CN109544262A - Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing - Google Patents
Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing Download PDFInfo
- Publication number
- CN109544262A CN109544262A CN201811156779.0A CN201811156779A CN109544262A CN 109544262 A CN109544262 A CN 109544262A CN 201811156779 A CN201811156779 A CN 201811156779A CN 109544262 A CN109544262 A CN 109544262A
- Authority
- CN
- China
- Prior art keywords
- article
- user
- shape
- recommended
- 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
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention provides a kind of item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing, this method comprises: obtaining the shape of face information of user;According to the shape of face information and the first mapping relations of the user, determine at least one objective attribute target attribute corresponding with the shape of face information of the user, first mapping relations are used to indicate the mapping relations of each first combination and recommendation, the combination of the described first group attribute for being combined into shape of face information and article to be recommended, the corresponding recommendation of the objective attribute target attribute are greater than or equal to default recommendation threshold value;Push the information of the corresponding article to be recommended of at least one described objective attribute target attribute.This method, which can be realized, fast and accurately recommends article to user, so that be greatly saved article chooses the time, promotes the experience of user, promotes the income of businessman.
Description
Technical field
The present embodiments relate to computer technology more particularly to a kind of item recommendation method, device, electronic equipment, it is
System and readable storage medium storing program for executing.
Background technique
For actual needs, some people need wearing spectacles to promote eyesight, it is therefore desirable to choose glasses.
In the prior art, when user buys glasses, the subjective judgement of user or the warp of glasses sales force are relied primarily on
It tests to select the glasses that may be suitble to the user.
But the glasses picked out by subjective judgement or experience may be not appropriate for the user, then user needs weight
It is newly selected, so that the process for choosing glasses is complicated, not only influences the experience of user, it is also possible to will affect the quotient of sale glasses
The income of family.
Summary of the invention
The embodiment of the present invention provides a kind of item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing, uses
It is complicated in solving the problems, such as to choose glasses process in the prior art.
First aspect of the embodiment of the present invention provides a kind of item recommendation method, which comprises
Obtain the shape of face information of user;
According to the shape of face information and the first mapping relations of the user, determination is corresponding extremely with the shape of face information of the user
A few objective attribute target attribute, first mapping relations are used to indicate the mapping relations of each first combination and recommendation, and described the
The combination of one group of attribute for being combined into shape of face information and article to be recommended, the corresponding recommendation of the objective attribute target attribute are greater than or equal to pre-
If recommendation threshold value;
Push the information of the corresponding article to be recommended of at least one described objective attribute target attribute.
Further, the shape of face information and the first mapping relations according to the user, the determining face with the user
Before at least one corresponding objective attribute target attribute of type information, further includes:
Obtain first mapping relations.
Further, before acquisition first mapping relations, further includes:
Obtain the picture of each of article set to be recommended article to be recommended;
According to the picture of each article to be recommended, the characteristic information of each article to be recommended is extracted;
According to the characteristic information of each article to be recommended, and, the mapping relations of characteristic information and attribute determine every
The attribute of a article to be recommended.
It is further, described to obtain first mapping relations, comprising:
According to every kind of shape of face information, the attribute of each article to be recommended, each first combination is obtained;
According to each first combination, the corresponding recommendation of each first combination is determined;
Corresponding recommendation is combined according to each described first, establishes first mapping relations.
Further, the shape of face information for obtaining user, comprising:
Receive the shape of face information of the user input by user.
Further, the shape of face information for obtaining user, comprising:
Obtain the facial image of the user;
According to the facial image, the face characteristic of the user is identified;
According to the face characteristic of the user, and, the mapping relations of face characteristic and shape of face information determine the user
Shape of face information.
Further, the attribute includes at least one of following:
The shape of the article, the color of the article, the mark of the article.
Further, the article to be recommended is glasses.
Second aspect of the embodiment of the present invention provides a kind of article recommendation apparatus, and described device includes:
First obtains module, for obtaining the shape of face information of user;
First determining module, for the shape of face information and the first mapping relations according to the user, the determining and user
At least one corresponding objective attribute target attribute of shape of face information, first mapping relations be used to indicate it is each first combination and recommendation
Mapping relations, the combination of the described first group attribute for being combined into shape of face information and article to be recommended, the objective attribute target attribute is corresponding
Recommendation is greater than or equal to default recommendation threshold value;
Pushing module, for pushing the information of the corresponding article to be recommended of at least one described objective attribute target attribute.
