CN109559193A - Product method for pushing, device, computer equipment and the medium of intelligent recognition - Google Patents
Product method for pushing, device, computer equipment and the medium of intelligent recognition Download PDFInfo
- Publication number
- CN109559193A CN109559193A CN201811255718.XA CN201811255718A CN109559193A CN 109559193 A CN109559193 A CN 109559193A CN 201811255718 A CN201811255718 A CN 201811255718A CN 109559193 A CN109559193 A CN 109559193A
- Authority
- CN
- China
- Prior art keywords
- product
- pushed information
- user
- mood value
- push
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Abstract
The invention belongs to micro- Expression Recognition fields, disclose product method for pushing, device, computer equipment and the medium of a kind of intelligent recognition, this method comprises: obtaining facial image, wherein the facial image includes user identifier；The facial image is input to and is preset in micro- Expression Recognition model, M expression unit of the facial image is obtained；User mood value is obtained according to the M expression units；Product pushed information is sent according to the user mood value and the user identifier.Technical solution provided by the invention carries out the push of product according to user mood value, keeps user's acceptance high, improves the efficiency of product push.
Description
Technical field
The invention belongs to micro- Expression Recognition fields, more specifically, be the product method for pushing for being related to a kind of intelligent recognition,
Device, computer equipment and medium.
Background technique
Many APP have many good products at present, but since no suitably push means make product promotion
Efficiency is lower, such as very few causes user's awareness not high without carrying out product push or product push；Or product push
User is excessively caused to be sick of；Or not carrying out product push on suitable opportunity causes user's acceptance not high, results in
Many invalid product push, so that product pushing efficiency is lower.
Summary of the invention
The embodiment of the present invention provides product method for pushing, device, computer equipment and the medium of a kind of intelligent recognition, with solution
The certainly lower problem of product pushing efficiency.
A kind of product method for pushing of intelligent recognition, comprising:
Obtain facial image, wherein the facial image includes user identifier；
The facial image is input to and is preset in micro- Expression Recognition model, M expression list of the facial image is obtained
Member, wherein M is positive integer；
User mood value is obtained according to the M expression units；
Product pushed information is sent according to the user mood value and the user identifier.
A kind of product driving means of intelligent recognition, comprising:
Facial image obtains module, for obtaining facial image, wherein the facial image includes user identifier；
Expression unit obtains module, presets in micro- Expression Recognition model for the facial image to be input to, and obtains institute
State M expression unit of facial image, wherein M is positive integer；
Mood value obtains module, for obtaining user mood value according to the M expression units；
Pushed information sending module, for sending product push letter according to the user mood value and the user identifier
Breath.
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 product push of above-mentioned intelligent recognition when executing the computer program
The step of 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 product method for pushing of above-mentioned intelligent recognition when being executed by processor.
Product method for pushing, device, computer equipment and the medium of above-mentioned intelligent recognition, by obtaining facial image,
In, facial image includes user identifier；Then facial image is input to and is preset in micro- Expression Recognition model, obtain facial image
M expression unit；User mood value is obtained then according to M expression unit；Finally according to user mood value and user identifier
Send product pushed information.User mood value is obtained according to facial image, product push is carried out further according to user mood value, that is, exists
Product push is carried out when user mood is preferable, the push of product is then reduced when feeling blue, and makes to carry out to reach production when product push
The effect of product push, improves user's acceptance, also improves the efficiency of product push.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is an application environment schematic diagram of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 2 is a flow chart of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 3 is another flow chart of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 4 is another flow chart of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 5 is another flow chart of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 6 is another flow chart of the product method for pushing of intelligent recognition in one embodiment of the invention；
Fig. 7 is a functional block diagram of the product driving means of intelligent recognition in one embodiment of the invention；
Fig. 8 is the principle frame that mood value obtains module in the product driving means of intelligent recognition in one embodiment of the invention
Figure；
Fig. 9 is a principle of pushed information sending module in the product driving means of intelligent recognition in one embodiment of the invention
Block diagram；
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.
The product method for pushing of intelligent recognition provided by the present application, can be applicable in the application environment such as Fig. 1, wherein visitor
Family end is communicated by network with server-side, and server-side obtains facial image by client, then inputs facial image
To presetting in micro- Expression Recognition model, M expression unit of facial image is obtained, obtains user then according to M expression unit
Mood value finally sends product pushed information to client according to the user identifier that user mood value and facial image include.Its
In, client can be, but not limited to be various personal computers, laptop, smart phone, tablet computer and it is portable can
Wearable device.Server-side can be realized with the server cluster of the either multiple server compositions of independent server.
In one embodiment, it as shown in Fig. 2, providing a kind of product method for pushing of intelligent recognition, applies in this way
It is illustrated, includes the following steps: for server-side in Fig. 1
S10: facial image is obtained, wherein facial image includes user identifier.
Wherein, facial image can be obtained by the shooting tool shooting, collecting of client, such as can pass through mobile phone (visitor
Family end) camera shoot obtain.Optionally, the product method for pushing of intelligent recognition provided in an embodiment of the present invention can be by answering
It is realized, such as cell phone application, can be applied in the registering of APP with program.Optionally, APP can pass through recognition of face
Method logged in, i.e., when the user performs a log, server-side by client shooting tool obtain user face figure
Picture, and the facial image for the user that will acquire carries out recognition of face verifying, if being identified by, the face figure for the user that will acquire
As the facial image as this step.Optionally, when user registers, reward on total mark is carried out to user, improves user's label
The enthusiasm arrived, server-side judge that user mood value carries out the push of product further according to the facial image of acquisition, improve product and push away
The efficiency sent.User identifier refers to client for distinguishing the mark of different user, such as user account, cell-phone number or identity card
Number etc..Optionally, when client terminal start-up application program, server-side by client send user login validation instruct, when with
After family inputs account and password login, server-side obtains user identifier；It is used when server-side is obtained by the shooting tool of client
When the facial image at family, it is marked with facial image of the user identifier to user.
Optionally, when obtaining the facial image of user, first facial image can be identified, if the result of identification is
User is then obtained user identifier, then is marked with facial image of the user identifier to acquisition.Wherein, recognition of face can
To be realized by human face recognition model trained in advance.For example, the registrant of user is obtained when user registers first
Sample is input to the characteristics of image that sample is extracted in human face recognition model trained in advance and and user as sample by face image
Mark is bound；When users log on, then by human face recognition model trained in advance facial image when logging in is extracted
Characteristics of image；If Image Feature Matching when characteristics of image and the login of sample, obtain corresponding with the characteristics of image of sample
User identifier, then the facial image that obtains when logging in is marked with user identifier.
S20: facial image being input to and is preset in micro- Expression Recognition model, obtains M expression unit of facial image,
In, M is positive integer.
Wherein, it presets micro- Expression Recognition model and is based primarily upon face recognition technology, according to eyebrow, eyes, lip or on the face
The slight change of muscle etc. identifies to obtain the expression unit of facial image.Expression unit refers to the unit of composition facial expression,
It is alternatively possible to using the state at a position on face as expression unit, such as under eyebrow raises up, cheek lifts or the corners of the mouth
Draw etc..Optionally, the acquisition for presetting micro- Expression Recognition model can be by sample image gathered in advance, then to sample image
The annotation for carrying out expression unit, is finally trained neural network model according to the sample image for having annotated expression unit, from
And it obtains presetting micro- Expression Recognition model.
Optionally, micro- Expression Recognition model is preset to be mainly used for obtaining 19 kinds of expression lists that the world as shown in Table 1 passes through
First (AU):
1 expression cell list of table
Specifically, after getting facial image, facial image is input to and is preset in micro- Expression Recognition model, people is obtained
M expression unit of face image.Wherein, expression unit can be indicated with the AU label in table 1, such as AU25, expression pair
The expression answered separates for upper lower lip.
For example, the expression unit of face will include when the corresponding expression of facial image is glad: the corners of the mouth raises up, face
Cheek lifts, eyelid tightens motor unit, and facial image is input to and is preset in micro- Expression Recognition model, then available M table
Feelings unit is AU12, AU6, AU7.
S30: user mood value is obtained according to M expression unit.
Wherein, user mood value refers to the assessment numerical value of the corresponding user mood of the facial image of acquisition.It is alternatively possible to
User mood value is obtained according to the expression that expression unit comprehensive obtains, i.e., by institute's espressiove unit of the facial image of acquisition with
The expression unit that existing expression includes is matched, and similarity is reached the expression of similarity threshold as user's expression, by table
The corresponding mood value of feelings is as user mood value.For example, glad expression includes 5 expression lists if similarity threshold is 80%
Member, and there are 4 expression units to be consistent in the corresponding expression unit of facial image obtained with glad expression unit, i.e., it is similar
Degree is 80%, then can be using glad expression as user's expression；If the glad corresponding mood value of expression is 9, and user's heart
Feelings value is also 9.
S40: product pushed information is sent according to user mood value and user identifier.
Wherein, product pushed information refers to that pushed information relevant to product, such as certain APP have a new game products
The game products A information pushed is then product pushed information by A.Optionally, product pushed information can also include using
Show loving care for information or user account information in family.Wherein, user show loving care for information can according to user mood value push some warm hearts
Sentence improves user's attention rate for improving user mood value, facilitates the push of subsequent product information；And user account
Information can be the associated account information used the product by the user, such as subscriber's account information, facilitate checking for user, make user's shape
At the use habit of the application program of client, to facilitate the push of subsequent product information.
It is alternatively possible to set a threshold value, product pushed information is retransmited when user mood value reaches the threshold value, such as
Fruit does not reach the threshold value and does not send product PUSH message then, or only sends user to user and show loving care for information or user account letter
Breath.Product pushed information and user mood value can also be associated, it is right that user mood value height is sent if user mood is good
The product pushed information answered sends out the low corresponding product pushed information of user mood value if user mood difference.It is pushed away sending product
Deliver letters breath when, according to user identifier obtain corresponding cell-phone number, user account or subscriber mailbox etc. as send approach, then with
The forms such as short message, mail, message informing or wechat send product pushed information.It in a specific embodiment, can be direct
Using cell-phone number, user account or subscriber mailbox as user identifier, directly pushed away at this time according to the i.e. transmittable product of user identifier
Send message.
In the corresponding embodiment of Fig. 2, by obtaining facial image, wherein facial image includes user identifier；Then will
Facial image, which is input to, to be preset in micro- Expression Recognition model, and M expression unit of facial image is obtained；Then according to M expression
Unit obtains user mood value；Product pushed information is finally sent according to user mood value and user identifier.According to facial image
User mood value is obtained, product push is carried out further according to user mood value, i.e., carries out product push, the heart when user mood is preferable
The push that product is then reduced when feelings are bad makes achieve the effect that when product push that product pushes, improves user's acceptance,
Improve the efficiency of product push.
In one embodiment, in step s 30, i.e., user mood value is obtained according to M expression unit, as shown in figure 3, tool
Body may comprise steps of:
S31: the corresponding mood value of M expression unit is obtained according to preset micro- expression standards of grading.
It is alternatively possible to the corresponding mood value of expression unit be preset, using the corresponding mood value of expression unit as pre-
If micro- expression standards of grading, as shown in table 2:
The micro- expression standards of grading table of table 2
Specifically, after getting M expression unit of facial image, according to preset micro- expression scoring mark of upper table
Standard, the corresponding mood value of available to M expression unit.It is to be appreciated that the corresponding mood value of expression unit in above-mentioned table 2
It is only one specifically illustratively to illustrate, does not constitute the limitation to the present embodiment, can specifically set according to actual needs
It sets, details are not described herein.
S32: user mood value is calculated according to the corresponding mood value of M expression unit.
Specifically, after getting the corresponding mood value of M expression unit, mood value is subjected to summation remittance the long and and is made
For user mood value.For example, what is got is corresponding if M expression unit of facial image is respectively AU12, AU6, AU7
Mood value is respectively 3,1,4, then mood value is carried out summation and summarizes to obtain user mood value=3+1+4=8.
In the corresponding embodiment of Fig. 3, the corresponding mood of M expression unit is obtained according to preset micro- expression standards of grading
Value, is calculated user mood value further according to the corresponding mood value of M expression unit, and the facial image obtained is made to be preset micro- table
After the identification of feelings identification model, user mood value can be obtained according to preset micro- expression standards of grading, be worth the mood of user
To quantization, to more accurately reflect user mood value.Further, pushing away for product is carried out according to accurate user mood value
It send, the push of product can more be made to reach expected efficiency, improve the efficiency of product push.
In one embodiment, in step S40, i.e., product pushed information is sent according to user mood value and user identifier, such as
Shown in Fig. 4, it can specifically include following steps:
S41: alternate product pushed information and push mood value are associated, pushed information contingency table is formed.
Wherein, alternate product pushed information refers to all product pushed informations pushed.Push mood value refers to
Mood value corresponding with product pushed information.
Specifically, alternate product pushed information can be classified according to the section of specific push mood value, is made standby
It selects product pushed information to form being associated with for mapping relations with the section for pushing mood value, forms pushed information contingency table.Optionally,
It, can be according to the statistics of big data when alternate product pushed information is classified according to the section of specific push mood value
Classify, such as when user mood value is higher, acceptant A class product information, and when user mood value is lower, it is easy
Receive B class product information etc., then mood value by alternate product pushed information and is pushed according to the result of these big datas statistics
Association forms pushed information contingency table.
S42: user mood value is matched with push mood value, is closed according to matched push mood value from pushed information
Corresponding alternate product pushed information is obtained in connection table as product pushed information.
It specifically, will be in user mood value and pushed information contingency table after obtaining user mood value according to step S30
Mood value matched, if user mood value falls into the section of one of push mood value in pushed information contingency table
When, then the corresponding alternate product pushed information in mood value section is obtained as pushed information.
It is alternatively possible to after being screened according to the historical record of user to alternate product pushed information, further according to user
Mood value selection alternate product pushed information is pushed.Wherein, the historical record of user can check record, official communication for user
Consultation record or purchaser record etc..I.e. by the product of type same or similar with the historical record of user in alternate product pushed information
Pushed information is screened in alternate product pushed information, then is pushed away accordingly on the basis of screening according to user mood value
It send.For example, the purchaser record by user is known, user once bought A product, then will be with A product same type or close
The product pushed information of type screens in alternate product pushed information.
S43: product pushed information is sent according to user identifier.
It is alternatively possible to product pushed information be pushed by way of client message notifies, such as cell phone application
Message informing form.The cell-phone number that user can also be obtained according to user identifier sends the form transmission product push of short message
Information.The mailbox that user can also be obtained according to user identifier, sends product pushed information by way of sending mail.Its
In, mailbox of cell-phone number or user etc. obtains when can carry out the registration of client by user.
In the corresponding embodiment of Fig. 4, by the way that alternate product pushed information and push mood value to be associated, formation is pushed away
It delivers letters breath contingency table；Then user mood value is matched with push mood value, according to matched push mood value from push
Corresponding alternate product pushed information is obtained in information association table as product pushed information；It is finally sent and is produced according to user identifier
Product pushed information.Be associated the pushed information of product and specific mood value to form contingency table, make product pushed information into
The subdivision of one step is worth in conjunction with the mood of user and carries out the push of product more accurately, improves the acceptance of product pushed information, mention
The efficiency of high product push.
In one embodiment, after step S30, i.e., the step of obtaining user mood value according to M expression unit it
Afterwards, as shown in figure 5, the product method for pushing of intelligent recognition provided in an embodiment of the present invention is further comprising the steps of:
S51: user mood value is compared with default mood threshold value.
Wherein, it presets mood threshold value and refers to the threshold value that can send the user mood value of product pushed information.It is appreciated that
When user mood value is higher, product pushed information is easier to be received by user, sends product pushed information to reach
Purpose.It is alternatively possible to obtain default mood threshold value according to the statistics of big data, such as according to the statistics of big data, user
A possibility that mood value receives product pushed information when 8 points is higher, then sets up separately 8 and be set to default mood threshold value.
S52: it if user mood value reaches default mood threshold value, executes and production is sent according to user mood value and user identifier
The step of product pushed information.
Specifically, when user mood value reaches default mood threshold value, server-side thens follow the steps S40, i.e., according to user
The step of mood value and user identifier send product pushed information.Optionally, when user mood value is less than default mood threshold value,
Product pushed information is not sent, or only sends user to user and shows loving care for information, such as push warm innermost thoughts and feelings sentence to user, to improve
User mood value facilitates the push of subsequent product information.
In the corresponding embodiment of Fig. 5, by the way that user mood value to be compared with default mood threshold value, if user mood
Value reaches default mood threshold value, then executes the step of sending product pushed information according to user mood value and user identifier.Setting
One default mood threshold value just carries out the push of product, fully considers only when user mood value reaches default mood threshold value
With the mood for looking after user, so that the push of product is not carried out push when user mood is bad causes user to push product
Dislike, but the push for carrying out product again when user mood is good keeps the acceptance of user higher, improves the efficiency of product push.
It is appreciated that product pushed information can be to be multiple, in one embodiment, product pushed information is N number of, wherein N
For positive integer, after the step s 40, i.e., the step of sending product pushed information according to user mood value and user identifier it
Afterwards, as shown in fig. 6, the product method for pushing of intelligent recognition provided in an embodiment of the present invention is further comprising the steps of:
S61: obtain N number of product pushed information checks the time.
Optionally, product pushed information checks that the time can be arranged timer by client and realize.Specifically
Ground, when user reads a certain product pushed information, server-side calculates user by client triggering timing device and pushes away to the product
That delivers letters breath checks the time.Optionally, user jumps to the page of product pushed information by clicking the link of product pushed information
It is read in face；When the user clicks when the link of product pushed information, server-side receives click information, then passes through client
Timer is checked in triggering one；When user leaves the product pushed information page, server-side receives product pushed information
Return information then stops this and checks timer, while obtaining the time for checking timer, so that the product pushed information is checked
Time.Other products pushed information can similarly be obtained checks the time, and finally obtain N number of product pushed information checks the time.
S62: checking the time according to N number of product pushed information, adjusts the corresponding alternate product of N number of product pushed information and pushes away
It delivers letters push priority of the breath in pushed information contingency table.
It is appreciated that due to product pushed information be it is N number of, then user may just look at when checking product pushed information
One of them or in which several product pushed informations；Although each product pushed information checks that each product pushes away
That delivers letters breath checks that the time is all different, has with short, shows that user is different to the attention rate of each product pushed information.Cause
This, can be according to user's checking the time and adjust the push priority of product pushed information to product pushed information.
It is alternatively possible to which some product pushed information is checked that the time accounts for the time of checking of N number of product pushed information
Foundation of the ratio as adjustment push priority.Specifically, single product pushed information is checked that the time pushes away divided by N number of product
What the checking the time of breath (i.e. total time) of delivering letters obtained the product pushed information checks time scale.
Specifically, first time scale threshold value, such as 60% can be preset；When obtained time scale reaches
When one time scale threshold value, then it is alternative in pushed information contingency table to obtain the corresponding product pushed information of the time scale
The push priority of the alternate product pushed information is improved level-one by product pushed information.It is alternatively possible to when setting second
Between proportion threshold value, such as 20%, it is corresponding when time scale is lower than second time scale threshold value then to obtain the time scale
Alternate product pushed information of the product pushed information in pushed information contingency table, the push of the alternate product pushed information is excellent
First grade reduces level-one.It should be understood that being the type to product pushed information when adjusting the push priority of product pushed information
Push priority is adjusted.
S63: if the not up to default push of the push priority of any product pushed information in N number of product pushed information is excellent
First grade threshold value then removes the corresponding alternate product pushed information of the product pushed information from pushed information contingency table.
Specifically, the push priority of N number of product pushed information is compared with default push priority threshold value, if N
The push priority of any product pushed information in a product pushed information is more than or equal to default push priority threshold value,
Then this product pushed information is retained in pushed information contingency table.If any product in N number of product pushed information pushes letter
The push priority of breath is less than default push priority threshold value, then by the corresponding alternate product pushed information of this product pushed information
It is removed in pushed information contingency table.It is alternatively possible to which the push priority according to product pushed information is ranked up, will push
The higher product pushed information sequence of priority is preceding being sent to user.If the push priority of product pushed information is not up to pre-
If pushing priority threshold value, then user is not sent to.
It is appreciated that alternate product pushed information is to maintain update, that is, there is new product pushed information to be added to alternatively
In product pushed information.Optionally, when there is new product pushed information to be added to alternate product pushed information, new production is obtained
The product type of product pushed information, if the not up to default push priority threshold value of the corresponding push priority of product type, no
The new product pushed information is added in alternate product pushed information.
In the corresponding embodiment of Fig. 6, the time is checked by the N number of product pushed information of acquisition, is pushed according to N number of product
Information checks the time, adjusts push priority of N number of product pushed information in push contingency table；If N number of product push letter
The not up to default push priority threshold value of the push priority of product pushed information in breath, then it is the product pushed information is corresponding
Alternate product pushed information removed from pushed information contingency table.Product pushed information checks that the time represents user to production
The interest level of product pushed information, according to product pushed information to check the time preferential to adjust the push of product pushed information
Grade, preferentially pushes the high product pushed information of user's interest level；If the push priority of product pushed information is not
Reach default push priority threshold value, then shows that user is inadequate to the product pushed information interest level, then pushes away this product
Breath of delivering letters is removed from pushed information contingency table, improves the push precision of subsequent product pushed information, makes the product letter of push
Breath is more easier to be received by user, improves the efficiency of product push.
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 product driving means of intelligent recognition, the product driving means of the intelligent recognition are provided
It is corresponded with the product method for pushing of intelligent recognition in above-described embodiment.As shown in fig. 7, the product of the intelligent recognition pushes dress
It sets and obtains module 10 including facial image, expression unit obtains module 20, mood value obtains module 30 and pushed information sends mould
Block 40.Detailed description are as follows for each functional module:
Facial image obtains module 10, for obtaining facial image, wherein facial image includes user identifier.
Expression unit obtains module 20, presets in micro- Expression Recognition model for facial image to be input to, and obtains face
M expression unit of image, wherein M is positive integer.
Mood value obtains module 30, for obtaining user mood value according to M expression unit.
Pushed information sending module 40, for sending product pushed information according to user mood value and user identifier.
Further, as shown in figure 8, it includes that mood value acquiring unit 31 and mood value calculate list that mood value, which obtains module 30,
Member 32.
Mood value acquiring unit 31, for obtaining the corresponding feelings of M expression unit according to preset micro- expression standards of grading
Thread value.
Mood value computing unit 32, for user mood value to be calculated according to the corresponding mood value of M expression unit.
Further, as shown in figure 9, pushed information sending module 40 includes that contingency table forms unit 41, pushed information obtains
Take unit 42 and pushed information transmission unit 43.
Contingency table forms unit 41, for alternate product pushed information and push mood value to be associated, forms push
Information association table.
Pushed information acquiring unit 42 is pushed away for matching user mood value with push mood value according to matched
Mood value is sent to obtain corresponding alternate product information from pushed information contingency table as product pushed information.
Pushed information transmission unit 43, for sending product pushed information according to user identifier.
Further, the product driving means of intelligent recognition provided in an embodiment of the present invention further includes that mood value judges mould
Block, mood value judgment module include mood threshold value comparison unit and pushed information transmission unit.
Mood threshold value comparison unit, for user mood value to be compared with default mood threshold value.
Pushed information transmission unit executes if reaching default center value threshold value for user mood value according to user mood
The step of value and user identifier send product pushed information.
Further, product pushed information is N number of, wherein N is positive integer, intelligent recognition provided in an embodiment of the present invention
Product driving means further include priority adjustment module, priority adjustment module include check time acquisition unit, push it is excellent
First grade adjustment unit and alternate information removal unit.
It checks time acquisition unit, checks the time for obtain N number of product pushed information.
Priority adjustment unit is pushed, for checking the time according to N number of product pushed information, is adjusted described N number of
Push priority of the corresponding alternate product pushed information of product pushed information in the pushed information contingency table.
Alternate information removal unit, if for described in any product pushed information in N number of product pushed information
The not up to default push priority threshold value of priority is pushed, then by the corresponding alternate product pushed information of the product pushed information
It is removed from the pushed information contingency table.
The specific of product driving means about intelligent recognition limits the product that may refer to above for intelligent recognition
The restriction of method for pushing, details are not described herein.Modules in the product driving means of above-mentioned intelligent recognition can whole or portion
Divide and is realized by software, hardware and combinations thereof.Above-mentioned each module can be embedded in the form of hardware or independently of computer equipment
In processor in, can also be stored in a software form in the memory in computer equipment, in order to processor calling hold
The corresponding operation of the above modules of row.
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
The database of machine equipment is for storing micro- Expression Recognition model, expression unit, micro- expression standards of grading, product pushed information and pushing away
It delivers letters breath contingency table etc..The network interface of the computer equipment is used to communicate with external terminal by network connection.The calculating
A kind of product method for pushing of intelligent recognition is realized when machine program is executed by processor.
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
Obtain facial image, wherein facial image includes user identifier；
Facial image is input to and is preset in micro- Expression Recognition model, obtains M expression unit of facial image, wherein M
For positive integer；
User mood value is obtained according to M expression unit；
Product pushed information is sent according to user mood value and user identifier.
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
Obtain facial image, wherein facial image includes user identifier；
Facial image is input to and is preset in micro- Expression Recognition model, obtains M expression unit of facial image, wherein M
For positive integer；
User mood value is obtained according to M expression unit；
Product pushed information is sent according to user mood value and user identifier.
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 product method for pushing of intelligent recognition characterized by comprising
Obtain facial image, wherein the facial image includes user identifier；
The facial image is input to and is preset in micro- Expression Recognition model, M expression unit of the facial image is obtained,
In, M is positive integer；
User mood value is obtained according to the M expression units；
Product pushed information is sent according to the user mood value and the user identifier.
2. the product method for pushing of intelligent recognition as described in claim 1, which is characterized in that described according to the M expressions
Unit obtains user mood value, comprising:
The corresponding mood value of the M expression units is obtained according to preset micro- expression standards of grading；
The user mood value is calculated according to the corresponding mood value of the described expression unit of M.
3. the product method for pushing of intelligent recognition as described in claim 1, which is characterized in that described according to the user mood
Value and the user identifier send product pushed information, comprising:
Alternate product pushed information and push mood value are associated, pushed information contingency table is formed；
The user mood value is matched with the push mood value, is pushed away according to the matched push mood value from described
It delivers letters and obtains the corresponding alternate product pushed information as product pushed information in breath contingency table；
The product pushed information is sent according to the user identifier.
4. the product method for pushing of intelligent recognition as described in claim 1, which is characterized in that described according to the M tables
After feelings unit obtains the step of user mood value, the product method for pushing of the intelligent recognition further include:
The user mood value is compared with default mood threshold value；
If the user mood value reaches the default center value threshold value, execute described according to the user mood value and the use
The step of family mark sends product pushed information.
5. the product method for pushing of intelligent recognition as claimed in claim 3, which is characterized in that the product PUSH message is N
It is a, wherein N is positive integer；
After described the step of sending product pushed information according to the user mood value and the user identifier, the intelligence
The product method for pushing of identification further include:
Obtain N number of product pushed information checks the time；
According to checking the time for N number of product pushed information, adjusts the corresponding alternate product of N number of product pushed information and push away
It delivers letters push priority of the breath in the pushed information contingency table；
If the not up to default push of the push priority of any product pushed information in N number of product pushed information is excellent
First grade threshold value, then by the corresponding alternate product pushed information of the product pushed information from the pushed information contingency table
It removes.
6. a kind of product driving means of intelligent recognition characterized by comprising
Facial image obtains module, for obtaining facial image, wherein the facial image includes user identifier；
Expression unit obtains module, presets in micro- Expression Recognition model for the facial image to be input to, obtains the people
M expression unit of face image, wherein M is positive integer；
Mood value obtains module, for obtaining user mood value according to the M expression units；
Pushed information sending module, for sending product pushed information according to the user mood value and the user identifier.
7. the product driving means of intelligent recognition as claimed in claim 6, which is characterized in that the mood value obtains module packet
Include mood value acquiring unit and mood value computing unit；
The mood value acquiring unit, it is corresponding for obtaining the M expression units according to preset micro- expression standards of grading
Mood value；
The mood value computing unit, for user's heart to be calculated according to the corresponding mood value of the described expression unit of M
Feelings value.
8. the product driving means of intelligent recognition as claimed in claim 6, which is characterized in that the pushed information sending module
Unit, pushed information acquiring unit and pushed information transmission unit are formed including contingency table；
The contingency table forms unit, for alternate product pushed information and push mood value to be associated, forms push letter
Cease contingency table；
The pushed information acquiring unit, for the user mood value to be matched with the push mood value, according to
The push mood value matched obtains corresponding alternate product information as the product from the pushed information contingency table and pushes away
It delivers letters breath；
The pushed information transmission unit, for sending the product pushed information according to the user identifier.
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 product method for pushing of any one of 5 intelligent recognitions.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In the product push of realization intelligent recognition as described in any one of claim 1 to 5 when the computer program is executed by processor
The step of method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811255718.XA CN109559193A (en) | 2018-10-26 | 2018-10-26 | Product method for pushing, device, computer equipment and the medium of intelligent recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811255718.XA CN109559193A (en) | 2018-10-26 | 2018-10-26 | Product method for pushing, device, computer equipment and the medium of intelligent recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109559193A true CN109559193A (en) | 2019-04-02 |
Family
ID=65865478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811255718.XA Pending CN109559193A (en) | 2018-10-26 | 2018-10-26 | Product method for pushing, device, computer equipment and the medium of intelligent recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109559193A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209934A (en) * | 2019-05-20 | 2019-09-06 | 平安普惠企业管理有限公司 | Information-pushing method and relevant apparatus based on micro- Expression Recognition |
| CN110245291A (en) * | 2019-05-23 | 2019-09-17 | 广州至真信息科技有限公司 | A kind of display methods of business datum, device, computer equipment and storage medium |
| CN110310169A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, equipment and medium based on interest value |
| CN110389662A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Content displaying method, device, storage medium and the computer equipment of application program |
| 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 |
| CN113409067A (en) * | 2021-05-07 | 2021-09-17 | 支付宝(杭州)信息技术有限公司 | User interaction method, device and equipment |
| CN113472834A (en) * | 2020-04-27 | 2021-10-01 | 海信集团有限公司 | Object pushing method and device |
| CN117499477A (en) * | 2023-11-16 | 2024-02-02 | 北京易华录信息技术股份有限公司 | Information pushing method and system based on large model training |
-
2018
- 2018-10-26 CN CN201811255718.XA patent/CN109559193A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209934A (en) * | 2019-05-20 | 2019-09-06 | 平安普惠企业管理有限公司 | Information-pushing method and relevant apparatus based on micro- Expression Recognition |
| CN110310169A (en) * | 2019-05-22 | 2019-10-08 | 深圳壹账通智能科技有限公司 | Information-pushing method, device, equipment and medium based on interest value |
| CN110245291A (en) * | 2019-05-23 | 2019-09-17 | 广州至真信息科技有限公司 | A kind of display methods of business datum, device, computer equipment and storage medium |
| CN110389662A (en) * | 2019-06-19 | 2019-10-29 | 深圳壹账通智能科技有限公司 | Content displaying method, device, storage medium and the computer equipment of application program |
| WO2020253360A1 (en) * | 2019-06-19 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Content display method and apparatus for application, storage medium, and computer 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 |
| CN113472834A (en) * | 2020-04-27 | 2021-10-01 | 海信集团有限公司 | Object pushing method and device |
| CN113409067A (en) * | 2021-05-07 | 2021-09-17 | 支付宝(杭州)信息技术有限公司 | User interaction method, device and equipment |
| CN117499477A (en) * | 2023-11-16 | 2024-02-02 | 北京易华录信息技术股份有限公司 | Information pushing method and system based on large model training |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109559193A (en) | Product method for pushing, device, computer equipment and the medium of intelligent recognition | |
| CN109344682A (en) | Classroom monitoring method, device, computer equipment and storage medium | |
| CN109472206B (en) | Risk assessment method, device, equipment and medium based on micro-expressions | |
| CN107704834A (en) | Householder method, device and storage medium are examined in micro- expression face | |
| CN105205779B (en) | A kind of eyes image processing method, system and camera terminal based on anamorphose | |
| US11748980B2 (en) | Makeup evaluation system and operating method thereof | |
| CN109359521A (en) | The two-way assessment system of Classroom instruction quality based on deep learning | |
| US8565493B2 (en) | Method, system, and computer-readable recording medium for recognizing face of person included in digital data by using feature data | |
| WO2021078157A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN108829900A (en) | A kind of Research on face image retrieval based on deep learning, device and terminal | |
| CN108171463A (en) | A kind of long-range face label method, electronic device and computer readable storage medium | |
| CN107895168A (en) | The method of data processing, the device of data processing and computer-readable recording medium | |
| EP3579176A1 (en) | Makeup evaluation system and operation method thereof | |
| CN109685611A (en) | A kind of Products Show method, apparatus, computer equipment and storage medium | |
| CN111476222B (en) | Image processing method, image processing device, computer equipment and computer readable storage medium | |
| CN110111136B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| CN111428662A (en) | Advertisement playing change method and system based on crowd attributes | |
| CN104766062A (en) | Face recognition system and register and recognition method based on lightweight class intelligent terminal | |
| CN110516558A (en) | Sample data acquisition methods, device, computer equipment and storage medium | |
| US11749019B2 (en) | Systems and methods for matching facial images to reference images | |
| CN109271930A (en) | Micro- expression recognition method, device and storage medium | |
| CN107730372A (en) | The method and apparatus that a kind of Bank Hall personalized product based on recognition of face is recommended | |
| CN109522824A (en) | Face character recognition methods, device, computer installation and storage medium | |
| CN110458594A (en) | A kind of network surveying questionnaire generation method and device based on user's weight | |
| DE102016200047A1 (en) | Multimodal physical activity monitoring systems |
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 |