CN108364207A - A kind of facial skin care product and skin care proposal recommending method - Google Patents
A kind of facial skin care product and skin care proposal recommending method Download PDFInfo
- Publication number
- CN108364207A CN108364207A CN201810084756.7A CN201810084756A CN108364207A CN 108364207 A CN108364207 A CN 108364207A CN 201810084756 A CN201810084756 A CN 201810084756A CN 108364207 A CN108364207 A CN 108364207A
- Authority
- CN
- China
- Prior art keywords
- skin care
- skin
- facial
- care item
- attribute
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of facial skin care product and skin care proposal recommending methods, belong to technique in skin care field;Method includes:Acquire facial image;Cloud Server obtains all first dimensional attributes of facial skin state according to face image processing;Cloud Server obtains the recommendation index for being associated with each skin care item according to all second dimensional attributes for all first dimensional attributes and each skin care item for being associated with facial image, respectively processing;Cloud Server is from high to low ranked up all skin care item according to recommendation index, selection top n skin care item form a recommendation results and feed back to the user terminal of long-range connection Cloud Server, and recommendation results include top n skin care item and are associated with the skin care scheme of top n skin care item.The advantageous effect of above-mentioned technical proposal is:It helps user to select suitable skin care item, the well-formedness for promoting skin care item selection while user independently selects difficulty is solved the problems, such as, to promote user experience.
Description
Technical field
The present invention relates to technique in skin care field more particularly to a kind of facial skin care product and skin care proposal recommending methods.
Background technology
In addition, either according to the recommendation of itself custom or other users, there is no the methods of science to evaluate face
The using effect of portion's skin care item, user evaluate according to autoscopia there are certain error, for example, the subtle improvement of skin
User can not accurately have found.
With the promotion of people's quality of the life, more and more people especially women begins to focus on the skin of itself,
More and more maintenance products for skin also occupy very important status on the market.Wherein, women is especially
The skin of face can be paid close attention to, such as whether canthus has whether wrinkle, face have decree line etc., and can be according to these skins
Situation selection uses the product of different maintenance and skin care.
It is typically rule of thumb or the recommendation of other users, such as to like that people, which select the mode of facial skin care product, at present
Oneself common brand is vigorously continued to use, corresponding brand is inquired according to the skin of itself from network and is recommended, or according to colleague
Recommendation with friend selects new brand etc., the mode that this skin care item are recommended to be based only on to the relatively coarse of facial skin
Understanding, there is no accurately go to recommend and use corresponding skin care item for skin.Also, even if user continues to use always certain brand
Some type of skin care item, facial skin situation is also can be constantly changed, and the skin care item not continued to use always are exactly most
It is suitble to the skin care item of user's facial skin.In other words, problems of the prior art are people usually according to the custom of itself
And the artificial of other users recommends, to select facial skin care products, to be judged and pushed away there is no a kind of real facial skin
That recommends more accurately recommends method to help user to select, and can not provide the association skin care scheme of skin care item so as in essence
The range of choice of user is expanded on the basis of really recommending.
Invention content
According to the above-mentioned problems in the prior art, a kind of facial skin care product and skin care proposal recommending method are now provided
Technical solution, it is intended to help user to select suitable skin care item by detecting facial skin state, solving user, independently selection is tired
Well-formedness, accuracy and the association skin Scheme Choice model based on accuracy of skin care item selection are promoted while the problem of hardly possible
It encloses, to promote user experience.
Above-mentioned technical proposal specifically includes:
A kind of facial skin care product and skin care proposal recommending method, wherein be in advance defined as the facial skin state of user
Including multiple first dimensional attributes, each first dimensional attribute is used to indicate a classification of the facial skin state,
And
In a Cloud Server multiple second dimensional attributes, second dimension are preset for each skin care item
Attribute is corresponded with first dimensional attribute, and each second dimensional attribute is for indicating the skin care item for correspondence
First dimensional attribute represented by one kind facial skin state improvement;
In the Cloud Server multiple skin care schemes, the skin care scheme packet are preset for each skin care item
The introductory offer for being associated with the skin care item is included, each introductory offer is respectively provided with second dimensional attribute;
Further include:
Step S1 obtains the facial image of user's face using an image acquisition device, and is uploaded to long-range connection
In the Cloud Server of described image harvester;
Step S2, the Cloud Server obtain all described of the facial skin state according to the face image processing
First dimensional attribute;
Step S3, the Cloud Server is according to all first dimensional attributes for being associated with the facial image and often
All second dimensional attributes of a skin care item, respectively processing obtain being associated with the recommendations of each skin care item and refer to
Number;
Step S4, the Cloud Server are from high to low ranked up all skin care item according to the recommendation index,
Skin care item described in selection top n form a recommendation results and feed back to the user terminal for remotely connecting the Cloud Server, described
Recommendation results include skin care item described in top n and are associated with the skin care scheme of skin care item described in top n.
Preferably, which recommends method, wherein first dimensional attribute includes:
The oil state and/or the facial skin of the moisture state of the facial skin and/or the facial skin
Cleannes state and/or the facial skin allergic state and/or the facial skin go out acne state and/or institute
The wrinkle state of the color spot state of facial skin and/or the colour of skin state of the facial skin and/or the facial skin is stated,
And/or the state of pores of the facial skin.
Preferably, which recommends method, wherein in the step S3, one is obtained according to following formula manipulation
The recommendation index of a skin care item:
A_i=X_1*Y_1_i+X_2*Y_2_i+...+X_N*Y_N_i;
Wherein, A is for indicating the recommendation index, and i is for indicating i-th of skin care item;
X_N is used to indicate the value of the first dimensional attribute described in the n-th in the facial image;
Y_N is used to indicate the value of the second dimensional attribute described in the n-th in the skin care item.
Preferably, which recommends method, wherein is set separately according to the operation instruction of each skin care item
All second dimensional attributes of each skin care item.
Preferably, which recommends method, wherein according to the Feedback Evaluation for the user for using the skin care item
All second dimensional attributes of each skin care item are set separately in statistical result.
Preferably, it includes one first sub- attribute and one which, which recommends method, each second dimensional attribute,
Second sub- attribute;
The first sub- attribute sets to be formed according to the operation instruction of the corresponding skin care item;
The second sub- attribute sets to be formed according to the statistical result of the Feedback Evaluation of the user of the corresponding skin care item;
In the step S3, the recommendation index of the skin care item is obtained according to following formula manipulation:
A_i=a*A1_i+(1-a)*A2_i;
Wherein, A is for indicating the recommendation index, the recommendation that A1 is used to indicate to handle according to the described first sub- attribute
Component, the recommendation component that A2 is used to indicate to handle according to the described second sub- attribute, i is for indicating i-th of skin care item;
A is constant.
Preferably, which recommends method, wherein obtains the described first sub- attribute according to following formula manipulation:
A1_ i=X_1*Y1_1_i+X_2*Y1_2_i+...+X_N*Y1_N_i;
Wherein, Y1_N is for indicating the first sub- attribute described in n-th.
Preferably, which recommends method, wherein obtains the described first sub- attribute according to following formula manipulation:
A2_ i=X_1*Y2_1_i+X_2*Y2_2_i+...+X_N*Y2_N_i;
Wherein, Y2_N is for indicating the second sub- attribute described in n-th.
Preferably, which recommends method, wherein described image harvester is arranged in a skin detection mirror
On;
In a wireless communication apparatus is arranged in the skin detection mirror, described image harvester connects the wireless telecommunications
Device, and the facial image is uploaded to by the Cloud Server by the wireless communication apparatus.
The advantageous effect of above-mentioned technical proposal is:A kind of facial skin care product and skin care proposal recommending method, Neng Goutong are provided
Crossing detection facial skin state helps user to select suitable skin care item, solves the problems, such as to carry while user independently selects difficulty
Well-formedness, accuracy and the association skin Scheme Choice range based on accuracy for rising skin care item selection, to promote user
Experience.
Description of the drawings
Fig. 1 is in the preferred embodiment of the present invention, and a kind of facial skin care product recommend the overall procedure schematic diagram of method;
Fig. 2 is in the preferred embodiment of the present invention, and 34 layer depths as image recognition and the kernel model of analysis are residual
The schematic diagram of poor network;
Fig. 3 be the present invention preferred embodiment in, on the basis of Fig. 2, the specific signal of one of residual error module
Figure.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art obtained under the premise of not making creative work it is all its
His embodiment, shall fall within the protection scope of the present invention.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the present invention can phase
Mutually combination.
The invention will be further described in the following with reference to the drawings and specific embodiments, but not as limiting to the invention.