Further, further includes:
Second obtains module, for obtaining first mapping relations.
Further, further includes:
Third obtains module, for obtaining the picture of each of article set to be recommended article to be recommended;
Extraction module extracts the spy of each article to be recommended for the picture according to each article to be recommended
Reference breath;
Second determining module, for the characteristic information according to each article to be recommended, and, characteristic information and attribute
Mapping relations, determine the attribute of each article to be recommended.
Further, the second acquisition module includes:
First acquisition unit obtains each institute for the attribute according to every kind of shape of face information, each article to be recommended
State the first combination;
Determination unit, for determining the corresponding recommendation of each first combination according to each first combination;
Unit is established, for combining corresponding recommendation according to each described first, establishes first mapping relations.
Further, the first acquisition module includes:
Receiving unit, for receiving the shape of face information of the user input by user.
Further, described first module is obtained further include::
Second acquisition unit, for obtaining the facial image of the user;
Recognition unit, for identifying the face characteristic of the user according to the facial image;
Second determination unit, for the face characteristic according to the user, and, the mapping of face characteristic and shape of face information
Relationship determines the shape of face information of the user.
Further, the attribute includes at least one of following:
The shape of the article, the color of the article, the mark of the article.
Further, the article to be recommended is glasses.
The third aspect of the embodiment of the present invention provides a kind of electronic equipment, comprising:
Memory, for storing program instruction;
Processor executes side described in above-mentioned first aspect for calling and executing the program instruction in the memory
Method step.
Fourth aspect of the embodiment of the present invention provides a kind of article recommender system, sets including electronics described in the above-mentioned third aspect
It is standby.
The 5th aspect of the embodiment of the present invention provides a kind of readable storage medium storing program for executing, and calculating is stored in the readable storage medium storing program for executing
Machine program, the computer program is for executing method described in above-mentioned first aspect.
Item recommendation method, device provided by the embodiment of the present invention, electronic equipment, system and readable storage medium storing program for executing, base
In the user of shopping goods shape of face information and can indicate the combination of shape of face and goods attribute and the mapping relations of recommendation,
Can determine with the matched objective attribute target attribute of the shape of face of user, since the mapping relations can embody user's shape of face, goods attribute
And therefore the relationship of recommendation can be based on the mapping relations and the obtained objective attribute target attribute of user's shape of face information
It for can be with attribute recommended to the user, and then realizes and fast and accurately recommends article to user, to be greatly saved the choosing of article
The time is purchased, the experience of user is promoted, promotes the income of businessman.
Detailed description of the invention
It, below will be to embodiment or the prior art in order to illustrate more clearly of the present invention or technical solution in the prior art
Attached drawing needed in description is briefly described, it should be apparent that, the accompanying drawings in the following description is of the invention one
A little embodiments for those of ordinary skill in the art without any creative labor, can also be according to this
A little attached drawings obtain other attached drawings.
Fig. 1 is a kind of illustrative system architecture diagram;
Fig. 2 is the flow diagram of item recommendation method embodiment one provided in an embodiment of the present invention;
Fig. 3 is the flow diagram of item recommendation method embodiment two provided in an embodiment of the present invention;
Fig. 4 is the flow diagram of item recommendation method embodiment three provided in an embodiment of the present invention;
Fig. 5 is the flow diagram of item recommendation method example IV provided in an embodiment of the present invention;
Fig. 6 provides a kind of function structure chart of article recommendation apparatus embodiment one for the embodiment of the present invention;
Fig. 7 provides a kind of function structure chart of article recommendation apparatus embodiment two for the embodiment of the present invention;
Fig. 8 provides a kind of function structure chart of article recommendation apparatus embodiment three for the embodiment of the present invention;
Fig. 9 provides a kind of function structure chart of article recommendation apparatus example IV for the embodiment of the present invention;
Figure 10 provides a kind of function structure chart of article recommendation apparatus embodiment five for the embodiment of the present invention;
Figure 11 provides a kind of function structure chart of article recommendation apparatus embodiment six for the embodiment of the present invention;
Figure 12 is the entity block diagram of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached in the embodiment of the present invention
Figure, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Item recommendation method provided by the embodiment of the present invention can be adapted in the scene of shopping goods.Either on line
It chooses and chooses mode under mode or line, provided method can be pushed away through the embodiment of the present invention to user's progress article
It recommends.Fig. 1 is a kind of illustrative system architecture diagram, as shown in Figure 1, the embodiment of the present invention can be related to terminal and server, it should
Terminal can be the terminal in merchant store, thereon can be to run on-line selling system on deploying client or the terminal
Client to acquire the information of the article in the merchant store and patronize the shape of face information of merchant store user, and will adopt
The information collected is sent to server, and server can provided method be through the embodiment of the present invention that user's progress article pushes away
It recommends.In addition to system architecture shown in FIG. 1, the embodiment of the present invention is also based on independent electronic equipment to execute, for example, by quotient
Terminal in family shop carrys out execution information acquisition and article is recommended.
For ease of description, the main body for executing present invention method is referred to as " electronic equipment " by the embodiment of the present invention.
Fig. 2 is the flow diagram of item recommendation method embodiment one provided in an embodiment of the present invention, the execution of this method
Main body can be above-mentioned electronic equipment, as shown in Fig. 2, this method comprises:
S201, the shape of face information for obtaining user.
Optionally, above-mentioned user can be for just in the user of shopping goods.
Optionally, the shape of face information of user can refer to shape of face type of user, such as square face, round face etc..
S202, shape of face information and the first mapping relations according to above-mentioned user, the determining shape of face information pair with above-mentioned user
At least one objective attribute target attribute answered.
Wherein, above-mentioned first mapping relations are used to indicate each first combination and the mapping relations of recommendation, and this first group
It is combined into the combination of the attribute of shape of face information and article to be recommended, the corresponding recommendation of above-mentioned objective attribute target attribute is greater than or equal to default push away
Degree of recommending threshold value.
Optionally, article to be recommended involved in the embodiment of the present invention can be glasses.
Optionally, above-mentioned recommendation article can also be other articles being worn on, such as cap, ear pendant
Deng the embodiment of the present invention is not specifically limited in this embodiment.
Optionally, above-mentioned attribute refers to the attribute of article to be recommended, which can be at least one in following:
The mark of the shape of article, the color of article and article.
Illustratively, it is assumed that article to be recommended is glasses, and the attribute of article to be recommended is the number and glasses of glasses
Shape then in embodiments of the present invention for every a glasses that businessman is sold, can determine its shape, and will first
Number, shape and each shape of face of the glasses respectively obtain a combination and combine to get to multiple first.For example, businessman
The number of certain a glasses be 1, shape is circle, and possible shape of face information includes round face and square face, then is directed to the glasses, can
To there is 2 first combinations, first are as follows: number 1, circle, round face, second are as follows: number 1, circle, square face.
In turn, in embodiments of the present invention, available to first combination and recommendation for each first combination
Mapping relations, referred to as the first mapping relations.It is available first to arrive above-mentioned first mapping relations i.e. before this step.First
Combination can have it is multiple, correspondingly, the first mapping relations can also have it is multiple.
Wherein, above-mentioned recommendation is used for the recommendation degree of marking articles, and recommendation for example may include recommending, being general, no
Recommend etc..
Illustratively, above-mentioned first first is combined, the first corresponding mapping relations is first combinations and push away
The corresponding relationship recommended then illustrates the user for round face, the shape of face which is 1, shape is circular glasses Yu the user
Match, can recommend that the number is 1, shape is circular glasses to the user of the round face.
In turn, in this step, electronic equipment shape of face information based on the user of shopping goods and can be got
First mapping relations determine at least one objective attribute target attribute.
Illustratively, electronic equipment can be selected from multiple first mapping relations and match (example with the shape of face of the user
As identical) the first mapping relations, then select recommendation for the mapping relations of " recommendation " from the first mapping relations selected,
Using the attribute in the first combination included in these mapping relations as objective attribute target attribute.For example, being round face for a shape of face
User, electronic equipment pass through the process, can will " circle " be used as objective attribute target attribute, then explanation can to the user recommendation circle
Glasses.
The information of S203, the corresponding article to be recommended of at least one above-mentioned objective attribute target attribute of push.
Illustratively, electronic equipment can choose the glasses that shape in all glasses of Merchant sales is " circle ", by this
The information of a little glasses is pushed to the user for currently choosing glasses.
In a kind of optional way, the information of above-mentioned article to be recommended can be picture and text.
Illustratively, electronic equipment can believe the picture of the article with above-mentioned objective attribute target attribute and price, material etc.
Breath is shown to user one by one.
