CN112417535A - Clothing matching recommendation method, control device, storage medium and wardrobe - Google Patents
Clothing matching recommendation method, control device, storage medium and wardrobe Download PDFInfo
- Publication number
- CN112417535A CN112417535A CN202011283403.3A CN202011283403A CN112417535A CN 112417535 A CN112417535 A CN 112417535A CN 202011283403 A CN202011283403 A CN 202011283403A CN 112417535 A CN112417535 A CN 112417535A
- Authority
- CN
- China
- Prior art keywords
- clothes
- matching
- clothing
- target object
- pictures
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012216 screening Methods 0.000 claims abstract description 30
- 230000006399 behavior Effects 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 14
- 230000007246 mechanism Effects 0.000 claims description 14
- 238000005192 partition Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000013145 classification model Methods 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000037237 body shape Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000001932 seasonal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/535—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- Library & Information Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a clothing matching recommendation method, a control device, a storage medium and a wardrobe, wherein the method comprises the following steps: when a clothing matching request sent by a target object is received, screening out clothing matching pictures from a known clothing matching picture library according to current environment information, known personal information of the target object and attendance occasion information in the clothing matching request; and for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value with the clothes from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object, so that clothes matching meeting the requirements of the user can be recommended to the user based on the existing clothes of the user, and the time for the user to independently wear and place the clothes is saved.
Description
Technical Field
The invention belongs to the technical field of clothing matching application, and particularly relates to a clothing matching recommendation method, a control device, a storage medium and a wardrobe.
Background
With the development of the internet era and the arrival of the big data era, people gradually enter the information overload era from the information scarcity era. Therefore, the recommendation engine module is developed to allow the user to efficiently acquire necessary information from a large amount of information.
The recommendation engine module carries out personalized recommendation of the user by comparing the consumption preference of the data mining algorithm and other users. And more recommendation engine modules are deployed on the e-commerce platform for accurate marketing. The recommendation engine module does not need the user to provide explicit needs, but models the user's interests by analyzing the user's historical behavior, thereby proactively recommending to the user information that can satisfy their interests and needs. The recommendation information obtained by each user is related to the self behavior characteristics and interests, but not general public information. The main task of the recommendation engine module is to contact users and information, which on one hand helps users to find information valuable to themselves, and on the other hand enables information to be presented to users interested in the information, thereby realizing win-win situation between information consumers and information producers. The recommendation engine module based on big data learns the preference of the user by analyzing the historical record of the user, so that the interested information is actively recommended to the user, and the personalized recommendation requirement of the user is met.
At present, people can spend much time in selecting clothes-wearing matching when going out, and especially for people with selection difficulty, a great deal of time can be spent in clothes-wearing matching. How to improve the efficiency of clothes matching is very important.
There is a need for a clothing matching recommendation method, a control device, a storage medium, and a wardrobe.
Disclosure of Invention
The invention aims to solve the technical problem of automatically recommending the preferred clothing matching to the user according to the existing clothing of the user, thereby effectively saving the time cost for the user to independently wear and take.
In order to solve the problems, the invention provides a clothing matching recommendation method, a control device, a storage medium and a wardrobe.
In a first aspect, the invention provides a clothing matching recommendation method, which comprises the following steps:
when a clothing matching request sent by a target object is received, screening out clothing matching pictures from a known clothing matching picture library according to current environment information, known personal information of the target object and attendance occasion information in the clothing matching request;
for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object;
and matching the clothes corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture, and generating a new clothes matching and recommending the new clothes matching to the target object.
According to the embodiment of the present invention, preferably, screening out the clothing matching picture from the known clothing matching picture library according to the current environment information, the personal information of the known target object and the presence occasion information in the clothing matching request comprises the following steps:
screening out a clothing matching picture set from a known clothing matching picture library according to the personal information of a known target object based on a mixed recommendation mechanism;
and screening out clothing matching pictures from the clothing matching picture set according to the current environment information and the attendance occasion information.
According to an embodiment of the present invention, preferably, the hybrid recommendation mechanism includes a demographic-based recommendation, a content-based recommendation, and a collaborative filtering recommendation, and the method for screening out the clothing matching picture set from the known clothing matching picture library according to the personal information of the known target object includes the following steps:
based on demographic recommendation, screening out a first clothing matching picture set with the same or similar personal information from a known clothing matching picture library according to the personal information of a known target object;
recording the personalized behavior of the target object according to the feedback of the target object to the recommended clothing matching;
respectively based on content recommendation and collaborative filtering recommendation, screening out a second clothing matching picture set and a third clothing matching picture set from a known clothing matching picture library according to the personalized behavior of the target object;
correspondingly, the clothing matching picture is screened out from the clothing matching picture set according to the current environment information and the attendance information, and the method comprises the following steps:
and screening out clothing matching pictures from the first clothing matching picture set, the second clothing matching picture set and the third clothing matching picture set according to the current environment information and the attendance occasion information.
According to the embodiment of the present invention, preferably, the personalized behavior includes a preferred clothing matching, and the second clothing matching picture set and the third clothing matching picture set are screened out from a known clothing matching picture library according to the personalized behavior of the target object based on the recommendation of the content and the recommendation of the collaborative filtering, including the following steps:
based on the recommendation of the content, screening out clothes matching pictures with the same clothes matching characteristics as the preference of the target object from a known clothes matching picture library and combining the clothes matching pictures into a second clothes matching picture set;
and screening out clothing matching pictures associated with the preferred clothing matching of the target object from a known clothing matching picture library and combining the clothing matching pictures into a third clothing matching picture set based on the recommendation of the collaborative filtering.
According to an embodiment of the present invention, preferably, after screening out the clothes matching pictures from the first, second and third sets of clothes matching pictures according to the current environment information and presence information, the method further includes the steps of:
displaying the clothes matching pictures respectively screened from the first clothes matching picture set, the second clothes matching picture set and the third clothes matching picture set in a partition mode;
correspondingly, matching the clothes respectively corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture to generate new clothes matching recommendation to the target object, and the method comprises the following steps:
and matching clothes corresponding to each piece of clothes of each clothes matching picture displayed in a partition mode according to the clothes matching mode of the clothes matching picture to generate new clothes matching, and recommending the new clothes matching to the target object in a partition mode.
According to an embodiment of the present invention, preferably, the clothing database of the target object is constructed according to the picture of the clothing owned by the target object, including the following steps:
collecting pictures of clothes owned by a target object;
and classifying the pictures of the clothes owned by the target object by utilizing a classification model to obtain a clothes database of the classified target object, wherein the classification model is obtained by training a known clothes picture library.
According to the embodiment of the present invention, preferably, selecting a garment with similarity exceeding a preset threshold with the garment from a garment database of known target objects comprises the following steps:
and selecting the clothes with the similarity of the color and/or the style of the clothes exceeding a preset threshold from the clothes database of the known target object.
In a second aspect, the invention provides a storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
In a third aspect, the present invention provides a clothing matching recommendation control device, which includes a memory and a processor, wherein the memory stores a computer program, and the computer program implements the steps of the above method when executed by the processor.
In a fourth aspect, the invention provides a wardrobe, which comprises the clothing matching recommendation control device.
Compared with the prior art, one or more embodiments in the above scheme can have the following advantages or beneficial effects:
by applying the clothing matching recommendation method, when a clothing matching request sent by a target object is received, clothing matching pictures are screened from a known clothing matching picture library according to current environment information, known personal information of the target object and attendance occasion information in the clothing matching request; and for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value with the clothes from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object, so that clothes matching meeting the requirements of the user can be recommended to the user based on the existing clothes of the user, and the time for the user to independently wear and place the clothes is saved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
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 specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart illustrating a method for recommending a matching service according to an embodiment of the present invention;
FIG. 2 is a flowchart of a second clothing collocation recommendation method according to an embodiment of the invention;
fig. 3 shows a flow chart of the construction of three modules of a five-clothes matching recommendation control device according to an embodiment of the invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be provided with reference to the drawings and examples, so that how to apply the technical means to solve the technical problems and achieve the technical effects can be fully understood and implemented. It should be noted that, as long as there is no conflict, the embodiments and the features of the embodiments of the present invention may be combined with each other, and the technical solutions formed are within the scope of the present invention.
Example one
In order to solve the technical problems in the prior art, the embodiment of the invention provides a clothing matching recommendation method.
Referring to fig. 1, the clothing matching recommendation method of the embodiment includes the following steps:
s110, monitoring whether a clothing matching request sent by a target object is received in real time:
if yes, go to step S120;
if not, no response is given;
s120, screening out a clothing matching picture set from a known clothing matching picture library according to the personal information of a known target object based on a mixed recommendation mechanism;
s130, screening out clothing matching pictures from the clothing matching picture set according to the current environment information and the attendance occasion information;
s140, for each piece of clothes of each screened clothes matching picture, selecting clothes of which the similarity with the clothes exceeds a preset threshold value from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object;
s150, matching the clothes respectively corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture, and generating new clothes matching and recommending the new clothes matching to the target object.
In step S120, the personal information of the known target object is provided in advance for the target object, the personal information of the known target object includes the personal shape of the target object and the interested clothing matching, and the known clothing matching picture library is constructed by collecting the known clothing matching pictures in advance.
In step S130, the current environmental information includes at least the current season and the current temperature.
In step S140, the clothing database of the target object is constructed according to the pictures of the clothing owned by the target object, including the following steps:
collecting pictures of clothes owned by a target object;
and classifying the pictures of the clothes owned by the target object by utilizing a classification model to obtain a clothes database of the classified target object, wherein the classification model is obtained by training a known clothes picture library.
In the clothing matching recommendation method of the embodiment, when a clothing matching request sent by a target object is received, clothing matching pictures are screened out from a known clothing matching picture library according to current environment information, known personal information of the target object and presence occasion information in the clothing matching request; and for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value with the clothes from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object, so that clothes matching meeting the requirements of the user can be recommended to the user based on the existing clothes of the user, and the time for the user to independently wear and place the clothes is saved.
Example two
In order to solve the above technical problems in the prior art, an embodiment of the present invention provides a clothing matching recommendation method based on the first embodiment, where the method in the first embodiment of the present invention improves steps S120, S130 and S150, and in step S120, the hybrid recommendation mechanism includes demographic-based recommendation, content-based recommendation and collaborative filtering recommendation.
Referring to fig. 2, the method of the present embodiment includes the following steps:
s210, monitoring whether a clothing matching request sent by a target object is received in real time:
if yes, go to step S221;
if not, no response is given;
s221, based on demographic recommendation, screening out a first clothing matching picture set with the same or similar personal information from a known clothing matching picture library according to the personal information of a known target object;
s222, recording the personalized behavior of the target object according to the feedback of the target object to the recommended clothing matching;
s223, respectively based on the content recommendation and the collaborative filtering recommendation, screening out a second clothing matching picture set and a third clothing matching picture set from a known clothing matching picture library according to the personalized behavior of the target object;
s231, screening out clothing matching pictures from the first clothing matching picture set, the second clothing matching picture set and the third clothing matching picture set according to the current environment information and the attendance occasion information;
s232, performing partition display on the clothes matching pictures respectively screened from the first clothes matching picture set, the second clothes matching picture set and the third clothes matching picture set;
s240, for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to pictures of the clothes owned by the target object;
and S250, matching the clothes respectively corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture, and generating a new clothes matching and recommending the new clothes matching to the target object.
In step S233, when the personalized behavior includes a preferred clothing match, a second clothing match picture set and a third clothing match picture set are screened from a known clothing match picture library according to the personalized behavior of the target object based on the recommendation of the content and the recommendation of the collaborative filtering, respectively, including the following steps:
based on the recommendation of the content, screening out clothes matching pictures with the same clothes matching characteristics as the preference of the target object from a known clothes matching picture library and combining the clothes matching pictures into a second clothes matching picture set;
and screening out clothing matching pictures associated with the preferred clothing matching of the target object from a known clothing matching picture library and combining the clothing matching pictures into a third clothing matching picture set based on the recommendation of the collaborative filtering.
The following illustrates, by way of example, a dress match picture associated with a preferred dress match of a target object: assuming that the preferred clothing matches of the target object are a and B and the preferred clothing matches of the other target objects are A, B and C, then C is the clothing match picture associated with the preferred clothing matches of the target object a and B.
In step S240, the similarity includes similarity of clothing color and/or style.
In step S250, after recommending a new clothing match partition to a target object, the clothing match recommendation method further includes the following steps:
and recording the personalized preference of the target object to each recommended dress collocation, and returning the personalized preference to the step S223 as a personalized behavior.
The embodiment carries out personalized preference recording based on the feedback of the user to the clothing matching recommended each time so as to achieve the effect that the recommendation mechanism is more and more accurate.
EXAMPLE III
In order to solve the above technical problems in the prior art, an embodiment of the present invention further provides a storage medium.
The storage medium of the present embodiment has stored thereon a computer program which, when executed by a processor, implements the steps of the method in the above-described embodiments.
Example four
In order to solve the technical problems in the prior art, the embodiment of the invention also provides a clothing matching recommendation control device.
The clothing matching recommendation control device of the embodiment comprises a memory and a processor, wherein the memory stores a computer program, and the computer program realizes the steps of the method when being executed by the processor.
EXAMPLE five
In order to solve the technical problems in the prior art, the embodiment of the invention also provides the wardrobe.
The wardrobe of the embodiment comprises the clothing collocation recommendation control device, wherein the clothing collocation recommendation control device can be embedded into the wardrobe.
Referring to fig. 3, the clothing matching recommendation control device needs a large amount of data to construct a cloud database: a user basic information clothing database, a user preference analysis database, a clothing matching picture database, a season temperature database and the like. The data can be acquired through a web crawler technology, the efficiency of data collection can be improved by automatically collecting data through the script, and the efficiency of a cloud big data platform is built.
As shown in fig. 3, the clothing matching recommendation control device is mainly divided into three parts: the system comprises an intelligent classification and arrangement module, a user search engine module and a recommendation engine module. The intelligent classification and arrangement module is mainly used for classifying all clothes in the wardrobe based on a deep learning algorithm-image recognition by utilizing a clothes library owned by a user at present and a clothes picture library owned by a big data platform cloud, and then automatically arranging the clothes. The wardrobe after automatic processing is not only tidy but also orderly classified. The user search engine module is mainly used for constructing a search engine by utilizing a user basic information clothing database, a cloud clothing matching picture database, an intelligently classified user clothing database and a seasonal air temperature database which are accumulated by a cloud end, so that a user can conveniently input a place of departure to obtain the corresponding wearing and taking of the corresponding place of departure. And the recommendation engine module sequentially performs human body type analysis and user interest model construction based on the big data user personalized clothing matching model, and then performs personalized recommendation on the user.
The deep learning algorithm which can be adopted in the intelligent classification and arrangement module is as follows: convolutional neural network model (CNN for short). The convolutional neural network is commonly used for analyzing and processing image data, so the algorithm is adopted in the intelligent classification module. The convolutional neural network is mainly applied to image classification, target detection and semantic segmentation. In this scenario, the algorithm is used to resolve the image classification. The intelligent classification and arrangement module comprises the following operation steps: the method comprises the steps of obtaining images of all clothes of a user's personal wardrobe, classifying all clothes of the user's personal wardrobe by using a convolutional neural network classification model trained by a cloud-side clothes picture library, and then automatically arranging the user's personal wardrobe. The intelligent classification and arrangement module makes full use of the space of the wardrobe and reduces the time cost for manually classifying the wardrobe clothes.
The user search engine module is a search engine module which is built based on a plurality of cloud databases and is related to the place of going out, the user can input the place of going out, and the search engine can feed back the corresponding place of going out to the user. The search engine and the recommendation engine module are integrated, information returned to the user by the search engine module is a user personalized clothing matching model based on big data by the recommendation engine module, human body shape analysis is sequentially carried out, a user interest model is constructed, and personalized recommendation is carried out on the user. The recommendation engine mainly has the following three types: demographic based recommendations, content based recommendations, collaborative filtering based recommendations. Demographic-based recommendations: and discovering the relevance degree of the user according to the basic information of the system user. Content-based recommendation: according to the metadata of the recommended item or content, the relevance of the item and the content is found. Collaborative filtering based recommendations: according to the preference of the user for the item or the information, the relevance of the item or the content is found, or the relevance of the user is found. In order to make the user have more recommendation choices, a hybrid recommendation mechanism is used on the mechanism employed by the recommendation engine module. In the hybrid recommendation mechanism, the mixing of partitions is considered. The partition mixing adopts a plurality of recommendation mechanisms, and different recommendation results are displayed to the user in different partitions. The recommendation mechanism can effectively perform personalized recommendation for the user, and can greatly reduce the time cost consumed by the user in the aspect of wearing and taking.
The clothing matching recommendation control device of the embodiment is divided into three parts: the system comprises an intelligent classification and arrangement module, a user search engine and a recommendation engine module. The intelligent classification and arrangement module is mainly used for classifying all clothes in the wardrobe based on a deep learning algorithm-image recognition by utilizing a clothes library owned by a user at present and a clothes picture library owned by a big data platform cloud, and then automatically arranging the clothes. The wardrobe after automatic processing is not only tidy but also orderly classified. The user search engine is mainly used for constructing a search engine by utilizing a user basic information clothing database, a cloud clothing matching picture database, an intelligently classified user clothing database and a seasonal air temperature database, which are accumulated at the cloud, so that a user can conveniently input a place of departure to obtain the corresponding wearing and taking of the corresponding place of departure. And the recommendation engine module sequentially performs human body type analysis and user interest model construction based on the big data user personalized clothing matching model, and then performs personalized recommendation on the user. Therefore, the clothing matching recommendation control device can effectively carry out intelligent classification and arrangement on the existing clothing of the user through the three modules, upload the existing clothing types and types of the user to the cloud database, establish a related search engine, and carry out personalized wearing and putting on recommendation through the places where the user needs to go out and based on the recommendation engine module preferred by the user.
The wardrobe serves as an intelligent home, the recommendation engine module is deployed on the wardrobe, a user personalized clothing matching model based on big data is provided based on a user basic information clothing database, a user preference analysis database and a clothing matching picture library accumulated at the cloud, human body shape analysis and user interest model construction are sequentially carried out, then personalized recommendation is carried out on a user, the problem of personalized matching of the user is solved, and time cost consumed by the user in wearing and taking is saved.
The recommendation engine of the embodiment analyzes a certain rule or directly performs prediction calculation on the wearing preference of the user according to different recommendation mechanisms which may be applied to different parts of the data source, so that the time cost for the user to independently wear the data source can be effectively saved.
Although the embodiments of the present invention have been described above, the above description is only for the convenience of understanding the present invention, and is not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A clothing matching recommendation method is characterized by comprising the following steps:
when a clothing matching request sent by a target object is received, screening out clothing matching pictures from a known clothing matching picture library according to current environment information, known personal information of the target object and attendance occasion information in the clothing matching request;
for each piece of clothes of each screened clothes matching picture, selecting clothes with similarity exceeding a preset threshold value from a clothes database of a known target object as clothes corresponding to the clothes, wherein the clothes database of the target object is constructed according to the pictures of the clothes owned by the target object;
and matching the clothes corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture, and generating a new clothes matching and recommending the new clothes matching to the target object.
2. The method of claim 1, wherein screening out clothing matching pictures from a library of known clothing matching pictures according to current environment information, personal information of known target objects, and presence information in the clothing matching request comprises the steps of:
screening out a clothing matching picture set from a known clothing matching picture library according to the personal information of a known target object based on a mixed recommendation mechanism;
and screening out clothing matching pictures from the clothing matching picture set according to the current environment information and the attendance occasion information.
3. The method of claim 2, wherein the hybrid recommendation mechanism comprises demographic-based recommendations, content-based recommendations, and collaborative filtering recommendations, and wherein the step of screening out the set of clothing matching pictures from the library of known clothing matching pictures according to the personal information of the known target object based on the hybrid recommendation mechanism comprises the steps of:
based on demographic recommendation, screening out a first clothing matching picture set with the same or similar personal information from a known clothing matching picture library according to the personal information of a known target object;
recording the personalized behavior of the target object according to the feedback of the target object to the recommended clothing matching;
respectively based on content recommendation and collaborative filtering recommendation, screening out a second clothing matching picture set and a third clothing matching picture set from a known clothing matching picture library according to the personalized behavior of the target object;
correspondingly, the clothing matching picture is screened out from the clothing matching picture set according to the current environment information and the attendance information, and the method comprises the following steps:
and screening out clothing matching pictures from the first clothing matching picture set, the second clothing matching picture set and the third clothing matching picture set according to the current environment information and the attendance occasion information.
4. The method of claim 3, wherein the personalized behavior comprises a preferred clothing match, the second and third sets of clothing match pictures are filtered out of a library of known clothing match pictures according to the personalized behavior of the target object based on the content recommendation and the collaborative filtering recommendation, respectively, comprising the steps of:
based on the recommendation of the content, screening out clothes matching pictures with the same clothes matching characteristics as the preference of the target object from a known clothes matching picture library and combining the clothes matching pictures into a second clothes matching picture set;
and screening out clothing matching pictures associated with the preferred clothing matching of the target object from a known clothing matching picture library and combining the clothing matching pictures into a third clothing matching picture set based on the recommendation of the collaborative filtering.
5. The method of claim 3, wherein after screening out a clothing matching picture from the first, second, and third sets of clothing matching pictures according to current environmental information and presence information, the method further comprises the steps of:
displaying the clothes matching pictures respectively screened from the first clothes matching picture set, the second clothes matching picture set and the third clothes matching picture set in a partition mode;
correspondingly, matching the clothes respectively corresponding to each piece of clothes of each screened clothes matching picture according to the clothes matching mode of the clothes matching picture to generate new clothes matching recommendation to the target object, and the method comprises the following steps:
and matching clothes corresponding to each piece of clothes of each clothes matching picture displayed in a partition mode according to the clothes matching mode of the clothes matching picture to generate new clothes matching, and recommending the new clothes matching to the target object in a partition mode.
6. The method according to claim 1, wherein the clothing database of the target object is constructed from pictures of clothing owned by the target object, comprising the steps of:
collecting pictures of clothes owned by a target object;
and classifying the pictures of the clothes owned by the target object by utilizing a classification model to obtain a clothes database of the classified target object, wherein the classification model is obtained by training a known clothes picture library.
7. The method of claim 1, wherein selecting out the clothing with similarity degree exceeding the preset threshold from the clothing database of the known target object comprises the following steps:
and selecting the clothes with the similarity of the color and/or the style of the clothes exceeding a preset threshold from the clothes database of the known target object.
8. A storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
9. A clothing matching recommendation control apparatus comprising a memory and a processor, characterized in that the memory has stored thereon a computer program which, when executed by the processor, implements the steps of the method of any one of claims 1 to 7.
10. A wardrobe comprising the clothing collocation recommendation control device of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011283403.3A CN112417535A (en) | 2020-11-16 | 2020-11-16 | Clothing matching recommendation method, control device, storage medium and wardrobe |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011283403.3A CN112417535A (en) | 2020-11-16 | 2020-11-16 | Clothing matching recommendation method, control device, storage medium and wardrobe |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112417535A true CN112417535A (en) | 2021-02-26 |
Family
ID=74830899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011283403.3A Withdrawn CN112417535A (en) | 2020-11-16 | 2020-11-16 | Clothing matching recommendation method, control device, storage medium and wardrobe |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112417535A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140176565A1 (en) * | 2011-02-17 | 2014-06-26 | Metail Limited | Computer implemented methods and systems for generating virtual body models for garment fit visualisation |
| CN106649300A (en) * | 2015-10-28 | 2017-05-10 | 中通服公众信息产业股份有限公司 | Intelligent clothing matching recommendation method and system based on cloud platform |
| CN108334650A (en) * | 2018-05-10 | 2018-07-27 | 王瑞枞 | A kind of clothing matching recommendation method and device |
| CN109360050A (en) * | 2018-09-27 | 2019-02-19 | 东华大学 | Personal care garment management and personalized collocation recommendation intelligence system based on perceptual demand |
| WO2019134560A1 (en) * | 2018-01-08 | 2019-07-11 | Oppo广东移动通信有限公司 | Method for constructing matching model, clothing recommendation method and device, medium, and terminal |
-
2020
- 2020-11-16 CN CN202011283403.3A patent/CN112417535A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140176565A1 (en) * | 2011-02-17 | 2014-06-26 | Metail Limited | Computer implemented methods and systems for generating virtual body models for garment fit visualisation |
| CN106649300A (en) * | 2015-10-28 | 2017-05-10 | 中通服公众信息产业股份有限公司 | Intelligent clothing matching recommendation method and system based on cloud platform |
| WO2019134560A1 (en) * | 2018-01-08 | 2019-07-11 | Oppo广东移动通信有限公司 | Method for constructing matching model, clothing recommendation method and device, medium, and terminal |
| CN108334650A (en) * | 2018-05-10 | 2018-07-27 | 王瑞枞 | A kind of clothing matching recommendation method and device |
| CN109360050A (en) * | 2018-09-27 | 2019-02-19 | 东华大学 | Personal care garment management and personalized collocation recommendation intelligence system based on perceptual demand |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chu et al. | A hybrid recommendation system considering visual information for predicting favorite restaurants | |
| CN111444428B (en) | Information recommendation method and device based on artificial intelligence, electronic equipment and storage medium | |
| Messina et al. | Content-based artwork recommendation: integrating painting metadata with neural and manually-engineered visual features | |
| CN111125422B (en) | Image classification method, device, electronic equipment and storage medium | |
| CN101946249B (en) | Using related users data to enhance web search | |
| US20080281790A1 (en) | System and Method for Determining and Applying Affinity Profiles for Research, Marketing, and Recommendation Systems | |
| CN113158023B (en) | Public digital life accurate classification service method based on mixed recommendation algorithm | |
| Kuroda et al. | An image retrieval system by impression words and specific object names–IRIS | |
| WO2009126815A2 (en) | Diversified, self-organizing map system and method | |
| CN111291191B (en) | Broadcast television knowledge graph construction method and device | |
| CN111538751B (en) | Tagged user portrait generation system and method for Internet of things data | |
| US20200327600A1 (en) | Method and system for providing product recommendation to a user | |
| Zhang et al. | Image retrieval of wool fabric. Part II: based on low-level color features | |
| CN117331460B (en) | Digital exhibition hall content optimization method and device based on multidimensional interaction data analysis | |
| CN115659008A (en) | Information pushing system and method for big data information feedback, electronic device and medium | |
| US20070266048A1 (en) | System and Method for Determining Affinity Profiles for Research, Marketing, and Recommendation Systems | |
| CN117786086A (en) | Reply text generation method, reply text generation device, computer equipment and readable storage medium | |
| Zhu et al. | Multimodal sparse linear integration for content-based item recommendation | |
| CN114528479A (en) | Event detection method based on multi-scale different composition embedding algorithm | |
| CN116051192A (en) | Method and device for processing data | |
| CN112417535A (en) | Clothing matching recommendation method, control device, storage medium and wardrobe | |
| CN113902526B (en) | Product recommendation method and device based on artificial intelligence, computer equipment and medium | |
| Casabayó et al. | Using AI techniques in the grocery industry: Identifying the customers most likely to defect | |
| CN112418333A (en) | Wine data pushing method and device, computer equipment and storage medium | |
| Kolstad et al. | Rethinking Conventional Collaborative Filtering for Recommending Daily Fashion Outfits. |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210226 |
|
| WW01 | Invention patent application withdrawn after publication |