CN101950400A - Network shopping guiding method - Google Patents
Network shopping guiding method Download PDFInfo
- Publication number
- CN101950400A CN101950400A CN2010105010270A CN201010501027A CN101950400A CN 101950400 A CN101950400 A CN 101950400A CN 2010105010270 A CN2010105010270 A CN 2010105010270A CN 201010501027 A CN201010501027 A CN 201010501027A CN 101950400 A CN101950400 A CN 101950400A
- Authority
- CN
- China
- Prior art keywords
- commodity
- picture
- feature
- client
- related group
- 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
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a network shopping guiding method. In the method, a client searches for the commodity picture display of the association group of the pictures of solid commodities on a server through a picture searching engine. The method comprises that: the server receives commodity pictures and establishes an association group of the similarity of all commodity pictures; the display interface of the client sends a clicked commodity picture retrieving instruction through the image searching engine; and the server sends the clicked commodity picture in the association group of the commodity pictures to the client to display the picture on a display interface. The network shopping guiding method of the invention guides users in commodity purchasing by using the association group of the commodity pictures, allows the users to find target commodities with reduced click times and improves network shopping efficiency.
Description
Technical field
The invention belongs to the shopping at network technical field, relate in particular to a kind of shopping at network air navigation aid.
Background technology
Along with the development of infotech, the appearance as online shopping mall's picture is emerged rapidly in large numbersBamboo shoots after a spring rain, the appearance of magnanimity commodity make how to organize these information to become a new difficult problem.Traditional method by brand and pattern classification can't satisfy the growing needs of shopping at network.The consumer is generally can search at the demand of oneself carrying out shopping at network, to dwindle the commodity amount that need browse.Nonetheless, in some large-scale online shopping malls, still have a large amount of commodity and enter Search Results.For example, in some large-scale shopping at network platform, it is two that men and women's formula footwear that businessman sells reach hundreds of thousands, even if the kind of footwear, pattern, size, price etc. are limited, the quantity of the footwear that search obtains often still has thousands of even up to ten thousand two, here face look for a pair of special style footwear just as look for a needle in a haystack, the shopping of formula of browsing is page by page experienced and is allowed the consumer be difficult to accept.
That has used at present all is based on the search of the Word message of commodity at the search technique of particular commodity, specifically, the supplier of information imports the various information of commodity earlier with written form, and the consumer comes the content of limit search by literal in the process of shopping and select specific commodity to carry out detailed consulting in the result of search.The shortcoming of this searching method is to have ignored fully information such as a large amount of shape that picture comprised, texture, color of commodity, and these intuitively information in the net purchase process, provide huge convenient and the client finally made a decision buy the considerable effect that plays to the consumer.
Therefore, there is defective in prior art, is further improved and develops.
Summary of the invention
The object of the present invention is to provide a kind of shopping at network air navigation aid, make the user in the magnanimity commodity of network, can find own needed commodity easily.
Technical scheme of the present invention is as follows:
A kind of shopping at network air navigation aid, related group the commodity picture presentation that client is searched the physical commodity picture by photographic search engine at server end may further comprise the steps:
A, described server end receive the commodity picture, set up the related group of all commodity picture analogies degree;
The display interface of B, described client sends the search instruction of clicked commodity picture by described photographic search engine;
C, described server end send to described client with the related group's of clicked commodity picture commodity picture by search engine to be showed at display interface.
Described method, wherein, described steps A also comprises picture commodity Feature Extraction and storage, the calculating of the distance between the commodity feature and storage, the related group's of the calculating of feature weight and storage and commodity picture calculating and storage.
Described method, wherein, the commodity Feature Extraction in the described steps A also comprises: regularization of the normal distribution process of feature obtains the relative value of feature.
Described method wherein, adopts the related group of similarity between K-means algorithm or the intensified learning classifier algorithm counting yield feature in the described steps A.
Described method, wherein, the calculating of described feature weight comprises initial weight and the calculating of weight in real time.
Described method, wherein, client is showed a plurality of features of commodity among the described step C in the mode of various dimensions.
Described method, wherein, client is showed the feature of various dimensions among the described step C with the mode projection of two-dimentional Cartesian coordinates.
