CN109949116A - Clothing matching recommended method, device, storage medium and mobile terminal - Google Patents
Clothing matching recommended method, device, storage medium and mobile terminal Download PDFInfo
- Publication number
- CN109949116A CN109949116A CN201711382746.3A CN201711382746A CN109949116A CN 109949116 A CN109949116 A CN 109949116A CN 201711382746 A CN201711382746 A CN 201711382746A CN 109949116 A CN109949116 A CN 109949116A
- Authority
- CN
- China
- Prior art keywords
- collocation
- clothing matching
- picture
- dress ornament
- suggestion
- 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
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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the present application discloses a kind of clothing matching recommended method, device, storage medium and mobile terminal.This method comprises: obtaining using dress ornament single-item as the shooting picture of object;The shooting picture is inputted into preconfigured disaggregated model, to identify the classification information of dress ornament single-item described in the shooting picture, wherein the disaggregated model is the deep learning model according to different classes of dress ornament picture sample training;Clothing matching suggestion is generated according to the classification information, shows the clothing matching suggestion, realizes the dress ornament single-item inputted based on user, the collocation suggestion of profession is provided in time, shortens the time that user spends in shopping collocation.
Description
Technical field
The invention relates to mobile terminal technology more particularly to a kind of clothing matching recommended method, device, storage Jie
Matter and mobile terminal.
Background technique
With economic rapid development, the kind of clothing products, pattern become extremely to enrich and complicated, meanwhile, people couple
The requirement of clothes and accessories also increasingly improves.The dress ornament many and diverse in face of kind, pattern, it is often desirable to obtain professional and scientific
Collocation suggestion.
But user is difficult timely to obtain expert when going window-shopping targetedly to help.In the related technology, user wears
Clothing collocation knowledge, which generally passes through, reads Fashion Magazines acquisition;There are also dress ornament providers to attempt by being set to showing in market
Display screen shows the arranging scheme of wearing the clothes that the designer of the garment beauty provides, thus, taking for the dress ornament of the brand is provided for user
With suggestion, but this collocation suggests that there are limitations, and real-time is bad.
Summary of the invention
The embodiment of the present application provides a kind of clothing matching recommended method, device, storage medium and mobile terminal, can be effective
Ground optimizes clothing matching suggested design.
In a first aspect, the embodiment of the present application provides a kind of clothing matching recommended method, comprising:
It obtains using dress ornament single-item as the shooting picture of object;
The shooting picture is inputted into preconfigured disaggregated model, to identify dress ornament single-item described in the shooting picture
Classification information, wherein the disaggregated model is the deep learning model according to different classes of dress ornament picture sample training;
Clothing matching suggestion is generated according to the classification information, shows the clothing matching suggestion.
Second aspect, the embodiment of the present application also provides a kind of clothing matching recommendation apparatus, which includes:
Picture shooting module, for obtaining the shooting picture using dress ornament single-item as object;
Dress ornament identification module, for the shooting picture to be inputted preconfigured disaggregated model, to identify the shooting
The classification information of dress ornament single-item described in picture, wherein the disaggregated model is to be instructed according to different classes of dress ornament picture sample
Experienced deep learning model;
It is recommended that generation module shows that the clothing matching is built for generating clothing matching suggestion according to the classification information
View.
The third aspect, the embodiment of the present application also provides a kind of computer readable storage mediums, are stored thereon with computer
Program realizes the clothing matching recommended method as described in above-mentioned first aspect when the program is executed by processor.
Fourth aspect processor and is stored in the embodiment of the present application also provides a kind of mobile terminal, including memory
On reservoir and the computer program that can run in processor, the processor realizes such as above-mentioned the when executing the computer program
Clothing matching recommended method described in one side.
The embodiment of the present application provides a kind of clothing matching suggested design, by obtaining using dress ornament single-item as the shooting figure of object
Piece;The shooting picture is inputted into preconfigured disaggregated model, to identify the classification information of the dress ornament single-item in the shooting picture;
Clothing matching suggestion is generated according to category information, shows the clothing matching suggestion.By adopting the above technical scheme, according to classification mould
Type identifies shooting picture, determines the classification of dress ornament single-item in shooting picture, determines further according to the category matching
Collocation is suggested, realizes the dress ornament single-item inputted based on user, provides the collocation suggestion of profession in time, without limiting locating for user
Scene, shorten user's time for spending in shopping collocation.
Detailed description of the invention
Fig. 1 is a kind of flow chart of clothing matching recommended method provided by the embodiments of the present application;
Fig. 2 is that a kind of clothing matching provided by the embodiments of the present application recommends interface schematic diagram;
Fig. 3 is the flow chart of another clothing matching recommended method provided by the embodiments of the present application;
Fig. 4 is the flow chart of another clothing matching recommended method provided by the embodiments of the present application;
Fig. 5 is a kind of clothing matching recommendation apparatus provided by the embodiments of the present application;
Fig. 6 is a kind of structural block diagram of mobile terminal provided by the embodiments of the present application;
Fig. 7 is a kind of structural block diagram of smart phone provided by the embodiments of the present application.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the application, rather than the restriction to the application.It also should be noted that in order to just
Part relevant to the application is illustrated only in description, attached drawing rather than entire infrastructure.
It should be mentioned that some exemplary embodiments are described as before exemplary embodiment is discussed in greater detail
The processing or method described as flow chart.Although each step is described as the processing of sequence by flow chart, many of these
Step can be implemented concurrently, concomitantly or simultaneously.In addition, the sequence of each step can be rearranged.When its operation
The processing can be terminated when completion, it is also possible to have the additional step being not included in attached drawing.The processing can be with
Corresponding to method, function, regulation, subroutine, subprogram etc..
In the related technology, the algorithm that many realization clothes are classified automatically has been proposed in researchers.Traditional classification
Algorithm generally uses two-stage process, and the first step calculates the feature being artificially arranged from input picture, and second step is according to calculating
Feature goes one classifier of training, the classification for test data.Due to the limitation of the feature of engineer, conventional method effect
The quality of fruit is heavily dependent on whether the feature artificially selected is reasonable, and tool bears the character of much blindness, generally existing classification
The low problem of accuracy rate.In order to solve the above technical problems, the application proposes a kind of clothing matching suggested design, it can be quickly and quasi-
True identification clothing type, and clothing matching suggestion is provided in real time.