Based on the above problem involved in the prior art, a kind of facial skin care product and skin care proposal recommending method are now provided,
In this method, in advance the facial skin state of user is defined as to include multiple first dimensional attributes, each first dimensional attribute
A classification for indicating facial skin state, and
In a Cloud Server multiple second dimensional attributes, the second dimensional attribute and are preset for each skin care item
Dimension attribute corresponds, and each second dimensional attribute is for indicating skin care item for represented by corresponding first dimensional attribute
A kind of facial skin state improvement;
It further include following step as shown in Figure 1:
Step S1 obtains the facial image of user's face using an image acquisition device, and is uploaded to long-range connection
In the Cloud Server of image collecting device;
Multiple skin care schemes are preset for each skin care item in Cloud Server, skin care scheme includes being associated with skin care
The introductory offer of product, each introductory offer are respectively provided with one second dimensional attribute;
Step S2, Cloud Server obtain all first dimensional attributes of facial skin state according to face image processing;
Step S3, Cloud Server is according to all first dimensional attributes and the institute of each skin care item for being associated with facial image
There is the second dimensional attribute, processing respectively obtains the recommendation index for being associated with each skin care item;
Step S4, Cloud Server select top n skin care according to recommending index to be ranked up from high to low to all skin care item
Product form the user terminal that a recommendation results simultaneously feed back to long-range connection Cloud Server, recommendation results include top n skin care item and
It is associated with the skin care scheme of top n skin care item.
In the present embodiment, first by the facial skin state of user there are many state, each state corresponds to one first
Dimensional attribute, each first dimensional attribute have a value, and the skin of corresponding type is indicated by the value of the first dimensional attribute
The present case of skin state.
Above-mentioned first dimensional attribute includes one or several kinds described below:
The moisture state of facial skin, cleannes state, allergic state, goes out acne state, color spot state, skin at oil state
Color state, wrinkle state and state of pores.
The value range of above-mentioned each first dimensional attribute not [0,1], wherein 0 expression the type skin condition be in
Worst situation, 1 indicates that the skin condition of the type is in best situation.
In the present embodiment, above-mentioned all first dimensional attributes form the set of first dimensional attribute, are adopted as image
The attribute set that the collected face images of acquisition means all have.Further, using image collecting device to
After family face is shot to obtain facial image, which is uploaded to Cloud Server, and to this in Cloud Server
Facial image is handled and is analyzed, to obtain the property set for including all first dimensional attributes corresponding to the facial image
It closes.
Correspondingly, include the second dimensional attribute in advance in Cloud Server for each skin care item in the present embodiment.On
It states the second dimensional attribute and the first dimensional attribute corresponds.Such as facial image includes one and is used to indicate face's moisture shape
First dimensional attribute of state, each skin care item are corresponded in Cloud Server just should be including one for indicating to face's moisture shape
The second dimensional attribute that state is improved.In another example facial image includes first dimension for indicating face's oil state
Attribute is spent, each skin care item are corresponded in Cloud Server should just improve face's oil state for indicating including one
The second dimensional attribute.
In the present embodiment, the value of above-mentioned second dimensional attribute is equally in [0,1], and specifically, 0 for indicating the skin care
Product do not improve the facial skin state represented by corresponding first dimensional attribute completely, and 1 for indicating the skin care item pair
Facial skin state represented by corresponding first dimensional attribute is improved completely.
In the present embodiment, for a width facial image, Cloud Server handles to obtain all the first of the facial image
After dimensional attribute, handles obtain each skin care item respectively according to these first dimensional attributes and corresponding second dimensional attribute
Recommend index, and these recommendation indexes are ranked up from high to low.Final Cloud Server is by the top n skin care item after sequence
And the association skin care scheme of top n skin care item is put into a recommendation results and is pushed to the use for remotely connecting the Cloud Server
Family terminal.Above-mentioned top n skin care item can be for first 5 or 10 first, is specifically voluntarily selected by user.It is each in Cloud Server
All there is skin care item corresponding association skin care scheme, association skin care scheme to include the skin care item and can match with the skin care item
Close other introductory offers (introductory offer is other skin care item and/or cosmetics) used, while recommending user's skin care item to
User recommends the association skin care scheme of the skin care item, and to be supplied to user than more complete skin care scheme, skin care scheme can be more
Mend the more unilateral problem of single skin care item effect.
In the preferred embodiment of the present invention, it can be arranged in above-mentioned Cloud Server and obtain the first dimension category for handling
Property processing model, processing model during training can by special training data being arranged to realizing, corresponding one
A specific processing model should be arranged to be handled and be analyzed in a first dimensional attribute.Some corresponding first dimension category
Property, the special training data which is arranged in the training process to may include the facial image obtained in advance and
It is commented for what facial skin state aspect progress artificial marking of the facial image represented by above-mentioned first dimensional attribute obtained
Estimate score.Such as the first dimensional attribute for face's moisture state, setting training data clock synchronization may include facial image with
And the corresponding facial image assesses score by the moisture manually given a mark;In another example for the first dimension of face's oil state
Attribute, setting data clock synchronization may include that facial image and the corresponding facial image are divided by the oil assessment manually given a mark
Number.
Further, in preferred embodiment of the invention, as shown in Figure 2 34 layers may be used in above-mentioned processing model
Depth residual error network to be formed to train, using the kernel model as facial image identification and attributive analysis.Above-mentioned 34 layer depth is residual
Each residual error module is specifically as shown in Figure 3 in poor network.
In the preferred embodiment of the present invention, in above-mentioned steps S3, skin care item are obtained according to following formula manipulation
Recommend index:
A_i=X_1*Y_1_i+X_2*Y_2_i+...+X_N*Y_N_i;
(1)
Wherein, A recommends index for indicating, i is for indicating i-th of skin care item;
X_N is used to indicate the value of the first dimensional attribute of n-th in facial image;
Y_N is used to indicate the value of the second dimensional attribute of n-th in skin care item.
X_N*Y_N may be used for indicating the skin care item for the skin condition represented by the first dimensional attribute of n-th
Improvement.All X_N*Y_N are added the whole of the face that can indicate the skin care item for the user corresponding to facial image
The recommendation index of body improvement namely the skin care item for the user.
In the preferred embodiment of the present invention, the second dimensional attribute of each skin care item is said by the use of the skin care item
Bright to obtain, i.e., developer determines the second of the skin care item according to the operation instruction (such as specification) of each skin care item in advance
Dimensional attribute.
In another preferred embodiment of the present invention, the second dimensional attribute of each skin care item is according to using the skin care
The statistical result of the Feedback Evaluation of the user of product is set respectively.Specifically, it can be carried out in advance for a skin care item
Investigation, the user for counting different are directed to using after the skin care item per the facial skin state represented by the first dimensional attribute of class
Improvement then sets each second dimensional attribute according to statistical result.It is right such as a skin care item
The improvement of face's oil state forms score according to statistical result and be 0.5 (score can be that one after counting puts down
Mean value), then the setting value that can will improve the second dimensional attribute of face's oil state is 0.5.In another example for a shield
Skin product, the improvement to face's allergic state are 0.8, then are 0.8 by the setting value of corresponding second dimensional attribute.
In the preferred embodiment of the present invention, according to actual conditions, above two can be set the second dimensional attribute
Method is used in combination, i.e., determines the second dimensional attribute of skin care item according to operation instruction first, and be directed in operation instruction not
The statistical result that the second dimensional attribute being related to is used using user sets to supplement, so that the second of each skin care item
Dimensional attribute is more complete.
In the preferred embodiment of the present invention, the second dimension that can also be obtained according to the different setting method of above two
Attribute comes to recommending index to carry out disposed of in its entirety.Specifically, each second dimensional attribute includes one first sub- attribute and one second
Sub- attribute;
First sub- attribute sets to be formed according to the operation instruction of corresponding skin care item;
Second sub- attribute sets to be formed according to the statistical result of the Feedback Evaluation of the user of corresponding skin care item;
In step S3, the recommendation index of a skin care item is obtained according to following formula manipulation:
A_i=a*A1_i+(1-a)*A2_i;
(2) wherein, A recommends index, A1 to be used to indicate the recommendation component that the first sub- attribute of foundation is handled for indicating,
The recommendation component that A2 is used to indicate to handle according to the second sub- attribute, i is for indicating i-th of skin care item;
A is constant, is specially the constant that can be adjusted according to actual effect.
Second dimensional attribute of the corresponding first method setting for before of above-mentioned first sub- attribute is (i.e. according to skin care item
Operation instruction is set), calculation is carried out according to above-mentioned formula (1), as:
A1_ i=X_1*Y1_1_i+X_2*Y1_2_i+...+X_N*Y1_N_i;
(3)
Second dimensional attribute of the corresponding second method setting for before of above-mentioned second sub- attribute is (i.e. according to skin care item
User's statistical result is set), calculation is carried out also according to above-mentioned formula (1), as:
A2_ i=X_1*Y2_1_i+X_2*Y2_2_i+...+X_N*Y2_N_i;(4)
By the recommendation component handled according to the first sub- attribute and the recommendation component handled according to the second sub- attribute
It is weighted the calculating of addition, to obtain final recommendation index.This method is also in conjunction with two kind of second dimensional attribute
Setting means so that finally obtained recommendation index is more accurate.
In the preferred embodiment of the present invention, above-mentioned image collecting device is arranged on a skin detection mirror, further
Above-mentioned image collecting device can be a camera, can be arranged in the surface of skin detection mirror, so as to complete
Ground takes the front face of user.The appearance of above-mentioned skin detection mirror can be that common being placed on is made up on table
Or the vanity mirror on wall.
Further, in a wireless communication apparatus is arranged in skin detection mirror, image collecting device connects wireless telecommunications dress
It sets, and facial image is uploaded to by Cloud Server by wireless communication apparatus.Above-mentioned wireless communication apparatus can be logical for WiFi
Device is interrogated, long-range Cloud Server can be connected by the router of indoor setting, and image collecting device is supplied to carry out
Data transmission.
In the preferred embodiment of the present invention, the user terminal that user uses can be bound with above-mentioned skin detection mirror, tool
Body, the user of the ID number and the user using the skin detection mirror on skin detection mirror can be realized by Cloud Server in advance
The operation that terminal is bound, what subsequent Cloud Server can analyze the facial image uploaded according to skin detection mirror
Recommendation results are issued in the user terminal corresponding to the skin detection mirror, so that user checks.
The foregoing is merely preferred embodiments of the present invention, are not intended to limit embodiments of the present invention and protection model
It encloses, to those skilled in the art, should can appreciate that all with made by description of the invention and diagramatic content
Equivalent replacement and obviously change obtained scheme, should all be included within the scope of the present invention.
Claims (9)
1. a kind of facial skin care product and skin care proposal recommending method, which is characterized in that in advance determine the facial skin state of user
Justice be include multiple first dimensional attributes, each first dimensional attribute is used to indicate one point of the facial skin state
Class, and
In a Cloud Server multiple second dimensional attributes, second dimensional attribute are preset for each skin care item
It is corresponded with first dimensional attribute, each second dimensional attribute is for indicating the skin care item for corresponding institute
State the improvement of one kind facial skin state represented by the first dimensional attribute;
Multiple skin care schemes are preset for each skin care item in the Cloud Server, the skin care scheme includes closing
It is coupled to the introductory offer of the skin care item, each introductory offer is respectively provided with second dimensional attribute;
Further include:
Step S1 obtains the facial image of user's face using an image acquisition device, and is uploaded to long-range connection image
In the Cloud Server of harvester;
Step S2, Cloud Server obtain all first dimensional attributes of facial skin state according to face image processing;
Step S3, Cloud Server is according to all the of all first dimensional attributes and each skin care item for being associated with facial image
Two-dimensions attribute, respectively processing obtain the recommendation index for being associated with each skin care item;
Step S4, Cloud Server select top n skin care item shape according to recommending index to be ranked up from high to low to all skin care item
At a recommendation results and the long-range user terminal for connecting Cloud Server is fed back to, recommendation results include top n skin care item and association
In the skin care scheme of top n skin care item.
2. facial skin care product as described in claim 1 and skin care proposal recommending method, which is characterized in that the first dimension category
Property includes:
The oil state and/or the facial skin of the moisture state of the facial skin and/or the facial skin it is clear
The allergic state and/or the facial skin of cleanliness state and/or the facial skin go out acne state and/or the face
The wrinkle state of the color spot state of portion's skin and/or the colour of skin state of the facial skin and/or the facial skin, and/
Or the state of pores of the facial skin.
3. facial skin care product as described in claim 1 and skin care proposal recommending method, which is characterized in that in the step S3,
The recommendation index of the skin care item is obtained according to following formula manipulation:
A_i=X_1*Y_1_i+X_2*Y_2_i+...+X_N*Y_N_i;
Wherein, A is for indicating the recommendation index, and i is for indicating i-th of skin care item;
X_N is used to indicate the value of the first dimensional attribute described in the n-th in the facial image;
Y_N is used to indicate the value of the second dimensional attribute described in the n-th in the skin care item.
4. facial skin care product as described in claim 1 and skin care proposal recommending method, which is characterized in that according to each shield
All second dimensional attributes of each skin care item are set separately in the operation instruction of skin product.
5. facial skin care product as described in claim 1 and skin care proposal recommending method, which is characterized in that according to using the shield
All second dimensional attributes of each skin care item are set separately in the statistical result of the Feedback Evaluation of the user of skin product.
6. facial skin care product as described in claim 1 and skin care proposal recommending method, each second dimensional attribute include
One first sub- attribute and one second sub- attribute;
The first sub- attribute sets to be formed according to the operation instruction of the corresponding skin care item;
The second sub- attribute sets to be formed according to the statistical result of the Feedback Evaluation of the user of the corresponding skin care item;
In the step S3, the recommendation index of the skin care item is obtained according to following formula manipulation:
A_i=a*A1_i+(1-a)*A2_i;
Wherein, A is for indicating the recommendation index, the recommended hour that A1 is used to indicate to handle according to the described first sub- attribute
Amount, the recommendation component that A2 is used to indicate to handle according to the described second sub- attribute, i is for indicating i-th of skin care item;
A is constant.
7. facial skin care product as claimed in claim 6 and skin care proposal recommending method, which is characterized in that at following formula
Reason obtains the described first sub- attribute:
A1_ i=X_1*Y1_1_i+X_2*Y1_2_i+...+X_N*Y1_N_i;
Wherein, Y1_N is for indicating the first sub- attribute described in n-th.
8. facial skin care product as claimed in claim 6 and skin care proposal recommending method, which is characterized in that at following formula
Reason obtains the described first sub- attribute:
A2_ i=X_1*Y2_1_i+X_2*Y2_2_i+...+X_N*Y2_N_i;
Wherein, Y2_N is for indicating the second sub- attribute described in n-th.
9. facial skin care product as described in claim 1 and skin care proposal recommending method, which is characterized in that described image acquisition dress
It installs on a skin detection mirror;
In a wireless communication apparatus is arranged in the skin detection mirror, described image harvester connects the wireless telecommunications dress
It sets, and the facial image is uploaded to by the Cloud Server by the wireless communication apparatus.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810084756.7A CN108364207A (en) | 2018-01-29 | 2018-01-29 | A kind of facial skin care product and skin care proposal recommending method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810084756.7A CN108364207A (en) | 2018-01-29 | 2018-01-29 | A kind of facial skin care product and skin care proposal recommending method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108364207A true CN108364207A (en) | 2018-08-03 |
Family
ID=63007242
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810084756.7A Pending CN108364207A (en) | 2018-01-29 | 2018-01-29 | A kind of facial skin care product and skin care proposal recommending method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108364207A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109381165A (en) * | 2018-09-12 | 2019-02-26 | 维沃移动通信有限公司 | A kind of skin detecting method and mobile terminal |
CN110033344A (en) * | 2019-03-06 | 2019-07-19 | 百度在线网络技术(北京)有限公司 | Skin care item recommended method, device and storage medium neural network based |
CN111161007A (en) * | 2019-01-31 | 2020-05-15 | 深圳碳云智能数字生命健康管理有限公司 | Product information processing method and device, computer equipment and storage medium |
WO2020135778A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳碳云智能数字生命健康管理有限公司 | Product information pushing and displaying method and device, and storage medium |
CN113421150A (en) * | 2021-07-21 | 2021-09-21 | 北京沃东天骏信息技术有限公司 | Article recommendation method, article recommendation device, storage medium, and electronic device |
CN117351545A (en) * | 2023-10-11 | 2024-01-05 | 广东圣千科技有限公司 | Skin care management method and system based on big data mining |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
CN105982640A (en) * | 2015-01-28 | 2016-10-05 | 鸿富锦精密工业(深圳)有限公司 | Automatic skin care device and automatic skin care method |
CN107122989A (en) * | 2017-03-21 | 2017-09-01 | 浙江工业大学 | A kind of multi-angle towards cosmetics mixes recommendation method |
CN107280350A (en) * | 2017-06-12 | 2017-10-24 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
US9842358B1 (en) * | 2012-06-19 | 2017-12-12 | Brightex Bio-Photonics Llc | Method for providing personalized recommendations |
-
2018
- 2018-01-29 CN CN201810084756.7A patent/CN108364207A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9842358B1 (en) * | 2012-06-19 | 2017-12-12 | Brightex Bio-Photonics Llc | Method for providing personalized recommendations |
CN105982640A (en) * | 2015-01-28 | 2016-10-05 | 鸿富锦精密工业(深圳)有限公司 | Automatic skin care device and automatic skin care method |
CN105117924A (en) * | 2015-07-01 | 2015-12-02 | 向莉妮 | Personalized commodity recommendation system |
CN107122989A (en) * | 2017-03-21 | 2017-09-01 | 浙江工业大学 | A kind of multi-angle towards cosmetics mixes recommendation method |
CN107280350A (en) * | 2017-06-12 | 2017-10-24 | 美的集团股份有限公司 | Control method, control device, Intelligent mirror and computer-readable recording medium |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109381165A (en) * | 2018-09-12 | 2019-02-26 | 维沃移动通信有限公司 | A kind of skin detecting method and mobile terminal |
WO2020135778A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳碳云智能数字生命健康管理有限公司 | Product information pushing and displaying method and device, and storage medium |
CN111161007A (en) * | 2019-01-31 | 2020-05-15 | 深圳碳云智能数字生命健康管理有限公司 | Product information processing method and device, computer equipment and storage medium |
WO2020156109A1 (en) * | 2019-01-31 | 2020-08-06 | 深圳碳云智能数字生命健康管理有限公司 | Product information processing method, apparatus, computer device and storage medium |
CN110033344A (en) * | 2019-03-06 | 2019-07-19 | 百度在线网络技术(北京)有限公司 | Skin care item recommended method, device and storage medium neural network based |
CN113421150A (en) * | 2021-07-21 | 2021-09-21 | 北京沃东天骏信息技术有限公司 | Article recommendation method, article recommendation device, storage medium, and electronic device |
CN117351545A (en) * | 2023-10-11 | 2024-01-05 | 广东圣千科技有限公司 | Skin care management method and system based on big data mining |
CN117351545B (en) * | 2023-10-11 | 2024-03-15 | 广东圣千科技有限公司 | Skin care management method and system based on big data mining |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108364207A (en) | A kind of facial skin care product and skin care proposal recommending method | |
CN108334589A (en) | A kind of facial skin care product recommendation method | |
CN108198043A (en) | A kind of facial skin care product recommended based on user recommend method | |
CN104850825B (en) | A kind of facial image face value calculating method based on convolutional neural networks | |
Phan et al. | Color orchestra: Ordering color palettes for interpolation and prediction | |
CN106413555B (en) | Concentration degree evaluating apparatus and program | |
Sartori et al. | Who's afraid of itten: Using the art theory of color combination to analyze emotions in abstract paintings | |
CN104981830A (en) | Clothing matching system and method | |
CN106920277A (en) | Simulation beauty and shaping effect visualizes the method and system of online scope of freedom carving | |
CN108335727A (en) | A kind of facial skin care product recommendation method based on historical record | |
CN105378781A (en) | Made-to-order system for cosmetics, and compounding system | |
CN108492294A (en) | A kind of appraisal procedure and device of image color harmony degree | |
CN107018330A (en) | A kind of guidance method and device of taking pictures in real time | |
CN110047071A (en) | A kind of image quality measure method, apparatus and medium | |
CN109584153A (en) | Modify the methods, devices and systems of eye | |
CN108876930A (en) | A kind of personal image management application method and system | |
CN107992783A (en) | Face image processing process and device | |
CN110288097A (en) | A kind of method and relevant apparatus of model training | |
CN109559362A (en) | A kind of image subject face replacement method and device | |
CN111582450A (en) | Neural network model training method based on parameter evaluation and related device | |
CN110074788A (en) | A kind of body data acquisition methods and device based on machine learning | |
CN108324247A (en) | A kind of designated position wrinkle of skin appraisal procedure and system | |
CN108269175A (en) | A kind of facial skin care product of combination user custom recommend method | |
CN108363964A (en) | A kind of pretreated wrinkle of skin appraisal procedure and system | |
CN113779289A (en) | Drawing step reduction system based on artificial intelligence |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180803 |
|
RJ01 | Rejection of invention patent application after publication |