CN111582979A - Clothing matching recommendation method and device and electronic equipment - Google Patents
Clothing matching recommendation method and device and electronic equipment Download PDFInfo
- Publication number
- CN111582979A CN111582979A CN202010358230.0A CN202010358230A CN111582979A CN 111582979 A CN111582979 A CN 111582979A CN 202010358230 A CN202010358230 A CN 202010358230A CN 111582979 A CN111582979 A CN 111582979A
- Authority
- CN
- China
- Prior art keywords
- accessory
- target
- accessories
- score
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000015654 memory Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003860 storage Methods 0.000 description 8
- 230000003993 interaction Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2431—Multiple classes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a clothing matching recommendation method and device and electronic equipment. Wherein, the method comprises the following steps: obtaining picture information of a target garment; calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes; the matching score between the picture information and each accessory in the second accessory set is calculated, the accessory with the score larger than or equal to the first preset threshold value is recommended to the target user, the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, the purpose that the accessory which belongs to the same brand with the target clothes and is favored by the public is recommended for the target clothes from the big data of the accessory matching set is achieved, and the technical problem that effective suggestions cannot be obtained when the accessory information for matching the target clothes is obtained in the prior art is solved.
Description
Technical Field
The invention relates to the field of information processing, in particular to a clothing matching recommendation method and device and electronic equipment.
Background
Along with the development of production, the grades of variety and style change of clothing products are rich and complex, and meanwhile, the requirements of people on clothing and accessories are increasingly improved. In the face of clothes with complex varieties and styles, people usually want to obtain professional and scientific matching suggestions.
At present, when a user selects clothes or accessories of the clothes during online shopping or shopping, matched accessories and clothes are generally obtained by reading fashionable magazines or other shop window displays of merchants, targeted matching help is difficult to obtain, and better shopping experience cannot be provided for the user.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a clothing matching recommendation method and device and electronic equipment, and at least solves the technical problem that effective suggestions cannot be obtained when accessory information of matching target clothing is obtained in the prior art.
According to an aspect of an embodiment of the present invention, a clothing matching recommendation method is provided, including: acquiring picture information of a target garment; calculating the similarity between the picture information and each accessory in a first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the scores larger than or equal to a first preset threshold value to a target user, wherein the score is used for representing the degree of the matching between the target clothes and the accessories in the second accessory set, and the higher the score is, the more popular the matching is.
According to another aspect of the embodiments of the present invention, there is also provided a clothing matching recommendation device, including: the first acquisition unit is used for acquiring the picture information of the target clothes; the determining unit is used for calculating the similarity between the picture information and each accessory in a first accessory library and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes; and the first recommending unit is used for calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessory with the score being larger than or equal to a first preset threshold value to a target user, wherein the score is used for indicating the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the score is more popular as the score is higher.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, in which a computer program is stored, where the computer program is configured to execute the clothing collocation recommendation method when running.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the clothing matching recommendation method through the computer program.
In the embodiment of the invention, the picture information of the target clothes is obtained; calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the target clothes belonging to the same brand; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being more than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the accessories are, so that the aim of recommending the accessories which belong to the same brand with the target clothes and are favored by the public from the big data of the accessory matching set is fulfilled, thereby realizing the technical effect of obtaining the accessories of the target clothes from massive data, and further solving the technical problem that effective suggestions can not be obtained in obtaining the accessory information of the matching target clothes in the prior art.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a schematic diagram of an application environment of an alternative clothing matching recommendation method according to an embodiment of the invention;
FIG. 2 is a flow chart of an alternative clothing collocation recommendation method according to an embodiment of the invention;
FIG. 3 is a schematic structural diagram of an alternative clothing collocation recommendation device according to an embodiment of the invention;
fig. 4 is a schematic structural diagram of an electronic device of an optional clothing matching recommendation method according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
According to an aspect of the embodiments of the present invention, a clothing matching recommendation method is provided, optionally, as an optional implementation, the clothing matching recommendation method may be applied to, but not limited to, an environment as shown in fig. 1.