Fig. 1 is a kind of flow chart of clothing matching recommended method provided by the embodiments of the present application, and this method can be by dress ornament
Recommendation apparatus arrange in pairs or groups to execute, wherein the device can be implemented by software and/or hardware, and can generally integrate in the terminal, such as
Mobile terminal with camera.As shown in Figure 1, this method comprises:
Step 110 is obtained using dress ornament single-item as the shooting picture of object.
Wherein, dress ornament single-item can be the general name of the article of decoration human body, including but not limited to jacket, trousers, skirt, shoes
Son, cap, scarf, necktie, bag, belt, jewellery etc..
Shooting picture may include user using selected dress ornament single-item as reference object, presses button of taking pictures, passes through camera shooting
The picture of head capture.Wherein, shooting picture can be the picture taken pictures to the existing dress ornament single-item of user, can be with
It is the picture that the dress ornament single-item tried on to user is taken pictures, or to the dress ornament list for hanging or tiling in brand shop
The picture etc. that the dress ornament single-item of picture or pedestrian's dress that product are taken pictures is taken pictures.For example, user is strolling
A jacket is had purchased when street, in order to learn the dress ornament arranged in pairs or groups with it, can be taken pictures to the jacket, be obtained the bat of the jacket
Take the photograph picture.
Optionally, shooting picture can also be user in the case where shooting interface, click the history that picture library (or photograph album) obtains
Shoot picture.For example, user is in the case where shooting interface, the picture being located near button of taking pictures is clicked, into picture library or photograph album, into
And the history comprising dress ornament single-item is selected to shoot picture.
The shooting picture is inputted preconfigured disaggregated model by step 120, to identify described in the shooting picture
The classification information of dress ornament single-item.
Wherein, which is the deep learning model according to different classes of dress ornament picture sample training.Optionally,
Deep learning model can choose convolutional neural networks model.It constructs in the server, train and optimize above-mentioned disaggregated model.This
Apply in embodiment to network parameters such as the number of plies of the convolutional neural networks model, the quantity of neuron, convolution kernel and/or weights
It is not construed as limiting.
The convolutional neural networks model is trained by using different classes of dress ornament picture sample, obtains classification mould
Type.Wherein, the dress ornament picture sample for training the convolutional neural networks model includes clothes single-item and ornaments single-item picture, packet
Include but be not limited to jacket picture, trousers picture, skirt picture, shoes picture, cap picture, scarf picture, necktie picture, bag
Picture, belt picture, jewellery picture.
Illustratively, it can be and dress ornament single-item picture downloaded from the network platform by web crawlers, wherein in the network platform
Dress ornament single-item picture source can be shopping website, the dress ornament single-item picture that the Fashion Magazines of electronic edition or user upload
Deng, and the dress ornament single-item picture downloaded is classified.Classification foundation can be based on dress ornament gender (i.e. audient for man also
Ms), dress ornament style (as campus, pseudo-classic, office or lie fallow etc.), dress ornament style it is (including long sleeves, cotta, trousers, short
The structures such as trousers, fashion elements and quality etc.) and functional information (including conventional dress ornament or functional dress ornament).For example, by jacket
Picture according to women T-shirt, man's T-shirt, Ms's shirt, man's shirt, lady business suit jacket, Men's Suits jacket, dust coat for women,
Man's wind coat, Ms's overcoat, man's overcoat, leopard line, design of scattered small flowers and plants, campus and office etc. are classified.By trousers picture according to Ms
Trousers, man's trousers, woman pants, man pants, campus, pseudo-classic and quality etc. are classified.It can be right according to actual needs
The dress ornaments pictures such as skirt picture, shoes picture, jewellery picture are classified, mode classification and above-mentioned jacket picture and trousers picture
Mode classification it is similar, will not enumerate herein.Then, classification is good that dress ornament picture is with its classification information associated storage
Dress ornament picture sample.
In order to make it easy to understand, being said below to the process based on dress ornament picture sample training convolutional neural networks model
It is bright.
Firstly, carrying out model construction, that is, preset the number and input layer of hidden layer, each layer of hidden layer and output layer
Number of nodes, and initialization convolutional neural networks the first parameter, wherein the first parameter include each layer bias and each side
Weight, tentatively obtain the frame of convolutional neural networks model.
Then, propagated forward and backward is carried out to the pre-set convolutional neural networks model using dress ornament picture sample
Propagate the training in two stages.When the error that back-propagating training is calculated reaches expected error value, training terminates, and
To disaggregated model.It specifically can be according to dress ornament picture sample, which trained using propagated forward algorithm and Back Propagation Algorithm
Product neural network model, learns the second parameter of neural network model out, wherein the second parameter is to calculate dress ornament picture sample
The deviation of reality output and desired output is used to adjust the first parameter according to the deviation using what Back Propagation Algorithm was calculated
Correction value.First parameter is updated using the second parameter, continues to execute above-mentioned training process.Then, computation model error,
In, model error can be determined according to the reality output of dress ornament picture sample and the deviation of desired output, in the model error
When reaching expected error value, training terminates, and obtains disaggregated model.
After the completion of disaggregated model training, the downloading request of mobile terminal is responded, which is transplanted to mobile whole
In end.It should be noted that being transplanted since there are larger differences for the operational capability of server and mobile terminal by disaggregated model
To before mobile terminal, it is also necessary to be optimized to disaggregated model.Illustratively, using preset optimisation strategy to the convolution
Neural network model optimizes, wherein the optimization to the convolutional neural networks model includes internal networking structure optimization, volume
At least one of in the implementation optimization of lamination, the implementation optimization of pond layer.For example, increasing residual block building residual error mind
Through network model, or the structure of adjustment residual block.For another example, reduction output can be for the optimization of the implementation of convolutional layer
The connection quantity in channel and input channel, i.e. output channel are no longer related with all input channels, only and adjacent input channel
It is related.For another example, increase base in the realization of convolutional layer, convolution is divided into two steps: firstly, each channel of input is independent
Operation, under the action of same size convolution kernel, each channel obtains results of intermediate calculations, by each of results of intermediate calculations
Channel is known as a base;Then, each channel is merged, obtains the output result of convolutional layer.For another example, pass through needs
The matrix of compression of images is used in the layer of compression of images factor design pond.