In another way, the information of above-mentioned article to be recommended can be augmented reality (Augmented Reality, letter
Claim AR) image.
Illustratively, electronic equipment can generate AR image for the article with above-mentioned objective attribute target attribute, and capture user
Face image, in turn, on face image of the AR image superposition to user for the article that will have above-mentioned objective attribute target attribute.
In the present embodiment, the shape of face information of the user based on shopping goods and the group that can indicate shape of face and goods attribute
Close with the mapping relations of recommendation, can determine with the matched objective attribute target attribute of the shape of face of user, since the mapping relations can
Therefore the relationship for embodying user's shape of face, goods attribute and recommendation can be based on the mapping relations and user's shape of face
The obtained objective attribute target attribute of information is can be with attribute recommended to the user, and then realizes and fast and accurately recommend article to user,
The time is chosen to be greatly saved article, the experience of user is promoted, promotes the income of businessman.
On the basis of the above embodiments, it is to be recommended to be related to the determination before obtaining above-mentioned first mapping relations for the present embodiment
The process of the attribute of article.
Fig. 3 is the flow diagram of item recommendation method embodiment two provided in an embodiment of the present invention, as shown in figure 3,
Before obtaining above-mentioned first mapping relations, further includes:
S301, the picture for obtaining each of article set to be recommended article to be recommended.
Optionally, above-mentioned article set to be recommended can be the collection as composed by businessman's all or part of article for sale
It closes.
In the specific implementation process, businessman can take the picture of article for sale in advance, and by these articles
Picture inputs in electronic equipment, these pictures can be saved as above-mentioned article set to be recommended by electronic equipment.
S302, according to the picture of each above-mentioned article to be recommended, extract the characteristic information of each above-mentioned article to be recommended.
S303, according to the characteristic information of each above-mentioned article to be recommended, and, the mapping relations of characteristic information and attribute,
Determine the attribute of each above-mentioned article to be recommended.
In a kind of optional way, the feature that article to be recommended can be extracted by one goods attribute model of training is believed
Breath, and determine the attribute of each article to be recommended.
Wherein, above-mentioned goods attribute model can first pass through a large amount of labeled data in advance and be trained.
In turn, in the present embodiment, the picture of each article to be recommended is input in above-mentioned goods attribute model one by one,
The goods attribute model can therefrom extract the characteristic information of article to be recommended, and this feature information for example can be the side of article
Angle, radian of frame etc..In turn, characteristic information and characteristic information and attribute of the goods attribute model based on acquisition reflect
Relationship is penetrated, determines the attribute of article to be recommended.Wherein, the mapping relations of characteristic information and attribute can by training come
It arrives.
Illustratively, it is assumed that article to be recommended is glasses, when being trained data mark, can define the attribute of glasses
For shape of glasses, also, shape of glasses may include round and rectangular, then can be circle by the corresponding attribute labeling of training data
Shape is rectangular.In turn, in the present embodiment, the picture of some glasses for sale of businessman is input to goods attribute model
Afterwards, i.e., it is exportable this it is items for sale to be round or rectangular as a result, to obtain the attribute of the article.
On the basis of the above embodiments, the present embodiment is related to obtaining a kind of optional way of above-mentioned first mapping relations.
Fig. 4 is the flow diagram of item recommendation method embodiment three provided in an embodiment of the present invention, as shown in figure 4, obtaining
A kind of optional way for taking above-mentioned first mapping relations may include:
S401, according to every kind of shape of face information, each state the attribute of article to be recommended, obtain each above-mentioned first combination.
Optionally, in specific implementation process, a variety of shape of face information, such as round face, square face etc. can be pre-defined.
In turn, it on the basis of obtaining the attribute of each article to be recommended by the above process, can establish each to be recommended
The attribute of article is combined with the first of every kind of shape of face information.
Illustratively, shape of face information predetermined includes round face and square two kinds of face, and there are two articles to be recommended, an object
The number of product is 1, shape be circle, the number of another article is 2, shape be it is rectangular, then available following four kind first
Combination:
(1) number 1, circle, round face
(2) number 1, circle, square face
(3) number 2, rectangular, round face
(4) number 2, rectangular, square face
S402, it is combined according to each described first, determines the corresponding recommendation of each above-mentioned first combination.
In a kind of optional way, the corresponding recommendation of the first combination can be determined by one recommendation model of training.
Wherein, above-mentioned recommendation model can first pass through a large amount of labeled data in advance and be trained.
