CN109829784A - Products Show method, apparatus, equipment and storage medium based on micro- expression - Google Patents
Products Show method, apparatus, equipment and storage medium based on micro- expression Download PDFInfo
- Publication number
- CN109829784A CN109829784A CN201910042535.8A CN201910042535A CN109829784A CN 109829784 A CN109829784 A CN 109829784A CN 201910042535 A CN201910042535 A CN 201910042535A CN 109829784 A CN109829784 A CN 109829784A
- Authority
- CN
- China
- Prior art keywords
- information
- micro
- product
- expression
- identified
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 239000000047 product Substances 0.000 claims description 486
- 238000001914 filtration Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 239000006227 byproduct Substances 0.000 claims description 2
- 238000005070 sampling Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 10
- 230000001815 facial effect Effects 0.000 description 9
- 230000036651 mood Effects 0.000 description 7
- 238000002372 labelling Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000013066 combination product Substances 0.000 description 2
- 229940127555 combination product Drugs 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Products Show method, apparatus, computer equipment and storage mediums based on micro- expression, obtain user images to be identified first, carry out subscriber identity information matching to user images to be identified in pre-set image library；If it fails to match for subscriber identity information, a new user identifier is distributed for the user images to be identified；After determining that the user is new user, it is rapidly processed after micro- expression information to be identified by acquiring predetermined quantity in real time, recommended products information is generated in time, to guarantee targetedly to carry out better Products Show to the user, also ensures the accuracy of Products Show.
Description
Technical field
The present invention relates to micro- Expression Recognition field more particularly to a kind of Products Show method, apparatus based on micro- expression, set
Standby and storage medium.
Background technique
With the continuous development of big data technology, more and more enterprises can pass through the browsing of user record, user information
Or product information is that user forms recommended products information.Such as: by obtain user purchase, browsing or viewing data come
The degree that commodity are welcome is counted, is come with this to some similar commodity of user-customized recommended.There is following lack in this way of recommendation
Fall into: when user does not buy commodity economic cause or due to not liking, recommender system can only be according to the number of user's browsing
According to counting the welcome degree of commodity, however user browses certain commodity does not represent user and like the commodity, at this moment simply
The true hobby of user cannot be embodied to count the welcome degree of commodity obviously by the data that user browses, so as to cause a
The accuracy that propertyization is recommended is not high, and the way of recommendation is only applicable to the situation of shopping online, for the mode of physical operating
It can not be formed and effectively be recommended.
Summary of the invention
The embodiment of the present invention provides a kind of Products Show method, apparatus based on micro- expression, computer equipment and storage and is situated between
Matter, to solve the problems, such as that Products Show accuracy is not high.
A kind of Products Show method based on micro- expression, comprising:
User images to be identified are obtained, user's body is carried out to the user images to be identified in preset reference image library
Part information matches；
If it fails to match for the subscriber identity information, a new user identifier is distributed for the user images to be identified；
Micro- expression information to be identified of the new user identifier is acquired in real time, wherein each micro- expression letter to be identified
Breath includes product identification；
If the quantity of micro- expression information to be identified of the new user identifier be more than present count magnitude, will it is each described in
It identifies that micro- expression information is input in micro- Expression Recognition model to be identified, it is corresponding micro- to obtain each micro- expression information to be identified
Expression Recognition information；
Target is obtained from product identification based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Product identification；
Target product information based on target product mark generates recommended products information.
A kind of Products Show device based on micro- expression, comprising:
Identity information matching module, for obtaining user images to be identified, in preset reference image library to it is described to
Identify that user images carry out subscriber identity information matching；
New user identifier distribution module, if it fails to match for the subscriber identity information, for the user to be identified
Image distributes a new user identifier；
Real-time acquisition module, for acquiring micro- expression information to be identified of the new user identifier in real time, wherein Mei Yisuo
Stating micro- expression information to be identified includes product identification；
Micro- Expression Recognition data obtaining module, if the quantity of micro- expression information to be identified for the new user identifier is super
Present count magnitude is crossed, then each micro- expression information to be identified is input in micro- Expression Recognition model and is identified, obtained
The corresponding micro- Expression Recognition information of each micro- expression information to be identified；
First object product identification obtains module, for based on the corresponding micro- expression of each micro- expression information to be identified
Identification information obtains target product mark from product identification；
First recommended products information generating module, the target product information generation for being identified based on the target product are pushed away
Recommend product information.
A kind of computer equipment, including memory, processor and storage are in the memory and can be in the processing
The computer program run on device, the processor realize that the above-mentioned product based on micro- expression pushes away when executing the computer program
The step of recommending method.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
Calculation machine program realizes the step of above-mentioned Products Show method based on micro- expression when being executed by processor.
In the above-mentioned Products Show method, apparatus based on micro- expression, computer equipment and storage medium, obtained first wait know
Other user images carry out subscriber identity information matching to user images to be identified in pre-set image library.If subscriber identity information
It fails to match, then distributes a new user identifier for user images to be identified.And micro- table to be identified of new user identifier is acquired in real time
Feelings information, wherein each micro- expression information to be identified includes product identification.If micro- expression information to be identified of new user identifier
Quantity is more than present count magnitude, then each micro- expression information to be identified is input in micro- Expression Recognition model and is identified, obtained
To the corresponding micro- Expression Recognition information of each micro- expression information to be identified.Based on the corresponding micro- table of each micro- expression information to be identified
Feelings identification information obtains target product mark from product identification.Target product information based on target product mark, which generates, recommends
Product information.It is laggard by the micro- expression information to be identified for acquiring predetermined quantity in real time after determining that the user is new user
Row rapidly processes, and generates recommended products information in time, to guarantee targetedly to carry out better Products Show to the user,
Also ensure the accuracy of Products Show.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below by institute in the description to the embodiment of the present invention
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is an application environment schematic diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 2 is an exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 3 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 4 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 5 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 6 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 7 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 8 is another exemplary diagram of the Products Show method in one embodiment of the invention based on micro- expression；
Fig. 9 is a functional block diagram of the Products Show device in one embodiment of the invention based on micro- expression；
Figure 10 is a schematic diagram of computer equipment in one embodiment of the invention.
Specific embodiment
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 description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
Products Show method provided in an embodiment of the present invention based on micro- expression, can be applicable in the application environment such as Fig. 1,
Wherein, client (computer equipment) is communicated by network with server-side.Client sends user images to be identified to clothes
Business end, server-side obtain user images to be identified, carry out user identity to the user images to be identified in pre-set image library
Information matches；If it fails to match for subscriber identity information, a new user identifier is distributed for user images to be identified；Acquisition is new in real time
Micro- expression information to be identified of user identifier, wherein each micro- expression information to be identified includes product identification；If new user identifier
Micro- expression information to be identified be more than present count magnitude, then each micro- expression information to be identified is input to micro- Expression Recognition model
In identified, obtain the corresponding micro- Expression Recognition information of each micro- expression information to be identified；Based on each micro- expression to be identified
The corresponding micro- Expression Recognition information of information obtains target product mark from product identification；Target based on target product mark produces
Product information generates recommended products information.Wherein, client (computer equipment) can be, but not limited to various personal computers, notes
This computer, smart phone, tablet computer and portable wearable device.Server-side can be either multiple with independent server
The server cluster of server composition is realized.
In one embodiment, it as shown in Fig. 2, providing a kind of Products Show method based on micro- expression, applies in this way
It is illustrated, includes the following steps: for server-side in Fig. 1
S10: obtaining user images to be identified, carries out user's body to user images to be identified in preset reference image library
Part information matches.
Wherein, user images to be identified are the image comprising user's face information of client acquisition.It is alternatively possible to
Shop entrances or the necessary place of user carry out the acquisition of user images to be identified, to collected user images to be identified into
Row user identity identification obtains mark to be identified.It is to be identified to be identified as the use to be identified for carrying out obtaining after user identity identification
The corresponding user identifier of family image.User identifier is the unique identification for distinguishing different user.Reference image library is preparatory
Store the image library of benchmark image.Specifically, user images to be identified can be carried out with the extraction of feature vector, then will be extracted
To feature vector and reference image library in each reference vector carry out characteristic similarity calculating, according to the spy being calculated
Sign similarity come judge the identification user images subscriber identity information matching whether successful match.
In a specific embodiment, as shown in figure 3, in preset reference image library to user images to be identified into
The matching of row subscriber identity information, specifically comprises the following steps:
S11: each benchmark in each user images to be identified and reference image library is calculated using similarity calculation algorithm
The characteristic similarity of image.
Wherein, and benchmark image be some users gathered in advance facial image.And each benchmark image corresponds to
One user identifier.Similarity calculation algorithm can be Euclidean distance algorithm, manhatton distance algorithm, Minkowski distance
Algorithm or cosine similarity algorithm etc..In this step, each user to be identified is calculated by using similarity calculation algorithm
The characteristic similarity of each benchmark image in image and reference image library.
S12: the maximum characteristic similarity of numerical value is obtained in the characteristic similarity of each user images to be identified, as mesh
Mark similarity.
From the characteristic similarity of each user images to be identified, the maximum characteristic similarity of numerical value is obtained, as each
The target similarity of user images to be identified.
S13: if target similarity be greater than or equal to preset similarity threshold, subscriber identity information successful match, and
The Datum identifier of the corresponding benchmark image of target similarity is determined as to the user identifier of the user images to be identified.
A similarity threshold is preset, if target similarity is greater than or equal to preset similarity threshold, illustrates this
The similarity degree of the corresponding user images to be identified of target similarity and benchmark image is very high, it is believed that the two represents
Be same user, therefore, the Datum identifier of the corresponding benchmark image of target similarity is determined as the user images to be identified
User identifier.
In the present embodiment, each user images to be identified and reference image library are first calculated using similarity calculation algorithm
In each benchmark image characteristic similarity.It is maximum that numerical value is obtained in the characteristic similarity of each user images to be identified
Characteristic similarity, as target similarity.If target similarity is greater than or equal to preset similarity threshold, and target is similar
The Datum identifier for spending corresponding benchmark image is determined as the user identifier of the user images to be identified.It can be with by the embodiment
Quickly corresponding user identifier is determined for user images to be identified.
In a specific embodiment, if target similarity is less than preset similarity threshold, subscriber identity information
It fails to match.
S20: if it fails to match for subscriber identity information, a new user identifier is distributed for user images to be identified.
In this step, if it fails to match for subscriber identity information, illustrate corresponding user images to be identified not in benchmark
Corresponding benchmark image is found in image library.Therefore, corresponding user may be new user in the user images to be identified, for this
New user distributes a new user identifier.Specifically, the new user identifier is by least one in number, letter, text or symbol
Item composition.
S30: micro- expression information to be identified of new user identifier is acquired in real time, wherein each micro- expression information packet to be identified
Include product identification.