The terminal device 102 may include, but is not limited to: a human-computer interaction screen 104, a processor 106 and a memory 108. The man-machine interaction screen 104 is used for acquiring a man-machine interaction instruction through a man-machine interaction interface and is also used for presenting picture information of the target clothes; the processor 106 is configured to push accessory information of the target apparel in response to the human-computer interaction instruction. The memory 108 is used for storing the target clothes picture information, the first accessory set, the second accessory set, the similarity information and the like. Here, the server may include but is not limited to: the database 114 and the processing engine 116, the processing engine 116 is configured to invoke the first accessory set stored in the database 114, calculate a similarity between the picture information and each accessory in the first accessory library, and determine a second accessory set corresponding to the target accessory, where the similarity is used to represent a similarity between the accessory and the accessory belonging to the same brand of the target accessory; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being more than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the accessories are, so that the aim of recommending the accessories which belong to the same brand with the target clothes and are favored by the public from the big data of the accessory matching set is fulfilled, thereby realizing the technical effect of obtaining the accessories of the target clothes from massive data, and further solving the technical problem that effective suggestions can not be obtained in obtaining the accessory information of the matching target clothes in the prior art.
The specific process comprises the following steps: the man-machine interaction screen 104 in the terminal device 102 displays the picture information of the target clothes. In steps S102-S108, the picture information of the target clothes is obtained and sent to the server 112 via the network 110. Calculating the similarity between the picture information and each accessory in the first accessory library at the server 112, and determining a second accessory set corresponding to the target accessory, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target accessory; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the scores larger than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the matching is. And then returns the determined result to the terminal device 102.
Then, in step S102-S108, the terminal device 102 obtains the picture information of the target clothes; calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the target clothes belonging to the same brand; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being more than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the accessories are, so that the aim of recommending the accessories which belong to the same brand with the target clothes and are favored by the public from the big data of the accessory matching set is fulfilled, thereby realizing the technical effect of obtaining the accessories of the target clothes from massive data, and further solving the technical problem that effective suggestions can not be obtained in obtaining the accessory information of the matching target clothes in the prior art.
Optionally, in this embodiment, the terminal device 102 may be a terminal device configured with a target client, and may include but is not limited to at least one of the following: mobile phones (such as Android phones, iOS phones, etc.), notebook computers, tablet computers, palm computers, MID (Mobile Internet Devices), PAD, desktop computers, smart televisions, etc. The target client may be a video client, an instant messaging client, a browser client, an educational client, etc. Such networks may include, but are not limited to: a wired network, a wireless network, wherein the wired network comprises: a local area network, a metropolitan area network, and a wide area network, the wireless network comprising: bluetooth, WIFI, and other networks that enable wireless communication. The server may be a single server, a server cluster composed of a plurality of servers, or a cloud server. The above is merely an example, and this is not limited in this embodiment.
Optionally, as an optional implementation manner, as shown in fig. 2, the clothing matching recommendation method includes:
and step S202, acquiring picture information of the target clothes.
Step S204, calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes.
Step S206, calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being greater than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the matching is.
Optionally, the solution of the present embodiment may include but is not limited to be applied to: firstly, when a user enters a detailed page of a certain commodity, if the matched commodity exists, the commodity can be recommended to the user according to a certain rule; secondly, after the user adds the commodities into the shopping cart (for example, in the scene of WeChat ecology, each mall is an independent shop), the matched commodities are recommended to the user according to another rule.
It should be noted that the image information of the target clothes may be clothes selected by the user in online shopping, and the clothes may include, but are not limited to, coats, trousers, and the like. Selecting the accessories which can be matched with the clothes according to the clothes, calculating the accessories which belong to the same brand with the clothes in each accessory, and calculating the accessories which are fashionable relative to the clothes matching after determining all the accessories which can be matched with the clothes.