If mobile terminal gets the start-up operation for the clothing matching function that user inputs in the case where shooting interface, dress ornament is enabled
Matching function provides the collocation suggestion with the dress ornament single-item in the shooting picture in order to the shooting picture specified according to user.
After clothing matching function enabling, the shooting picture obtained is inputted into disaggregated model, can quickly and accurately identify the bat
The classification for taking the photograph dress ornament single-item in picture obtains its classification information.Wherein, classification information includes the corresponding gender of dress ornament single-item, wind
Lattice, style and functional information etc..Due to implicitly being extracted to the feature of image by disaggregated model, compared to the relevant technologies
The feature extraction of middle engineer is more quickly and accurate.
Step 130 generates clothing matching suggestion according to the classification information, shows the clothing matching suggestion.
Wherein, clothing matching suggestion includes building for offer and the matched suit of dress ornament single-item shot in photo or ornaments etc.
Discuss information, the including but not limited to verbal description and shooting picture with the matched collocation dress ornament of dress ornament single-item in shooting picture
In the matched collocation dress ornament picture of dress ornament single-item.
Illustratively, taking in mobile terminal is pre-configured according to the classification information inquiry of dress ornament single-item in shooting picture
With database, the collocation suggestion being consistent with category information is determined.Wherein, collocation suggests that the collocation including a rule records.Example
It such as, include the movement half body skirt of one cotton of collocation for the collocation record of sports type women's shirt;And for sports type female
The collocation record of scholar's jacket can also be that one cotton of collocation breathes out human relations trousers;Alternatively, for sports type women's shirt one function of collocation
Energy type rapid-curing cutback trousers etc..Collocation record for lady business suit includes one pair of tooling Western-style trousers of collocation;And taking for lady business suit
It can also include the skirt of one suit facing material of collocation with record;Or it can also be including taking for the collocation record of lady business suit
With shorts etc..It should be noted that above-mentioned collocation record be by the clothing matching picture in the network platform into
Row statistics, analysis processing, the clothing matching strategy taken out.It specifically can be, construct collocation database in advance by server,
And the collocation database built is handed down to mobile terminal.For example, server is miscellaneous from shopping website, fashion by web crawlers
The network platforms such as will or clothes news conference download clothing matching picture.The dress ornament downloaded using the means analysis of big data analysis
Collocation picture, takes out the collocation strategy of clothes and ornaments, with the classification letter of the form associated storage dress ornament single-item for record of arranging in pairs or groups
The characteristic information of breath and collocation dress ornament, and record storage will be arranged in pairs or groups in collocation database.
After generating clothing matching and suggesting, user and the dress ornament single-item can be prompted to arrange in pairs or groups by way of popping up dialog box
Clothes or ornaments characteristic information, in order to which user looks for matching commodity according to this feature information.Fig. 2 is the application
A kind of clothing matching provided recommends interface schematic diagram.As shown in Fig. 2, pressing bat after user enables clothing matching function
The Ms's crew neck long sleeves pure color cotton underwear hung according to 220 Duis of button is taken pictures, and a shooting picture 210 is obtained.Mobile terminal
It after getting the shooting picture 210, is inputted in preset disaggregated model automatically, which is identified by disaggregated model
Classification information include: Ms, crew neck, long-sleeved shirt, cotton and pure color.After the classification information for obtaining the jacket, call pre-
If collocation database, corresponding collocation is inquired according to category information and suggests including but is not limited to one a, collocation pure color V
Lead sweater;B, arrange in pairs or groups a pair of trousers A;C, arrange in pairs or groups a skirt B;D, arrange in pairs or groups a cap C;E, arrange in pairs or groups a single shoulder satchel D;f,
Arrange in pairs or groups a wrist-watch E.Above-mentioned collocation suggestion is shown to pop up the form of dialog box 230.
Optionally, collocation suggestion is sent to cloud server by mobile terminal, and the collocation is proposed to be used in instruction institute
State the location information that matched commodity are suggested in cloud server inquiry with the collocation;Obtain that the cloud server returns with
The location information of matched commodity is suggested in the collocation, and shows the location information on the electronic map.Specifically, if user
It is currently located in market, cloud server (such as shopping mall server or third-party server) can be connected by mobile terminal.
The characteristic information of collocation dress ornament in the pop-up dialog box is sent to cloud server by mobile terminal, to pass through cloud server
Inquire in this market or other markets for closing in whether merchandise news with this feature information matches is provided.It is attached inquiring
When the nearly merchandise news existed with this feature information matches, merchant location and shop title are pushed into mobile terminal.It is exemplary
, mobile terminal is in the matched quotient of characteristic information with the collocation dress ornament in pop-up dialog box for getting cloud server transmission
When the location information of product, invocation map application program marks the location information and shop title of the commodity in map.
The technical solution of the present embodiment, by shooting interface in enable clothing matching function, will acquire with dress ornament
Single-item is that the shooting picture of object inputs preconfigured disaggregated model, to identify the classification of the dress ornament single-item in the shooting picture
Information;Preset collocation database is called according to category information, generates clothing matching suggestion, and show that the clothing matching is built
View.By adopting the above technical scheme, shooting picture is fast and accurately identified according to disaggregated model, is determined in shooting picture
The classification of dress ornament single-item determines matching collocation suggestion further according to the category, realizes the dress ornament single-item inputted based on user,
The collocation suggestion of profession is provided in time, shortens the time that user spends in shopping collocation.
Fig. 3 is the flow chart of another clothing matching recommended method provided by the embodiments of the present application.As shown in figure 3, the party
Method includes:
Step 301 is obtained using dress ornament single-item as the shooting picture of object.
Step 302, the status information for obtaining clothing matching function.
Wherein, for providing clothing matching suggestion, which can be preconfigured in mobile terminal clothing matching function
It is interior, and enabled or disabled according to the operation instruction that user inputs.It is taken for example, integrating the dress ornament in the camera applications of mobile terminal
With function, if user opens camera applications, the clothing matching function can be enabled or disabled by clicking setting interface switch.
Wherein, status information includes initiate mode and disabled status, and is setting interface switch in the open state,
The status information for determining the clothing matching function is that initiate mode determines the dress ornament when setting closed state at interface switch
The status information of matching function is disabled status.