Wherein, micro- expression information to be identified is the information to be identified of the sampling instrument acquisition of client, micro- table to be identified
Feelings information can be video information or image information.Product identification refers to the unique identification for distinguishing different product, can
Selection of land, product identification can be made of at least one of number, letter, text or symbol.Illustratively, product can be each
Plant the commodity shown on sales counter perhaps shelf for example: jewelry product, supermarket's product or automobile product etc..It is alternatively possible to
For corresponding one sampling instrument of products configuration of each product identification, which is used to acquire image or video information, when
Sampling instrument detects when facial image occurs within the acquisition range of sampling instrument or has detected that facial image goes out
It within the acquisition range of present sampling instrument and stops after predetermined time (such as 2 seconds, 3 seconds or 5 seconds etc.), sampling instrument is certainly
Dynamic triggering carries out image or video information acquisition, obtains micro- expression information to be identified, since each sampling instrument corresponds to one
A product, it is possible to distribute product identification according to sampling instrument for micro- expression information to be identified.That is adopting corresponding to product A
The product identification that the collected micro- expression information to be identified of collection tool includes is the product identification of product A.It is specific real at one
It applies in mode, user is including that the regions of multiple products is walked about, and sampling instrument is according to trigger timing (when sampling instrument detects
When thering is facial image to occur within the acquisition range of sampling instrument or detect that sampling instrument occurs in facial image
Within acquisition range and stop after the predetermined time) acquisition of micro- expression information to be identified is carried out to user.After acquisition is completed,
Subscriber identity information matching can be carried out to micro- expression information, specific matching way can be identical with step S10, passes through user
Identity information matching, will obtain out with micro- expression information of new user identifier successful match, be determined as new user identifier to
Identify micro- expression information.
In a specific embodiment, micro- expression information to be identified is image information.In this embodiment, it acquires
When tool detects that facial image is appeared within the acquisition range of sampling instrument, directly acquisition predetermined quantity is to be identified micro-
Expression information, and using collected human face image information as micro- expression information to be identified.Or sampling instrument acquisition video letter
Breath, then sub-frame processing is carried out to video information, obtain micro- expression information to be identified comprising facial image.Further, wait know
Not micro- expression information is video information, then sampling instrument detects that facial image occurs within the acquisition range of sampling instrument
When, the video information comprising facial image is directly acquired, as micro- expression information to be identified.
S40:, will be each to be identified if the quantity of micro- expression information to be identified of new user identifier is more than present count magnitude
Micro- expression information is input in micro- Expression Recognition model and is identified, obtains the corresponding micro- expression of each micro- expression information to be identified
Identification information.
Wherein, which is a preset numerical value, micro- expression information to be identified for acquiring to needs
Quantity be defined.The present count magnitude can be set according to actual needs, it is possible to understand that ground, the present count magnitude are got over
Height, then the recommended products information being subsequently formed can be more accurate, and correspondingly, the acquisition time of micro- expression information to be identified can be got over
It is long.Therefore, comprehensive selection can be carried out according to accuracy and treatment effeciency.It is alternatively possible to preset a counter, use
It is counted in the quantity of micro- expression information to be identified to new user identifier.In step s 30, the new user of a width is often collected
The counter is carried out plus one operates, then by the numerical value of the counter and present count by micro- expression information to be identified of mark
Magnitude is compared, if the numerical value (quantity of micro- expression information to be identified of i.e. new user identifier) of the counter is more than present count
Each micro- expression information to be identified is then input in micro- Expression Recognition model and identifies by magnitude, obtains each to be identified micro-
The corresponding micro- Expression Recognition information of expression information.
Micro- Expression Recognition model is the identification model for judging face mood in micro- expression information to be identified, micro- expression
Identification model may determine that probability value of the face corresponding to preset a variety of moods in micro- expression information to be identified, if certain mood
Probability value be more than corresponding preset threshold, then obtaining the corresponding mood of the micro- expression information to be identified is micro- expression information.
For example, the mood in Expression Recognition model can be set as to happy, surprised, detest, is angry, is tranquil and 6 kinds disappointed.Specifically
Ground can acquire in advance and respectively represent the great amount of samples picture of this 6 kinds of moods and be labeled, form samples pictures collection, then select
It selects corresponding neural network model or classifier is trained, finally obtain micro- Expression Recognition model.Alternatively, acquisition point in advance
The great amount of samples video for not representing this 6 kinds of moods is labeled, and is formed Sample video collection, is then selected corresponding neural network mould
Type (such as: convolutional neural networks model+length in short-term recurrent neural networks model) is trained, and finally obtains micro- Expression Recognition mould
Type.It hereafter, in this step, will be every if the quantity of micro- expression information to be identified of new user identifier is more than present count magnitude
One micro- expression information to be identified, which is input in micro- Expression Recognition model, to be identified, it is corresponding to obtain each micro- expression information to be identified
Micro- Expression Recognition information.
S50: target is obtained from product identification based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Product identification.
Wherein, target product is identified as the interested product of user and/or the corresponding product mark of uninterested product
Know.It, can according to micro- Expression Recognition information after obtaining the corresponding micro- Expression Recognition information of each micro- expression information to be identified
To know user to the fancy grade of the corresponding product of the product identification.Specifically, pre-define it is different preset micro- expression and
The relationship of product fancy grade according to micro- Expression Recognition information and is preset micro- expression and is matched, user can be learned to the production
Product identify the fancy grade of corresponding product.Setting preset micro- expression collection A correspond to product it is interested, set this and preset micro- table
Feelings collection B, which corresponds to, loses interest in product.
Illustratively, if the corresponding micro- Expression Recognition information of a micro- expression information to be identified be it is happy or surprised,
The user is more interested to the corresponding product of the product identification.If the corresponding micro- expression of a micro- expression information to be identified
Identification information is to detest, is angry or disappointed, then the user is uninterested to the corresponding product of the product identification.It can manage
Example whether Xie Di, above-mentioned specific micro- Expression Recognition information and user interested is only an illustrative explanation, is not answered
It is interpreted as unique embodiment to this motion.
In this step, first selected from the corresponding micro- Expression Recognition information of micro- expression information to be identified meet preset it is micro-
Expression collection A and/or meet the micro- expression information to be identified for presetting micro- expression collection B, then by this part micro- expression information pair to be identified
The product identification answered is determined as target product mark.