Taking the apparel as an example of a jacket, the first accessory set stores accessories that can be matched with the jacket, such as necklaces and trousers that can be matched with the jacket, but the accessories in the first accessory set include accessories in a plurality of brands, so as to select the accessories corresponding to the jacket conveniently, the accessories are selected from the same shop as the jacket, so that a second accessory set is determined, and the trousers or necklaces matched with the jacket are selected from the second accessory set. Thereby promoting the sales volume of the shops where the jacket is located.
In practical applications, since the collocation library (the first accessory set) is derived from each brand party, and data of each brand party is separated, when one brand party purchases, products of other brands cannot be recommended. Therefore, it is also necessary to calculate the similarity between the collocated goods and the same category of the brand, screen out the goods greater than a certain threshold, and record the similarity result S2. Matching score S of each accessory and the commodity1Corresponding to S2And multiplying to obtain a final similarity result, sequencing the final similarity result, and recommending the first K commodities to the user. The method can be applied to recommending collocation to the commodity detail page when the user clicks the commodity detail page.
Optionally, in this embodiment, calculating a similarity between the picture information and each accessory in the first accessory library, and determining the second accessory set corresponding to the target garment may include:
acquiring picture information;
inputting the picture information into a deep neural network model, and determining the similarity between the picture information and each accessory in a first accessory library, wherein the deep neural network is the deep neural network model trained according to different types of clothing sample pictures;
and determining the similarity with the similarity greater than or equal to a second preset threshold value as the accessory in the second accessory set.
Note that, the commodity (clothing) data: the commodity data is stored in a commodity database, and the attributes of the commodity data are as follows: the commodity ID, the commodity name, the brand to which the commodity belongs, the commodity price, the commodity picture, the commodity category and other attributes.
In order to recommend matched commodities to a user, a batch of matched data needs to be generated in advance to serve as a pre-training sample. These data may be provided by brands, i.e. each brand may provide a batch of collocation data, the data content being in the form of: service A (item ID) may be collocated with B, C, D and provide a corresponding buyer show, thus associating a particular item with the item with which it can be collocated. When the matching is stored, the matched picture and the matched commodity ID are stored and are associated with the commodity data.
Meanwhile, each brand can not provide the full amount of matching data, but information interaction among the brands can obtain richer clothing matching data. In order to enrich the collocation data, other methods can be adopted, for example, a mode of information collection (obtaining the collocation of people from social platforms such as small red books and ins) or a manual scoring mode can be adopted to select excellent seller shows from the seller shows as new collocation.
Optionally, in this embodiment, calculating a matching score between the picture information and each accessory in the second accessory set, and recommending accessories with scores greater than or equal to a first predetermined threshold to the target user, includes:
and generating a matching picture by the accessory with the score larger than or equal to the first preset threshold value and the target clothes, and pushing the matching picture to the target user.
Optionally, in this embodiment, calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessory with the score greater than or equal to the first predetermined threshold to the target user may include:
acquiring accessory data matched with a target garment in a plurality of application platforms;
ordering the accessory data according to the degree of user preference;
and determining the matching score between the target clothes and accessories according to the sequencing result.
As an optional embodiment, after obtaining the picture information of the target apparel, the method may further include:
acquiring all other accessory information belonging to the same application interface with the target clothes, wherein the time for adding other accessories into the application interface is earlier than that of the target clothes;
calculating matching scores between the target clothes and all other accessories;
and recommending the accessory corresponding to the score greater than or equal to the third threshold value to the target user after the target clothes are added into the application interface.
The scheme of the embodiment can be applied to recommending collocation to the user after the user joins the shopping cart. The shopping cart has a plurality of commodities, the image similarity of each commodity in the shopping cart and the same category commodity in the matching library is calculated, the matching pair with the calculated similarity is obtained as the rule 1, and if no commodity in the matching pair exists in the shopping cart, the matching pair is the same as the rule 1.
If the matching center commodity set exists, the items with high similarity to the items added into the shopping cart by the user are preferentially recommended (the similarity of the items is detailed after calculation). For example, A, B, C, D is added to the shopping cart by the user, wherein A and B, A and C, A and D can form matching, the similarity of matching with the person is known, and the similarity of BCD and each of the same category commodities is calculated respectively. And multiplying the similarity by a coefficient alpha, adding the corresponding matching similarity of the people who arrive and multiplying the coefficient beta to obtain the final similarity, and recommending the final similarity to the user in a descending order. This is due to the shopping habit of the user, who thinks that the items that the user adds to the shopping cart are more suitable for the taste of the user, and the coefficients are used to control the specific gravity of the items in order to be close to the taste of the user and to match the similarity with the arrival similarity.
It should be noted that another method may be adopted: the CNN classifies the two types of the data, and the classification result is 1: similarly, 0: are not similar. The above scheme can be recommended randomly without calculating the threshold. For example, assuming that the product ID selected by the user is a and there is a matching library set D, where | D | ═ N, two classifications are performed on each of the products of the same category in a and D, and the product with the classification result of 1 is selected to obtain a { matching product, matching result } pair. For the obtained collocated goods, we need further processing: since the collocation database is derived from each brand party, and the data of each brand party is separated, when one brand party purchases, products of other brands cannot be recommended. Therefore, the matched commodities and the similar commodities need to be selected, and K commodities are randomly selected to be recommended to the user.
It should be further noted that the calculation of the similarity of the articles may include:
for the item similarity, consider the following indicators: price, title similarity (which may be calculated by word-shift distance, tfidf, etc.), category and picture similarity. Consider calculating the similarity of item a and item B.
The articles need to belong to the same category, so that different categories impose large punishment, and when the categories are different, the punishment value is 10; if picture similarity calculation is adopted, the picture similarity can be used as a calculated component, and if the two classifications are adopted, great punishment is applied to the pictures which are not judged to be similar, just like the classification.
If the picture similarity calculation is adopted, the calculation method is as follows:
s＝α(priceA-priceB)+β(similartitleAB)+γ(similarpicAB)+C1
wherein, C1Is a class penalty value.
Optionally, in this embodiment, after adding the target apparel to the application interface, recommending, to the target user, the accessory corresponding to the score being greater than or equal to the third threshold, may include:
and pushing the picture information of the target user, which is obtained by matching the accessory corresponding to the score greater than or equal to the third threshold value with the target clothes.
According to the embodiment provided by the application, the picture information of the target clothes is obtained; calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the target clothes belonging to the same brand; and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being more than or equal to a first preset threshold value to the target user, wherein the score is used for representing the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the higher the score is, the more popular the accessories are, so that the aim of recommending the accessories which belong to the same brand with the target clothes and are favored by the public from the big data of the accessory matching set is fulfilled, thereby realizing the technical effect of obtaining the accessories of the target clothes from massive data, and further solving the technical problem that effective suggestions can not be obtained in obtaining the accessory information of the matching target clothes in the prior art.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
According to another aspect of the embodiment of the invention, a clothing matching recommendation device for implementing the clothing matching recommendation method is further provided. As shown in fig. 3, the clothing collocation recommending apparatus includes: a first obtaining unit 31, a determining unit 33 and a first recommending unit 35.
A first obtaining unit 31, configured to obtain picture information of the target apparel.
The determining unit 33 is configured to calculate a similarity between the picture information and each accessory in the first accessory library, and determine a second accessory set corresponding to the target accessory, where the similarity is used to indicate a similarity between the accessory and the accessory belonging to the same brand of the target accessory.
And the first recommending unit 35 is configured to calculate a matching score between the picture information and each accessory in the second accessory set, and recommend the accessory with the score being greater than or equal to a first predetermined threshold value to the target user, where the score is used to indicate how popular the matching between the target clothes and the accessories in the second accessory set is to the user, and the score is higher and more popular.
Optionally, in this embodiment, the determining unit 33 may include:
the first acquisition module is used for acquiring picture information;
the first determining module is used for inputting the picture information into a deep neural network model and determining the similarity between the picture information and each accessory in a first accessory library, wherein the deep neural network is the deep neural network model trained according to different types of clothing sample pictures;
and the second determining module is used for determining the similarity with the similarity larger than or equal to a second preset threshold as the accessory in the second accessory set.
Optionally, in this embodiment, the first recommending unit 35 may include:
and the first recommending module is used for generating a matching picture by the accessory with the score being more than or equal to a first preset threshold value and the target clothes and pushing the matching picture to the target user.
Optionally, in this embodiment, the first recommending unit 35 may include:
the second acquisition module is used for acquiring accessory data matched with the target clothes in the plurality of application platforms;
the ordering module is used for ordering according to the degree of the user's preference in the determining process of the accessory data;
and the third determining module is used for determining the matching score between the target clothes and accessories according to the sequencing result.
Optionally, the apparatus may further include:
the second acquisition unit is used for acquiring all other accessory information belonging to the same application interface with the target clothes after acquiring the picture information of the target clothes, wherein the time for adding other accessories into the application interface is earlier than that of the target clothes;
the calculating unit is used for calculating matching scores between the target clothes and all other accessories;
and the second recommending unit is used for recommending the accessories corresponding to the scores of which are more than or equal to the third threshold value to the target user after the target clothes are added into the application interface.
The second recommending unit may include:
and the second recommending module is used for pushing the picture information of the target user, which is obtained by matching the accessory corresponding to the score which is more than or equal to the third threshold value with the target clothes.
By the embodiment provided by the application, the first obtaining unit 31 obtains the picture information of the target clothes; the determining unit 33 calculates a similarity between the picture information and each accessory in the first accessory library, and determines a second accessory set corresponding to the target garment, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target garment; the first recommending unit 35 calculates a matching score between the picture information and each accessory in the second accessory set, and recommends the accessory with the score being greater than or equal to a first preset threshold value to the target user, wherein the score is used for indicating the degree of the matching between the target clothes and the accessories in the second accessory set, and the higher the score is, the more popular the matching is. The method achieves the purpose of recommending popular accessories belonging to the same brand with the target clothes for the target clothes from the big data of the accessory matching set, thereby achieving the technical effect of acquiring the accessories of the target clothes from massive data, and further solving the technical problem that effective suggestions cannot be obtained when acquiring the accessory information of the matching target clothes in the prior art.
According to another aspect of the embodiment of the present invention, there is also provided an electronic device for implementing the clothing matching recommendation method, where the electronic device may be a terminal device or a server shown in fig. 1. The present embodiment takes the electronic device as a server as an example for explanation. As shown in fig. 4, the electronic device comprises a memory 402 and a processor 404, the memory 402 having stored therein a computer program, the processor 404 being arranged to perform the steps of any of the above-described method embodiments by means of the computer program.
Optionally, in this embodiment, the electronic device may be located in at least one network device of a plurality of network devices of a computer network.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring picture information of the target clothes;
s2, calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes;
and S3, calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being larger than or equal to a first preset threshold value to the target user, wherein the score is used for indicating the degree of the matching between the target clothes and the accessories in the second accessory set, and the higher the score is, the more popular the matching is.
Alternatively, it can be understood by those skilled in the art that the structure shown in fig. 4 is only an illustration, and the electronic device may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 4 is a diagram illustrating a structure of the electronic device. For example, the electronics may also include more or fewer components (e.g., network interfaces, etc.) than shown in FIG. 4, or have a different configuration than shown in FIG. 4.
The memory 402 may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for recommending clothing matching in the embodiment of the present invention, and the processor 404 executes various functional applications and data processing by running the software programs and modules stored in the memory 402, that is, implements the method for recommending clothing matching. The memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 402 may further include memory located remotely from the processor 404, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The memory 402 may be used to store, but not limited to, first accessory set information, second accessory set information, similarity information, picture information of the target apparel, and the like. As an example, as shown in fig. 4, the memory 402 may include, but is not limited to, the first obtaining unit 31, the determining unit 33, and the first recommending unit 35 of the clothing matching recommending apparatus. In addition, the system may further include, but is not limited to, other module units in the clothing matching recommendation device, which is not described in this example again.
Optionally, the transmission device 406 is used for receiving or sending data via a network. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 406 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 406 is a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
In addition, the electronic device further includes: a display 408 for displaying the collocated picture; and a connection bus 410 for connecting the respective module parts in the above-described electronic apparatus.
In other embodiments, the terminal device or the server may be a node in a distributed system, where the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting a plurality of nodes through a network communication. Nodes can form a Peer-To-Peer (P2P, Peer To Peer) network, and any type of computing device, such as a server, a terminal, and other electronic devices, can become a node in the blockchain system by joining the Peer-To-Peer network.
According to a further aspect of an embodiment of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the above-mentioned computer-readable storage medium may be configured to store a computer program for executing the steps of:
s1, acquiring picture information of the target clothes;
s2, calculating the similarity between the picture information and each accessory in the first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes;
and S3, calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the score being larger than or equal to a first preset threshold value to the target user, wherein the score is used for indicating the degree of the matching between the target clothes and the accessories in the second accessory set, and the higher the score is, the more popular the matching is.
Alternatively, in this embodiment, a person skilled in the art may understand that all or part of the steps in the methods of the foregoing embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The integrated unit in the above embodiments, if implemented in the form of a software functional unit and sold or used as a separate product, may be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing one or more computer devices (which may be personal computers, servers, network devices, etc.) to execute all or part of the steps of the method according to the embodiments of the present invention.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed client may be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (13)
1. A clothing matching recommendation method is characterized by comprising the following steps:
acquiring picture information of a target garment;
calculating the similarity between the picture information and each accessory in a first accessory library, and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes;
and calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessories with the scores larger than or equal to a first preset threshold value to a target user, wherein the score is used for representing the degree of the matching between the target clothes and the accessories in the second accessory set, and the higher the score is, the more popular the matching is.
2. The method of claim 1, wherein calculating a similarity between the picture information and each accessory in a first accessory library, determining a second set of accessories corresponding to the target apparel comprises:
acquiring the picture information;
inputting the picture information into a deep neural network model, and determining the similarity between the picture information and each accessory in the first accessory library, wherein the deep neural network is the deep neural network model trained according to different types of accessory sample pictures;
and determining the similarity with the similarity greater than or equal to a second preset threshold value as the accessory in the second accessory set.
3. The method of claim 1, wherein calculating a collocation score between the picture information and each accessory in the second set of accessories, recommending accessories with scores greater than or equal to a first predetermined threshold to a target user, comprises:
and generating a collocation picture by the accessory with the score larger than or equal to a first preset threshold value and the target clothes, and pushing the collocation picture to the target user.
4. The method of claim 1, wherein calculating a collocation score between the picture information and each accessory in the second set of accessories, recommending accessories with scores greater than or equal to a first predetermined threshold to a target user, comprises:
acquiring accessory data matched with the target clothes in a plurality of application platforms;
determining from the accessory data a ranking according to the user's preference;
and determining a matching score between the target clothes and the accessories according to the sequencing result.
5. The method of claim 1, wherein after obtaining the picture information of the target apparel, the method further comprises:
acquiring information of all other accessories belonging to the same application interface with the target clothes, wherein the time for adding the other accessories into the application interface is earlier than that of the target clothes;
calculating matching scores between the target clothes and all other accessories;
after the target clothes are added into the application interface, recommending the accessories corresponding to the scores which are larger than or equal to the third threshold value to the target user.
6. The method of claim 5, wherein recommending, to the target user, the accessory corresponding to the score being greater than or equal to a third threshold value after adding the target apparel to the application interface comprises:
and pushing the picture information of the target user, which is obtained by matching the accessory corresponding to the score greater than or equal to the third threshold value with the target accessory.
7. A clothing collocation recommendation device, comprising:
the first acquisition unit is used for acquiring the picture information of the target clothes;
the determining unit is used for calculating the similarity between the picture information and each accessory in a first accessory library and determining a second accessory set corresponding to the target clothes, wherein the similarity is used for representing the similarity between the accessories and the accessories of the same brand of the target clothes;
and the first recommending unit is used for calculating a matching score between the picture information and each accessory in the second accessory set, and recommending the accessory with the score being larger than or equal to a first preset threshold value to a target user, wherein the score is used for indicating the degree that the matching between the target clothes and the accessories in the second accessory set is favored by the user, and the score is more popular as the score is higher.
8. The apparatus of claim 7, wherein the determining unit comprises:
the first acquisition module is used for acquiring the picture information;
the first determining module is used for inputting the picture information into a deep neural network model and determining the similarity between the picture information and each accessory in the first accessory library, wherein the deep neural network is a deep neural network model trained according to different types of clothes sample pictures;
and the second determining module is used for determining the similarity with the similarity larger than or equal to a second preset threshold as the accessory in the second accessory set.
9. The apparatus of claim 7, wherein the first recommending unit comprises:
and the first recommending module is used for generating a collocation image by the accessory with the score larger than or equal to a first preset threshold value and the target accessory and pushing the collocation image to the target user.
10. The apparatus of claim 7, wherein the first recommending unit comprises:
the second acquisition module is used for acquiring accessory data matched with the target clothes in a plurality of application platforms;
the ordering module is used for ordering according to the degree of the accessory data favored by the user;
and the third determining module is used for determining the matching score between the target clothes and the accessories according to the sequencing result.
11. The apparatus of claim 7, further comprising:
the second obtaining unit is used for obtaining all other accessory information belonging to the same application interface with the target clothes after obtaining the picture information of the target clothes, wherein the time for adding other accessories into the application interface is earlier than that of the target clothes;
the calculating unit is used for calculating matching scores between the target clothes and all other accessories;
and the second recommending unit is used for recommending the accessory corresponding to the score which is greater than or equal to a third threshold value to the target user after the target clothes are added into the application interface.
12. The apparatus of claim 11, wherein the second recommending unit comprises:
and the second recommending module is used for pushing the picture information of the target user, which is obtained by matching the accessory corresponding to the score which is more than or equal to the third threshold value with the target accessory.
13. An electronic device comprising a memory and a processor, characterized in that the memory has stored therein a computer program, the processor being arranged to execute the method of any of claims 1 to 6 by means of the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010358230.0A CN111582979A (en) | 2020-04-29 | 2020-04-29 | Clothing matching recommendation method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010358230.0A CN111582979A (en) | 2020-04-29 | 2020-04-29 | Clothing matching recommendation method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582979A true CN111582979A (en) | 2020-08-25 |
Family
ID=72122709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010358230.0A Pending CN111582979A (en) | 2020-04-29 | 2020-04-29 | Clothing matching recommendation method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582979A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307242A (en) * | 2020-11-11 | 2021-02-02 | 百度在线网络技术（北京）有限公司 | Clothing matching method and device, computing equipment and medium |
| CN113628011A (en) * | 2021-08-16 | 2021-11-09 | 唯品会(广州)软件有限公司 | Commodity collocation method and device |
| CN113763114A (en) * | 2021-03-04 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article information matching method and device and storage medium |
| WO2022222779A1 (en) * | 2021-04-22 | 2022-10-27 | 京东科技控股股份有限公司 | Image generation method and apparatus, and electronic device and computer-readable medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951966A (en) * | 2015-07-13 | 2015-09-30 | 百度在线网络技术（北京）有限公司 | Clothes commodity recommending method and device |
| CN106504064A (en) * | 2016-10-25 | 2017-03-15 | 清华大学 | Clothes classification based on depth convolutional neural networks recommends method and system with collocation |
| CN108319639A (en) * | 2017-12-20 | 2018-07-24 | 北京康得新创科技股份有限公司 | The methods of exhibiting and device of clothing matching |
| CN110659958A (en) * | 2019-09-06 | 2020-01-07 | 电子科技大学 | Clothing matching generation method based on generation of countermeasure network |
| CN110909746A (en) * | 2018-09-18 | 2020-03-24 | 深圳云天励飞技术有限公司 | Clothing recommendation method, related device and equipment |
-
2020
- 2020-04-29 CN CN202010358230.0A patent/CN111582979A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951966A (en) * | 2015-07-13 | 2015-09-30 | 百度在线网络技术（北京）有限公司 | Clothes commodity recommending method and device |
| CN106504064A (en) * | 2016-10-25 | 2017-03-15 | 清华大学 | Clothes classification based on depth convolutional neural networks recommends method and system with collocation |
| CN108319639A (en) * | 2017-12-20 | 2018-07-24 | 北京康得新创科技股份有限公司 | The methods of exhibiting and device of clothing matching |
| CN110909746A (en) * | 2018-09-18 | 2020-03-24 | 深圳云天励飞技术有限公司 | Clothing recommendation method, related device and equipment |
| CN110659958A (en) * | 2019-09-06 | 2020-01-07 | 电子科技大学 | Clothing matching generation method based on generation of countermeasure network |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307242A (en) * | 2020-11-11 | 2021-02-02 | 百度在线网络技术（北京）有限公司 | Clothing matching method and device, computing equipment and medium |
| US11810177B2 (en) | 2020-11-11 | 2023-11-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Clothing collocation |
| CN113763114A (en) * | 2021-03-04 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Article information matching method and device and storage medium |
| WO2022222779A1 (en) * | 2021-04-22 | 2022-10-27 | 京东科技控股股份有限公司 | Image generation method and apparatus, and electronic device and computer-readable medium |
| CN113628011A (en) * | 2021-08-16 | 2021-11-09 | 唯品会(广州)软件有限公司 | Commodity collocation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9744466B2 (en) | Widgetized avatar and a method and system of creating and using same | |
| US11037222B1 (en) | Dynamic recommendations personalized by historical data | |
| US20190073710A1 (en) | Color based social networking recommendations | |
| CN111582979A (en) | Clothing matching recommendation method and device and electronic equipment | |
| US8577753B1 (en) | Community-based shopping profiles | |
| US8533610B2 (en) | Widgetized avatar and a method and system of creating and using same | |
| US8718369B1 (en) | Techniques for shape-based search of content | |
| US7792706B2 (en) | Method and system of providing recommendations during online shopping | |
| CN106791970A (en) | The method and device of merchandise news is presented in video playback | |
| US10074121B2 (en) | Shopper helper | |
| CN112132660B (en) | Commodity recommendation method, system, equipment and storage medium | |
| WO2016188277A1 (en) | Method and device for providing business object collocation information | |
| CN111699503A (en) | Advertisement recommendation method and device and electronic equipment | |
| CN103377193A (en) | Information providing method, webpage server and webpage browser | |
| CA2869053C (en) | Method and system for creating step by step projects | |
| WO2020085086A1 (en) | Commodity recommendation system | |
| US20090037292A1 (en) | Intelligent shopping search system | |
| JP6085017B1 (en) | Styling providing system | |
| CN110599291A (en) | Intelligent e-commerce operation system and method for efficiently and accurately fusing multiple markets of merchant and buyer | |
| WO2016188278A1 (en) | Method and device for collecting information about service object | |
| KR102619084B1 (en) | Method for recommending products and service server using the same | |
| CN107632989B (en) | Method and device for selecting commodity objects, determining models and determining use heat | |
| JP2008052498A (en) | Selling support system, selling support method, and selling support program | |
| CN113191840A (en) | Article information display method and device, electronic equipment and computer readable medium | |
| JP7219863B2 (en) | Processing device, processing method and processing program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |