CN106779791B - Generation method and device for collocation object picture combination - Google Patents
Generation method and device for collocation object picture combination Download PDFInfo
- Publication number
- CN106779791B CN106779791B CN201510831134.2A CN201510831134A CN106779791B CN 106779791 B CN106779791 B CN 106779791B CN 201510831134 A CN201510831134 A CN 201510831134A CN 106779791 B CN106779791 B CN 106779791B
- Authority
- CN
- China
- Prior art keywords
- picture
- object picture
- combination
- collocation
- similarity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0282—Rating or review of business operators or products
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a generating method and a device for a collocation object picture combination, wherein the method comprises the following steps: determining a first collocation object picture combination; and generating a second collocation object picture combination according to the similarity between each object picture in the picture library and each collocation object picture contained in the first collocation object picture combination and the associated information of the object picture of which the corresponding similarity accords with the specified condition in each object picture. By the method, the second collocation object picture combination can be automatically generated based on any first collocation object picture combination, so that the number of the collocation object picture combinations can be increased, and the server can provide more reference information for the user based on the increased collocation object picture combination.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for generating a combination of collocated object pictures.
Background
At present, online shopping is a very common shopping means. The user can freely select the mental commodity by browsing various commodity pictures and other detailed information of the commodity on the shopping website.
Generally, most users rarely purchase only one product alone, but may purchase a plurality of products that can be matched with each other. For example, for apparel-like goods, a user may simultaneously purchase an upper garment, a pair of shoes, an apparel accessory, etc., that may be paired with one another. For example, for a mobile communication type product, a user may purchase a mobile phone and a mobile phone shell matched with the mobile phone at the same time, and so on.
However, since the number of the commodities on the shopping website is large, and the commodities that can be matched with each other do not necessarily belong to the same brand, it is necessary to consume a great deal of effort of the user to find the network commodities that can be matched with each other, and the shopping convenience is poor.
In the prior art, a collocation object picture combination can be generated in a manual editing manner, each collocation object picture combination comprises at least two collocation object pictures, wherein in a shopping scene, the object can be a commodity on a shopping website. The commodities (i.e. objects) in the at least two matching object pictures can be matched with each other. And then the server of the shopping website can generate the collocation object picture combination in a manual editing mode to serve as reference information for providing collocation for the shopping of the user.
However, in practical applications, human resources are limited, and the number of manually edited collocation object picture combinations is small, so that the server may provide less reference information for the user based on each manually edited collocation object picture combination.
Disclosure of Invention
The embodiment of the application provides a method and a device for generating a collocation object picture combination, which are used for solving the problem that reference information provided by a server for a user based on each collocation object picture combination edited manually is less due to the fact that the number of the manually edited collocation object picture combinations is less in the prior art.
The method for generating the collocation object picture combination provided by the embodiment of the application comprises the following steps:
determining a first collocation object picture combination;
and generating a second collocation object picture combination according to the similarity between each object picture in the picture library and each collocation object picture contained in the first collocation object picture combination and the associated information of the object picture of which the corresponding similarity accords with the specified condition in each object picture.
The generation device of collocation object picture combination that this application embodiment provided includes:
the determining module is used for determining the first collocation object picture combination;
and the generating module is used for generating a second collocation object picture combination according to the similarity between each object picture in the picture library and each collocation object picture contained in the first collocation object picture combination and the associated information of the object picture of which the corresponding similarity accords with the specified condition in each object picture.
According to the embodiment of the application, by at least one technical scheme, the second matching object picture combination can be automatically generated based on any first matching object picture combination, so that the number of the matching object picture combinations can be increased, and the server can provide more reference information for the user based on the increased matching object picture combinations.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1a is a process of generating a collocation object picture combination according to an embodiment of the present disclosure;
fig. 1b is a schematic diagram of a recommendation request trigger button in practical application according to an embodiment of the present application;
fig. 2 is a process of generating a collocation object picture combination according to an embodiment of the present disclosure;
fig. 3 is a detailed process of generating a collocation object picture combination according to a commodity price corresponding to each commodity picture included in each similar commodity picture set based on a greedy thought according to the embodiment of the present application;
fig. 4 is a schematic diagram illustrating a reordered similarity list by using a linked list according to an embodiment of the present application;
fig. 5 is a specific process implemented by using the method in fig. 3 in an actual application scenario, provided by the embodiment of the present application;
fig. 6 is a process of determining, for a specified object picture, an object picture in which prices of objects included in the object picture match prices of objects in the object picture, according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of a device for generating a collocation object picture combination according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1a is a process for generating a collocation object picture combination according to an embodiment of the present application, which specifically includes the following steps:
s101: and determining the first collocation object picture combination.
The execution main body of the generation method of the collocation target picture combination provided by the embodiment of the application can be a server, for example, a server of a shopping website, a server of a price comparison website, a server of a design material website, and the like. The execution subject is not limited to the present application, and for convenience of description, the embodiment of the present application is described by taking a server of which the execution subject is a shopping website as an example.
In this embodiment, the first combination of matching object pictures may be a combination of matching object pictures determined based on a manual editing manner or other manners. For example, the operation and maintenance staff of the server may determine a plurality of objects that can be collocated with each other on the shopping website in advance according to a currently popular object collocation manner, and determine object pictures (which may be referred to as collocation object pictures) corresponding to the plurality of objects as a collocation object picture combination to be used as reference information provided for the shopping of the user. Obviously, there may be a plurality of matching object picture combinations, and according to the present application, one or more matching object picture combinations may be arbitrarily determined from existing matching object picture combinations as the first matching object picture combination, and then the subsequent steps are respectively performed for each determined first matching object picture combination.
It should be noted that, in practical applications, the matching object picture included in the first matching object picture combination may be represented by any information that can identify or index the matching object picture (e.g., a storage path, a name, a hyperlink address, a name and a model of an object in the matching object picture, etc.).
S102: and generating a second collocation object picture combination according to the similarity between each object picture in the picture library and each collocation object picture contained in the first collocation object picture combination and the associated information of the object picture of which the corresponding similarity accords with the specified condition in each object picture.
In the embodiment of the present application, the picture library may be a pre-designated picture library. For example, in a shopping scenario, the photo gallery may be a photo gallery of merchandise pictures on a shopping website.
Further, the associated information of the matching object picture may include a price, a material, a brand, and the like of an object in the matching object picture.
By executing step S102, an object picture (also referred to as a collocation object picture) meeting a specific condition (detailed later) can be selected from the object pictures in the picture library as a generated second collocation object picture combination, and a plurality of second collocation object picture combinations may be generated, so that more reference information can be provided for the user to shop.
In the embodiment of the present application, the similarity between each object picture in the picture library and each matching object picture included in the first matching object picture combination can be calculated based on the related art. For example, the method provided in the patent application entitled "a method and apparatus for recommending network goods" filed by the applicant at 26.8.2013 under the application number 201310376347.1 may be used to calculate the similarity between object pictures based on the color of the object pictures, which is not described herein again.
In this embodiment, the generated association information of part or all of the collocation object pictures included in the second collocation object picture combination may be matched with each other, or the generated association information of part or all of the collocation object pictures included in the second collocation object picture combination may be matched with the association information of at least one collocation object picture included in the first collocation object picture combination. In the former case, the user can directly refer to the second matching object picture combination for shopping, and in the latter case, the user can combine the first matching object picture combination and the second matching object picture combination as a reference for shopping. In the embodiments of the present application, the description is mainly made with respect to the former case.
The matching of the associated information of the different matching object pictures means that the associated information of the different matching object pictures is the same, or the difference between the associated information of the different matching object pictures is within a preset difference range.
For example, when the associated information of the collocation object picture is the price of the object in the collocation object picture, taking the example that the prices of part of the objects or all the objects included in the second collocation object picture combination are matched with each other, it is assumed that the part of the objects includes: one jacket, a pair of trousers, this jacket and this trousers price match can indicate: the price range of the jacket is similar to or the same as the price range of the trousers. When the price range of the jacket is not similar to or the same as the price range of the trousers, the price of the jacket is not matched with that of the trousers.
For another example, when the associated information of the collocation object picture is the material of the object in the collocation object picture, taking the example that the associated information of part or all of the collocation object pictures included in the second collocation object picture combination is matched with the associated information of at least one collocation object picture included in the first collocation object picture combination, it is assumed that the part of the object includes: a jacket, wherein the at least one matching object comprises a pair of trousers, and the matching of the jacket and the trousers can mean: the upper garment and the trousers are made of the same or similar materials. If when this jacket is the cotton material, if this trousers are the cotton material (same with this jacket material) or when the wool material (close with this jacket material), can think this jacket and this trousers material match, and if this trousers are the silk material (neither the same with this jacket material also is close), can think this jacket and this trousers material mismatch.
Similarly, the associated information of the matching object picture may also be a brand, a texture, a pattern, and the like of the object in the matching object picture.
By the method, the first collocation object picture combination can be a manually edited collocation object picture combination, and the second collocation object picture combination can be automatically generated based on any one of the first collocation object picture combinations, so that the number of the collocation object picture combinations can be increased, and the server can provide more reference information for the user based on the increased collocation object picture combination.
Further, the embodiment of the present application may support generating a plurality of second collocation object picture combinations based on any one of the first collocation object picture combinations.
It should be noted that after the second collocation object picture combination is generated, the second collocation object picture combination can be used as a new first collocation object picture combination, and the scheme of the present application is executed again, so that more second collocation object picture combinations can be generated.
In this embodiment of the application, for step S101, determining the first combination of collocation object pictures may include: receiving a picture combination recommendation request; and responding to the picture combination recommendation request, and determining a first collocation object picture combination. The picture combination recommendation request is triggered by at least one of the following operations:
executing a predetermined operation for the first collocation object picture combination, such as clicking, browsing or collecting the object picture in the first collocation object picture combination;
operating a recommendation request trigger button displayed by the client and related to the first collocation object picture combination, for example, displaying the recommendation request trigger button shown in fig. 1b on the client; the user can trigger the client to send a picture combination recommendation request by operating (such as clicking, long-pressing or dragging) the button;
and inputting a first collocation object picture combination, namely taking the related information of the first collocation object picture combination as search keyword information.
In practical applications, the at least one operation may be performed by a user on the client, or may be performed automatically by the client according to a preset logic.
In this embodiment, in practical applications, each object in a group of objects that can be collocated with each other may belong to a different category, where the category may be a subclass subdivided from an object class, and taking a common shopping website as an example, the object class may include: apparel, food, books, audiovisual products, household appliances, etc., and further, as for the broad category of apparel, may be classified as: upper body apparel, lower body apparel, shoes, apparel accessories, etc. (for ease of description, the subclasses may be referred to as object classes). Thus, a group of objects that may be paired with one another that fall within this broad category of apparel may include an upper body garment, a lower body garment, a pair of shoes, and an accessory.
In this embodiment, the objects in the collocated object pictures included in the first collocated object picture group belong to different object categories respectively.
Further, it can be seen that, for step S102, the second matching object picture combination is generated mainly according to two types of factors.
The first type factor is the similarity between each object picture in the picture library and each matching object picture contained in the first matching object picture combination. This factor can make the generated second collocation object picture combination similar to the first collocation object picture combination, and further can make objects in each collocation object picture included in the second collocation object picture combination collocate with each other (mutually collocate, that is, coordinate and unify visually, and conform to the public aesthetic sense). The specified condition in step S102 may include that the similarity is not less than a preset threshold, where the preset threshold may be a value between 0 and 100%, and an applicable preset threshold may be determined according to an actual application scenario.
The second type of factor is the associated information of the objects in each object picture in the picture library. Based on the factor, the association information of the objects in the collocated commodity pictures included in the generated second collocated object picture combination can be matched with each other. For convenience of description, the following description will be given taking as an example that the related information of the target picture is the price of the target in the target picture.
When a plurality of second matching object picture combinations are generated, each second matching object picture combination can respectively correspond to different price grades, and therefore, each user with consumption capacity at different levels can search the network commodities which are suitable for the consumption capacity of the user and can be matched with each other according to the corresponding second matching object picture combination.
According to the above description, as shown in fig. 2, the step S102 may specifically include the following sub-steps:
s201: according to the similarity between each object picture in the picture library and each matching object picture contained in the first matching object picture combination, aiming at each matching object picture, respectively screening out each object picture which contains the same object type as the object in the matching object picture and has the similarity with the matching object picture not less than a preset threshold value from each object picture, and forming a similarity picture set corresponding to the matching object picture.
In practical application, the preset threshold value can be set to be 20%, so that the practical effect is better. Obviously, the greater the similarity, the more similar the subsequently generated second collocation object picture combination is to the first collocation object picture combination.
Next, taking an example that all objects in the matching object pictures included in the first matching object picture combination belong to the major class of clothing, a specific implementation process of the scheme in step S201 is described.
All commodity pictures on the shopping website can form the picture library. Suppose that any upper body clothing picture on the shopping website is represented as TjAny one of the lower body clothing pictures on the shopping website is represented as BkAny shoe picture on the shopping website is represented as FkRepresenting any clothing accessory picture on the shopping website as AyWherein j, k, x and y are positive integers.
Assuming that 1 first matching object picture combination is determined, each matching object picture contained in the first matching object picture combination is: an upper body clothing picture, a lower body clothing picture, a shoe picture, a clothing accessory picture, then can be expressed this first collocation object picture combination as:
C0＝(T0,B0,F0,A0)；
wherein, C0Indicates the first matching object picture combination, T, determined in the above step S1010Is represented by C0Upper body clothing picture contained in (B)0Is represented by C0Lower body clothing picture contained in (1), F0Is represented by C0The shoe picture contained in A0Is represented by C0The clothing accessory picture contained in (1).
Assume a total of N on the shopping siteTAn and T0The upper body clothing picture with the similarity not less than the preset threshold value has NBA and B0The lower body clothing picture with the similarity not less than the preset threshold value has NFAn and F0The shoe pictures with the similarity not less than the preset threshold value have NAA and A0The similarity of the images is not less than a preset threshold value. In practical application, when the preset threshold is 20%, N isT、NB、NF、NAThe calculation result of (a) is typically an integer between 20 and 200.
C can be calculated according to the prior art0The similarity between any matching object picture included in the matching object picture and each object picture with the same type on the shopping website is obtained, and a similarity list (namely, the similarity commodity picture set in the embodiment of the application) is obtained.
For example, for T0The obtained similarity list can be expressed as follows:
wherein, T1Is equal to T0Has a similarity of
Upper body clothing picture, T2Is equal to T0Has a similarity of
The picture of the upper body clothes can be analogized,
is equal to T0Has a similarity of
The upper body clothing picture.
Similarly, for B0、F0、A0The similarity lists can be obtained separately and expressed as follows:
as described above, ListT0、ListB0、ListF0、ListA0Wherein each similarity is not less than a preset threshold.
Further, ListT may be used subsequently0、ListB0、ListF0、ListA0Any object picture pair C in (1)0Replacing the matched object picture belonging to the same category as the object picture to obtain' replaced C0". Wherein "substituted C0The objects in the object picture included in "can still be collocated with each other. In addition, the value of "C after replacement" can be measured based on the similarity between the object pictures based on the replacement0And C0The degree of match between them.
For example, suppose C is to be0T in (1)0Is replaced by T1Generating a new collocation object picture combination C'0＝(T1,B0,F0,A0) And then C'0And C0May be equal to T1And T0Degree of similarity of
As another example, suppose C0T in (1)0Is replaced by T1、B0Is replaced by B1、F0Is replaced by F1、A0Is replaced by A1Generating a new matching object picture combination C0＝(T1,B1,F1,A1) Then C ″)0AndC0the matching degree between the object pictures can be equal to the product of the corresponding similarity of each object picture used in the replacement, that is,
s202: and generating a second collocation object picture combination according to the price of the object in each object picture contained in each similarity picture set.
In the above step S201, a method for generating a collocation object picture combination similar to the first collocation object picture combination according to the first collocation object picture combination has been mentioned, but the collocation object picture generated by this method is not enough to completely solve the problems in the background art, and therefore, the method is improved according to the price of the object in each object picture to generate the second collocation object picture combination.
Further, following the above example, the defects of the generated method for combining the images of the matching objects in step S201 are analyzed to derive a specific implementation method of step S202 provided in the embodiment of the present application.
Will be according to C0The combination of collocated object pictures that can be generated is represented as:
Ci＝(Tj,Bk,Fx,Ay)；
wherein i, j, k, x and y are positive integers, j is more than or equal to 1 and is more than or equal to NT，1≤k≤NB，1≤x≤NF，1≤y≤NA，1≤i≤NT×NB×NF×NA。
Apparently, theoretically, according toC0At most N can be generatedT×NB×NF×NAEach matching object picture is combined, and C can be combinediAnd C0The degree of matching is expressed as:
Si＝STj×SBk×SFx×SAy；
wherein S isTjRepresents TjAnd T0Similarity of (D), SBkIs represented by BkAnd B0Similarity of (D), SFxIs represented by FxAnd F0Similarity of (D), SAyIs represented by AyAnd A0The similarity of (c).
However, in practical applications not every CiThe corresponding set of apparel items is suitable for recommendation to the user. There are mainly two problems:
first, each CiPrices of upper body apparel, lower body apparel, shoes, and apparel accessories in a corresponding set of apparel items may not match one another. And users generally tend to select price-matched collocation items.
Price matching can mean that the prices of all matched commodities have a relatively fixed proportional relationship (the proportional relationship can be changed in a certain range), and the prices of all the matched commodities belong to the same or similar price grades in the respective categories. For example, according to daily life experience, the price ratio between price-matched upper body garments, lower body garments, shoes and accessories may be 1: 1: 2: 5, the price ratio may have a floating range of about 50% in practical applications), for example, assuming that the price of the jacket is 300 yuan and the price of the trousers is 1000 yuan, it is obvious that although the jacket and the trousers may be matched with each other visually, they are not suitable for being recommended to the user as matched goods, because the user who wants to buy the jacket with 300 yuan may feel that the trousers with 1000 yuan is too expensive, and the user who wants to buy the trousers with 1000 yuan may feel that the jacket with 300 yuan is too cheap and the grade of the trousers is not matched with 1000 yuan.
Second, due to different CiCan contain partially identical object pictures, and thus, CiA total of NT×NB×NF×NAThe number of the combination modes is huge, and the combination modes can be tens of thousands or even millions. Obviously, in practical application, because the time of the user is limited, it is impossible to browse C corresponding to all combinationsiInstead, only a few (generally no more than 100) combinations of C's are browsedi. In this case, each C that the user may wish to browse throughiThe contained object pictures are not repeated, namely, each C recommended to the useriIn this way, the user can browse the collocation object picture combination which is as many as possible and not repeated (any object picture contained in the collocation object picture combination is not repeated) in a short time, so that the efficiency and the convenience of purchasing mutually-collocated network commodities by the user can be improved.
According to the above analysis, the matching object pictures suitable for recommendation to the user, that is, the generated second matching object picture combination may satisfy the following conditions as much as possible: the second collocation object picture combination is similar to the first collocation object picture combination; the prices of all objects in all object pictures in the second matching object picture combination are mutually matched; each second matching object picture combination does not contain repeated object pictures.
However, if all the second matching object picture combinations satisfying the above conditions are generated according to the first matching object picture combination, the calculation complexity requirement for the generation algorithm is very high, and it is difficult for the shopping website having a large number of object pictures to bear the calculation resource consumption.
Based on such consideration, the embodiment of the present application proposes a method that only consumes linear time based on the greedy idea to implement step S202. As shown in fig. 3, the method may specifically include the following steps:
s301: respectively aiming at each similarity picture set, executing: and sequencing all the object pictures contained in the similarity picture set according to the prices of the objects in the object pictures.
S302: and selecting one similarity picture set from each sorted similarity picture set as a reference set.
S303: and sequentially taking each target picture contained in the reference set as a reference picture, and executing the following steps for the reference picture: and judging whether a target object picture with the price of the included object matched with the price of the object in the reference picture exists in the object pictures respectively contained in each sorted and unselected similarity picture set, and if so, generating a second collocation object picture combination by the reference picture and each target object picture.
Further, in step S303, a target object picture whose price of an object included in each sorted and unselected similarity picture set matches the price of an object in the reference picture may be determined according to the following method:
and according to the arrangement sequence of all the object pictures contained in the sorted and unselected similarity picture set, sequentially judging whether the prices of the specified object picture and the objects in each object picture behind the specified object picture fall within a specified price interval or not from the specified object picture in all the object pictures, and when the judgment result is yes at least once, determining the first object picture falling within the specified price interval as the object picture with the price of the contained object matched with the price of the object in the reference picture, otherwise, determining the object picture to fail.
Wherein the designated price interval may be determined according to the price of the object in the reference picture. More specifically, the designated price interval may be determined according to the price of the object in the reference picture and a preset price ratio corresponding to each object category.
A previous object picture of the designated object picture may be included in the generated second collocation object picture combination, and all object pictures located after the designated object picture are not included in the generated second collocation object picture combination; or, the designated object picture is a first object picture in the object pictures, and all object pictures located after the designated object picture are not included in the generated second collocation object picture combination.
In order to reduce the calculation amount as much as possible, in practical application, the above scheme can be implemented by using a pointer. The following describes the implementation of the schemes in steps S301 to S303, using the above examples in steps S201 and S202.
First, four similarity lists ListT may be listed0、ListB0、ListF0、ListA0The objects in the object picture are reordered from low to high (in this example, the order from low to high is adopted) or are represented as a new list correspondingly, according to the order from low to high, respectively, as follows:
wherein the content of the first and second substances,
represents T1The price of the object in (1) and so on, which are not described herein again.
Suppose that PriceListT is selected0As a reference set, then priceisb0、PriceListF0、PriceListA0All as the picture set to be matched.
As shown in FIG. 4, PriceListT0、PriceListB0、PriceListF0、PriceListA0Respectively expressed by the data structure of the linked list, and T is0Inserted as head node in linked list PriceListT0A head of (B)0Inserted as head node in linked list PriceListB0A head of (D) A, B0Inserted as head node in linked list PriceListF0A head of (A)0Inserted as head node in linked list PriceListA0Defines 4 pointers PTT、PTB、PTF、PTAInitially point to T in the above-mentioned linked list respectively0、B0、F0、A0。
Fig. 5 shows the process of implementing the step S303 by the 4 pointers in this example, which may specifically include the following steps:
s501: judging PTT、PTB、PTF、PTAIf the tail parts of the corresponding linked lists are pointed, the process is ended, otherwise, the step S502 is executed.
S502: will PTTPlus 1, point to the next object picture in the corresponding linked list, where PTTThe real-time pointed object picture is recorded as Ti，TiThe price of the object in (1) is recorded
S503: record PTB、PTF、PTACurrent pointing object pictures, respectively for PTB、PTF、PTATraversing the linked lists corresponding to the pointers from the object picture currently pointed by each pointer to try to determine the price and PT of the latest object contained in each linked listTAnd the prices of the objects in the pointed object pictures are matched with each other.
S504: it is determined whether the determination in step S503 is successful, if yes, step S505 is executed, otherwise, the determination is failed, and step S506 is executed.
S505: output PTT、PTB、PTF、PTAThe current pointed object picture as the generated one and TiThe corresponding second matching object picture combination is returned to execute step S501.
S506: will PTB、PTF、PTAThe target pictures pointed to at the beginning of step S503 are pointed to, and the process returns to step S501.
Further, with PT onlyBFor example, the implementation of the above step S503 will be described (PT)F、PTASimilarly), as shown in fig. 6, the method may specifically include the following steps:
s601: record PTBPicture of object currently pointed to, according to PTTDetermining PT based on the price of the object in the current pointed object picture and the preset price ratio between the upper clothing object class and the lower clothing object classTCurrently pointed to object picture TiThe corresponding designated price interval is recorded as
Following the examples given in the background, the price ratio between price matched upper body garments, lower body garments, shoes and accessories of the apparel 1: 1: 2: 5, and may have a 50% floating range. Then PT is assumedTThe price of the object in the current pointed object picture is 500 yuan, and according to the price ratio (and the floating range), the price corresponding to the object picture can be calculated
Equal to 250 yuan, corresponding to the object picture
Equal to 750 bins. Similarly, it may also be PTFThe corresponding designated price interval (500 yuan to 1000 yuan) is also calculated as PTAThe corresponding designated price interval (1250 yuan to 3750 yuan) is also calculated.
S602: will PTBPlus 1, point to the next object picture in the corresponding linked list, wherePTBThe real-time pointed object picture is marked as Bj，BjThe price of the object in (1) is recorded
S603: judgment of
Whether or not less than
If yes, the process returns to step S602, otherwise, step S604 is performed.
S604: judgment of
Whether or not greater than
If so, go to step S605, otherwise go to step S606.
S605: a failure is determined.
S606: determining success, and comparing BjDetermining a price and PT for a recently included objectTAnd the prices of the objects in the pointed object pictures are matched with each other.
In the embodiment of the application, after the second matching object picture combination is generated, the second matching object picture combination can be recommended to the user, and the recommending mode can be that the second matching object picture combination is actively pushed to a terminal of the user for the user to browse, or the second matching object picture combination can be sent to the terminal of the user after a recommendation request sent by the user through the terminal is received, so that the user can browse.
In practical applications, after recommending the second combination of matching object pictures to the user, the user may send a request for obtaining other related information (such as object information, payment page, etc.) to the server based on the second combination of matching object pictures. In this case, the server may further perform: receiving an operation request aiming at the recommended second collocation object picture combination; and responding to the operation request, and executing corresponding operation.
Further, the performing of the corresponding operation may include at least one of: pushing or displaying object information related to the recommended second matching object picture combination; pushing or displaying a payment page for an object in the object pictures included in the recommended second collocated object picture combination.
In the method for generating a collocation object picture combination provided in the embodiment of the present application, further, in practical applications, in order to facilitate recommendation of a generated second collocation object picture combination to a User, a corresponding User Interface (UI) may be provided for the User. In the above fig. 1b, besides a recommendation request trigger button, a user interface for matching and recommending network goods is also shown in practical application. FIG. 1b is further described below.
It can be seen that a first combination of matching object pictures (or a second combination of matching object pictures that has been generated) belonging to the category of apparel pictures is being presented on the user interface, including an upper garment picture (picture of chiffon), a lower garment picture (picture of shorts), a shoe picture (picture of high heels), a picture of apparel accessories (picture of handbags).
The control (i.e., the recommendation request trigger button) for matching the object with the clothing category may be set for each clothing category, where the control may be in the form of a button, a scroll bar, a slider, and the like, and the attributes of the control, such as shape, color, and shadow, may also be set arbitrarily (in fig. 1b, a triangular button control is used, and two sides of each object picture are provided with one button control, which may be used to switch forward and backward matching object pictures).
Specifically, the effects that can be achieved by clicking the control include, but are not limited to, the following two, which can be achieved alternatively or simultaneously in practical applications according to user requirements:
clicking the control can correspondingly switch the group of object pictures displayed on the user interface into the collocation object picture combination which is generated by adopting the generation method of the collocation object picture combination provided by the embodiment of the application and has similar style and matched price with the group of object pictures. That is, all 4 object pictures on the user interface are switched, and an object in each object picture displayed after switching and an object in a corresponding object picture before switching belong to the same object class, and prices of objects in each object picture displayed after switching are matched with each other.