Described method, wherein, commodity picture among the described step C among the related group is filled full described two-dimentional Cartesian coordinates according to the distance between the two-dimentional Cartesian coordinates, and the two-dimentional cartesian coordinate map that will fill full related group commodity picture shows at described display interface.
Described method, wherein, the distance between the described Cartesian coordinates is Euclidean distance or mahalanobis distance.
Compared with prior art, the invention provides a kind of shopping at network air navigation aid, client sends to server end with the information of clicked commodity picture by photographic search engine, server end returns to client with the related group's of clicked commodity picture commodity picture transmission by photographic search engine, and the display interface of client shows the related group's of clicked commodity picture commodity picture.Shopping at network air navigation aid of the present invention is user shopping guide commodity in the related group's of commodity picture mode, makes the user find the target commodity rapidly under the situation that reduces number of clicks, improves the efficient of shopping at network.
Description of drawings
Fig. 1 is the structural drawing of shopping at network navigational system of the present invention;
Fig. 2 is the structural drawing of server end of the present invention.
Fig. 3 is the sparse distribution figure of toe-cap feature of the present invention;
Fig. 4 is the normal distribution of toe-cap feature of the present invention;
Fig. 5 is the synoptic diagram of display of commodity display on the client display interface;
The synoptic diagram of the proper vector that Fig. 6 represents for client multi-dimensional degree module;
Fig. 7 shows the synoptic diagram of the two-dimentional Cartesian coordinates that projection module is represented for the client two dimension;
Fig. 8 is a client display interface search instruction synoptic diagram.
Embodiment
Below in conjunction with accompanying drawing, preferred embodiment of the present invention is described in further detail.
Shopping at network navigational system provided by the invention can be used for any physical commodity shopping navigation on the network, is example now with footwear, and the shopping at network navigational system is made detailed explanation.
Described shopping at network navigational system is the shopping at network navigation by picture presentation, picture searching, as shown in Figure 1, has:
Server end comprises data server end and calculation server end, data such as the feature of described data server end storing commodity picture, commodity picture, the distance between the commodity feature, feature weight; Described calculation server is used for the feature of analytical calculation commodity picture, distance, the feature weight between the commodity feature;
Photographic search engine according to the search instruction of client, at the picture of described server end inquiry command adapted thereto, and returns to described client;
Client is used for connecting with server end, and sends the search instruction of shopping.
The peripheral profile of footwear, color, toe-cap, upper of a shoe, sole, texture are bought the considerable effect that plays to finally making a decision of client, and traditional text search can only be carried out index to relevant literal, has ignored the information such as peripheral profile, color, toe-cap, upper of a shoe, sole, texture of the footwear that product picture comprised fully.
According to the commodity picture of footwear, utilize image analysis technology to extract the feature of picture, comprise information such as peripheral profile, color, toe-cap, upper of a shoe, sole, texture.Described calculation server comprises pretreatment unit, can handle the irregular picture that receives, to obtain being used to showing the material with picture analyzing.
Calculation server of the present invention comprises the product input block, is used for the input of commodity picture; Feature extraction unit is used for the extraction of the value of commodity picture feature.Described product input block also can be a client of separating with described server.
For this commodity of footwear, described feature extraction unit can comprise peripheral profile extraction module, color extracting module, toe-cap extraction module, upper of a shoe extraction module, sole extraction module and texture extraction module.
Described peripheral profile extraction module can utilize the profile of footwear in the commodity picture to calculate the peripheral contour feature of footwear.The color extracting module can use the color histogram of HSV to obtain the color characteristic of footwear according to the picture of footwear.The toe-cap extraction module can according to the feature of toe-cap in the picture do by opening to remain silent, by point to blunt analysis, thereby obtain the toe-cap feature.The upper of a shoe extraction module is exactly the upper of a shoe feature that obtains footwear according to the specificity analysis of upper of a shoe relevant position in the picture.The sole extraction module is according to the shape of sole in the picture being done the sole feature that rim detection obtains footwear, edge detection method employing Prewitt/canny algorithm.The texture extraction module is to be undertaken carrying out the textural characteristics that wavelet transform obtains footwear again after gray scale is handled by the image to footwear
The peripheral contour feature of described footwear, color characteristic, toe-cap feature, upper of a shoe feature, sole feature, these six features of textural characteristics can be used proper vector S (s
1, s
2, s
3, s
4, s
5, s
6), and the weight of each eigenwert in the S vector is T (t
1, t
2, t
3, t
4, t
5, t
6), the population characteristic value of each shoes is exactly K=S*T like this, and per two couples of shoes (K
1, K
2) between similarity just can use | K
1-K
2| represent.
