CN109685611A - A kind of Products Show method, apparatus, computer equipment and storage medium - Google Patents
A kind of Products Show method, apparatus, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109685611A CN109685611A CN201811537275.3A CN201811537275A CN109685611A CN 109685611 A CN109685611 A CN 109685611A CN 201811537275 A CN201811537275 A CN 201811537275A CN 109685611 A CN109685611 A CN 109685611A
- Authority
- CN
- China
- Prior art keywords
- expression
- micro
- target
- time point
- preset
- 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 46
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000014509 gene expression Effects 0.000 claims abstract description 197
- 239000002131 composite material Substances 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 13
- 238000013507 mapping Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 4
- 230000009191 jumping Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims 1
- 239000000284 extract Substances 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 155
- 230000006870 function Effects 0.000 description 8
- 230000005540 biological transmission Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000001815 facial effect Effects 0.000 description 5
- 210000004709 eyebrow Anatomy 0.000 description 4
- 230000002452 interceptive effect Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 210000000744 eyelid Anatomy 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 208000002193 Pain Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 210000000887 face Anatomy 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0236—Incentive or reward received by requiring registration or ID from user
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Physics & Mathematics (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of Products Show methods, device, computer equipment and storage medium, the described method includes: obtaining the application identities of the application program of client, and obtain the corresponding each default shooting time point of application identities, when reaching any one default shooting time point, the default corresponding live video stream of shooting time point is obtained from client, and therefrom extract the face-image of active user, and then pass through micro- Expression Recognition, obtain the default corresponding micro- expression of target of shooting time point, so that judging active user to the preference of the product by the micro- expression of target, so that the recommendation of product has specific aim, improve the success rate of product information recommendation, simultaneously, according to the preset weights of each micro- expression, determine the corresponding preference value of each product, and target product is obtained according to preference value, and target product is corresponding pre- It sets up the prize product, realizes in the case where not influencing user experience, analyze the preference of user and push, improve the efficiency of Products Show.
Description
Technical field
The present invention relates to artificial intelligence field more particularly to a kind of Products Show method, apparatus, computer equipment and storage
Medium.
Background technique
With the development of social economy and the growth of people's living standard, more and more new commodities appear in the life of people
In work, the product of oneself is understood for the ease of people, many enterprises can adopt the product information to promote oneself in various manners.
Currently, with the development of internet technology, the network promotion because its expense is low, flow is big and by numerous enterprises
Heat hold in both hands, become the main way of promotion, the current network way of promotion includes but is not limited to: the advertisement of page periphery, pop-up formula promote,
Popularization etc. is propagated in advertisement promotion and virus-type before video or page load, these promotion method specific aims are not strong, and are easy to draw
User's dislike is played, although there are some subtle effects, on the whole, still makes the recommendation success rate of product information low, and
Recommend low efficiency.
Summary of the invention
The embodiment of the present invention provides a kind of Products Show method, apparatus, computer equipment and storage medium, to solve tradition
The pushing efficiency of product information caused by product method for pushing is low, low success rate of problem.
A kind of Products Show method, comprising:
Obtain the application identities of the currently running application program of client, wherein the application program is bundled with pre- in advance
If the product information of quantity；
From preset database, the corresponding each default shooting time point of the application identities is obtained, wherein Mei Gesuo
It states default shooting time point and corresponds at least one described product information；
If detecting, the runing time point of the corresponding application program of the application identities reaches any one of default bat
It takes the photograph time point, then obtains the corresponding live video stream of the default shooting time point from the client；
The face-image of the active user is obtained from the live video stream；
Micro- Expression Recognition is carried out to the face-image, obtains the corresponding micro- expression of target of the default shooting time point；
After getting the corresponding micro- expression of target of each default shooting time point, according to each micro- table of target
The preset weights of feelings determine the active user to the preference of the corresponding product information of each default shooting time point
Value, and the sequence descending according to the preference value, the product information corresponding to the preference value are ranked up, obtain
Product serial；
From the product serial, the product information of preset quantity is chosen as target product information；
If receiving the application program that the client is sent executes the message completed, to the client push
The corresponding default prize of the target product information.
A kind of Products Show device, comprising:
Label detection module, for obtaining the application identities of the currently running application program of client, wherein the application
Program is bundled with the product information of preset quantity in advance；
Node obtains module, for from preset database, obtaining the corresponding each default shooting of the application identities
Time point, wherein each default shooting time point corresponds at least one described product information；
Video acquiring module, if appointing for detecting that the runing time point of the corresponding application program of the application identities reaches
One default shooting time point of meaning then obtains the corresponding real-time video of the default shooting time point from the client
Stream；
Image zooming-out module, for obtaining the face-image of the active user from the live video stream；
Expression Recognition module obtains the default shooting time point for carrying out micro- Expression Recognition to the face-image
The corresponding micro- expression of target；
Preference analysis module, for after getting the corresponding micro- expression of target of each default shooting time point, root
According to the preset weights of each micro- expression of target, determine that the active user is corresponding to each default shooting time point
The preference value of the product information, and the sequence descending according to the preference value, the production corresponding to the preference value
Product information is ranked up, and obtains product serial；
Product determining module, for choosing the product information of preset quantity as target product from the product serial
Information；
Prize sending module, if executing the message completed for receiving the application program that the client is sent,
Then to the corresponding default prize of target product information described in the client push.
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 the step of the said goods recommended method when executing the computer program
Suddenly.
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
The step of calculation machine program realizes the said goods recommended method when being executed by processor.
Products Show method, apparatus, computer equipment and storage medium provided in an embodiment of the present invention, on the one hand, obtain
The application identities of the currently running application program of client, and from preset database, it is corresponding each to obtain application identities
Default shooting time point reaches any one default shooting in the runing time point for detecting the corresponding application program of application identities
When time point, the default corresponding live video stream of shooting time point is obtained from client, and then packet is obtained from live video stream
Face-image containing active user, then micro- Expression Recognition is carried out to face-image, obtain the default corresponding target of shooting time point
Micro- expression is conducive to the preference for obtaining user so that judging active user to the preference of the product by the micro- expression of target
Product improves the success rate of product information recommendation, on the other hand, user is obtaining so that the recommendation of product has specific aim
To after the corresponding micro- expression of target of each default shooting time point, according to the preset weights of the micro- expression of each target, determine current
User is to the preference value of the corresponding product information of each default shooting time point, and the sequence descending according to preference value, right
The corresponding product information of preference value is ranked up, and obtains product serial, and from product serial, is chosen front preset quantity and is produced
Product information is as target product information, when the application program for receiving client transmission executes the message completed, to visitor
Family end pushes default prize, so that can to get target product information by client corresponding with product information phase by active user
The prize of pass allows to through user when with application program interactive, in the case where not influencing user experience, according to application
Reflection of the product and user that the product information occurred in the operational process of program occurs to the product, analyzes the inclined of user
It is good, and recommend relevant product information according to user preference, improve the efficiency 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 the application environment schematic diagram of Products Show method provided in an embodiment of the present invention；
Fig. 2 is the implementation flow chart of Products Show method provided in an embodiment of the present invention；
Fig. 3 is the implementation flow chart of step S40 in Products Show method provided in an embodiment of the present invention；
Fig. 4 is the implementation flow chart of step S50 in Products Show method provided in an embodiment of the present invention；
Fig. 5 is the implementation flow chart of step S52 in Products Show method provided in an embodiment of the present invention；
Fig. 6 is to guide user to get default prize relevant to product in Products Show method provided in an embodiment of the present invention
Implementation flow chart；
Fig. 7 is the schematic diagram of Products Show device provided in an embodiment of the present invention；
Fig. 8 is the schematic diagram of computer equipment provided in an embodiment of the present 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.
Referring to Fig. 1, Fig. 1 shows the application environment of Products Show method provided in an embodiment of the present invention.The Products Show
Method is applied and product information is pushed in the Products Show scene of user.The Products Show scene includes server-side, client
And monitoring client, wherein be attached between server-side and client by network, client provides real-time video to server-side
Stream, server-side obtain live video stream from client, and are analyzed live video stream to obtain the product of user preference, and will
The corresponding default prize of the product of user preference is sent to the user of client, and client specifically can be, but not limited to be various
The intelligent terminals such as people's computer, laptop and tablet computer, server-side specifically can with independent server or
The server cluster of multiple server compositions is realized.
Referring to Fig. 2, being applied in this way Fig. 2 shows a kind of Products Show method provided in an embodiment of the present invention in Fig. 1
In server-side for be illustrated, details are as follows:
S10: the application identities of the currently running application program of client are obtained, wherein application program is bundled with pre- in advance
If the product information of quantity.
Specifically, user is when running preset application program by client, and client is by the application of the application program
Mark is sent to server-side, so as to active user dividing as user preference product of server-side pair and the application program interactive
Analysis.
Wherein, the application program in the present embodiment refer in advance be bundled with preset quantity product information small routine or
Trivial games are applied in operational process, every mistake 5 seconds can for example, getting the trivial games for being identified as " lucky flying disc " at this
There is a product information, user needs to reach preset condition in 5 seconds, it is possible to can obtain after trivial games
Obtain the relevant prize of the product information.
S20: from preset database, the corresponding each default shooting time point of application identities is obtained, wherein each pre-
If shooting time point corresponds at least one product information.
Specifically, server-side is after receiving the application identities, and from preset database, it is corresponding to obtain the application identities
Each of default shooting time point.
Wherein, shooting time point refers to the period shot by client to active user, for example, journey will be applied
The runing time of sequence second one shooting time point of conduct from 15 seconds to 18, in each default shooting time point, client is to current
User shoots, and obtains the default corresponding live video stream of shooting time point.
Wherein, preset database is previously stored with multiple application identities and the corresponding default bat of each application identities
It takes the photograph a little, due to often recommending a plurality of products in an application program, thus, each application identities generally correspond to multiple products,
At the time point that each product occurs in application program implementation procedure, it is set as a shooting time point.
In the present embodiment, run to preset time in application program, can by the product introduction of binding to user, this when
Between section be arranged to default shooting time point, i.e., will appear product in this time range, client can shoot and have at this time
The live video stream of the micro- expression of user.
S30: if detect that the runing time point of the corresponding application program of application identities reaches any one default shooting
Between point, then obtain the default corresponding live video stream of shooting time point from client.
Specifically, server-side reaches any one in the corresponding runing time point of application identities for detecting client and presets
When shooting time point, by the network transmission protocol, client is obtained in the corresponding real-time view of default shooting time point from client
Frequency flows.
Wherein, the time range of the time of live video stream corresponding default shooting point is identical, and live video stream is visitor
Family end is shot to obtain in the time range of default shooting point to the face of active user.
Wherein, the network transmission protocol includes but is not limited to: Internet Control Message agreement (Internet Control
Message Protocol, ICMP), address resolution protocol (ARP Address Resolution Protocol, ARP) and text
Part transport protocol (File Transfer Protocol, FTP) etc..
S40: the face-image of active user is obtained from live video stream.
Specifically, by obtaining the picture frame of preset quantity from live video stream, and then people is carried out to each picture frame
Face detection, using comprising the most complete picture frame of face characteristic as the face-image of active user.
S50: carrying out micro- Expression Recognition to face-image, obtains the default corresponding micro- expression of target of shooting time point.
Specifically, by way of micro- Expression Recognition, micro- Expression Recognition is carried out to face-image, obtains default shooting time
The corresponding micro- expression of target of point.
Wherein, micro- expression is a part of the micro- reaction of psychological stress, it is from human instinct, not by the control of thought,
It can not cover up, can not pretend, then the people that " can be filled ", encountering the first moment after effective stimulus also will appear micro- expression, because
This, is that the loyal of people's underlying thought is presented using micro- expression as micro- reaction of representative, is to understand a true idea of people's heart most
Accurate clue, thus, the present embodiment are micro- come the target that obtains active user by identifying to micro- expression in base image
Expression to judge psychology of the user by unmanned store exit when, and then predicts the payment status of active user.
Wherein, the mode of micro- Expression Recognition includes but is not limited to: micro- Expression Recognition algorithm neural network based, based on flat
It part three value modes (Mean Grayscale-Local Ternary Patterns, the MG-LTP) algorithm of equal gray scale and is based on
Gabor characteristic and micro- Expression Recognition algorithm of support vector machines etc..
It is worth noting that default shooting time point includes one or more face-images, shooting time point is each preset
Corresponding live video stream obtains the micro- expression of target after micro- Expression Recognition, thus, the finally obtained micro- expression of target
It also is multiple, and the micro- expression of each target corresponds to a default shooting time point.
S60: after getting the corresponding micro- expression of target of each default shooting time point, according to the micro- expression of each target
Preset weights determine active user to the preference value of the corresponding product information of each default shooting time point, and according to preference value
Descending sequence is ranked up the corresponding product information of preference value, obtains product serial.
Specifically, each micro- expression is corresponding with preset weights, is getting the corresponding target of each default shooting time point
It is after micro- expression, the corresponding preset weights of the micro- expression of each target are small, as active user to each default shooting time point pair
The preference value for the product information answered, and the more descending sequence of preference value, are ranked up the corresponding product information of preference value.
S70: from product serial, the product information of preset quantity is chosen as target product information.
Specifically, it to find preference product in the application for different user, binds in the application
The quantity of product information is more, more targeted when to avoid subsequent recommendation product, from product serial, according to from front to back
Sequence, choose the product information of preset quantity as target product information, phase pushed according to target product information so as to subsequent
The default prize closed.
Wherein, preset quantity can be configured according to actual needs, be not specifically limited herein, such as be set as 3, i.e.,
Obtain product serial in, sort front three product information as target product information.
S80: if the message that the application execution for receiving client transmission is completed, to client push target product information
Corresponding default prize.
Specifically, after the application program of client has executed, the message for executing and completing, server-side can be sent to server-side
After receiving the message, the corresponding default prize of target product information is obtained, and default prize is pushed to client, so that currently
User gets default prize by client.
Wherein, default prize includes but is not limited to: product coupons, product rebating certificate, product material object play even summation product and record
Read product etc..
In the present embodiment, the application identities of the currently running application program of client are obtained, and from preset database
In, and then the corresponding each default shooting time point of application identities is obtained, detecting the corresponding application program of application identities
When runing time point reaches any one default shooting time point, the default corresponding real-time view of shooting time point is obtained from client
Frequency flows, and then the face-image comprising active user is obtained from live video stream, then carries out micro- Expression Recognition to face-image,
The default corresponding micro- expression of target of shooting time point is obtained, so that judging active user to the inclined of the product by the micro- expression of target
Good degree is conducive to the preference product for obtaining user, so that the recommendation of product has specific aim, improves product information recommendation
Success rate, meanwhile, user is after getting the corresponding micro- expression of target of each default shooting time point, according to the micro- table of each target
The preset weights of feelings determine active user to the preference value of the corresponding product information of each default shooting time point, and according to inclined
It is worth descending sequence well, the corresponding product information of preference value is ranked up, obtain product serial, and from product serial
In, preset quantity product information is chosen as target product information, has been executed in the application program for receiving client transmission
At message when, prize is preset to client push, so that active user can get target product information pair by client
The prize relevant to product information answered, allows to through user when with application program interactive, is not influencing user experience
In the case where, the product occurred according to the product information occurred in the operational process of application program and user are to the anti-of the product
It reflects, analyzes the preference of user, and recommend relevant product information according to user preference, improve the efficiency of Products Show.
On the basis of the corresponding embodiment of Fig. 2, below by a specific embodiment come to being mentioned in step S40
And slave live video stream in obtain the concrete methods of realizing of face-image of active user and be described in detail.
Referring to Fig. 3, Fig. 3 shows the specific implementation flow of step S40 provided in an embodiment of the present invention, details are as follows:
S41: according to the preset time interval, the getting frame image from live video stream obtains the frame comprising predetermined number
The frame image collection of image.
Specifically, server-side according to the preset time interval, extracts video frame from the live video stream received, obtains
Frame image collection comprising multiple frame images.
For example, in a specific embodiment, preset time interval is 8 successive video frames corresponding time, connecing
After the live video stream for receiving client transmission, the live video stream comprising 128 successive video frames that server will acquire
In, using 8 video frames as a sets of video frames, and the last one video frame images in each sets of video frames are obtained,
One is obtained 128/8=16 video frame images, using this 16 frame images as frame image collection.
S42: using Face datection algorithm, carries out Face datection to the frame image in frame image collection, obtains testing result.
Specifically, by human face detection tech, to each frame image in the frame image collection got in step S41 into
Row Face datection, in the present embodiment, obtain live video stream in frame image be in order to carry out micro- Expression Recognition, thus, it is right
Face is detected, mainly in detection frame image whether include complete display facial image, thus, testing result include two
Kind situation: comprising complete face characteristic and complete face characteristic is not included.
Wherein, human face detection tech, which is mainly used for detection frame image septum reset face, profile and important facial camber line, is
No complete display, specific implementation include but is not limited to: Adaboost algorithm, the recognizer of human face characteristic point
Algorithm (the Recognition that (Feature-based recognition algorithms), neural network are identified
Algorithms using neural network) and based on principal component analysis (Principal Component
Analysis, PCA) Eigenface etc..
S43: will test in result, and each frame image comprising complete face characteristic is used as the face figure of active user
Picture.
It specifically, is the frame image comprising complete face characteristic as active user's using testing result in step S42
Face-image, when getting the frame image comprising complete face characteristic, to each feature of the face in these frame images
It is detected, by the most apparent frame image of each feature, as face-image.
It is worth noting that the face-image of the active user got is at least one, if active user has not been obtained
Face-image, then it is assumed that the state of active user obtains abnormal, and the live video stream that will acquire is sent to monitoring client, and to
Monitoring client sends abnormity prompt early warning.
In the present embodiment, according to the preset time interval, the getting frame image from live video stream is obtained comprising default
The frame image collection of the frame image of number carries out Face datection to the frame image in frame image collection using Face datection algorithm,
Testing result is obtained, will test in result, each frame image comprising complete face characteristic is used as face-image, realizes from reality
When video flowing in choose facial image, be conducive to subsequent carry out micro- Expression Recognition using the face-image.
On the basis of the corresponding embodiment of Fig. 2, below by a specific embodiment come to being mentioned in step S50
And micro- Expression Recognition is carried out to face-image, obtain the concrete methods of realizing of the default corresponding micro- expression of target of shooting time point
It is described in detail.
Referring to Fig. 4, Fig. 4 shows the specific implementation flow of step S50 provided in an embodiment of the present invention, details are as follows:
S51: by preset convolutional neural networks model, the identification of expression unit is carried out to face-image, obtains facial figure
The unit set to be identified for including as in.
Specifically, using base image obtained in step S40 as input picture, it is input to trained preset convolution
It is identified in neural network, in the full articulamentum of convolutional neural networks, is preset with 19 classifiers, each classifier corresponding one
Preset motor unit (Facial Action Unit, hereinafter referred to as AU) is planted, totally 19 kinds of preset AU, by the knowledge of classifier
Not, the multiple basic expression units for including in the face-image, and then all underlying tables that same facial expression is obtained are obtained
Feelings unit, as a unit set to be identified.
Wherein, AU refers to that the face of involved party is adopted in the present embodiment to express the expression unit of the expression of involved party
AU is AU in international 19, shown in specific table one:
| AU label | AU description |
| AU1 | Interior eyebrow raises up |
| AU2 | Outer eyebrow raises up |
| AU4 | Eyebrow pushes |
| AU5 | On the face raises up |
| AU6 | Cheek lifts |
| AU7 | Eyelid tightening |
| AU9 | Nose crease |
| AU10 | Upper lip raises up |
| AU12 | The corners of the mouth raises up |
| AU14 | Tighten the corners of the mouth |
| AU15 | Corners of the mouth drop-down |
| AU16 | Lower lip pushes |
| AU17 | Chin tightens |
| AU18 | Lip fold |
| AU20 | Lip stretching, extension |
| AU23 | Lip is shunk |
| AU24 | Lip compresses |
| AU25 | Upper lower lip separates |
| AU26 | Lower jaw drop-down |
Table one
Wherein, convolutional Neural net (Convolutional Neural Network, CNN) is a kind of feedforward neural network,
Its artificial neuron can respond the surrounding cells in a part of coverage area, can rapidly and efficiently carry out image procossing,
In the present embodiment, using preparatory trained convolutional neural networks, the AU for including in base image can quickly recognize out.
For example, in a specific embodiment, the base image that will acquire is input in preset convolutional neural networks
After being identified, obtained basic expression unit class is other are as follows: AU4, AU7, AU9 and AU24, i.e. eyebrow are pushed, eyelid is tightened, nose
Sub- crease and lip compress.
It is worth noting that the prior art mainly uses space-time Local textural feature (Local Binary Patterns
From Three Orthogonal Planes, hereinafter referred to as LBP-TOP) operator identifies micro- expression, but in this implementation
It is to obtain face-image by obtaining live video stream in example, the face inclination of active user in the face-image got
Angle and the angle of unmanned shop light, shooting include many uncertain factors, and LBP-TOP operator is to standard faces figure
As carrying out identifying accuracy rate with higher, but in embodiment, but and it is not suitable for, thus, the present embodiment uses convolutional Neural
Network identifies the expression unit of involved party in base image, and determines involved party's according to the expression unit recognized
Relative to LBP-TOP operator, the operation speed of micro- Expression Recognition is carried out using convolutional neural networks in the present embodiment for micro- expression
It spends faster, and accuracy of identification is higher.
S52: according in preset expression unit composite set, each preset expression unit combination and each micro- expression it
Between mapping relations, the corresponding micro- expression of the unit set to be identified for including in face-image is determined, as default shooting time
The corresponding micro- expression of target of point.
Specifically, preset expression unit composite set includes multiple preset expression unit combinations, each preset table
The combination of feelings unit has mapping relations with a micro- expression, by from preset expression unit composite set, chooses and face
The immediate preset expression unit combination of the unit set to be identified for including in portion's image, is combined as target expression unit,
And then corresponding micro- expression target expression unit is combined, as the corresponding micro- expression of target of default shooting time point.
Wherein, it chooses and is combined with the immediate preset expression unit of the unit set to be identified for including in face-image,
It specifically can be by calculating each preset expression unit in unit set to be identified and preset expression unit composite set
Combined similarity, and then maximum similarity value is chosen as target similarity value from obtained similarity value, and then will
The corresponding preset expression unit combination of target similarity value as with the immediate preset expression list of unit set to be identified
Member combination.
In the present embodiment, for each face-image in base image set, pass through preset convolutional neural networks
Model carries out the identification of expression unit to face-image, obtains the unit set to be identified for including in each face-image, Jin Ergen
According in preset expression unit composite set, each preset expression unit combines the mapping relations between each micro- expression,
Determine that the corresponding micro- expression of the unit set to be identified for including in face-image realizes as the micro- expression of target and passes through nerve
Network carries out intelligent recognition to each face-image in base image set, obtains the micro- expression of target of each face-image,
Improve the efficiency for obtaining the micro- expression of target.
On the basis of the corresponding embodiment of Fig. 4, below by a specific embodiment come to being mentioned in step S52
And the mapping according in preset expression unit composite set, between each preset expression unit combination and each micro- expression
Relationship determines the corresponding micro- expression of the unit set to be identified for including in face-image, corresponding as default shooting time point
The concrete methods of realizing of the micro- expression of target is described in detail.
Referring to Fig. 5, Fig. 5 shows the specific implementation flow of step S52 provided in an embodiment of the present invention, details are as follows:
S521: preset expression unit composite set is obtained, wherein expression unit composite set includes m preset tables
The combination of feelings unit, each preset expression unit combine a corresponding micro- expression, and m is positive integer.
Specifically, m expression unit combination, each expression unit combination packet are included in preset expression unit composite set
At least two motor unit is included, each preset expression unit combines a corresponding micro- expression.
Wherein, the combination of expression unit refers to the combination that two or more motor unit is formed, each preset
Expression unit combines a corresponding micro- expression.
For example, in a specific embodiment, the expression unit combination got includes 3 kinds of motor units, it is respectively as follows:
AU2, AU6 and AU20, it is " happy " which, which combines corresponding micro- expression,.
Wherein, the value of expression unit number of combinations m can be configured according to the actual situation, be not particularly limited herein,
The value of m is 16 in the present embodiment as a preferred method, that is, includes expression unit combination in 16.
S522: the similarity that unit set to be identified is combined with each preset expression unit is calculated separately, m phase is obtained
Like angle value.
Specifically, the similarity that unit set to be identified is combined with each preset expression unit respectively, to obtain m
Similarity value, specific similarity calculation mode can be with are as follows: in unit set to be identified, it is every there are one in preset expression list
The identical motor unit of motor unit that member combination includes, similarity value add 2；In unit set to be identified, every there are one
The similar motor unit of motor unit for including is combined with preset expression unit, similarity value adds 1；In unit set to be identified
In, every there are one that the incoherent motor unit of motor unit any of is combined with preset expression unit, similarity
It is worth constant；In unit set to be identified, every motor unit for including there are a preset expression unit combination is identical to be had
The value of the motor unit of opposite meaning, similarity subtracts 1.
Wherein, similar motor unit refers to two different motor units, and the meaning of expression is similar, for example, lip is received
Contracting and lip compress the two motor units, can be regarded as stinging the one kind of people under nervous or inflexible rush state is automatic
The movement of tight lip, but slightly different in degree for the two.
For example, in a specific embodiment, need to calculate basic expression unit is " AU1, AU7, AU9 and AU23 " and a table
Feelings unit group is combined into the similarity of " AU2, AU7, AU9 and AU24 ", wherein AU1 and AU2 is meaning similar movement unit, AU23
It is the similar expression of meaning to AU24, AU7, AU9 exist in unit set to be identified and the combination of preset expression unit, because
And unit set to be identified and the similarity value of preset expression unit combination are 1+2+2+1=6.
S523: it chooses the corresponding expression unit of maximum similarity value in m similarity value and combines, as object element group
It closes.
Specifically, from the m similarity value got, maximum similarity value is chosen, as target similarity value, and
The corresponding preset expression unit combination of target similarity value is obtained, is combined as object element.
S524: according to mapping relations, obtaining object element and combine corresponding micro- expression, corresponding as default shooting time point
The micro- expression of target.
Specifically, according to the mapping relations of preset unit combination and micro- expression, it is corresponding micro- to obtain object element combination
Expression, as the corresponding micro- expression of target of default shooting time point.
In the present embodiment, preset expression unit composite set is obtained, and calculates separately unit set to be identified and pre-
If expression unit composite set in the preset expression unit combination of m similarity, obtain m similarity value, then choose m
The corresponding expression unit combination of maximum similarity value, is combined, and then closed according to mapping as object element in a similarity value
System obtains object element and combines corresponding micro- expression, determines mesh by way of calculating similarity value as the micro- expression of target
Unit combination is marked, and then obtains object element and combines corresponding micro- expression, improves the accuracy for obtaining the micro- expression of target.
In one embodiment, after step S80, which further includes that guidance user gets target product pair
The prize answered.
Referring to Fig. 6, Fig. 6, which shows guidance user provided in an embodiment of the present invention, gets the corresponding prize of target product
Specific implementation flow, details are as follows:
S91: it when receiving active user and getting request by the prize that client is sent, obtains prize and gets in request
The account information for the active user for including.
Specifically, after user is by Client browse to default prize, the button of getting of client is clicked, triggers client
Prize is sent to server-side and gets request, and server-side obtains current use after receiving the prize and getting request from the request
The corresponding default prize of account information and target product information at family.
S92: the convertible note for exchanging the corresponding default prize of target product information is generated.
Specifically, according to the corresponding default prize of target product information, the convertible note for exchanging the default prize is generated,
The form of the convertible note includes but is not limited to: bar code, two dimensional code and character redemption code etc..
S93: the account information of convertible note and active user are bound, and obtain target convertible note.
Specifically, since the present embodiment is to be shown by monitoring user when with application program interactive to pre-set product
Micro- expression shape change, user preference product is analyzed, and then provide the relevant default prize of preference product, it is then desired to by current
The account information of user and the convertible note of default prize are bound, and target convertible note is obtained, so that the target convertible note can only
Be active user account information carry out using.
S94: sending the instruction for jumping to the page relevant to product information to client, and receiving client active user makes
With the confirmation operation of target convertible note.
Specifically, server-side sends the default corresponding product page jump instruction of prize to client, jumps client
To the corresponding product page of default prize, so that user can use target convertible note by the page, and receives client and work as
Preceding user uses the confirmation operation of target convertible note.
In the present embodiment, when receiving active user and getting request by the prize that client is sent, prize is obtained
The account information for the active user for including in request is got, and then is generated for exchanging the corresponding default prize of target product information
Convertible note, and the account information of the convertible note and active user is bound, obtains target convertible note, then send out to client
The instruction for jumping to the page relevant to product information is sent, so that active user passes through on the page relevant to product information
The account information of active user uses target convertible note, so that user, after getting winnings information, guidance user gets prize,
And jump to relevant to the product page carry out prize get with it is practical, improve the success rate of Products Show.
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.
Fig. 7 shows the functional block diagram with the one-to-one Products Show device of above-described embodiment Products Show method.Such as Fig. 7
Shown, which includes label detection module 10, node acquisition module 20, video acquiring module 30, image zooming-out
Module 40, Expression Recognition module 50, preference analysis module 60, product determining module 70 and prize sending module 80.Each function mould
Detailed description are as follows for block:
Label detection module 10, for obtaining the application identities of the currently running application program of client, wherein apply journey
Sequence is bundled with the product information of preset quantity in advance；
Node obtains module 20, for from preset database, when obtaining the corresponding each default shooting of application identities
Between point, wherein each default shooting time point corresponds at least one product information；
Video acquiring module 30, if for detecting that it is any that the runing time point of the corresponding application program of application identities reaches
One default shooting time point then obtains the default corresponding live video stream of shooting time point from client；
Image zooming-out module 40, for obtaining the face-image of active user from live video stream；
It is corresponding to obtain default shooting time point for carrying out micro- Expression Recognition to face-image for Expression Recognition module 50
The micro- expression of target；
Preference analysis module 60, for after getting the corresponding micro- expression of target of each default shooting time point, according to
The preset weights of each micro- expression of target determine active user to the preference of the corresponding product information of each default shooting time point
Value, and the sequence descending according to preference value, are ranked up the corresponding product information of preference value, obtain product serial；
Product determining module 70, the product information for from product serial, choosing preset quantity are believed as target product
Breath；
Prize sending module 80, if the application program for receiving client transmission executes the message completed, to visitor
Family end pushes the corresponding default prize of target product information, so that active user gets default prize by client.
Further, image zooming-out module 40 includes:
Gather acquiring unit 41, is used for following preset time intervals, the getting frame image from live video stream is wrapped
The frame image collection of frame image containing predetermined number；
Face datection unit 42 carries out face inspection to the frame image in frame image collection for using Face datection algorithm
It surveys, obtains testing result；
Image acquisition unit 43, for will test in result, each frame image comprising complete face characteristic, which is used as, works as
The face-image of preceding user.
Further, Expression Recognition module 50 includes:
Expression acquiring unit 51 to be identified, for carrying out table to face-image by preset convolutional neural networks model
The identification of feelings unit, obtains the unit set to be identified for including in face-image；
The micro- expression determination unit 52 of target, for according in preset expression unit composite set, each preset expression
Mapping relations between unit combination and each micro- expression, determine that the unit set to be identified for including in face-image is corresponding micro-
Expression, as the corresponding micro- expression of target of default shooting time point.
Further, the micro- expression determination unit 52 of target includes:
Composite set obtains subelement 521, for obtaining preset expression unit composite set, wherein expression unit group
It includes m preset expression unit combinations that intersection, which is closed, and each preset expression unit combines a corresponding micro- expression, and m is positive whole
Number；
Similarity calculation subelement 522, for calculating separately unit set to be identified and each preset expression unit group
The similarity of conjunction obtains m similarity value；
Objective cross determines subelement 523, for choosing the corresponding expression list of maximum similarity value in m similarity value
Member combination, is combined as object element；
The micro- expression of target chooses subelement 524, for obtaining object element and combining corresponding micro- table according to mapping relations
Feelings, as the corresponding micro- expression of target of default shooting time point.
The Products Show device further include:
Request module 91 is got, for getting request by the prize that client is sent receiving active user
When, obtain the account information that prize gets the active user for including in request；
Convertible note generation module 92, for generating the convertible note for exchanging the corresponding default prize of target product information；
Target convertible note obtains module 93 and obtains mesh for binding the account information of convertible note and active user
Mark convertible note；
Product page jump module 94, for sending the instruction for jumping to the page relevant to product information to client,
Receive the confirmation operation that the client active user uses target convertible note.
Specific about Products Show device limits the restriction that may refer to above for Products Show method, herein not
It repeats again.Modules in the said goods recommendation apparatus can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
Fig. 8 is the schematic diagram for the computer equipment that one embodiment of the invention provides.The computer equipment can be server-side,
Its internal structure chart can be as shown in Figure 8.The computer equipment includes processor, the memory, net connected by system bus
Network interface and database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The computer equipment
Memory includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer journey
Sequence and database.The built-in storage provides ring for the operation of operating system and computer program in non-volatile memory medium
Border.The database of the computer equipment is for storing the corresponding each default shooting time point of application identities.The computer equipment
Network interface be used to communicate with external terminal by network connection.To realize one when the computer program is executed by processor
Kind Products Show method.
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 realize above-described embodiment Products Show side when executing computer program
The step of method, such as step S10 shown in Fig. 2 to step S80.Alternatively, processor realizes above-mentioned reality when executing computer program
Apply the function of each module/unit of a Products Show device, such as module shown in Fig. 7 10 is to the function of module 80.To avoid
It repeats, which is not described herein again.
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.
In one embodiment, a computer readable storage medium is provided, meter is stored on the computer readable storage medium
The step of calculation machine program, which realizes above-described embodiment Products Show method when being executed by processor, alternatively, the meter
Calculation machine program realizes the function of each module/unit in above-described embodiment Products Show device when being executed by processor.To avoid weight
Multiple, which is not described herein again.
It is to be appreciated that the computer readable storage medium may include: that can carry the computer program code
Any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic disk, CD, computer storage, read-only memory
(Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), electric carrier signal and
Telecommunication signal etc..
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, which is characterized in that the Products Show method includes:
Obtain the application identities of the currently running application program of client, wherein the application program is bundled with present count in advance
The product information of amount；
From preset database, the corresponding each default shooting time point of the application identities is obtained, wherein each described pre-
If shooting time point corresponds at least one described product information；
If detect that the runing time point of the corresponding application program of the application identities reaches any one of default shooting
Between point, then obtain the corresponding live video stream of the default shooting time point from the client；
The face-image of the active user is obtained from the live video stream；
Micro- Expression Recognition is carried out to the face-image, obtains the corresponding micro- expression of target of the default shooting time point；
After getting the corresponding micro- expression of target of each default shooting time point, according to each micro- expression of target
Preset weights, determine the active user to the preference value of the corresponding product information of each default shooting time point,
And the sequence descending according to the preference value, the product information corresponding to the preference value are ranked up, are produced
Product sequence；
From the product serial, the product information of preset quantity is chosen as target product information；
If receiving the application program that the client is sent executes the message completed, to described in the client push
The corresponding default prize of target product information.
2. Products Show method as described in claim 1, which is characterized in that it is described from the live video stream obtain include
The face-image of active user includes:
According to the preset time interval, the getting frame image from the live video stream obtains the frame image comprising predetermined number
Frame image collection；
Using Face datection algorithm, Face datection is carried out to the frame image in the frame image collection, obtains testing result；
By in the testing result, the face of the active user is used as comprising each of the complete face characteristic frame image
Image.
3. Products Show method as described in claim 1, which is characterized in that described to carry out micro- expression knowledge to the face-image
Not, obtaining the corresponding micro- expression of target of the default shooting time point includes:
By preset convolutional neural networks model, the identification of expression unit is carried out to the face-image, obtains the face figure
The unit set to be identified for including as in；
According to the mapping in preset expression unit composite set, between each preset expression unit combination and each micro- expression
Relationship determines the corresponding micro- expression of include in the face-image described unit set to be identified, as the default shooting
The time point micro- expression of corresponding target.
4. Products Show method as claimed in claim 3, which is characterized in that described according to preset expression unit composite set
In, the mapping relations between each preset expression unit combination and each micro- expression determine in the face-image and include
The corresponding micro- expression of the unit set to be identified includes: as the corresponding micro- expression of target of the default shooting time point
Obtain preset expression unit composite set, wherein the expression unit composite set includes the m preset expressions
Unit combination, each preset expression unit combine corresponding micro- expression, and m is positive integer；
The similarity that the unit set to be identified is combined with each preset expression unit is calculated separately, m phase is obtained
Like angle value；
The corresponding expression unit combination of maximum similarity value in m similarity values is chosen, as object element group
It closes；
According to the mapping relations, obtains the object element and combine corresponding micro- expression, when as the default shooting
Between put the corresponding micro- expression of target.
5. such as the described in any item Products Show methods of Claims 1-4, which is characterized in that if receiving the client
The application program sent executes the message completed, then corresponding default to target product information described in the client push
After prize, the Products Show method further include:
When receiving the active user and getting request by the prize that the client is sent, obtains the prize and get and ask
The account information for the active user for including in asking；
Generate the convertible note for exchanging the corresponding default prize of the target product information；
The convertible note and the account information of the active user are bound, target convertible note is obtained；
The instruction for jumping to the page relevant to product information is sent to the client, receiving the client active user makes
With the confirmation operation of the target convertible note.
6. a kind of Products Show device, which is characterized in that the Products Show device includes:
Label detection module, for obtaining the application identities of the currently running application program of client, wherein the application program
It is bundled with the product information of preset quantity in advance；
Node obtains module, for from preset database, obtaining the corresponding each default shooting time of the application identities
Point, wherein each default shooting time point corresponds at least one described product information；
Video acquiring module, if for detecting that it is any one that the runing time point of the corresponding application program of the application identities reaches
A default shooting time point then obtains the corresponding live video stream of the default shooting time point from the client；
Image zooming-out module, for obtaining the face-image of the active user from the live video stream；
It is corresponding to obtain the default shooting time point for carrying out micro- Expression Recognition to the face-image for Expression Recognition module
The micro- expression of target；
Preference analysis module, for after getting the corresponding micro- expression of target of each default shooting time point, according to every
The preset weights of a micro- expression of the target determine that the active user is corresponding to each default shooting time point described
The preference value of product information, and the sequence descending according to the preference value, the product letter corresponding to the preference value
Breath is ranked up, and obtains product serial；
Product determining module, for choosing the product information of preset quantity as target product information from the product serial；
Prize sending module, if executing the message completed for receiving the application program that the client is sent, to
The corresponding default prize of target product information described in the client push.
7. Products Show device as claimed in claim 6, which is characterized in that described image extraction module includes:
Gather acquiring unit, is used for following preset time intervals, the getting frame image from the live video stream is included
The frame image collection of the frame image of predetermined number；
Face datection unit carries out Face datection to the frame image in the frame image collection for using Face datection algorithm,
Obtain testing result；
Image acquisition unit, for including the frame image conduct of each of complete face characteristic in the testing result
The face-image of the active user.
8. Products Show device as claimed in claim 6, which is characterized in that Expression Recognition module includes:
Expression acquiring unit to be identified, for carrying out expression to the face-image by preset convolutional neural networks model
Unit identification, obtains the unit set to be identified for including in the face-image；
The micro- expression determination unit of target, for according in preset expression unit composite set, each preset expression unit group
The mapping relations between each micro- expression are closed, determine that the unit set to be identified for including in the face-image is corresponding
Micro- expression, as the corresponding micro- expression of target of the default shooting time point.
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 5 described in any item Products Show methods.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the step of realization such as Products Show method described in any one of claim 1 to 5 when the computer program is executed by processor
Suddenly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537275.3A CN109685611A (en) | 2018-12-15 | 2018-12-15 | A kind of Products Show method, apparatus, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537275.3A CN109685611A (en) | 2018-12-15 | 2018-12-15 | A kind of Products Show method, apparatus, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109685611A true CN109685611A (en) | 2019-04-26 |
Family
ID=66186146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811537275.3A Pending CN109685611A (en) | 2018-12-15 | 2018-12-15 | A kind of Products Show method, apparatus, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109685611A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298242A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | APP method for switching theme, device, equipment and storage medium based on research and development management |
| CN110298245A (en) * | 2019-05-22 | 2019-10-01 | 平安科技（深圳）有限公司 | Interest collection method, device, computer equipment and storage medium |
| 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 |
| CN110458647A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN110473049A (en) * | 2019-05-22 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Finance product recommended method, device, equipment and computer readable storage medium |
| CN110598099A (en) * | 2019-09-02 | 2019-12-20 | 深圳壹账通智能科技有限公司 | Method and device for sending recommendation information to user, electronic equipment and storage medium |
| CN110648170A (en) * | 2019-09-02 | 2020-01-03 | 平安科技（深圳）有限公司 | Article recommendation method and related device |
| CN110766519A (en) * | 2019-09-30 | 2020-02-07 | 万翼科技有限公司 | House decoration scheme recommendation system and method |
| CN111191207A (en) * | 2019-12-23 | 2020-05-22 | 深圳壹账通智能科技有限公司 | Electronic file control method and device, computer equipment and storage medium |
| CN111753745A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | User experience processing method and device for self-service business handling equipment |
| CN112529048A (en) * | 2020-11-23 | 2021-03-19 | 浙江大学 | Product display video aided design method and device based on perception experience |
| CN113450169A (en) * | 2020-03-27 | 2021-09-28 | 杭州大搜车汽车服务有限公司 | Method and system for processing vehicle recommendation information, computer equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402765A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术（上海）有限公司 | Electronic-commerce recommendation method based on user expression analysis |
| CN104298682A (en) * | 2013-07-18 | 2015-01-21 | 广州华久信息科技有限公司 | Information recommendation effect evaluation method and mobile phone based on facial expression images |
| 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 |
| CN106257489A (en) * | 2016-07-12 | 2016-12-28 | 乐视控股（北京）有限公司 | Expression recognition method and system |
| CN106779802A (en) * | 2016-11-16 | 2017-05-31 | 深圳Tcl数字技术有限公司 | Ad quality appraisal procedure and device |
| 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 |
| 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 |
| CN108449514A (en) * | 2018-03-29 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Information processing method and device |
| CN108446390A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
-
2018
- 2018-12-15 CN CN201811537275.3A patent/CN109685611A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402765A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术（上海）有限公司 | Electronic-commerce recommendation method based on user expression analysis |
| CN104298682A (en) * | 2013-07-18 | 2015-01-21 | 广州华久信息科技有限公司 | Information recommendation effect evaluation method and mobile phone based on facial expression images |
| CN106257489A (en) * | 2016-07-12 | 2016-12-28 | 乐视控股（北京）有限公司 | Expression recognition method and system |
| 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 |
| CN106779802A (en) * | 2016-11-16 | 2017-05-31 | 深圳Tcl数字技术有限公司 | Ad quality appraisal procedure and device |
| 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 |
| 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 |
| CN108446390A (en) * | 2018-03-22 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Method and apparatus for pushed information |
| CN108449514A (en) * | 2018-03-29 | 2018-08-24 | 百度在线网络技术（北京）有限公司 | Information processing method and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298242A (en) * | 2019-05-22 | 2019-10-01 | 深圳壹账通智能科技有限公司 | APP method for switching theme, device, equipment and storage medium based on research and development management |
| CN110298245A (en) * | 2019-05-22 | 2019-10-01 | 平安科技（深圳）有限公司 | Interest collection method, device, computer equipment and storage medium |
| CN110473049A (en) * | 2019-05-22 | 2019-11-19 | 深圳壹账通智能科技有限公司 | Finance product recommended method, device, equipment and computer readable storage medium |
| CN110298245B (en) * | 2019-05-22 | 2023-10-13 | 平安科技（深圳）有限公司 | Interest collection method, interest collection device, computer equipment and storage medium |
| 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 |
| CN110458647A (en) * | 2019-07-05 | 2019-11-15 | 深圳壹账通智能科技有限公司 | Product method for pushing, device, computer equipment and storage medium |
| CN110648170A (en) * | 2019-09-02 | 2020-01-03 | 平安科技（深圳）有限公司 | Article recommendation method and related device |
| WO2021042850A1 (en) * | 2019-09-02 | 2021-03-11 | 平安科技（深圳）有限公司 | Item recommending method and related device |
| CN110598099A (en) * | 2019-09-02 | 2019-12-20 | 深圳壹账通智能科技有限公司 | Method and device for sending recommendation information to user, electronic equipment and storage medium |
| CN110766519A (en) * | 2019-09-30 | 2020-02-07 | 万翼科技有限公司 | House decoration scheme recommendation system and method |
| CN111191207A (en) * | 2019-12-23 | 2020-05-22 | 深圳壹账通智能科技有限公司 | Electronic file control method and device, computer equipment and storage medium |
| CN113450169A (en) * | 2020-03-27 | 2021-09-28 | 杭州大搜车汽车服务有限公司 | Method and system for processing vehicle recommendation information, computer equipment and storage medium |
| CN111753745A (en) * | 2020-06-28 | 2020-10-09 | 中国银行股份有限公司 | User experience processing method and device for self-service business handling equipment |
| CN112529048A (en) * | 2020-11-23 | 2021-03-19 | 浙江大学 | Product display video aided design method and device based on perception experience |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109685611A (en) | A kind of Products Show method, apparatus, computer equipment and storage medium | |
| Kollias et al. | Distribution matching for heterogeneous multi-task learning: a large-scale face study | |
| CN107742107B (en) | Facial image classification method, device and server | |
| CN110166827B (en) | Video clip determination method and device, storage medium and electronic device | |
| CN110263681B (en) | Facial expression recognition method and device, storage medium and electronic device | |
| Ouellet | Real-time emotion recognition for gaming using deep convolutional network features | |
| Abd El Meguid et al. | Fully automated recognition of spontaneous facial expressions in videos using random forest classifiers | |
| JP6267861B2 (en) | Usage measurement techniques and systems for interactive advertising | |
| KR20200068545A (en) | System and method for training a convolutional neural network and classifying an action performed by a subject in a video using the trained convolutional neural network | |
| WO2018200031A1 (en) | Conducting digital surveys that collect and convert biometric data into survey respondent characteristics | |
| CN108875525A (en) | Behavior prediction method, apparatus, system and storage medium | |
| CN110472090A (en) | Image search method and relevant apparatus, storage medium based on semantic label | |
| JP2004529406A5 (en) | ||
| CN107122744A (en) | A kind of In vivo detection system and method based on recognition of face | |
| CN109902660A (en) | A kind of expression recognition method and device | |
| EP2915101A1 (en) | Method and system for predicting personality traits, capabilities and suggested interactions from images of a person | |
| CN105740808B (en) | Face identification method and device | |
| CN109840793A (en) | Method for pushing and device, storage medium, the electronic device of promotion message | |
| CN110569759B (en) | Method, system, server and front end for acquiring individual eating data | |
| CN110163154A (en) | Video monitoring system based on artificial intelligence | |
| CN108596256B (en) | Object recognition classifier construction method based on RGB-D | |
| US11127181B2 (en) | Avatar facial expression generating system and method of avatar facial expression generation | |
| CN108959323A (en) | Video classification methods and device | |
| Zhang et al. | Intelligent Facial Action and emotion recognition for humanoid robots | |
| CN109670517A (en) | Object detection method, device, electronic equipment and target detection model |
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 |