In practical application, the clicking control does not switch all the group of object pictures, but only switches the object picture corresponding to the clicked control to another similar object picture. For example, clicking on a button control contained in the dashed circle in FIG. 1b can switch a shorts picture in the user interface to another similar lower body garment picture.
It should be noted that, the above description mainly takes the object and the object picture of the clothing object class as an example, and the generation method of the collocation object picture combination provided by the present application is also applicable to the object and the object picture of other object classes (such as mobile phones, home appliances, and the like), and is not described herein again.
Based on the same idea, the above method for generating a combination of matching object pictures provided in this embodiment of the present application further provides a corresponding device for generating a combination of matching object pictures, as shown in fig. 7.
Fig. 7 is a schematic structural diagram of a device for generating a collocation object picture combination according to an embodiment of the present application, which specifically includes:
a determining module 701, configured to determine a first collocation object picture combination;
a generating module 702, configured to generate a second matching object picture combination according to the similarity between each object picture in the picture library and each matching object picture included in the first matching object picture combination, and the associated information of the object picture in which the corresponding similarity meets the specified condition in each object picture.
The objects in the collocated object pictures included in the first collocated object picture combination belong to different object categories respectively.
The specified conditions comprise that the similarity is not less than a preset threshold value; the associated information of the collocation object picture comprises the price of the object in the collocation object picture;
the generating module 702 is specifically configured to: according to the similarity between each object picture in a picture library and each matching object picture contained in the first matching object picture combination, aiming at each matching object picture, respectively screening out each object picture which contains an object and an object in the matching object picture, belong to the same object class, and has the similarity with the matching object picture not less than a preset threshold value, and forming a similarity picture set corresponding to the matching object picture; and generating a second collocation object picture combination according to the price of the object in each object picture contained in each similarity picture set.
The generating module 702 is specifically configured to: respectively aiming at each similarity picture set, executing: sequencing all the object pictures contained in the similarity picture set according to the prices of the objects in the object pictures; selecting one similarity picture set from each sorted similarity picture set as a reference set; and sequentially taking each target picture contained in the reference set as a reference picture, and executing the following steps for the reference picture: and judging whether a target object picture with the price of the included object matched with the price of the object in the reference picture exists in the object pictures respectively contained in each sorted and unselected similarity picture set, and if so, generating a second collocation object picture combination by the reference picture and each target object picture.
In this case, the generating module 702 is specifically configured to determine, in the object pictures respectively included in each sorted and unselected similarity picture set, a target object picture whose price of the included object matches the price of the object in the reference picture according to the following method: according to the arrangement sequence of all object pictures contained in the sorted and unselected similarity picture set, sequentially judging whether the prices of the specified object pictures and objects in each object picture behind the specified object pictures fall within a specified price interval or not from the specified object pictures in all the object pictures, and when the judgment result is yes at least once, determining the first object picture falling within the specified price interval as the object picture with the price of the contained object matched with the price of the object in the reference picture, otherwise, determining the object picture to fail; wherein the designated price interval is determined according to the price of the object in the reference picture.
The device further comprises:
and a recommending module 703, configured to recommend the at least one generated second matching object picture combination to the user.
The determining module 701 is specifically configured to: receiving a picture combination recommendation request; and responding to the picture combination recommendation request, and determining a first collocation object picture combination.
The picture combination recommendation request is triggered by at least one of the following operations:
executing a predetermined operation for the first collocation object picture combination;
operating a recommendation request trigger button which is displayed by a client and is related to the first collocation object picture combination;
and inputting a first collocation object picture combination.
The device further comprises:
an operation module 704, configured to receive an operation request for a recommended second matching object picture combination after the recommendation module recommends at least one generated second matching object picture combination to a user; and responding to the operation request, and executing corresponding operation.
The operation module is specifically configured to perform at least one of the following corresponding operations:
pushing or displaying object information related to the recommended second matching object picture combination;
pushing or displaying a payment page for an object in the object pictures included in the recommended second collocated object picture combination.
The apparatus shown in fig. 7 may be located on a server.
By using the device, the second collocation object picture combination can be automatically generated based on any first collocation object picture combination, so that the number of the collocation object picture combinations can be increased, and the server can provide more reference information for the user based on the increased collocation object picture combination.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (22)
1. A generation method of a collocation object picture combination is characterized by comprising the following steps:
determining a first collocation object picture combination;
generating a second collocation object picture combination according to the similarity between each object picture in a picture library and each collocation object picture contained in the first collocation object picture combination and the corresponding correlation information of the object picture of which the similarity meets the specified conditions in each object picture, wherein the correlation information of part or all of the collocation object pictures contained in the second collocation object picture combination is matched with each other;
wherein the specified condition includes that the similarity is not less than a preset threshold; generating a second collocation object picture combination according to the similarity between each object picture in the picture library and each collocation object picture contained in the first collocation object picture combination and the corresponding associated information of the object picture of which the corresponding similarity meets the specified conditions in each object picture, and specifically comprises the following steps:
according to the similarity between each object picture in a picture library and each matching object picture contained in the first matching object picture combination, aiming at each matching object picture, respectively screening out each object picture which contains an object and an object in the matching object picture, belong to the same object class, and has the similarity with the matching object picture not less than a preset threshold value, and forming a similarity picture set corresponding to the matching object picture;
and generating a second collocation object picture combination according to the associated information of each object picture contained in each similarity picture set.