The feature of using these vector representations do between the shoes similarity relatively before, we will carry out the relative value of feature earlier and handle because the absolute value of feature is nonsensical, just relative value is just meaningful.
Toe-cap feature s3 such as for every pair of footwear has 20,000 pairs footwear, just with 20,000 discrete points, these 20,000 points may be equally distributed, possibility but more is a uneven distribution, very intensive of certain zone, and very as shown in Figure 3 sparse of other zone.
In order better to reflect similarity,, make the curve of these 20,000 pairs of footwear of reflection meet normal distribution, as shown in Figure 4 with regularization that the data of feature are carried out normal distribution.
Server end of the present invention is provided with regularization module, is used for the feature that feature extraction unit is extracted is done regularization of normal distribution, obtains the relative value of feature.The relative value of feature can be stored in the characteristic storage unit of described database server.
The weight that how to calculate each feature is a key of the present invention, and solution of the present invention is as follows:
The weight of feature comprises initial weight and real-time weight.
Initial weight is that the shopping at network navigational system is initially the weight that each feature is provided with, the quantity of for example getting sample set is 100, be exactly 100 pairs of shoes, with each the feature queuing of artificial method with these 100 pairs of footwear, guarantee that the similarity between the adjacent shoes is the highest, distance between any three couples of shoes ABC that ordering is good like this, | A-B|＜| A-C| and | B-C|＜| A-C|, so just can find the weighted value T of all these 100 orders of adaptation.
Weight is based on initial weight in real time, does machine learning according to client's click and selection, then weight is adjusted.Certainly to dissimilar footwear the different weighted value of one cover will be arranged all, for example the weighted value of the weighted value of sandals and sport footwear is different.Concrete, described calculation server comprises weight unit, according to the user click of feature and the weight calculation of selecting constantly to regulate individual features is gone out real-time weight, for example:
The client has selected A, B, three pairs of shoes of C successively in selecting the process of footwear, the weight of the feature of A is less than B, and the weight of the feature of B is less than C, and described weight unit is adjusted the T vector according to user's selection.
The adjustment of weight in real time mainly is to calculate when the variety classes shoes are adjusted the interval of weight, or the step-length of weight.And the calculating of weight step-length is the training set by a group, progressively approaches acquisition with the observation of human eye by the method for intensified learning.Such as eigenwert overall for sport footwear is 1 to 100, the present invention supposes that the step-length of weight is 5, and the training set of this group is selected, and finding the clicks of target shoes such as the training set of this group is (10,8,2,15,7, ... 4,10), and the desirable clicks that finds target is: 1, and that tries one's best lacks.2, the difference of each shoes clicks also is little as far as possible.This two standards have been arranged, just can ceaselessly change step-length, found the optimal step-length of approaching.
The weight storage unit of database server side comprises having and the corresponding weight memory module in real time of client, can store the real-time weight vectors of the specific client that weight unit calculates.
The present invention is according to the similarity between the feature, and promptly the distance between the feature is set up the related group between the commodity, after analyzing good these characteristic distances, utilizes the similarity between the commodity to set up related group.Described calculation server comprises related computing unit, is used to realize the related group of similarity between the commodity.
A kind of interrelational form of described related computing unit is that the kind according to footwear is divided into the different footwear of N kind as starting condition with footwear; Concrete related account form is as follows:
At first, footwear are divided into variety classeses such as sport footwear, playshoes, sandals, be example with the related group who sets up sport footwear, introduce the computing method of related computing unit.
Secondly, choose the vectorial S of feature of a pair of shoes in the sport footwear as the initial characteristics vector.
Three, the proper vector S that calculates each two sport footwear successively according to the distance between the sport footwear proper vector, sets up related group to the distance between the initial characteristics vector.Distance of the present invention is exactly a similarity, but the standard that similarity is eyes to be found out, and distance is the numerical value that utilizes eigenwert to calculate, the present invention is exactly a difference of utilizing range marker eyes similarity.
Described related computing unit can adopt K-means algorithm or intensified learning classifier algorithm to come the related group of similarity between the counting yield feature.The K-means algorithm is accepted input quantity k; Then n data object is divided into k cluster so that make the cluster that is obtained satisfy: the object similarity in the same cluster is higher; And the object similarity in the different clusters is less.
Client of the present invention comprises user's display interface, and described user's display interface comprises the search instruction display unit, as shown in Figure 8, comprises the kind of commodity, for example: clothes, footwear, bag etc.; The type that comprises commodity, for example sport footwear, leather shoes, sandals etc.
The described type of merchandise can display with picture, and for example Fig. 5 displays out the picture of dissimilar footwear.Because every pictures all has related group, the user clicks any one in the picture, and the related group's of clicked commodity picture commodity figure sector-meeting is presented at display interface.Every kind of picture of display interface can be connected by the association store unit of photographic search engine and server end.
Described every pictures has information display unit, described information display unit can be by photographic search engine from the commodity price of server end link storage unit query to data.Described information display unit is linked at display interface with the commodity price that inquires and shows, the approach and the information of purchase is provided for the user.
Described client also comprises merchandise display unit, and described merchandise display unit comprises various dimensions module and two dimension displaying projection module.
Described various dimensions module is used to represent a kind of proper vector of commodity, and each feature of commodity picture occupies a dimension, as shown in Figure 6.
Described two dimension is showed projection module, it is Cartesian coordinates with two dimension, the proper vector of representing commodity, concrete with the axle of a feature in the proper vector as two-dimentional Cartesian coordinates, other the another one axle of the two-dimentional Cartesian coordinates of comprehensive conduct of proper vector of commodity of commodity.
For example, the two dimension of footwear as shown in Figure 7 shows that transverse axis is a shape facility, and transverse axis combines 5 big characteristics such as peripheral profile, toe-cap, upper of a shoe, sole, texture, and ordinate then is the color characteristic of footwear.The two dimension of the feature of product is as shown in Figure 7 showed, is starting point with initial point (upper left), and the lower right is a terminal point, and is from the near point of starting point distance, similar more, and from starting point point far away, then similarity is just poor more.The present invention can use Euclidean distance (Euclidean distance) or mahalanobis distance (Mahalanobis) distance as eigen vector.
Two dimension of the present invention show projection module be exactly the eigenvector projection of multidimensional in two-dimensional coordinate, by reducing the complexity that dimension solves problem.It briefly is exactly the vector that the various dimensions module is set up peripheral profile, color, toe-cap, upper of a shoe, sole, texture 6 dimensions.In the coordinate system of two dimension, the extension of each dimension is exactly the Euclidean or the mahalanobis distance of this vector value to two dimension displaying projection module with 6 vector projections that are, and the part between any two axles is exactly the two comprehensive distance.
After described two dimension showed that projection module is set up two-dimentional Cartesian coordinates, described client also comprised the product packing module.Described packing module is filled the picture of footwear and is shown according to the distance between the two-dimensional coordinate as shown in Figure 7.
Described packing module has different filling algorithms, and principle is to fill earlier from the point that initial point is near more, like this by the initial point countless concentric circles that to draw that sets out, and on each specific circumference, the direction of filling can be clockwise, and is perhaps counterclockwise.Such filling effect just as radar scanning, is from the close-by examples to those far off filled two-dimensional coordinate full successively.Sector region at each fritter, owing to be to be between two features, can calculate his distance, add the weight of distance like this with the distance of these two features to adjacent two feature axis (reference), just can the sector region of centre is populated.
In the two-dimentional Cartesian coordinates of projection, certain feature is successively decreased along increasing progressively of a certain direction, for example the profile similarity degree of picture successively decreases along increasing progressively of X-axis, the similarity of texture is along X, Y-axis 45 increasing progressively of angle of degree successively decrease, and the similarity of color is successively decreased along increasing progressively of Y-axis.Fan-shaped to external radiation along with initial point like this, the picture analogies degree is to stretch out according to certain rules, is exactly in some sense to have simulated the progressive law of human eye to the commodity similarity.
Shopping at network air navigation aid provided by the invention, related group by picture commodity characteristic similarity, mode with photographic search engine, product is provided the displaying of commodity picture for the user according to the related group's of similarity mode, make website product picture rule present to the client, very convenient client selects product.
Purchasing footwear with network is example, and the shopping at network air navigation aid may further comprise the steps:
Step 1, the server end of navigational system receives the picture of footwear, sets up the related group of the similarity of footwear on all pictures, specifically comprises:
Step 101, server end extracts the feature of picture, comprises peripheral contour feature, color characteristic, toe-cap feature, upper of a shoe feature, sole feature, the textural characteristics of footwear, and with the vectorial S (s after these regularization of features usefulness normal distribution
1, s
2, s
3, s
4, s
5, s
6) expression, and with the eigenwert after regularization of normal distribution or the vector value storage at server end.
Step 102, server end are provided with the initial weight of each feature of footwear, and with initial weight T (t
1, t
2, t
3, t
4, t
5, t
6) storage.
The general characteristic that step 103, server end are calculated each shoes is exactly K=S*T, and per two couples of shoes (K
1, K
2) between similarity just can use | K
1-K
2| represent.Shopping at network air navigation aid of the present invention is differentiated the difference of product similarity with the numerical value sign product naked eyes of similarity.
Step 104, server end employing K-means algorithm or intensified learning classifier algorithm come the association of similarity between the counting yield, make up the related group of similarity.
Step 2, client comprise the display interface that is used for display of commodity, and display interface is provided with search instruction; The various dimensions module that also comprises the representation feature vector, and with the two dimension displaying projection module of proper vector with two-dimentional Cartesian coordinates sign.The two-dimentional Cartesian coordinates of display interface after according to eigenvector projection arranged in the mode of two dimension the picture of commodity and to be shown at display interface.Client sends to server end by search engine with search instruction.
Step 3, any commodity picture of client display interface is clicked, and this clicked picture inquires the related group of similarity of this clicked picture by photographic search engine at server end, and related group's picture showed according to related group's two-dimentional Cartesian coordinates, as shown in Figure 7.
When the user clicked picture, photographic search engine sent to server end with the record of the picture of click, and server end calculates the real-time weight of commodity according to clicking record.
Owing to click every commodity picture, client can show the related group's of similarity of clicked picture photo, 50 commodity of display interface for example, the related group of the similarity of each commodity has 50 similar commodity, 2500 commodity have just been contained in such 2 times click, click for three times and can cover 12.5 ten thousand commodity, just click for four times and can arrive millions of commodity, consider that can there be the commodity of repetition the inside, like this 7, after 8 times the click, most clients can both find the target commodity by the network picture searching fast.Though the present invention is with the embodiment that is retrieved as of footwear, any physical commodities such as clothes, case and bag can retrieve with the picture form on network fast by the present invention, have improved effectiveness of retrieval.
Should be understood that above-mentioned statement at preferred embodiment of the present invention is comparatively detailed, can not therefore think the restriction to scope of patent protection of the present invention, scope of patent protection of the present invention should be as the criterion with claims.
Claims (9)
1. shopping at network air navigation aid, client is searched the related group's of physical commodity picture commodity picture presentation by photographic search engine at server end, may further comprise the steps:
A, described server end receive the commodity picture, set up the related group of all commodity picture analogies degree;
The display interface of B, described client sends the search instruction of clicked commodity picture by described photographic search engine;
C, described server end send to described client with the related group's of clicked commodity picture commodity picture by search engine to be showed at display interface.
2. method according to claim 1, it is characterized in that, described steps A also comprises picture commodity Feature Extraction and storage, the calculating of the distance between the commodity feature and storage, the related group's of the calculating of feature weight and storage and commodity picture calculating and storage.
3. method according to claim 2 is characterized in that, the commodity Feature Extraction in the described steps A also comprises: regularization of the normal distribution process of feature obtains the relative value of feature.
4. method according to claim 3 is characterized in that, adopts the related group of similarity between K-means algorithm or the intensified learning classifier algorithm counting yield feature in the described steps A.
5. method according to claim 2 is characterized in that, the calculating of described feature weight comprises initial weight and the calculating of weight in real time.
6. method according to claim 1 is characterized in that, client is showed a plurality of features of commodity among the described step C in the mode of various dimensions.
7. method according to claim 6 is characterized in that, client is showed the feature of various dimensions among the described step C with the mode projection of two-dimentional Cartesian coordinates.
8. method according to claim 7, it is characterized in that, commodity picture among the described step C among the related group is filled full described two-dimentional Cartesian coordinates according to the distance between the two-dimentional Cartesian coordinates, and the two-dimentional cartesian coordinate map that will fill full related group commodity picture shows at described display interface.
9. method according to claim 8 is characterized in that, the distance between the described Cartesian coordinates is Euclidean distance or mahalanobis distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010501027.0A CN101950400B (en) | 2010-10-09 | 2010-10-09 | Picture retrieving method of network shopping guiding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201010501027.0A CN101950400B (en) | 2010-10-09 | 2010-10-09 | Picture retrieving method of network shopping guiding method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101950400A true CN101950400A (en) | 2011-01-19 |
| CN101950400B CN101950400B (en) | 2014-04-16 |
Family
ID=43453887
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201010501027.0A Expired - Fee Related CN101950400B (en) | 2010-10-09 | 2010-10-09 | Picture retrieving method of network shopping guiding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101950400B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013029234A1 (en) * | 2011-08-30 | 2013-03-07 | Nokia Corporation | Method and apparatus for providing deal combinations |
| CN103092900A (en) * | 2010-12-29 | 2013-05-08 | 微软公司 | Single, mixed-view presentation of related products |
| CN103186616A (en) * | 2011-12-30 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted information-processing system, cloud service center and vehicle-mounted equipment |
| CN103412938A (en) * | 2013-08-22 | 2013-11-27 | 成都数之联科技有限公司 | Commodity price comparing method based on picture interactive type multiple-target extraction |
| WO2015027805A1 (en) * | 2013-08-28 | 2015-03-05 | 上海合合信息科技发展有限公司 | Query method, apparatus, system and client for product description |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| US9135316B2 (en) | 2011-03-30 | 2015-09-15 | Rakuten, Inc. | Information providing device, method, program, information display device, method, program, information search system, and recording medium for enhanced search results |
| TWI505108B (en) * | 2011-03-31 | 2015-10-21 | Rakuten Inc | Information providing apparatus, information providing method, information display apparatus, information display method, information retrieval system, program product, and recording medium |
| WO2016066042A1 (en) * | 2014-10-29 | 2016-05-06 | 阿里巴巴集团控股有限公司 | Segmentation method for commodity picture and device thereof |
| WO2016112797A1 (en) * | 2015-01-15 | 2016-07-21 | 阿里巴巴集团控股有限公司 | Method and device for determining image display information |
| CN107103022A (en) * | 2011-11-30 | 2017-08-29 | 阿里巴巴集团控股有限公司 | page element search display method and device |
| JP7356665B2 (en) | 2021-11-02 | 2023-10-05 | 株式会社Virtusize | Shoe data generation device, shoe data generation method, shoe data generation program |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004748A (en) * | 2006-10-27 | 2007-07-25 | 北京航空航天大学 | Method for searching 3D model based on 2D sketch |
-
2010
- 2010-10-09 CN CN201010501027.0A patent/CN101950400B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004748A (en) * | 2006-10-27 | 2007-07-25 | 北京航空航天大学 | Method for searching 3D model based on 2D sketch |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103092900A (en) * | 2010-12-29 | 2013-05-08 | 微软公司 | Single, mixed-view presentation of related products |
| US9135316B2 (en) | 2011-03-30 | 2015-09-15 | Rakuten, Inc. | Information providing device, method, program, information display device, method, program, information search system, and recording medium for enhanced search results |
| TWI505108B (en) * | 2011-03-31 | 2015-10-21 | Rakuten Inc | Information providing apparatus, information providing method, information display apparatus, information display method, information retrieval system, program product, and recording medium |
| WO2013029234A1 (en) * | 2011-08-30 | 2013-03-07 | Nokia Corporation | Method and apparatus for providing deal combinations |
| CN107103022B (en) * | 2011-11-30 | 2021-07-02 | 阿里巴巴集团控股有限公司 | Page element search display method and device |
| CN107103022A (en) * | 2011-11-30 | 2017-08-29 | 阿里巴巴集团控股有限公司 | page element search display method and device |
| CN103186616A (en) * | 2011-12-30 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Vehicle-mounted information-processing system, cloud service center and vehicle-mounted equipment |
| CN103412938A (en) * | 2013-08-22 | 2013-11-27 | 成都数之联科技有限公司 | Commodity price comparing method based on picture interactive type multiple-target extraction |
| CN103412938B (en) * | 2013-08-22 | 2016-06-29 | 成都数之联科技有限公司 | A kind of commodity price-comparing method extracted based on picture interactive multiobjective |
| CN104424230A (en) * | 2013-08-26 | 2015-03-18 | 阿里巴巴集团控股有限公司 | Network commodity recommendation method and device |
| WO2015027805A1 (en) * | 2013-08-28 | 2015-03-05 | 上海合合信息科技发展有限公司 | Query method, apparatus, system and client for product description |
| WO2016066042A1 (en) * | 2014-10-29 | 2016-05-06 | 阿里巴巴集团控股有限公司 | Segmentation method for commodity picture and device thereof |
| US10297029B2 (en) | 2014-10-29 | 2019-05-21 | Alibaba Group Holding Limited | Method and device for image segmentation |
| WO2016112797A1 (en) * | 2015-01-15 | 2016-07-21 | 阿里巴巴集团控股有限公司 | Method and device for determining image display information |
| JP7356665B2 (en) | 2021-11-02 | 2023-10-05 | 株式会社Virtusize | Shoe data generation device, shoe data generation method, shoe data generation program |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101950400B (en) | 2014-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101937549B (en) | Picture guidance system for network shopping guidance | |
| CN101950400B (en) | Picture retrieving method of network shopping guiding method | |
| US10755128B2 (en) | Scene and user-input context aided visual search | |
| US10043109B1 (en) | Attribute similarity-based search | |
| US9558213B2 (en) | Refinement shape content search | |
| CN103544216B (en) | The information recommendation method and system of a kind of combination picture material and keyword | |
| TWI616834B (en) | Network product recommendation method and device | |
| CN107220365B (en) | Accurate recommendation system and method based on collaborative filtering and association rule parallel processing | |
| US8001152B1 (en) | Method and system for semantic affinity search | |
| US8774526B2 (en) | Intelligent image search results summarization and browsing | |
| US8447107B1 (en) | Processing and comparing images | |
| US20180181569A1 (en) | Visual category representation with diverse ranking | |
| CN107908685A (en) | The retrieval of various visual angles commodity image and recognition methods based on transfer learning | |
| US20130202213A1 (en) | Method and system for fast and robust identification of specific product images | |
| CN108492160A (en) | Information recommendation method and device | |
| US20210073890A1 (en) | Catalog-based image recommendations | |
| CN103049513A (en) | Multi-visual-feature fusion method of commodity images of clothing, shoes and bags | |
| Zhang et al. | 3D object retrieval with multi-feature collaboration and bipartite graph matching | |
| AU2018101525A4 (en) | Category-partitioned Content Based Image Retrieval for fine-grained objects with feature extraction through Convolution Neural Network and feature reduction through principle component analysis | |
| Greenspan et al. | Region correspondence for image matching via EMD flow | |
| CN107622071B (en) | Clothes image retrieval system and method under non-source-retrieval condition through indirect correlation feedback | |
| CN106557489B (en) | Clothing searching method based on mobile terminal | |
| US11941681B2 (en) | System, method, and computer program product for determining compatibility between items in images | |
| CN110020918B (en) | Recommendation information generation method and system | |
| Wang et al. | Query-by-sketch image retrieval using homogeneous painting style characterization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140416 Termination date: 20151009 |
|
| EXPY | Termination of patent right or utility model |