In turn, in the present embodiment, each first combination is input in above-mentioned recommendation model one by one, the recommendation mould
Type can obtain the attribute of shape of face information and article first, in turn, the attribute of feature and article based on shape of face information
Feature exports the first combined recommendation, such as recommends, is general, not recommending.
It should be noted that class included by attribute and recommendation of the embodiment of the present invention for shape of face information, article
Type is only illustrative, and in the specific implementation process, can according to need, to the attribute and recommendation of shape of face information, article
Carry out fine-grained division.Correspondingly, can choose described in training book step when recommendation model and largely belong to difference
The training data of shape of face, attribute or recommendation, so that model can export recommendation result more acurrate, that granularity is thinner.
S403, corresponding recommendation is combined according to each above-mentioned first, establishes above-mentioned first mapping relations.
After obtaining the corresponding recommendation of each first combination, it can combine the two, to form the first mapping relations.
By taking the example in above-mentioned steps S401 as an example, it is assumed that above-mentioned four kind of first combination determined by step S402
Recommendation successively are as follows: recommend, be general, not recommending and recommend, then can establish the first mapping relations shown in following table 1:
Table 1
First mapping relations number | First combination | Recommendation |
1 | Number 1, circle, round face | Recommend |
2 | Number 1, circle, square face | Generally |
3 | Number 2, rectangular, round face | Do not recommend |
4 | Number 2, rectangular, square face | Recommend |
On the basis of the above embodiments, the present embodiment is related to the method for obtaining the shape of face information of user.
In a kind of optional mode, shape of face information can be inputted by user, i.e. electronic equipment can receive by user
The shape of face information of the user of input.
Illustratively, electronic equipment can show possible shape of face information predetermined, be selected by user
Shape of face belonging to oneself.
In another optional mode, the shape of face information of user can also be obtained by following mode.
Fig. 5 is the flow diagram of item recommendation method example IV provided in an embodiment of the present invention, as shown in figure 5, on
Stating step S201 includes:
S501, the facial image for obtaining above-mentioned user.
Optionally, electronic equipment can acquire the facial image of user by equipment such as cameras.
Illustratively, it is assumed that electronic equipment is above-mentioned server, then server can indicate to be deployed in merchant store
Terminal shooting user facial image, captured facial image is sent to server again by terminal.
Optionally, multiple face pictures of the available above-mentioned user of electronic equipment, in turn, according to picture clarity, angle
The information such as degree, integrity degree are screened, and therefrom select the highest width face of mass as the subsequent treatment process of user.
S502, according to above-mentioned facial image, identify the face characteristic of above-mentioned user.
S503, according to the face characteristic of above-mentioned user, and, the mapping relations of face characteristic and shape of face information, in determination
State the shape of face information of user.
In a kind of optional way, the face characteristic of user can be identified by one shape of face disaggregated model of training, and
Determine the shape of face information of user.
Wherein, above-mentioned shape of face disaggregated model can first pass through a large amount of labeled data in advance and be trained.
In turn, in the present embodiment, the face picture that will acquire is input in above-mentioned face classification model, the face point
Class model can extract face characteristic from face picture China, which for example can be angle, the arc of facial contour
Degree etc..In turn, the mapping relations of face characteristic and face characteristic and shape of face information of the face disaggregated model based on acquisition,
Determine the shape of face information of user.Wherein, face characteristic and the mapping relations of shape of face information can be obtained by training.
Illustratively, it is assumed that the shape of face information of definition includes round face and square face, then can be by the corresponding shape of face of training data
Information labeling is round face or square face.In turn, in the present embodiment, the face picture of user is input to above-mentioned face classification model
Afterwards, i.e., the shape of face of exportable user is round face or square face as a result, to obtain the shape of face information of user.
Fig. 6 provides a kind of function structure chart of article recommendation apparatus embodiment one for the embodiment of the present invention, as shown in fig. 6,
The device includes:
First obtains module 601, for obtaining the shape of face information of user.
First determining module 602, for the shape of face information and the first mapping relations according to the user, the determining and use
At least one corresponding objective attribute target attribute of the shape of face information at family, first mapping relations are used to indicate each first combination and recommend
The mapping relations of degree, the combination of the described first group attribute for being combined into shape of face information and article to be recommended, the objective attribute target attribute are corresponding
Recommendation be greater than or equal to default recommendation threshold value.
Pushing module 603, for pushing the information of the corresponding article to be recommended of at least one described objective attribute target attribute.
The device is for realizing preceding method embodiment, and it is similar that the realization principle and technical effect are similar, and details are not described herein again.
Fig. 7 provides a kind of function structure chart of article recommendation apparatus embodiment two for the embodiment of the present invention, as shown in fig. 7,
The device further include:
Second obtains module 604, for obtaining first mapping relations.
Fig. 8 provides a kind of function structure chart of article recommendation apparatus embodiment three for the embodiment of the present invention, as shown in figure 8,
The device further include:
Third obtains module 605, for obtaining the picture of each of article set to be recommended article to be recommended.
Extraction module 606 extracts each article to be recommended for the picture according to each article to be recommended
Characteristic information.
Second determining module 607, for the characteristic information according to each article to be recommended, and, characteristic information with
The mapping relations of attribute determine the attribute of each article to be recommended.
Fig. 9 provides a kind of function structure chart of article recommendation apparatus example IV for the embodiment of the present invention, as shown in figure 9,
Second, which obtains module 604, includes:
First acquisition unit 6041 obtains every for the attribute according to every kind of shape of face information, each article to be recommended
A first combination.
First determination unit 6042, for determining that each first combination is corresponding according to each first combination
Recommendation.
Unit 6043 is established, for combining corresponding recommendation according to each described first, first mapping is established and closes
System.
Figure 10 provides a kind of function structure chart of article recommendation apparatus embodiment five for the embodiment of the present invention, such as Figure 10 institute
Show, the first acquisition module 601 includes:
Receiving unit 6011, for receiving the shape of face information of the user input by user.
Figure 11 provides a kind of function structure chart of article recommendation apparatus embodiment six for the embodiment of the present invention, such as Figure 11 institute
Show, first obtains module 601 further include:
Second acquisition unit 6012, for obtaining the facial image of the user.
Recognition unit 6013, for identifying the face characteristic of the user according to the facial image.
Second determination unit 6014, for the face characteristic according to the user, and, face characteristic and shape of face information
Mapping relations determine the shape of face information of the user.
In another embodiment, the attribute includes at least one of following:
The shape of the article, the color of the article, the mark of the article.
In another embodiment, the article to be recommended is glasses.
Figure 12 is the entity block diagram of electronic equipment provided in an embodiment of the present invention, as shown in figure 12, the electronic equipment 1200
Include:
Memory 1201, for storing program instruction.
Processor 1202 executes in above method embodiment for calling and executing the program instruction in memory 1201
Method and step.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above-mentioned each method embodiment can lead to
The relevant hardware of program instruction is crossed to complete.Program above-mentioned can be stored in a computer readable storage medium.The journey
When being executed, execution includes the steps that above-mentioned each method embodiment to sequence;And storage medium above-mentioned include: ROM, RAM, magnetic disk or
The various media that can store program code such as person's CD.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations;To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement;And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (19)
1. a kind of item recommendation method, which is characterized in that the described method includes:
Obtain the shape of face information of user;
According to the shape of face information and the first mapping relations of the user, corresponding with the shape of face information of the user at least one is determined
A objective attribute target attribute, first mapping relations are used to indicate each first combination and the mapping relations of recommendation, and described first group
It is combined into the combination of the attribute of shape of face information and article to be recommended, the corresponding recommendation of the objective attribute target attribute is greater than or equal to default push away
Degree of recommending threshold value;
Push the information of the corresponding article to be recommended of at least one described objective attribute target attribute.
2. the method according to claim 1, wherein described map according to the shape of face information of the user and first
Relationship, before determining corresponding with the shape of face information of the user at least one objective attribute target attribute, further includes:
Obtain first mapping relations.
3. according to the method described in claim 2, it is characterized in that, before acquisition first mapping relations, further includes:
Obtain the picture of each of article set to be recommended article to be recommended;
According to the picture of each article to be recommended, the characteristic information of each article to be recommended is extracted;
According to the characteristic information of each article to be recommended, and, the mapping relations of characteristic information and attribute determine each institute
State the attribute of article to be recommended.
4. according to the method described in claim 3, it is characterized in that, described obtain first mapping relations, comprising:
According to every kind of shape of face information, the attribute of each article to be recommended, each first combination is obtained;
According to each first combination, the corresponding recommendation of each first combination is determined;
Corresponding recommendation is combined according to each described first, establishes first mapping relations.
5. the method according to claim 1, wherein the shape of face information for obtaining user, comprising:
Receive the shape of face information of the user input by user.
6. the method according to claim 1, wherein the shape of face information for obtaining user, comprising:
Obtain the facial image of the user;
According to the facial image, the face characteristic of the user is identified;
According to the face characteristic of the user, and, the mapping relations of face characteristic and shape of face information determine the face of the user
Type information.
7. method according to claim 1-6, which is characterized in that the attribute includes at least one of following:
The shape of the article, the color of the article, the mark of the article.
8. method according to claim 1-6, which is characterized in that the article to be recommended is glasses.
9. a kind of article recommendation apparatus, which is characterized in that described device includes:
First obtains module, for obtaining the shape of face information of user;
First determining module, for the shape of face information and the first mapping relations according to the user, the determining face with the user
Type information at least one corresponding objective attribute target attribute, first mapping relations are used to indicate each first combination and reflect with recommendation
Penetrate relationship, the combination of the described first group attribute for being combined into shape of face information and article to be recommended, the corresponding recommendation of the objective attribute target attribute
Degree is greater than or equal to default recommendation threshold value;
Pushing module, for pushing the information of the corresponding article to be recommended of at least one described objective attribute target attribute.
10. device according to claim 9, which is characterized in that further include:
Second obtains module, for obtaining first mapping relations.
11. device according to claim 10, which is characterized in that further include:
Third obtains module, for obtaining the picture of each of article set to be recommended article to be recommended;
Extraction module extracts the feature letter of each article to be recommended for the picture according to each article to be recommended
Breath;
Second determining module, for the characteristic information according to each article to be recommended, and, characteristic information and attribute reflect
Relationship is penetrated, determines the attribute of each article to be recommended.
12. device according to claim 11, which is characterized in that described second, which obtains module, includes:
First acquisition unit obtains each described for the attribute according to every kind of shape of face information, each article to be recommended
One combination;
Determination unit, for determining the corresponding recommendation of each first combination according to each first combination;
Unit is established, for combining corresponding recommendation according to each described first, establishes first mapping relations.
13. device according to claim 9, which is characterized in that described first, which obtains module, includes:
Receiving unit, for receiving the shape of face information of the user input by user.
14. device according to claim 9, which is characterized in that described first obtains module further include::
Second acquisition unit, for obtaining the facial image of the user;
Recognition unit, for identifying the face characteristic of the user according to the facial image;
Second determination unit, for the face characteristic according to the user, and, the mapping of face characteristic and shape of face information is closed
System, determines the shape of face information of the user.
15. according to the described in any item devices of claim 9-14, which is characterized in that the attribute includes at least one of following:
The shape of the article, the color of the article, the mark of the article.
16. according to the described in any item devices of claim 9-14, which is characterized in that the article to be recommended is glasses.
17. a kind of electronic equipment characterized by comprising
Memory, for storing program instruction;
Processor, for calling and executing the program instruction in the memory, perform claim requires the described in any item sides of 1-8
Method step.
18. a kind of article recommender system, which is characterized in that including the electronic equipment described in claim 17.
19. a kind of readable storage medium storing program for executing, which is characterized in that be stored with computer program, the meter in the readable storage medium storing program for executing
Calculation machine program requires the described in any item methods of 1-8 for perform claim.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811156779.0A CN109544262A (en) | 2018-09-30 | 2018-09-30 | Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811156779.0A CN109544262A (en) | 2018-09-30 | 2018-09-30 | Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109544262A true CN109544262A (en) | 2019-03-29 |
Family
ID=65841373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811156779.0A Pending CN109544262A (en) | 2018-09-30 | 2018-09-30 | Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109544262A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111741337A (en) * | 2020-06-29 | 2020-10-02 | 北京金山安全软件有限公司 | Recommendation information display method, device and equipment |
CN112084398A (en) * | 2020-07-28 | 2020-12-15 | 北京旷视科技有限公司 | Accessory recommendation method, accessory virtual try-on method and device and electronic equipment |
CN112907312A (en) * | 2019-12-04 | 2021-06-04 | 深圳云天励飞技术有限公司 | Article recommendation method and system for offline user and storage medium |
CN114895747A (en) * | 2022-03-24 | 2022-08-12 | 青岛海信智慧生活科技股份有限公司 | Intelligent display device, glasses recommendation method, glasses recommendation device and media |
JP2023078857A (en) * | 2021-11-26 | 2023-06-07 | アイジャパン株式会社 | Eyewear virtual try-on system, eyewear selection system, eyewear try-on system, and eyewear classification system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130129210A1 (en) * | 2010-11-02 | 2013-05-23 | Sk Planet Co., Ltd. | Recommendation system based on the recognition of a face and style, and method thereof |
CN107862334A (en) * | 2017-11-06 | 2018-03-30 | 广东欧珀移动通信有限公司 | Recommendation method, apparatus, storage medium and the terminal device of glasses |
CN108305146A (en) * | 2018-01-30 | 2018-07-20 | 杨太立 | A kind of hair style recommendation method and system based on image recognition |
-
2018
- 2018-09-30 CN CN201811156779.0A patent/CN109544262A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130129210A1 (en) * | 2010-11-02 | 2013-05-23 | Sk Planet Co., Ltd. | Recommendation system based on the recognition of a face and style, and method thereof |
CN107862334A (en) * | 2017-11-06 | 2018-03-30 | 广东欧珀移动通信有限公司 | Recommendation method, apparatus, storage medium and the terminal device of glasses |
CN108305146A (en) * | 2018-01-30 | 2018-07-20 | 杨太立 | A kind of hair style recommendation method and system based on image recognition |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112907312A (en) * | 2019-12-04 | 2021-06-04 | 深圳云天励飞技术有限公司 | Article recommendation method and system for offline user and storage medium |
CN111741337A (en) * | 2020-06-29 | 2020-10-02 | 北京金山安全软件有限公司 | Recommendation information display method, device and equipment |
CN111741337B (en) * | 2020-06-29 | 2022-04-22 | 北京金山安全软件有限公司 | Recommendation information display method, device and equipment |
CN112084398A (en) * | 2020-07-28 | 2020-12-15 | 北京旷视科技有限公司 | Accessory recommendation method, accessory virtual try-on method and device and electronic equipment |
JP2023078857A (en) * | 2021-11-26 | 2023-06-07 | アイジャパン株式会社 | Eyewear virtual try-on system, eyewear selection system, eyewear try-on system, and eyewear classification system |
CN114895747A (en) * | 2022-03-24 | 2022-08-12 | 青岛海信智慧生活科技股份有限公司 | Intelligent display device, glasses recommendation method, glasses recommendation device and media |
CN114895747B (en) * | 2022-03-24 | 2023-09-15 | 青岛海信智慧生活科技股份有限公司 | Intelligent display device, glasses recommendation method, device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109544262A (en) | Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing | |
CN108197532A (en) | The method, apparatus and computer installation of recognition of face | |
US10204216B2 (en) | Verification methods and verification devices | |
US20180268458A1 (en) | Automated recommendation and virtualization systems and methods for e-commerce | |
CN107239725A (en) | A kind of information displaying method, apparatus and system | |
CN106055710A (en) | Video-based commodity recommendation method and device | |
CN106202316A (en) | Merchandise news acquisition methods based on video and device | |
CN108875523A (en) | Human synovial point detecting method, device, system and storage medium | |
CN110297943A (en) | Adding method, device, electronic equipment and the storage medium of label | |
CN106164959A (en) | Behavior affair system and correlation technique | |
CN105354792B (en) | A kind of virtual glasses try-on method and mobile terminal | |
US20110310260A1 (en) | Augmented Reality | |
JP2021520567A (en) | Face matching method and device, storage medium | |
CN108256537A (en) | A kind of user gender prediction method and system | |
CN108961183A (en) | Image processing method, terminal device and computer readable storage medium | |
CN109064217A (en) | Method, apparatus and electronic equipment are determined based on the core body strategy of user gradation | |
CN110046648A (en) | The method and device of business classification is carried out based at least one business disaggregated model | |
CN109074498A (en) | Visitor's tracking and system for the region POS | |
CN111738199A (en) | Image information verification method, image information verification device, image information verification computing device and medium | |
CN105847368A (en) | Evaluation information display method and device | |
CN108021693A (en) | A kind of image search method and device | |
CN106295673A (en) | Item Information processing method and processing means | |
Liu et al. | A clothing recommendation dataset for online shopping | |
Kwon et al. | An enhanced multi-view human action recognition system for virtual training simulator | |
CN110246280B (en) | Human-cargo binding method and device, computer equipment and readable medium |
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 |