intended to combine dress form and user model, while analyzing the compatibility between clothes and clothes and user
Compatibility between clothes, creation meet the capsule wardrobe of people's individual information.In view of the clothes in the original wardrobe of people, it is
Saving cost, the present embodiment by clothes that delete redundancy in original wardrobe or inappropriate, and add it is some suitable
Clothes create a complete new wardrobe, so that this new wardrobe --- and the clothes inside personalized capsule wardrobe can
It is as much as possible to be combined into suit that is not only good-looking but also being suitble to this people.
As Figure 1-Figure 2, a kind of personalized capsule wardrobe creation method based on clothes and user model, this method packet
It includes:
S1: the toggery in analysis user's purchaser record, including the description of commodity visual signature, text and purchase size,
The hobby of user and stature are modeled respectively, it is intended to find their corresponding potential collocation spaces respectively so that user with
Its sum liked is suitble to the commodity of its stature to have lesser distance, to establish user model U.
S2: utilizing shot and long term memory network, and the suit of analysis fashion community website collocation excavates wherein potential collocation rule
Then, to establish dress form G.
S3: by Combinatorial Optimization theory, being based on user model and dress form, maximizes wardrobe user kimonos by realizing
Model score is filled to optimize initial wardrobe, so that the wardrobe after optimization has both higher user and clothes and clothes and clothes simultaneously
Compatibility is realized and creates personalized capsule wardrobe by the original wardrobe of user.
The process that the step S1 user model is established further include:
S11: character representation.The disclosure obtains the clothes purchaser record of user from Amazon (shopping website), wherein often
Purchaser record includes commodity picture, verbal description, type label and purchase size, and passes through the visual information of clothes (picture)
Product features are indicated with text information (verbal description, type label), meanwhile, the purchase ruler of comprehensive all toggeries of certain user
Code is to indicate user's stature feature.
S12: user preferences.The disclosure analyzes user's by history purchaser record to user and product features modeling
Toggery hobby.Specifically, using fiIndicate that i toggery picture is special by the vision that trained ConvNet is obtained
Levy vector, tiIndicate the bag-of-word Text eigenvector of toggery Textual information, and then the product features of picture can be with
It is expressed as the splicing [f of commodity vision and text featurei,ti];θuIndicate u user for the hobby feature of product features;γuWith
γiRespectively indicate the global characteristics of u user and i toggery.The disclosure is usedTo calculate u user for the fancy grade of i toggery.Secondly, building
TripleIn conjunction with the loss of Bayes's personalized ordering algorithm building user preferences
Function:
S13: stature matching degree.The disclosure will excavate potential clothes by the history purchaser record and product features of user
Dress-stature matches knowledge.Specifically, firstly, being based on a stature classifier, user is expressed as to the stature of an one-hot
Feature vector us;Secondly, being matched respectively by the prediction stature that product features and user's history purchaser record establish toggery
Spend is=σ (Ws[fi,ti]+βs) and with reference to stature matching degreeFinally, the disclosure passes through
Mean square deviation loss function is minimized to ensure to predict and the consistency with reference to stature matching degree, that is,
The detailed process that the step S2 user model is established are as follows:
One is set with the ordered sequence (such as: housing, jacket and lower clothing) for regarding clothes as, every dress is as length
The input at each moment of phase memory network models the potential matching principle in fashion suit by network.Specifically, for
Each suit O={ o1,o2,…,on, dress form be intended to minimize the t+1 part clothes predicted by preceding t part clothes and
The difference of true+1 clothes of kth, therefore, the target equation of dress form is,
The process that the step S3 user model is established further include:
S31: score model.Based on user model and dress form, user model and clothes mould are realized by balance factor
Scoring model S (I is established in the weighted array of type*)=α U (I*)+(1-α)G(I*), to realize scoring model to wardrobe I*Use
The objective evaluation of the synthesis of family and clothes and clothes and clothes compatibility.
S32: personalized capsule wardrobe creation.Personalized capsule wardrobe creation problem is considered as combinatorial optimization and asked by the disclosure
Topic maximizes wardrobe score by optimizing original wardrobe (increase and decrease clothes).Specifically, the original wardrobe I of useruIt is purchased by user
The set for the clothes bought, the disclosure first determine whether IuIn clothes number under each catalogue whether reached preset range
([Nmin,Nmax]), and N is less than in those clothes numbersminCatalogue in from candidate clothes increase can maximum lift wardrobe obtain
The clothes divided is similarly more than N in those clothes numbersmaxCatalogue in delete least suitable clothes (deleting it can be most
It is big to promote wardrobe score).Secondly, the disclosure judges clothing in turn in the case that clothes number has reached preset range in wardrobe
It whether there is unsuitable clothes in cupboard, and if it exists, then delete that part clothes, otherwise, current wardrobe is optimal, as personalization
Capsule wardrobe.
Embodiment two
According to the one aspect of one or more other embodiments of the present disclosure, a kind of computer readable storage medium is provided.
A kind of computer readable storage medium, wherein being stored with a plurality of instruction, described instruction is suitable for by terminal device
Reason device loads and executes a kind of personalized capsule wardrobe creation method based on clothes and user model.
Embodiment three
According to the one aspect of one or more other embodiments of the present disclosure, a kind of terminal device is provided.
A kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction;Meter
Calculation machine readable storage medium storing program for executing is suitable for being loaded by processor and being executed described one kind and is based on for storing a plurality of instruction, described instruction
The personalized capsule wardrobe creation method of clothes and user model.
These computer executable instructions execute the equipment according to each reality in the disclosure
Apply method or process described in example.
In the present embodiment, computer program product may include computer readable storage medium, containing for holding
The computer-readable program instructions of row various aspects of the disclosure.Computer readable storage medium, which can be, can keep and store
By the tangible device for the instruction that instruction execution equipment uses.Computer readable storage medium for example can be-- but it is unlimited
In-- storage device electric, magnetic storage apparatus, light storage device, electric magnetic storage apparatus, semiconductor memory apparatus or above-mentioned
Any appropriate combination.The more specific example (non exhaustive list) of computer readable storage medium includes: portable computing
Machine disk, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read only memory (EPROM or
Flash memory), static random access memory (SRAM), Portable compressed disk read-only memory (CD-ROM), digital versatile disc
(DVD), memory stick, floppy disk, mechanical coding equipment, the punch card for being for example stored thereon with instruction or groove internal projection structure, with
And above-mentioned any appropriate combination.Computer readable storage medium used herein above is not interpreted instantaneous signal itself,
The electromagnetic wave of such as radio wave or other Free propagations, the electromagnetic wave propagated by waveguide or other transmission mediums (for example,
Pass through the light pulse of fiber optic cables) or pass through electric wire transmit electric signal.
Computer-readable program instructions described herein can be downloaded to from computer readable storage medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, local area network, wide area network and/or wireless network
Portion stores equipment.Network may include copper transmission cable, optical fiber transmission, wireless transmission, router, firewall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
Computer program instructions for executing present disclosure operation can be assembly instruction, instruction set architecture (ISA)
Instruction, machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programmings
The source code or object code that any combination of language is write, the programming language include the programming language-of object-oriented such as
C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer-readable program refers to
Order can be executed fully on the user computer, partly be executed on the user computer, as an independent software package
Execute, part on the user computer part on the remote computer execute or completely on a remote computer or server
It executes.In situations involving remote computers, remote computer can include local area network by the network-of any kind
(LAN) or wide area network (WAN)-is connected to subscriber computer, or, it may be connected to outer computer (such as utilize internet
Service provider is connected by internet).In some embodiments, by being believed using the state of computer-readable program instructions
Breath comes personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or programmable logic
Array (PLA), the electronic circuit can execute computer-readable program instructions, to realize the various aspects of present disclosure.
Example IV
According to the one aspect of one or more other embodiments of the present disclosure, a kind of based on clothes and user model is provided
Property capsule wardrobe creating device.
A kind of personalized capsule wardrobe creating device based on clothes and user model is based on clothes based on described one kind
With the personalized capsule wardrobe creation method of user model, comprising:
User model establishes module, and the toggery being configured as in calling and obtaining user purchaser record obtains the hobby of user
And stature, foundation like user with it and are suitble to stature toggery apart from small user model;
Dress form establishes module, is configured as excavating fashion community website collocation suit using shot and long term memory network
Potential collocation rule, establishes dress form;
Capsule wardrobe creation module is configured as based on user model and dress form, by realizing that maximizing wardrobe uses
Family model and dress form get the initial wardrobe of optimization, create personalized capsule wardrobe.
It should be noted that although being referred to several modules or submodule of equipment in the detailed description above, it is this
Division is only exemplary rather than enforceable.In fact, in accordance with an embodiment of the present disclosure, two or more above-described moulds
The feature and function of block can embody in a module.Conversely, the feature and function of an above-described module can be with
Further division is to be embodied by multiple modules.
Embodiment five
According to the one aspect of one or more other embodiments of the present disclosure, a kind of personalized capsule wardrobe is provided.
A kind of personalization capsule wardrobe is created based on the kind based on clothes and the personalized capsule wardrobe of user model
Device.
The disclosure the utility model has the advantages that
(1) a kind of personalized capsule wardrobe creation method, device and capsule wardrobe that the disclosure provides, by user model with
Dress form is integrated to during the creation of capsule wardrobe, proposes the personalized capsule wardrobe creation based on Combinatorial Optimization
Frame, the frame is in combination with user and dress form, and in user model, the present disclosure contemplates the hobby of user and statures
Two match clothes particularly important factor, it is ensured that the clothes in the wardrobe of creation meets the hobby of user and highlights
(cover) user's stature advantage (disadvantage).In dress form, the disclosure is by shot and long term memory network, while to the figure of clothes
Piece feature, character express and catalogue modeling can excavate implicit garment coordination principle in all directions.The disclosure iteratively optimizes
Original wardrobe, each iteration ensures that current wardrobe has higher user and clothes and clothes and clothes compatibility, so that most
The capsule wardrobe created eventually had not only been able to satisfy the customized information of user but also the suit for the more compatibility that can arrange in pairs or groups out.
(2) a kind of personalized capsule wardrobe creation method, device and capsule wardrobe that the disclosure provides, propose based on group
The personalized capsule wardrobe for closing optimization creates frame, in conjunction with user and dress form, so that the personalized capsule wardrobe of creation was both
The customized information for being able to satisfy user can arrange in pairs or groups out the suit of more compatibility again.
(3) a kind of personalized capsule wardrobe creation method, device and capsule wardrobe that the disclosure provides, take full advantage of use
The original wardrobe in family compares and is reconfigured for a capsule wardrobe according to user characteristics, the creation that user can be economic
Property capsule wardrobe.
(4) a kind of personalized capsule wardrobe creation method, device and capsule wardrobe that the disclosure provides, by score model
Realize the combinatorial optimization problem that personalized capsule wardrobe is arrived by original wardrobe, each iteration is all ensured of current optimal, therefore changes
Ensure that final personalized capsule wardrobe is optimal solution after generation.
The foregoing is merely preferred embodiment of the present disclosure, are not limited to the disclosure, for the skill of this field
For art personnel, the disclosure can have various modifications and variations.It is all within the spirit and principle of the disclosure, it is made any to repair
Change, equivalent replacement, improvement etc., should be included within the protection scope of the disclosure.Therefore, the disclosure is not intended to be limited to this
These embodiments shown in text, and it is to fit to the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. a kind of personalized capsule wardrobe creation method based on clothes and user model, which is characterized in that this method comprises:
Toggery in calling and obtaining user purchaser record, obtains the hobby and stature of user, and foundation makes user like and fit with it
Fit material toggery is apart from small user model;
Using shot and long term memory network, the potential collocation rule of fashion community website collocation suit is excavated, dress form is established;
Based on user model and dress form, by realizing that maximizing wardrobe user model and dress form gets the initial clothing of optimization
Cupboard creates personalized capsule wardrobe.
2. a kind of personalized capsule wardrobe creation method based on clothes and user model as described in claim 1, feature
It is, in the method, the toggery in user's purchaser record includes visual information, text information and sizing information,
The visual information is toggery picture, and the text information includes verbal description and type label, the visual information and
Text information indicates that user preferences product features, the sizing information indicate user's stature feature.
3. a kind of personalized capsule wardrobe creation method based on clothes and user model as described in claim 1, feature
It is, in the method, according to the hobby and stature of user, using the damage of Bayes's personalized ordering algorithm building user preferences
Lose function;
User is expressed as by identity characteristic vector using stature classifier, according to the hobby and stature of user, establishes toggery
Prediction stature matching degree and refer to stature matching degree, by minimize mean square deviation loss function ensure predict stature matching degree with
With reference to the consistency of stature matching degree.
4. a kind of personalized capsule wardrobe creation method based on clothes and user model as described in claim 1, feature
It is, in the method, the dress form indicates the t+1 part clothes predicted by preceding t part clothes and true t+1
The model of the minimum difference of part clothes.
5. a kind of personalized capsule wardrobe creation method based on clothes and user model as described in claim 1, feature
It is, in the method, is based on user model and dress form, the weighting by balance factor to user model and dress form
Scoring model is established in combination, and the user and clothes and clothes and clothes compatibility to wardrobe carry out comprehensive objective evaluation.
6. a kind of personalized capsule wardrobe creation method based on clothes and user model as described in claim 1, feature
It is, it is in the method, described that the tool for optimizing initial wardrobe is got by realization maximization wardrobe user model and dress form
Body step includes:
Judge whether the clothes number in the original wardrobe of user under each catalogue has reached preset range;
Increase the clothing for capableing of maximum lift wardrobe score from candidate clothes in catalogue of the clothes number less than stated range minimum
Clothes;
Least suitable clothes is deleted in catalogue of those clothes numbers more than range maximum value;
In the case that clothes number has reached preset range in wardrobe, judge with the presence or absence of unsuitable clothes in wardrobe, if
In the presence of then deleting that part clothes, otherwise, current wardrobe is optimal, as personalized capsule wardrobe.
7. a kind of computer readable storage medium, wherein being stored with a plurality of instruction, which is characterized in that described instruction is suitable for by terminal
The processor of equipment loads and executes a kind of cross-module state searcher based on level label as claimed in any one of claims 1 to 6
Method.
8. a kind of terminal device comprising processor and computer readable storage medium, processor is for realizing each instruction;It calculates
Machine readable storage medium storing program for executing is for storing a plurality of instruction, which is characterized in that described instruction is suitable for being loaded by processor and being executed such as power
Benefit requires a kind of described in any item cross-module state searching methods based on level label of 1-6.
9. a kind of cross-module state searcher based on level label, which is characterized in that based on as described in claim any one of 1-6
A kind of cross-module state searching method based on level label, comprising:
User model establishes module, the toggery being configured as in calling and obtaining user purchaser record, obtains the hobby and body of user
Material, foundation like user with it and are suitble to stature toggery apart from small user model;
Dress form establishes module, is configured as that it is potential to excavate fashion community website collocation suit using shot and long term memory network
Collocation rule, establish dress form;
Capsule wardrobe creation module, is configured as based on user model and dress form, maximizes wardrobe user mould by realizing
Type and dress form get the initial wardrobe of optimization, create personalized capsule wardrobe.
10. a kind of personalization capsule wardrobe, which is characterized in that be based on clothes based on as claimed in any one of claims 1 to 6 kind
With the personalized capsule wardrobe creating device of user model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910394490.0A CN110188414B (en) | 2019-05-13 | 2019-05-13 | Personalized capsule wardrobe creating method and device and capsule wardrobe |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910394490.0A CN110188414B (en) | 2019-05-13 | 2019-05-13 | Personalized capsule wardrobe creating method and device and capsule wardrobe |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110188414A true CN110188414A (en) | 2019-08-30 |
CN110188414B CN110188414B (en) | 2020-12-29 |
Family
ID=67716110
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910394490.0A Active CN110188414B (en) | 2019-05-13 | 2019-05-13 | Personalized capsule wardrobe creating method and device and capsule wardrobe |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110188414B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111930972A (en) * | 2020-08-04 | 2020-11-13 | 山东大学 | Cross-modal retrieval method and system for multimedia data by using label level information |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120133048A (en) * | 2011-05-30 | 2012-12-10 | 주식회사 샤트렌 | Funcktional clothes with anti-cellulite capsule |
CN107807535A (en) * | 2017-10-20 | 2018-03-16 | 王媛玥 | Clothing dresses intelligent collocation commending system |
CN107993131A (en) * | 2017-12-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Wear to take and recommend method, apparatus, server and storage medium |
CN108009268A (en) * | 2017-12-15 | 2018-05-08 | 惠州市敦雅科技有限公司 | A kind of individual, which wears, takes intelligent recommendation method |
CN109043861A (en) * | 2018-07-13 | 2018-12-21 | 湖南工程学院 | Clothes recommender system and recommended method based on Image Acquisition |
CN208297951U (en) * | 2018-05-08 | 2018-12-28 | 东莞市逸鹏智能科技有限公司 | A kind of Intelligent clothes cabinet system |
CN109619841A (en) * | 2018-10-30 | 2019-04-16 | 深圳市赛亿科技开发有限公司 | A kind of Intelligent clothes cabinet control method and system |
-
2019
- 2019-05-13 CN CN201910394490.0A patent/CN110188414B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20120133048A (en) * | 2011-05-30 | 2012-12-10 | 주식회사 샤트렌 | Funcktional clothes with anti-cellulite capsule |
CN107807535A (en) * | 2017-10-20 | 2018-03-16 | 王媛玥 | Clothing dresses intelligent collocation commending system |
CN108009268A (en) * | 2017-12-15 | 2018-05-08 | 惠州市敦雅科技有限公司 | A kind of individual, which wears, takes intelligent recommendation method |
CN107993131A (en) * | 2017-12-27 | 2018-05-04 | 广东欧珀移动通信有限公司 | Wear to take and recommend method, apparatus, server and storage medium |
CN208297951U (en) * | 2018-05-08 | 2018-12-28 | 东莞市逸鹏智能科技有限公司 | A kind of Intelligent clothes cabinet system |
CN109043861A (en) * | 2018-07-13 | 2018-12-21 | 湖南工程学院 | Clothes recommender system and recommended method based on Image Acquisition |
CN109619841A (en) * | 2018-10-30 | 2019-04-16 | 深圳市赛亿科技开发有限公司 | A kind of Intelligent clothes cabinet control method and system |
Non-Patent Citations (1)
Title |
---|
WEI-LIN HSIAO 等: "Creating Capsule Wardrobes from Fashion Images", 《IN PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111930972A (en) * | 2020-08-04 | 2020-11-13 | 山东大学 | Cross-modal retrieval method and system for multimedia data by using label level information |
Also Published As
Publication number | Publication date |
---|---|
CN110188414B (en) | 2020-12-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20230162071A1 (en) | Autonomous learning platform for novel feature discovery | |
CN111611472B (en) | Binding recommendation method and system based on graph convolution neural network | |
CN107832468B (en) | Demand recognition methods and device | |
CN108153901A (en) | The information-pushing method and device of knowledge based collection of illustrative plates | |
CN108141645A (en) | Video emphasis detection with pairs of depth ordering | |
CN107436875A (en) | File classification method and device | |
CN109992650A (en) | For providing the personalized cognition session proxy seen clearly in operation | |
CN110188209A (en) | Cross-module state Hash model building method, searching method and device based on level label | |
CN108171276A (en) | For generating the method and apparatus of information | |
CN108563767A (en) | Image search method and device | |
CN108920467A (en) | Polysemant lexical study method and device, search result display methods | |
CN106991576A (en) | A kind of heating power of geographic area shows method and apparatus | |
CN110955831B (en) | Article recommendation method and device, computer equipment and storage medium | |
US10909606B2 (en) | Real-time in-venue cognitive recommendations to user based on user behavior | |
CN110019732A (en) | A kind of intelligent answer method and relevant apparatus | |
CN109697641A (en) | The method and apparatus for calculating commodity similarity | |
CN108984658A (en) | A kind of intelligent answer data processing method and device | |
CN107291337A (en) | A kind of method and device that Operational Visit is provided | |
CN109189937A (en) | A kind of characteristic relation recommended method and device, a kind of calculating equipment and storage medium | |
CN110188210A (en) | One kind is based on figure regularization and the independent cross-module state data retrieval method of mode and system | |
CN108960912A (en) | Method and apparatus for determining target position | |
CN110019650A (en) | Method, apparatus, storage medium and the electronic equipment of search associational word are provided | |
KR20200141373A (en) | System, method and program of constructing dataset for training appearance recognition model | |
CN110019849A (en) | A kind of video concern moment search method and device based on attention mechanism | |
CN110119445A (en) | The method and apparatus for generating feature vector and text classification being carried out based on feature vector |
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 |