2. The method of claim 1, wherein the objects in the collocated object pictures included in the first collocated object picture group belong to different object classes respectively.
3. The method of claim 2, wherein the associated information of the collocated object picture includes a price of an object in the collocated object picture;
generating a second collocation object picture combination according to the associated information of each object picture contained in each similarity picture set, specifically comprising:
and generating a second collocation object picture combination according to the price of the object in each object picture contained in each similarity picture set.
4. The method of claim 3, wherein generating a second collocated object picture combination according to prices of objects in object pictures included in the similarity picture sets comprises:
respectively aiming at each similarity picture set, executing: sequencing all the object pictures contained in the similarity picture set according to the prices of the objects in the object pictures;
selecting one similarity picture set from each sorted similarity picture set as a reference set;
and sequentially taking each target picture contained in the reference set as a reference picture, and executing the following steps for the reference picture:
and judging whether a target object picture with the price of the included object matched with the price of the object in the reference picture exists in the object pictures respectively contained in each sorted and unselected similarity picture set, and if so, generating a second collocation object picture combination by the reference picture and each target object picture.
5. The method of claim 1, wherein the determined second combination of collocated object pictures does not contain the same object picture.
6. The method according to claim 4, wherein, in the object pictures respectively contained in each sorted and unselected similarity picture set, a target object picture is determined, in which the price of the contained object matches the price of the object in the reference picture, according to the following method:
according to the arrangement sequence of all object pictures contained in the sorted and unselected similarity picture set, sequentially judging whether the prices of the specified object pictures and objects in each object picture behind the specified object pictures fall within a specified price interval or not from the specified object pictures in all the object pictures, and when the judgment result is yes at least once, determining the first object picture falling within the specified price interval as the object picture with the price of the contained object matched with the price of the object in the reference picture, otherwise, determining the object picture to fail;
wherein the designated price interval is determined according to the price of the object in the reference picture.
7. The method of any of claims 1 to 6, further comprising:
and recommending at least one generated second collocation object picture combination to the user.
8. The method of claim 1, wherein determining a first collocation object picture combination comprises:
receiving a picture combination recommendation request;
and responding to the picture combination recommendation request, and determining a first collocation object picture combination.
9. The method of claim 8, wherein the request for recommending picture composition is triggered by at least one of:
executing a predetermined operation for the first collocation object picture combination;
operating a recommendation request trigger button which is displayed by a client and is related to the first collocation object picture combination;
and inputting a first collocation object picture combination.
10. The method of claim 7, wherein after recommending the at least one generated second collocation object picture combination to the user, the method further comprises:
receiving an operation request aiming at the recommended second collocation object picture combination;
and responding to the operation request, and executing corresponding operation.
11. The method of claim 10, wherein performing the respective operation comprises at least one of:
pushing or displaying object information related to the recommended second matching object picture combination;
pushing or displaying a payment page for an object in the object pictures included in the recommended second collocated object picture combination.
12. An apparatus for generating a combination of pictures of a matching object, comprising:
the determining module is used for determining the first collocation object picture combination;
a generating module, configured to generate a second matching object picture combination according to similarity between each object picture in the picture library and each matching object picture included in the first matching object picture combination and correlation information of object pictures in each object picture, where the corresponding similarity meets a specified condition, and correlation information of some or all matching object pictures included in the second matching object picture combination is matched with each other;
wherein the specified condition includes that the similarity is not less than a preset threshold; the generation module is specifically configured to: according to the similarity between each object picture in a picture library and each matching object picture contained in the first matching object picture combination, aiming at each matching object picture, respectively screening out each object picture which contains an object and an object in the matching object picture, belong to the same object class, and has the similarity with the matching object picture not less than a preset threshold value, and forming a similarity picture set corresponding to the matching object picture; and generating a second collocation object picture combination according to the associated information of each object picture contained in each similarity picture set.
13. The apparatus of claim 12, wherein objects in the collocated object pictures included in the first collocated object picture group belong to different object classes respectively.
14. The apparatus of claim 13, wherein the association information of the collocated object picture includes a price of an object in the collocated object picture;
the generation module is specifically configured to: and generating a second collocation object picture combination according to the price of the object in each object picture contained in each similarity picture set.
15. The apparatus of claim 14, wherein the generation module is specifically configured to: respectively aiming at each similarity picture set, executing: sequencing all the object pictures contained in the similarity picture set according to the prices of the objects in the object pictures; selecting one similarity picture set from each sorted similarity picture set as a reference set; and sequentially taking each target picture contained in the reference set as a reference picture, and executing the following steps for the reference picture: and judging whether a target object picture with the price of the included object matched with the price of the object in the reference picture exists in the object pictures respectively contained in each sorted and unselected similarity picture set, and if so, generating a second collocation object picture combination by the reference picture and each target object picture.
16. The apparatus of claim 12, wherein each of the determined second combination of collocated object pictures does not contain the same object picture.
17. The apparatus according to claim 15, wherein the generating module is specifically configured to determine, from the object pictures respectively included in the sorted and unselected similarity picture sets, a target object picture whose price of the included object matches the price of the object in the reference picture, according to the following method: according to the arrangement sequence of all object pictures contained in the sorted and unselected similarity picture set, sequentially judging whether the prices of the specified object pictures and objects in each object picture behind the specified object pictures fall within a specified price interval or not from the specified object pictures in all the object pictures, and when the judgment result is yes at least once, determining the first object picture falling within the specified price interval as the object picture with the price of the contained object matched with the price of the object in the reference picture, otherwise, determining the object picture to fail; wherein the designated price interval is determined according to the price of the object in the reference picture.