S60: the target product information based on target product mark generates recommended products information.
Wherein, target product information is the relevant information of corresponding product.Target product information may include name of product, produce
Product price, product category, Product labelling or product purchased record etc..It in this step, can according to target product mark
Get the target product information of corresponding product.
In the present embodiment, user images to be identified are obtained first, in pre-set image library to user images to be identified into
The matching of row subscriber identity information.If it fails to match for subscriber identity information, a new user identifier is distributed for user images to be identified.
And micro- expression information to be identified of new user identifier is acquired in real time, wherein each micro- expression information to be identified includes product identification.
If the quantity of micro- expression information to be identified of new user identifier is more than present count magnitude, and each micro- expression information to be identified is defeated
Enter into micro- Expression Recognition model and identified, obtains the corresponding micro- Expression Recognition information of each micro- expression information to be identified.Base
Target product mark is obtained from product identification in the corresponding micro- Expression Recognition information of each micro- expression information to be identified.Based on mesh
The target product information for marking product identification generates recommended products information.After determining that the user is new user, by adopting in real time
It is rapidly processed after collecting micro- expression information to be identified of predetermined quantity, generates recommended products information in time, to guarantee having needle
Better Products Show to property is carried out to the user, also ensures the accuracy of Products Show.
In one embodiment, as shown in figure 4, carrying out user to user images to be identified in preset reference image library
After the step of identity information matches, the Products Show method based on micro- expression of being somebody's turn to do further includes following steps:
S20 ': if subscriber identity information successful match, the corresponding target user's mark of user images to be identified is obtained.
Subscriber identity information matching is carried out to the user images to be identified in pre-set image library, if successful match,
Obtain the corresponding target user's mark of the user images to be identified.Specifically, it may refer to above-mentioned steps S13, can be obtained
The corresponding target user's mark of user images to be identified, details are not described herein.
S30 ': micro- expression information has been identified according to target user's mark acquisition is corresponding, has identified that micro- expression information includes
It has identified micro- expression unit and has generated product identification.
Wherein, identified that micro- expression information is to have carried out micro- expression to acquired image or video information in advance
The information obtained after identification.Identify that micro- expression information includes having identified micro- expression unit and having generated product identification.Wherein,
It has identified micro- Expression Recognition information that micro- expression information corresponds in step S20 and S30, has generated product identification corresponding to step
Target product identifies in S30.Corresponding acquisition modes be also it is identical with micro- Expression Recognition information and target product mark, herein
It repeats no more.
S40 ': identified that micro- expression unit is identified from acquisition target product in product identification has been generated based on each.
S50 ': the target product information based on target product mark generates recommended products information.
Wherein, step S40 ' is similar with S50 with the step S40 in above-described embodiment respectively with S50 ', and details are not described herein.
In the present embodiment, it if subscriber identity information successful match, obtains the corresponding target of user images to be identified and uses
Family mark.Micro- expression information has been identified according to target user's mark acquisition is corresponding, has identified that micro- expression information includes having identified
Micro- expression unit and product identification is generated.Identify that micro- expression unit obtains target from having generated in product identification based on each
Product identification.Target product information based on target product mark generates recommended products information.It can be schemed by user to be identified
Recommended products information is generated in time after identity as quickly recognizing the user, to guarantee targetedly to carry out the user
Better Products Show.
In one embodiment, as shown in figure 5, based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Target product mark is obtained from product identification, is specifically comprised the following steps:
S51: obtaining corresponding product identification from micro- Expression Recognition information according to preset micro- expression information of loseing interest in,
As product identification of loseing interest in.
Wherein, micro- expression information of loseing interest in does not feel emerging to the product watched for indicating user to be preset
Micro- expression of interest.Illustratively, which can be detest, angry or disappointment.On it is to be appreciated that
Example whether stating specific micro- Expression Recognition information and user interested is only an illustrative explanation, be should not be construed as pair
Unique embodiment of the embodiment of the present invention.The corresponding production of the uninterested product of identity user is identified as without product of interest
Product mark.
If the corresponding micro- Expression Recognition information of a micro- expression information to be identified is micro- expression information of loseing interest in, this is waited for
Identify that the corresponding product identification of micro- expression information is determined as product identification of loseing interest in.
S52: obtaining corresponding product identification from micro- Expression Recognition information according to preset micro- expression information interested, makees
For product of interest mark.
Wherein, micro- expression information interested is preset interested to the product watched for indicating user
Micro- expression.Illustratively, which can be happy or surprised.It is to be appreciated that above-mentioned specific micro-
Expression Recognition information and example whether user interested are only an illustrative explanations, should not be construed as implementing the present invention
Unique embodiment of example.And product of interest is identified as the corresponding product identification of the interested product of identity user.
If the corresponding micro- Expression Recognition information of a micro- expression information to be identified is micro- expression information interested, this is waited knowing
The corresponding product identification of not micro- expression information is determined as product of interest mark.
S53: product of interest is identified and is lost interest in product identification composition target product mark.
After obtaining product of interest mark and product identification of loseing interest in, the two is collectively constituted into target product mark
Know.
In the present embodiment, it is obtained from micro- Expression Recognition information according to preset micro- expression information of loseing interest in corresponding
Product identification, as product identification of loseing interest in.Further according to preset micro- expression information interested from micro- Expression Recognition information
Corresponding product identification is obtained, is identified as product of interest.And by product of interest mark and product identification group of loseing interest in
It is identified at target product.It fully considers the interested product identification of user and uninterested product identification, guarantees to be subsequently generated
Recommended products information have more accuracy.
In one embodiment, as shown in fig. 6, the target product information based on target product mark generates recommended products letter
Breath, specifically comprises the following steps:
S61: corresponding product of interest information is obtained according to product of interest mark.
Wherein, product of interest information is the relevant information of corresponding product.Product of interest information may include ProductName
At least one of title, product price, product category, Product labelling or product purchased record etc..In this step, according to interested
Product identification can get the product of interest information of corresponding product.
S62: it is calculated using collaborative filtering according to product of interest information, obtains the first product information.
It is alternatively possible to be generated using the collaborative filtering based on user or based on the collaborative filtering of article
First product information.Collaborative filtering is based on difference by the preference of the excavation discovery user to user's history behavioral data
Preference user is carried out group division and recommending to sample similar commodity.Collaborative Filtering Recommendation Algorithm is divided into two classes, is respectively
Collaborative filtering (user-based collaboratIve filtering) based on user and the collaboration based on article
It filters algorithm (item-based collaborative filtering).Collaborative filtering based on user is by user
Historical behavior data find that user likes (such as commodity purchasing, collection, content commenting or sharing) to commodity or content, and to this
A little hobbies are measured and are given a mark.It is calculated between user according to attitude and preference of the different user to identical commodity or content
Relationship.It is similar with the collaborative filtering based on user based on the collaborative filtering of article, commodity and user are carried out mutual
It changes.By calculating different user to the relationship the scoring acquisition article of different articles.Based on the relationship between article to user into
The recommendation of the similar article of row.In this step, according to the collaborative filtering based on user, can be believed according to product of interest
Product purchased record combination product label in breath generates the first product information.It is calculated according to the collaborative filtering based on article
Method can generate the first production according to name of product, product price, product category and the Product labelling in product of interest information
Product information.
S63: according to loseing interest in, product identification obtains corresponding product information of loseing interest in.
Wherein, product information of loseing interest in is the relevant information of corresponding product.Product information of loseing interest in may include producing
The name of an article claims, at least one of product price, product category, Product labelling or product purchased record etc..In this step, according to not
Product of interest identifies the product information of loseing interest in that can get corresponding product.
S64: it is calculated using collaborative filtering according to product information of loseing interest in, obtains the second product information.
It is alternatively possible to be generated using the collaborative filtering based on user or based on the collaborative filtering of article
Second product information.It in this step, can be according to product information of loseing interest according to the collaborative filtering based on user
In product purchased record combination product label generate the second product information.According to the collaborative filtering based on article,
The second production can be generated according to name of product, product price, product category and the Product labelling in product information of loseing interest in
Product information.
S65: the product information comprising the second product information is rejected from the first product information, obtains recommended products information.
In this step, the product information comprising the second product information is rejected from the first product information, i.e. rejecting user
Possible uninterested product, obtains recommended products information.Such as: if in the first product information including product A, B and C, and the
Two product informations include products C, D and E.The products C that the second product information is included then is rejected from the first product information, is obtained
It include the recommended products information of product A and B.Recommended products information is formed by two angles of obverse and reverse respectively, into
One step ensure that the accuracy of recommended products information.
In the present embodiment, corresponding product of interest information is first obtained according to product of interest mark.According to interested
Product information is calculated using collaborative filtering, obtains the first product information.It is obtained according to product identification of loseing interest in
Corresponding product information of loseing interest in.It is calculated according to product information is lost interest in using collaborative filtering, obtains second
Product information.It rejects from first product information comprising the product information in the second product information, obtains recommended products letter
Breath.Recommended products information is formed by two angles of obverse and reverse respectively, further ensures the standard of recommended products information
True property.
In one embodiment, as shown in fig. 7, generating recommended products in the target product information identified based on target product
After the step of information, the Products Show method based on micro- expression of being somebody's turn to do further includes following steps:
S71: product feedback information table is obtained, product feedback information table includes that product identification and each product identification are corresponding
Number interested and number of loseing interest in.
Wherein, product feedback information table refers to the statistical information to the pouplarity of each product.Pass through the product
Feedback information table can intuitively count the pouplarity of corresponding product, and carry out subsequent improvement or popularization.
Specifically, it can be identified according to above-mentioned product of interest and product identification of loseing interest in counts the product feedback information table.I.e.
The product of interest mark of each user and product identification of loseing interest in are summarized to get the product feedback information table is arrived.
The product feedback information table can be periodically updated.
S72: according to the number interested of corresponding product mark in target product mark upgrading products feedback information table or not
Number interested.
In this step, target product mark includes product of interest mark and product identification of loseing interest in.Therefore, according to
The number interested or number of loseing interest in of product of interest mark and product identification of loseing interest in corresponding product identification
It is updated, to guarantee the real-time of data.Illustratively, product of interest is identified to interested time of corresponding product identification
Number carries out plus an operation, and the number of loseing interest in of the corresponding product identification of product identification of loseing interest in is carried out plus one operates.
In the present embodiment, it by obtaining product feedback information table, and is identified according to the target product and updates corresponding produce
The number interested of product mark or number of loseing interest in, to guarantee the real-time and validity of product feedback information table.
In one embodiment, as shown in figure 8, generating recommended products in the target product information identified based on target product
After the step of information, the Products Show method based on micro- expression of being somebody's turn to do further includes following steps:
S71 ': obtaining Products Show information table, and Products Show information table includes that product identification and each product identification are corresponding
Recommendation number and do not recommend number.
In this embodiment, Products Show information table refers to the statistical information to the recommendation degree of each product.It is logical
Can intuitively the pouplarity of corresponding product be counted by crossing the Products Show information table, and carry out it is subsequent improvement or
Person promotes.Specifically, the Products Show information table can be counted according to above-mentioned first product information and the second product information.I.e.
The first product information of each user and the second product information are summarized to get the Products Show information table is arrived.The product
Recommendation information table can be periodically updated.And recommend number and do not recommend number respectively to be to each product in different user
The correspondence frequency of occurrence of first product information or the second product information.
S72 ': it according to the recommendation number of corresponding product mark in recommended products information update Products Show information table or does not push away
Recommend number.
In this step, recommended products information includes the first product information and the second product information.Therefore according to this first
Product information and the second product information are to the recommendation number of corresponding product identification or do not recommend number to be updated, to guarantee number
According to real-time.Illustratively, the recommendation number of the corresponding product identification of the first product information is carried out plus one operates, by second
The corresponding product identification of product information does not recommend number to carry out adding an operation.
In the present embodiment, it by obtaining Products Show information table, and is produced according to the recommended products information update is corresponding
The recommendation number of product mark does not recommend number, to guarantee the real-time and validity of Products Show information table.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
In one embodiment, a kind of Products Show device based on micro- expression is provided, it should the Products Show based on micro- expression
Products Show method in device and above-described embodiment based on micro- expression corresponds.As shown in figure 9, should the production based on micro- expression
Product recommendation apparatus includes identity information matching module 10, new user identifier distribution module 20, real-time acquisition module 30, the knowledge of micro- expression
Other data obtaining module 40, target product identifier acquisition module 50 and recommended products information generating module 60.Each functional module is detailed
Carefully it is described as follows:
Identity information matching module 10, for obtaining user images to be identified, to described in preset reference image library
User images to be identified carry out subscriber identity information matching；
New user identifier distribution module 20, if it fails to match for the subscriber identity information, for the use to be identified
Family image distributes a new user identifier；
Real-time acquisition module 30, for acquiring micro- expression information to be identified of the new user identifier in real time, wherein each
Micro- expression information to be identified includes product identification；
Micro- Expression Recognition data obtaining module 40, if the quantity of micro- expression information to be identified for the new user identifier
More than present count magnitude, then each micro- expression information to be identified is input in micro- Expression Recognition model and is identified, obtained
To the corresponding micro- Expression Recognition information of each micro- expression information to be identified；
First object product identification obtains module 50, for based on the corresponding micro- table of each micro- expression information to be identified
Feelings identification information obtains target product mark from product identification；
First recommended products information generating module 60, the target product information for being identified based on the target product are generated
Recommended products information.
Preferably, should Products Show device based on micro- expression further include target user's identifier acquisition module, identified it is micro-
Expression information obtains module, the second target product identifier acquisition module and the second recommended products information generating module.
Target user's identifier acquisition module obtains user images to be identified if being used for subscriber identity information successful match
Corresponding target user's mark；
Identify that micro- expression information obtains module, acquisition is corresponding to have identified that micro- expression is believed for identifying according to target user
Breath has identified that micro- expression information includes having identified micro- expression unit and having generated product identification；
Second target product identifier acquisition module, for having identified micro- expression unit from having generated product identification based on each
Middle acquisition target product mark；
Second recommended products information generating module, the target product information for being identified based on target product, which is generated, to be recommended to produce
Product information.
Preferably, first object product identification obtains module 50 and is used for according to preset micro- expression information of loseing interest in from micro-
Corresponding product identification is obtained in Expression Recognition information, as product identification of loseing interest in；According to preset micro- expression interested
Information obtains corresponding product identification from micro- Expression Recognition information, identifies as product of interest；Product of interest is identified
With product identification composition target product mark of loseing interest in.
Preferably, the first recommended products information generating module 60 is used to obtain corresponding sense according to product of interest mark emerging
Interesting product information；It is calculated using collaborative filtering according to product of interest information, obtains the first product information；According to not
Product of interest mark obtains corresponding product information of loseing interest in；Using collaborative filtering according to product information of loseing interest in
It is calculated, obtains the second product information；The product information comprising the second product information is rejected from the first product information, is obtained
Recommended products information.
Preferably, being somebody's turn to do the Products Show device based on micro- expression further includes that product feedback information table acquisition module and product are anti-
Feedforward information table update module.
Product feedback information table obtains module, and for obtaining product feedback information table, product feedback information table includes product
Identify number interested corresponding with each product identification and number of loseing interest in；
Product feedback information table update module, for identifying corresponding in upgrading products feedback information table produce according to target product
The number interested of product mark or number of loseing interest in.
Preferably, being somebody's turn to do the Products Show device based on micro- expression further includes that Products Show information table obtains module and recommends to produce
Product information update update module.
Products Show information table obtains module, and for obtaining Products Show information table, Products Show information table includes product
It identifies recommendation number corresponding with each product identification and does not recommend number；
Recommended products information update update module, for according to corresponding in recommended products information update Products Show information table
The recommendation number of product identification does not recommend number.
Specific restriction about the Products Show device based on micro- expression may refer to above for based on micro- expression
The restriction of Products Show method, details are not described herein.Modules in the above-mentioned Products Show device based on micro- expression can be complete
Portion or part are realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of calculating
In processor in machine equipment, it can also be stored in a software form in the memory in computer equipment, in order to processor
It calls and executes the corresponding operation of the above modules.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 10.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
Data of the database of machine equipment for being used in the above-mentioned Products Show method based on micro- expression.The net of the computer equipment
Network interface is used to communicate with external terminal by network connection.To realize a kind of base when the computer program is executed by processor
In the Products Show method of micro- expression.
In one embodiment, a kind of computer equipment is provided, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, processor perform the steps of when executing computer program
User images to be identified are obtained, user's body is carried out to the user images to be identified in preset reference image library
Part information matches；
If it fails to match for the subscriber identity information, a new user identifier is distributed for the user images to be identified；
Micro- expression information to be identified of the new user identifier is acquired in real time, wherein each micro- expression letter to be identified
Breath includes product identification；
If the quantity of micro- expression information to be identified of the new user identifier be more than present count magnitude, will it is each described in
It identifies that micro- expression information is input in micro- Expression Recognition model to be identified, it is corresponding micro- to obtain each micro- expression information to be identified
Expression Recognition information；
Target is obtained from product identification based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Product identification；
Target product information based on target product mark generates recommended products information.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
User images to be identified are obtained, user's body is carried out to the user images to be identified in preset reference image library
Part information matches；
If it fails to match for the subscriber identity information, a new user identifier is distributed for the user images to be identified；
Micro- expression information to be identified of the new user identifier is acquired in real time, wherein each micro- expression letter to be identified
Breath includes product identification；
If the quantity of micro- expression information to be identified of the new user identifier be more than present count magnitude, will it is each described in
It identifies that micro- expression information is input in micro- Expression Recognition model to be identified, it is corresponding micro- to obtain each micro- expression information to be identified
Expression Recognition information；
Target is obtained from product identification based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Product identification；
Target product information based on target product mark generates recommended products information.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
It is apparent to those skilled in the art that for convenience of description and succinctly, only with above-mentioned each function
Can unit, module division progress for example, in practical application, can according to need and by above-mentioned function distribution by different
Functional unit, module are completed, i.e., the internal structure of described device is divided into different functional unit or module, more than completing
The all or part of function of description.
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of Products Show method based on micro- expression characterized by comprising
User images to be identified are obtained, user identity letter is carried out to the user images to be identified in preset reference image library
Breath matching；
If it fails to match for the subscriber identity information, a new user identifier is distributed for the user images to be identified；
Micro- expression information to be identified of the new user identifier is acquired in real time, wherein each micro- expression information packet to be identified
Include product identification；
If the quantity of micro- expression information to be identified of the new user identifier is more than present count magnitude, will be each described to be identified
Micro- expression information is input in micro- Expression Recognition model and is identified, obtains the corresponding micro- expression of each micro- expression information to be identified
Identification information；
Target product is obtained from product identification based on the corresponding micro- Expression Recognition information of each micro- expression information to be identified
Mark；
Target product information based on target product mark generates recommended products information.
2. as described in claim 1 based on the Products Show method of micro- expression, which is characterized in that described in preset reference map
As carrying out subscriber identity information matching to the user images to be identified in library, specifically comprise the following steps:
Each benchmark image in each user images to be identified and reference image library is calculated using similarity calculation algorithm
Characteristic similarity；
The maximum characteristic similarity of numerical value is obtained in the characteristic similarity of each user images to be identified, as target phase
Like degree；
If the target similarity is greater than or equal to preset similarity threshold, subscriber identity information successful match, and by institute
The Datum identifier for stating the corresponding benchmark image of target similarity is determined as the user identifier of the user images to be identified.
3. as described in claim 1 based on the Products Show method of micro- expression, which is characterized in that described in preset benchmark
After the step of carrying out subscriber identity information matching to the user images to be identified in image library, the production based on micro- expression
Product recommended method further includes following steps:
If the subscriber identity information successful match, the corresponding target user's mark of the user images to be identified is obtained；
Identified according to the target user obtain it is corresponding identified micro- expression information, it is described to have identified that micro- expression information includes
It identifies micro- expression unit and has generated product identification；
Based on it is each it is described identified micro- expression unit from it is described generated in product identification obtain target product mark；
Target product information based on target product mark generates recommended products information.
4. as described in claim 1 based on the Products Show method of micro- expression, which is characterized in that it is described based on it is each it is described to
It identifies that the corresponding micro- Expression Recognition information of micro- expression information obtains target product mark from product identification, specifically includes following step
It is rapid:
Corresponding product identification is obtained from micro- Expression Recognition information according to preset micro- expression information of loseing interest in, as
Lose interest in product identification；
Corresponding product identification is obtained from micro- Expression Recognition information according to preset micro- expression information interested, as sense
Interest product identification；
By product of interest mark and the product identification composition target product mark of loseing interest in.
5. as claimed in claim 4 based on the Products Show method of micro- expression, which is characterized in that described to be produced based on the target
The target product information of product mark generates recommended products information, specifically comprises the following steps:
Corresponding product of interest information is obtained according to product of interest mark；
It is calculated using collaborative filtering according to the product of interest information, obtains the first product information；
Corresponding product information of loseing interest in is obtained according to the product identification of loseing interest in；
Product information of being lost interest according to using collaborative filtering is calculated, and the second product information is obtained；
The product information comprising second product information is rejected from first product information, obtains recommended products information.
6. as described in claim 1 based on the Products Show method of micro- expression, which is characterized in that be based on the target described
After the target product information of product identification generates the step of recommended products information, the Products Show method based on micro- expression
Further include following steps:
Product feedback information table is obtained, the product feedback information table includes that product identification and each product identification are corresponding
Number interested and number of loseing interest in；
According to the number interested of corresponding product mark in the target product mark update product feedback information table or not
Number interested.
7. as described in claim 1 based on the Products Show method of micro- expression, which is characterized in that be based on the target described
After the target product information of product identification generates the step of recommended products information, the Products Show method based on micro- expression
Further include following steps:
Products Show information table is obtained, the Products Show information table includes product identification and the corresponding recommendation of each product identification
Number and do not recommend number；
According to the recommendation number of corresponding product mark in Products Show information table described in the recommended products information update or do not push away
Recommend number.
8. a kind of Products Show device based on micro- expression characterized by comprising
Identity information matching module, for obtaining user images to be identified, to described to be identified in preset reference image library
User images carry out subscriber identity information matching；
New user identifier distribution module, if it fails to match for the subscriber identity information, for the user images to be identified
Distribute a new user identifier；
Real-time acquisition module, for acquiring micro- expression information to be identified of the new user identifier in real time, wherein it is each it is described to
Identify that micro- expression information includes product identification；
Micro- Expression Recognition data obtaining module, if the quantity of micro- expression information to be identified for the new user identifier is more than pre-
If quantitative value, then each micro- expression information to be identified is input in micro- Expression Recognition model and is identified, obtained each
The corresponding micro- Expression Recognition information of micro- expression information to be identified；
First object product identification obtains module, for based on the corresponding micro- Expression Recognition of each micro- expression information to be identified
Information obtains target product mark from product identification；
First recommended products information generating module, the target product information for being identified based on the target product, which is generated, to be recommended to produce
Product information.
9. a kind of computer equipment, including memory, processor and storage are in the memory and can be in the processor
The computer program of upper operation, which is characterized in that the processor realized when executing the computer program as claim 1 to
The step of Products Show method described in 7 any one based on micro- expression.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In product of the realization based on micro- expression as described in any one of claim 1 to 7 pushes away when the computer program is executed by processor
The step of recommending method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910042535.8A CN109829784A (en) | 2019-01-17 | 2019-01-17 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910042535.8A CN109829784A (en) | 2019-01-17 | 2019-01-17 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109829784A true CN109829784A (en) | 2019-05-31 |
Family
ID=66861757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910042535.8A Pending CN109829784A (en) | 2019-01-17 | 2019-01-17 | Products Show method, apparatus, equipment and storage medium based on micro- expression |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829784A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458644A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of information processing method and relevant device |
| CN113031456A (en) * | 2019-12-25 | 2021-06-25 | 佛山市云米电器科技有限公司 | Household appliance control method, system, device and computer readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131675A (en) * | 2016-07-19 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of Method of Commodity Recommendation, Apparatus and system |
| CN107203897A (en) * | 2017-04-24 | 2017-09-26 | 广东数相智能科技有限公司 | A kind of evaluation method of Products Show degree, apparatus and system |
| CN107463876A (en) * | 2017-07-03 | 2017-12-12 | 珠海市魅族科技有限公司 | Information processing method and device, computer installation and storage medium |
| CN107730372A (en) * | 2017-11-29 | 2018-02-23 | 济南浪潮高新科技投资发展有限公司 | The method and apparatus that a kind of Bank Hall personalized product based on recognition of face is recommended |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108230033A (en) * | 2018-01-04 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of output information |
-
2019
- 2019-01-17 CN CN201910042535.8A patent/CN109829784A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106131675A (en) * | 2016-07-19 | 2016-11-16 | 乐视控股（北京）有限公司 | A kind of Method of Commodity Recommendation, Apparatus and system |
| CN107203897A (en) * | 2017-04-24 | 2017-09-26 | 广东数相智能科技有限公司 | A kind of evaluation method of Products Show degree, apparatus and system |
| CN107463876A (en) * | 2017-07-03 | 2017-12-12 | 珠海市魅族科技有限公司 | Information processing method and device, computer installation and storage medium |
| CN107730372A (en) * | 2017-11-29 | 2018-02-23 | 济南浪潮高新科技投资发展有限公司 | The method and apparatus that a kind of Bank Hall personalized product based on recognition of face is recommended |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108230033A (en) * | 2018-01-04 | 2018-06-29 | 百度在线网络技术（北京）有限公司 | For the method and apparatus of output information |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110458644A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | A kind of information processing method and relevant device |
| CN113031456A (en) * | 2019-12-25 | 2021-06-25 | 佛山市云米电器科技有限公司 | Household appliance control method, system, device and computer readable storage medium |
| CN113031456B (en) * | 2019-12-25 | 2023-12-12 | 佛山市云米电器科技有限公司 | Household appliance control method, system, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829764B (en) | Recommendation information acquisition method, device, system, server and storage medium | |
| CN106776619B (en) | Method and device for determining attribute information of target object | |
| KR102127191B1 (en) | Method, apparatus and computer program for providing shopping informations | |
| US20190156395A1 (en) | System and Method for Analyzing and Searching for Features Associated with Objects | |
| US9639880B2 (en) | Photorealistic recommendation of clothing and apparel based on detected web browser input and content tag analysis | |
| CN109993595B (en) | Method, system and equipment for personalized commodity and service recommendation | |
| CN109785066A (en) | Products Show method, apparatus, equipment and storage medium based on micro- expression | |
| CN108460622A (en) | Interactive advertising system under a kind of line | |
| US20200342320A1 (en) | Non-binary gender filter | |
| US9477973B2 (en) | Visually generated consumer product presentation | |
| CN110428298A (en) | A kind of shop recommended method, device and equipment | |
| KR20200045668A (en) | Method, apparatus and computer program for style recommendation | |
| CN108335317A (en) | Shopping guide method and device under a kind of line | |
| CN110084657A (en) | A kind of method and apparatus for recommending dress ornament | |
| CN107590267A (en) | Information-pushing method and device, terminal and readable storage medium storing program for executing based on picture | |
| CN114936301B (en) | Intelligent household building material data management method, device, equipment and storage medium | |
| CN109829784A (en) | Products Show method, apparatus, equipment and storage medium based on micro- expression | |
| CN109544262A (en) | Item recommendation method, device, electronic equipment, system and readable storage medium storing program for executing | |
| CN110443666A (en) | Information processing method, device, terminal and server | |
| KR20210131198A (en) | Method, apparatus and computer program for advertising recommended product | |
| US20170300768A1 (en) | Method for determining and displaying products on an electronic display device | |
| CN117495513B (en) | Shopping recommendation method and system based on big data and artificial intelligence | |
| CN112418994B (en) | Commodity shopping guide method and device, electronic equipment and storage medium | |
| CN116089745A (en) | Information recommendation method, device, electronic equipment and computer readable storage medium | |
| CN111352624A (en) | Interface display method, information processing method and device |
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 |