Step 303 judges whether the clothing matching function is activated according to the state information, if it is not, then executing step
Rapid 304, it is no to then follow the steps 305.
Judge whether clothing matching function is activated according to the state of setting interface switch.Detecting that user opens this and set
It when determining interface switch, determines that clothing matching function is activated, executes step 305.Detecting that user closes the setting interface and open
Guan Shi determines that clothing matching function is disabled, executes step 304.
Shooting picture is stored in picture library by step 304.
The shooting picture is inputted preconfigured disaggregated model by step 305, to identify described in the shooting picture
The classification information of dress ornament single-item.
Step 306 inquires preset collocation database according to the classification information, and determination is matched with the classification information
Collocation is suggested.
Wherein, classification information includes gender, style, style and functional information etc..Illustratively, according to the dress ornament single-item
Gender, style, style and functional information inquire preset collocation database, determine that collocation corresponding with the dress ornament single-item is built
View.Since associated storage has collocation corresponding with classification information to record in preset collocation database, according to shooting picture
It is available with the matched collocation dress ornament of the dress ornament single-item that the classification information of middle dress ornament single-item inquires the preset collocation database
Characteristic information, this feature information constitute collocation suggest.For example, determining dress ornament single-item in shooting picture by disaggregated model
Classification information includes Ms, chiffon one-piece dress, crew neck, design of scattered small flowers and plants etc..It is true that preset collocation database is inquired based on category information
Fixed matching collocation suggestion includes but is not limited to: one a, collocation pure color surplus sweater S;B, one black fur clothing of collocation;
C, one black boots of collocation;D, arrange in pairs or groups a pure color housing R;E, one grid scarf of collocation;F, a red of arranging in pairs or groups is portable
Packet.Above-mentioned collocation suggestion can be reduced preset in such a way that text mode is stored in default collocation database using writing record
The data volume of collocation database avoids the memory space for excessively occupying mobile terminal.
Optionally, when mobile terminal inquires preset collocation database according to classification information, preset collocation number is called
According to library, the determining collocation suggestion with category information matches uses the sequence of default to show the collocation suggestion in the form of text
Show in impression window.
It optionally, can also be in the determining collocation with category information matches in order to more intuitively show the collocation suggestion
After it is recommended that, the commodity picture for meeting the collocation suggestion in the network platform is obtained, and shows the quotient in the form of impression window
Product picture.For example, by taking the classification information for shooting dress ornament single-item in picture includes Ms, chiffon one-piece dress, crew neck, design of scattered small flowers and plants as an example,
The network platform can be inquired based on above-mentioned collocation suggestion, be determined for compliance with the commodity picture of the collocation dress ornament of above-mentioned collocation suggestion, adopt
The commodity picture is scrolled with the form of impression window.Optionally, the clicking operation that can also detect user responds the click
Operation provides the details of selected commodity picture.
Collocation suggestion is sent to cloud server by step 307.
Mobile terminal and cloud server, which are established, to be communicated to connect, and collocation is suggested to be sent to cloud server.The cloud
Server is used to suggest the location information of matched commodity with the collocation according to the collocation suggestion is determining, and marks on the electronic map
The location information is infused, and designs the thumbnail for showing the commodity in each product locations.
Step 308 obtains the location information for suggesting matched commodity with the collocation that the cloud server returns.
Location information with the matched commodity of suggestion of arranging in pairs or groups is obtained by cloud server, and calls electronic map application program
Show the location information, and the corresponding position of information shows the thumbnail of the commodity in the position.
Step 309 obtains the feedback information that user suggests for the collocation.
Wherein, feedback information includes adopt situation of the user for collocation suggestion, and including but not limited to user's input is
It is no to adopt collocation suggestion and adopt information, for example, if user chooses a certain commodity picture, to further display the commodity picture
Details, then it is assumed that user, which adopts this and arranges in pairs or groups, to suggest.For another example, matched quotient is suggested in display and collocation on the electronic map
When the location information of product, if detecting, user inputs path planning instruction, and the destination of path planning instruction is the commodity pair
The position answered, then it is assumed that user, which adopts this and arranges in pairs or groups, to suggest.
Obtain user's input adopts information for collocation suggestion, as feedback information.
Step 310, the collocation hobby that user is determined according to the feedback information, and according to collocation hobby update
The recommended priority of clothing matching suggestion in collocation database.
Mobile terminal analyzes the feedback information of the user in certain period of time, and conclusion processing determines taking for user
With hobby, liked arranging in pairs or groups in adjustment collocation database the recommended priority of suggestion according to the collocation.For example, based on in one month
Field feedback analysis, conclude, determine user preferences leisure dress ornament, then according to the hobby be collocation database in phase
Matched collocation suggests that higher recommended priority is arranged.It is also possible that based on point to the field feedback in one month
Analysis is concluded, and determines that user likes jacket collocation half body skirt, then can configure higher recommendation for the half body skirt in collocation database
Priority.Optionally, record can also be adopted according to the history of collocation suggestion, user preferences are determined, according to user preferences into one
Step suggests sequence for collocation, thus, it is that distribution different priorities are suggested in collocation according to ranking results.
The technical solution of the present embodiment, by obtaining the shooting picture using dress ornament single-item as object;And by the shooting figure
Piece inputs preconfigured disaggregated model, to identify the classification information of dress ornament single-item described in the shooting picture;According to described
Classification information inquires preset collocation database, determining to suggest with the matched collocation of the classification information;It obtains in the network platform
Meet the commodity picture that the collocation is suggested, and shows the commodity figure according to the collocation hobby of user in the form of impression window
Piece arranges in pairs or groups with user and likes closer commodity, sort more forward, realizes that intuitive, image displaying is arranged in pairs or groups and suggests, convenient for using
Family is based on the collocation suggestion and does shopping, and saves the time of user's collocation dress ornament.In addition, collocation suggestion is sent to cloud
Server is held, so as to plan the guidance path for going to the position of the commodity by electronic map, to save user's
Shopping-time.
Fig. 4 is the flow chart of another clothing matching recommended method provided by the embodiments of the present application, this method comprises:
Step 410 is obtained using dress ornament single-item as the shooting picture of object.
Step 420, the status information for obtaining clothing matching function.
Step 430 judges whether the clothing matching function is activated according to the state information, if it is not, then executing step
Rapid 440, it is no to then follow the steps 450.
Shooting picture is stored in picture library by step 440.
The shooting picture is inputted preconfigured disaggregated model by step 450, to identify described in the shooting picture
The classification information of dress ornament single-item.
Step 460 inquires preset collocation database according to the classification information, and determination is matched with the classification information
Clothing matching picture.
Wherein, clothing matching picture is stored in preset collocation database.
It constructs collocation database in advance by server, and the collocation database built is handed down to mobile terminal.Example
Such as, server downloads clothing matching figure from network platforms such as shopping website, Fashion Magazines or clothes news conferences by web crawlers
Piece.It is stored in preset collocation database after carrying out a series of images processing to clothing matching picture, and corresponding mark is each
The classification information for the dress ornament single-item that clothing matching picture includes.Wherein, image procossing includes but is not limited to for only color difference
Clothing matching picture carry out duplicate removal processing, for the not high picture of discrimination, carry out retaining the higher clothing matching of clarity
The processing etc. of picture.
Since classification information and clothing matching picture are associated storages in collocation database, in identifying shooting picture
After the classification information of dress ornament single-item, collocation database, the determining clothes with category information matches can be inquired according to classification information
Decorations collocation picture.
Step 470 generates clothes with the clothes of dress ornament single-item collocation and/or ornaments according in the clothing matching picture
Decorations collocation is suggested, and the clothing matching suggestion is shown in the form of impression window.
Illustratively, it if the dress ornament single-item in shooting picture is Ms's chiffon design of scattered small flowers and plants one-piece dress, is taken according to the dress ornament
With in picture in addition to Ms's chiffon design of scattered small flowers and plants one-piece dress clothes and ornaments generate clothing matching suggestion, and with impression window
Form shows the clothing matching suggestion.Optionally, the detailed letter of each dress ornament single-item can also be shown according to user's clicking operation
Breath.
Collocation suggestion is sent to cloud server by step 480.
Optionally, when detecting that user is directed to the clicking operation of shown clothing matching suggestion, it will click on operation pair
The collocation suggestion answered is sent to cloud server.Illustratively, if user clicks black fur clothing, the picture of black fur clothing is sent out
It send to cloud server, so that cloud server searches the position of the commodity or similar commodity according to the picture.
Step 490 obtains the location information for suggesting matched commodity with the collocation that the cloud server returns.
The technical solution of the present embodiment, by obtaining the shooting picture using dress ornament single-item as object;And by the shooting figure
Piece inputs preconfigured disaggregated model, to identify the classification information of dress ornament single-item described in the shooting picture;According to described
Classification information inquires preset collocation database, the determining and matched clothing matching picture of the classification information;According to the clothes
Clothing matching suggestion is generated with the clothes and/or ornaments of dress ornament single-item collocation in decorations collocation picture, and with impression window
Form shows the clothing matching suggestion, realizes inquiry and the matched collocation of dress ornament single-item in the collocation database of mobile terminal
The picture of dress ornament can rapidly show clothing matching picture independent of network.In addition, collocation suggestion is sent to
Cloud server, so as to plan the guidance path for going to the position of the commodity by electronic map, to save user
Shopping-time.
Fig. 5 is a kind of clothing matching recommendation apparatus provided by the embodiments of the present application, which can be by software and/or hardware reality
It is existing, it generally can be incorporated in mobile terminal, for executing clothing matching recommended method provided by the embodiments of the present application.Such as Fig. 5
Shown, which includes:
Picture shooting module 510, for obtaining the shooting picture using dress ornament single-item as object;
Dress ornament identification module 520, for the shooting picture to be inputted preconfigured disaggregated model, to identify the bat
Take the photograph the classification information of dress ornament single-item described in picture, wherein the disaggregated model is according to different classes of dress ornament picture sample
Trained deep learning model;
It is recommended that generation module 530 shows the clothing matching for generating clothing matching suggestion according to the classification information
It is recommended that.
The technical solution of the present embodiment provides a kind of clothing matching recommendation apparatus, is carried out according to disaggregated model to shooting picture
It fast and accurately identifies, determines the classification of dress ornament single-item in shooting picture, matching collocation is determined further according to the category
It is recommended that realizing the dress ornament single-item inputted based on user, the collocation suggestion of profession is provided in time, shortens user in shopping collocation
The time of cost.
Optionally, the device further include:
State acquisition module, for obtaining dress ornament before the shooting picture is inputted preconfigured disaggregated model
The status information of matching function, wherein the clothing matching function is for providing clothing matching suggestion;
Function determination module, for judging whether the clothing matching function is activated according to the state information;If so,
Then execute the operation that the shooting picture is inputted to preconfigured disaggregated model.
Alternatively, it is proposed that generation module 530 is specifically used for:
Preset collocation database is inquired according to the classification information, it is determining to be built with the matched collocation of the classification information
View;
It obtains and meets the commodity picture that the collocation is suggested in the network platform, and show the quotient in the form of impression window
Product picture.
Alternatively, it is proposed that generation module 530 is specifically used for:
Inquire preset collocation database according to the gender of the dress ornament single-item, style, style and functional information, determine with
The corresponding collocation of the dress ornament single-item is suggested.
Optionally, the device further include:
Feedback information obtains module, for obtaining user after showing the commodity picture in the form of impression window
The feedback information suggested for the collocation;
Priority adjusts module, for determining that the collocation of user is liked according to the feedback information, and according to the collocation
Hobby updates the recommended priority of clothing matching suggestion in the collocation database.
Alternatively, it is proposed that generation module 530 is specifically used for:
Preset collocation database, the determining and matched clothing matching of the classification information are inquired according to the classification information
Picture;
It is built according to clothing matching is generated with the clothes of dress ornament single-item collocation and/or ornaments in the clothing matching picture
View, and the clothing matching suggestion is shown in the form of impression window.
Optionally, further includes:
It is recommended that sending module, for after showing that the clothing matching is suggested, collocation suggestion to be sent to cloud
Server, the collocation, which is proposed to be used in, indicates that the cloud server inquiry suggests that the position of matched commodity is believed with the collocation
Breath;
Position acquisition module, the position for suggesting matched commodity with the collocation returned for obtaining the cloud server
Confidence breath, and show the location information.
The embodiment of the present application also provides a kind of storage medium comprising computer executable instructions, and the computer is executable
Instruction is used to execute a kind of clothing matching recommended method when being executed by computer processor, this method comprises:
It obtains using dress ornament single-item as the shooting picture of object;
The shooting picture is inputted into preconfigured disaggregated model, to identify dress ornament single-item described in the shooting picture
Classification information, wherein the disaggregated model is the deep learning model according to different classes of dress ornament picture sample training;
Clothing matching suggestion is generated according to the classification information, shows the clothing matching suggestion.
Storage medium --- any various types of memory devices or storage equipment.Term " storage medium " is intended to wrap
It includes: install medium, such as CD-ROM, floppy disk or magnetic tape equipment;Computer system memory or random access memory, such as
DRAM, DDR RAM, SRAM, EDO RAM, Lan Basi (Rambus) RAM etc.;Nonvolatile memory, such as flash memory, magnetic medium
(such as hard disk or optical storage);Register or the memory component of other similar types etc..Storage medium can further include other
Memory of type or combinations thereof.In addition, storage medium can be located at program in the first computer system being wherein performed,
Or can be located in different second computer systems, second computer system is connected to the by network (such as internet)
One computer system.Second computer system can provide program instruction to the first computer for executing." storage is situated between term
Matter " may include may reside in different location (such as by network connection different computer systems in) two or
More storage mediums.Storage medium can store the program instruction that can be performed by one or more processors and (such as implement
For computer program).
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present application
The clothing matching that executable instruction is not limited to the described above recommends operation, can also be performed provided by the application any embodiment
Relevant operation in clothing matching recommended method.
The embodiment of the present application provides a kind of mobile terminal, has operating system in the mobile terminal, in the mobile terminal
Clothing matching recommendation apparatus provided by the embodiments of the present application can be integrated.Wherein, mobile terminal can be smart phone, PAD (plate
Computer), intelligent wearable device etc..Fig. 6 is a kind of structural block diagram of mobile terminal provided by the embodiments of the present application.Such as Fig. 6 institute
Show, which may include memory 610 and processor 620.The memory 610, for storing computer program, taking
With database and disaggregated model etc.;The processor 620 reads and executes the computer program stored in the memory 610.
The processor 620 performs the steps of acquisition when executing the computer program using dress ornament single-item as the shooting figure of object
Piece;The shooting picture is inputted into preconfigured disaggregated model, to identify the class of dress ornament single-item described in the shooting picture
Other information, wherein the disaggregated model is the deep learning model according to different classes of dress ornament picture sample training;According to institute
It states classification information and generates clothing matching suggestion, show the clothing matching suggestion.
The memory and processor enumerated in above-mentioned example are some components of mobile terminal, and the mobile terminal is also
It may include other components.By taking smart phone as an example, illustrate the possible structure of above-mentioned mobile terminal.Fig. 7 is that the application is implemented
A kind of structural block diagram for smart phone that example provides.As shown in fig. 7, the smart phone may include: memory 701, centre
Manage device (Central Processing Unit, CPU) 702 (also known as processor, hereinafter referred to as CPU), Peripheral Interface 703, RF
(Radio Frequency, radio frequency) circuit 705, voicefrequency circuit 706, loudspeaker 711, power management chip 708, input/output
(I/O) subsystem 709, other input/control devicess 710 and outside port 704, these components pass through one or more communications
Bus or signal wire 707 communicate.
It should be understood that illustrating the example that smart phone 700 is only mobile terminal, and smart phone 700
It can have than shown in the drawings more or less component, can combine two or more components, or can be with
It is configured with different components.Various parts shown in the drawings can include one or more signal processings and/or dedicated
It is realized in the combination of hardware, software or hardware and software including integrated circuit.
Just the smart phone provided in this embodiment for being integrated with clothing matching recommendation apparatus is described in detail below.
Memory 701, the memory 701 can be accessed by CPU702, Peripheral Interface 703 etc., and the memory 701 can
It can also include nonvolatile memory to include high-speed random access memory, such as one or more disk memory,
Flush memory device or other volatile solid-state parts.Computer program is stored in memory 701, can also arrange in pairs or groups data
Library and disaggregated model etc..
The peripheral hardware that outputs and inputs of equipment can be connected to CPU702 and deposited by Peripheral Interface 703, the Peripheral Interface 703
Reservoir 701.
I/O subsystem 709, the I/O subsystem 709 can be by the input/output peripherals in equipment, such as touch screen 712
With other input/control devicess 710, it is connected to Peripheral Interface 703.I/O subsystem 709 may include 7071 He of display controller
For controlling one or more input controllers 7092 of other input/control devicess 710.Wherein, one or more input controls
Device 7092 processed receives electric signal from other input/control devicess 710 or sends electric signal to other input/control devicess 710,
Other input/control devicess 710 may include physical button (push button, rocker buttons etc.), dial, slide switch, behaviour
Vertical pole clicks idler wheel.It is worth noting that input controller 7092 can with it is following any one connect: keyboard, infrared port,
The indicating equipment of USB interface and such as mouse.
Touch screen 712, the touch screen 712 are the input interface and output interface between user terminal and user, can
It is shown to user depending on output, visual output may include figure, text, icon, video etc..
Display controller 7071 in I/O subsystem 709 receives electric signal from touch screen 712 or sends out to touch screen 712
Electric signals.Touch screen 712 detects the contact on touch screen, and the contact that display controller 7071 will test is converted to and is shown
The interaction of user interface object on touch screen 712, i.e. realization human-computer interaction, the user interface being shown on touch screen 712
Object can be the icon of running game, the icon for being networked to corresponding network etc..It is worth noting that equipment can also include light
Mouse, light mouse are the extensions for the touch sensitive surface for not showing the touch sensitive surface visually exported, or formed by touch screen.
RF circuit 705 is mainly used for establishing the communication of mobile phone Yu wireless network (i.e. network side), realizes mobile phone and wireless network
The data receiver of network and transmission.Such as transmitting-receiving short message, Email etc..Specifically, RF circuit 705 receives and sends RF letter
Number, RF signal is also referred to as electromagnetic signal, and RF circuit 705 converts electrical signals to electromagnetic signal or electromagnetic signal is converted to telecommunications
Number, and communicated by the electromagnetic signal with communication network and other equipment.RF circuit 705 may include for executing
The known circuit of these functions comprising but it is not limited to antenna system, RF transceiver, one or more amplifiers, tuner, one
A or multiple oscillators, digital signal processor, CODEC (COder-DECoder, coder) chipset, user identifier mould
Block (Subscriber Identity Module, SIM) etc..
Voicefrequency circuit 706 is mainly used for receiving audio data from Peripheral Interface 703, which is converted to telecommunications
Number, and the electric signal is sent to loudspeaker 711.
Loudspeaker 711 is reduced to sound for mobile phone to be passed through RF circuit 705 from the received voice signal of wireless network
And the sound is played to user.
Power management chip 708, the hardware for being connected by CPU702, I/O subsystem and Peripheral Interface are powered
And power management.
Mobile terminal provided by the embodiments of the present application, the dress ornament single-item that can be inputted based on user, provides profession in time
Collocation suggestion, shorten user's time for spending in shopping collocation.
It is any that the application can be performed in clothing matching recommendation apparatus, storage medium and the mobile terminal provided in above-described embodiment
Clothing matching recommended method provided by embodiment has and executes the corresponding functional module of this method and beneficial effect.Not upper
The technical detail of detailed description in embodiment is stated, reference can be made to clothing matching recommended method provided by the application any embodiment.
Note that above are only the preferred embodiment and institute's application technology principle of the application.It will be appreciated by those skilled in the art that
The application is not limited to specific embodiment described here, be able to carry out for a person skilled in the art it is various it is apparent variation,
The protection scope readjusted and substituted without departing from the application.Therefore, although being carried out by above embodiments to the application
It is described in further detail, but the application is not limited only to above embodiments, in the case where not departing from the application design, also
It may include more other equivalent embodiments, and scope of the present application is determined by the scope of the appended claims.
Claims (10)
1. a kind of clothing matching recommended method characterized by comprising
It obtains using dress ornament single-item as the shooting picture of object;
The shooting picture is inputted into preconfigured disaggregated model, to identify the class of dress ornament single-item described in the shooting picture
Other information, wherein the disaggregated model is the deep learning model according to different classes of dress ornament picture sample training;
Clothing matching suggestion is generated according to the classification information, shows the clothing matching suggestion.
2. the method according to claim 1, wherein the shooting picture is inputted preconfigured classification mould
Before type, further includes:
Obtain the status information of clothing matching function, wherein the clothing matching function is for providing clothing matching suggestion;
Judge whether the clothing matching function is activated according to the state information;
If so, executing the operation that the shooting picture is inputted to preconfigured disaggregated model.
3. the method according to claim 1, wherein generating clothing matching suggestion, exhibition according to the classification information
Show the clothing matching suggestion, comprising:
Preset collocation database is inquired according to the classification information, it is determining to suggest with the matched collocation of the classification information;
It obtains and meets the commodity picture that the collocation is suggested in the network platform, and show the commodity figure in the form of impression window
Piece.
4. according to the method described in claim 3, it is characterized in that, inquiring preset collocation data according to the classification information
Library, it is determining to suggest with the matched collocation of the classification information, comprising:
Inquire preset collocation database according to the gender of the dress ornament single-item, style, style and functional information, it is determining with it is described
The corresponding collocation of dress ornament single-item is suggested.
5. according to the method described in claim 3, it is characterized in that, shown in the form of impression window the commodity picture it
Afterwards, further includes:
Obtain the feedback information that user suggests for the collocation;
The collocation hobby of user is determined according to the feedback information, and is updated in the collocation database according to collocation hobby
The recommended priority of clothing matching suggestion.
6. the method according to claim 1, wherein generating clothing matching suggestion, exhibition according to the classification information
Show the clothing matching suggestion, comprising:
Preset collocation database, the determining and matched clothing matching figure of the classification information are inquired according to the classification information
Piece;
Clothing matching suggestion is generated with the clothes of dress ornament single-item collocation and/or ornaments according in the clothing matching picture,
And the clothing matching suggestion is shown in the form of impression window.
7. method according to any one of claim 1 to 6, which is characterized in that suggest it in the displaying clothing matching
Afterwards, further includes:
Collocation suggestion is sent to cloud server, wherein the collocation is proposed to be used in the instruction cloud server and looks into
Ask the location information for suggesting matched commodity with the collocation;
The location information with the matched commodity of the collocation suggestion that the cloud server returns is obtained, and shows the position
Information.
8. a kind of clothing matching recommendation apparatus characterized by comprising
Picture shooting module, for obtaining the shooting picture using dress ornament single-item as object;
Dress ornament identification module, for the shooting picture to be inputted preconfigured disaggregated model, to identify the shooting picture
Described in dress ornament single-item classification information, wherein the disaggregated model is according to different classes of dress ornament picture sample training
Deep learning model;
It is recommended that generation module shows the clothing matching suggestion for generating clothing matching suggestion according to the classification information.
9. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is held by processor
The clothing matching recommended method as described in any one of claims 1 to 7 is realized when row.
10. a kind of mobile terminal, including memory, processor and storage are on a memory and can be in the computer of processor operation
Program, which is characterized in that the processor is realized as described in any one of claims 1 to 7 when executing the computer program
Clothing matching recommended method.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711382746.3A CN109949116A (en) | 2017-12-20 | 2017-12-20 | Clothing matching recommended method, device, storage medium and mobile terminal |
PCT/CN2018/116799 WO2019120031A1 (en) | 2017-12-20 | 2018-11-21 | Method, device, storage medium, and mobile terminal for making recommendation about clothing matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711382746.3A CN109949116A (en) | 2017-12-20 | 2017-12-20 | Clothing matching recommended method, device, storage medium and mobile terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109949116A true CN109949116A (en) | 2019-06-28 |
Family
ID=66992475
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711382746.3A Pending CN109949116A (en) | 2017-12-20 | 2017-12-20 | Clothing matching recommended method, device, storage medium and mobile terminal |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109949116A (en) |
WO (1) | WO2019120031A1 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161022A (en) * | 2019-12-26 | 2020-05-15 | 汉口北进出口服务有限公司 | Commodity recommendation method and device |
CN112069358A (en) * | 2020-08-18 | 2020-12-11 | 北京达佳互联信息技术有限公司 | Information recommendation method and device and electronic equipment |
CN112307242A (en) * | 2020-11-11 | 2021-02-02 | 百度在线网络技术(北京)有限公司 | Clothing matching method and device, computing equipment and medium |
CN113159876A (en) * | 2020-01-21 | 2021-07-23 | 海信集团有限公司 | Clothing matching recommendation device and method and storage medium |
CN113435941A (en) * | 2021-07-08 | 2021-09-24 | 武汉纺织大学 | Clothing matching recommendation method and device and readable storage medium |
CN113468353A (en) * | 2021-07-20 | 2021-10-01 | 柒久园艺科技(北京)有限公司 | Tourist interaction method and device based on graphics, electronic equipment and medium |
CN114820135A (en) * | 2022-05-16 | 2022-07-29 | 温州鞋革产业研究院 | Intelligent clothing matching system and method |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104951966A (en) * | 2015-07-13 | 2015-09-30 | 百度在线网络技术(北京)有限公司 | Clothes commodity recommending method and device |
CN105279679A (en) * | 2015-11-17 | 2016-01-27 | 小米科技有限责任公司 | Dress collocation method and apparatus |
CN105787574A (en) * | 2014-12-26 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Method and device used for providing seat information |
CN106504064A (en) * | 2016-10-25 | 2017-03-15 | 清华大学 | Clothes classification based on depth convolutional neural networks recommends method and system with collocation |
CN107123033A (en) * | 2017-05-04 | 2017-09-01 | 北京科技大学 | A kind of garment coordination method based on depth convolutional neural networks |
US10346893B1 (en) * | 2016-03-21 | 2019-07-09 | A9.Com, Inc. | Virtual dressing room |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331417B (en) * | 2014-10-09 | 2018-01-02 | 深圳码隆科技有限公司 | A kind of matching method of individual subscriber dress ornament |
-
2017
- 2017-12-20 CN CN201711382746.3A patent/CN109949116A/en active Pending
-
2018
- 2018-11-21 WO PCT/CN2018/116799 patent/WO2019120031A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105787574A (en) * | 2014-12-26 | 2016-07-20 | 阿里巴巴集团控股有限公司 | Method and device used for providing seat information |
CN104951966A (en) * | 2015-07-13 | 2015-09-30 | 百度在线网络技术(北京)有限公司 | Clothes commodity recommending method and device |
CN105279679A (en) * | 2015-11-17 | 2016-01-27 | 小米科技有限责任公司 | Dress collocation method and apparatus |
US10346893B1 (en) * | 2016-03-21 | 2019-07-09 | A9.Com, Inc. | Virtual dressing room |
CN106504064A (en) * | 2016-10-25 | 2017-03-15 | 清华大学 | Clothes classification based on depth convolutional neural networks recommends method and system with collocation |
CN107123033A (en) * | 2017-05-04 | 2017-09-01 | 北京科技大学 | A kind of garment coordination method based on depth convolutional neural networks |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161022A (en) * | 2019-12-26 | 2020-05-15 | 汉口北进出口服务有限公司 | Commodity recommendation method and device |
CN113159876A (en) * | 2020-01-21 | 2021-07-23 | 海信集团有限公司 | Clothing matching recommendation device and method and storage medium |
CN113159876B (en) * | 2020-01-21 | 2023-08-22 | 海信集团有限公司 | Clothing collocation recommendation device, method and storage medium |
CN112069358A (en) * | 2020-08-18 | 2020-12-11 | 北京达佳互联信息技术有限公司 | Information recommendation method and device and electronic equipment |
CN112307242A (en) * | 2020-11-11 | 2021-02-02 | 百度在线网络技术(北京)有限公司 | Clothing matching method and device, computing equipment and medium |
CN113435941A (en) * | 2021-07-08 | 2021-09-24 | 武汉纺织大学 | Clothing matching recommendation method and device and readable storage medium |
CN113468353A (en) * | 2021-07-20 | 2021-10-01 | 柒久园艺科技(北京)有限公司 | Tourist interaction method and device based on graphics, electronic equipment and medium |
CN114820135A (en) * | 2022-05-16 | 2022-07-29 | 温州鞋革产业研究院 | Intelligent clothing matching system and method |
Also Published As
Publication number | Publication date |
---|---|
WO2019120031A1 (en) | 2019-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110021061B (en) | Collocation model construction method, clothing recommendation method, device, medium and terminal | |
CN109949116A (en) | Clothing matching recommended method, device, storage medium and mobile terminal | |
KR102312628B1 (en) | Method and apparatus for presenting watch face, and smartwatch | |
US20220005101A1 (en) | System and method for social style mapping | |
CN108734557A (en) | Methods, devices and systems for generating dress ornament recommendation information | |
US20220335640A1 (en) | Computer vision assisted item search | |
US10346893B1 (en) | Virtual dressing room | |
CN107665238B (en) | Picture processing method and device for picture processing | |
CN104376160A (en) | Real person simulation individuality ornament matching system | |
CN106202317A (en) | Method of Commodity Recommendation based on video and device | |
CN108363750B (en) | Clothing recommendation method and related products | |
US20230419582A1 (en) | Virtual object display method and apparatus, electronic device, and medium | |
CN109635680A (en) | Multitask attribute recognition approach, device, electronic equipment and storage medium | |
CN109947510A (en) | A kind of interface recommended method and device, computer equipment | |
US10026176B2 (en) | Browsing interface for item counterparts having different scales and lengths | |
CN105426462A (en) | Image searching method and device based on image element | |
CN110309412A (en) | The method, apparatus and electronic equipment of clothing matching information are provided | |
CN103279519B (en) | Articles search method and apparatus | |
CN108319639A (en) | The methods of exhibiting and device of clothing matching | |
CN110020903A (en) | Method, apparatus, storage medium and the mobile terminal of analog subscriber trial assembly | |
CN115826835A (en) | Data processing method and device and readable storage medium | |
CN116739699A (en) | Method for providing commodity recommendation information and electronic equipment | |
JP2012194782A (en) | Server for outfit simulation, system for automatically creating image data of clothes or the like for outfit simulation, and method for automatically creating image data of clothes or the like for outfit simulation | |
US11804023B1 (en) | Systems and methods for providing a virtual dressing room and a virtual stylist | |
CN114125271B (en) | Image processing method and device and electronic equipment |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190628 |
|
RJ01 | Rejection of invention patent application after publication |