18. The apparatus of any of claims 12 to 17, further comprising:
and the recommending module is used for recommending at least one generated second collocation object picture combination to the user.
19. The apparatus of claim 12, wherein the determination module is specifically configured to: receiving a picture combination recommendation request; and responding to the picture combination recommendation request, and determining a first collocation object picture combination.
20. The apparatus of claim 19, wherein the request for recommending picture composition is triggered by at least one of:
executing a predetermined operation for the first collocation object picture combination;
operating a recommendation request trigger button which is displayed by a client and is related to the first collocation object picture combination;
and inputting a first collocation object picture combination.
21. The apparatus of claim 18, wherein the apparatus further comprises:
the operation module is used for receiving an operation request aiming at the recommended second collocation object picture combination after the recommendation module recommends at least one generated second collocation object picture combination to the user; and responding to the operation request, and executing corresponding operation.
22. The apparatus as claimed in claim 21, wherein said operation module is specifically configured to perform at least one of the following corresponding operations:
pushing or displaying object information related to the recommended second matching object picture combination;
pushing or displaying a payment page for an object in the object pictures included in the recommended second collocated object picture combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510831134.2A CN106779791B (en) | 2015-11-25 | 2015-11-25 | Generation method and device for collocation object picture combination |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510831134.2A CN106779791B (en) | 2015-11-25 | 2015-11-25 | Generation method and device for collocation object picture combination |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106779791A CN106779791A (en) | 2017-05-31 |
| CN106779791B true CN106779791B (en) | 2021-01-15 |
Family
ID=58964160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510831134.2A Active CN106779791B (en) | 2015-11-25 | 2015-11-25 | Generation method and device for collocation object picture combination |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106779791B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679155A (en) * | 2017-09-27 | 2018-02-09 | 百度在线网络技术（北京）有限公司 | Clothing matching storehouse method for building up, information recommendation method, device, equipment and medium |
| CN109785276A (en) * | 2017-11-10 | 2019-05-21 | 阿里巴巴集团控股有限公司 | A kind of synthetic method and device of business object picture |
| CN107967095A (en) * | 2017-11-24 | 2018-04-27 | 天脉聚源（北京）科技有限公司 | A kind of image display method and device |
| CN108228790B (en) * | 2017-12-29 | 2021-09-28 | 北京奇虎科技有限公司 | Display method and device of pushed pictures |
| CN111093025B (en) * | 2019-12-30 | 2021-07-30 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| 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 |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477560A (en) * | 2009-02-02 | 2009-07-08 | 林�智 | Clothing matching system and method based on scheme database |
| CN103136228A (en) * | 2011-11-25 | 2013-06-05 | 阿里巴巴集团控股有限公司 | Image search method and image search device |
| CN103177110A (en) * | 2013-03-28 | 2013-06-26 | 百度在线网络技术（北京）有限公司 | Whole set image searching method and whole set image searching equipment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012176317A1 (en) * | 2011-06-23 | 2012-12-27 | サイバーアイ・エンタテインメント株式会社 | Image recognition system-equipped interest graph collection system using relationship search |
-
2015
- 2015-11-25 CN CN201510831134.2A patent/CN106779791B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101477560A (en) * | 2009-02-02 | 2009-07-08 | 林�智 | Clothing matching system and method based on scheme database |
| CN103136228A (en) * | 2011-11-25 | 2013-06-05 | 阿里巴巴集团控股有限公司 | Image search method and image search device |
| CN103177110A (en) * | 2013-03-28 | 2013-06-26 | 百度在线网络技术（北京）有限公司 | Whole set image searching method and whole set image searching equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106779791A (en) | 2017-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106779791B (en) | Generation method and device for collocation object picture combination | |
| US10715478B2 (en) | Event-based comment grouping for content items | |
| CN108027701B (en) | Touch screen user interface for presenting media | |
| CN110020194B (en) | Resource recommendation method, device and medium | |
| CN106570714B (en) | Recommendation method for matching object picture, and mapping relation establishment method and device | |
| US20130311340A1 (en) | Systems and methods for displaying items | |
| CN110636325B (en) | Method and device for sharing push information on live broadcast platform and storage medium | |
| US20210208748A1 (en) | Recommending different song recording versions based on a particular song recording version | |
| US11627362B2 (en) | Touch gesture control of video playback | |
| US20200226168A1 (en) | Methods and systems for optimizing display of user content | |
| US20200226651A1 (en) | Methods and systems for product discovery in user generated content | |
| US10091556B1 (en) | Relating items to objects detected in media | |
| JP2019526097A (en) | Method, apparatus, and system for generating juxtaposed rendering | |
| US20230030560A1 (en) | Methods and systems for tagged image generation | |
| CN113849682A (en) | Video searching method, device, equipment and medium | |
| CN111815404A (en) | Virtual article sharing method and device | |
| US20160205447A1 (en) | Associating collections with subjects | |
| US11227189B2 (en) | Systems and methods for identifying items in a digital image | |
| CN111199443A (en) | Commodity information processing method, commodity information processing device and computer-readable storage medium | |
| CN109102177A (en) | Processing method, device and the equipment of cloud shelf | |
| US11048975B2 (en) | Systems and methods for identifying items in a digital image | |
| CN110020070A (en) | Webpage circle selects data processing method, apparatus and system | |
| CN115578143A (en) | Page information processing method, device, equipment and storage medium | |
| CN114677190A (en) | Method, device and system for processing visual material and computer terminal | |
| US20200226167A1 (en) | Methods and systems for dynamic content provisioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |