CN110097470A - Finance product promotion method, device and computer equipment based on artificial intelligence - Google Patents
Finance product promotion method, device and computer equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN110097470A CN110097470A CN201910209202.XA CN201910209202A CN110097470A CN 110097470 A CN110097470 A CN 110097470A CN 201910209202 A CN201910209202 A CN 201910209202A CN 110097470 A CN110097470 A CN 110097470A
- Authority
- CN
- China
- Prior art keywords
- user
- face
- information
- face image
- organ
- 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 38
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 60
- 230000003340 mental effect Effects 0.000 claims abstract description 35
- 230000004927 fusion Effects 0.000 claims abstract description 16
- 238000003860 storage Methods 0.000 claims abstract description 16
- 239000013598 vector Substances 0.000 claims description 79
- 210000000056 organ Anatomy 0.000 claims description 76
- 230000001815 facial effect Effects 0.000 claims description 45
- 238000004590 computer program Methods 0.000 claims description 18
- 239000000284 extract Substances 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 210000004709 eyebrow Anatomy 0.000 description 4
- 230000006855 networking Effects 0.000 description 4
- 230000001737 promoting effect Effects 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 210000000887 face Anatomy 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 210000004209 hair Anatomy 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- 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
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Finance (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Technology Law (AREA)
- Human Resources & Organizations (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention is suitable for field of artificial intelligence, provides a kind of finance product promotion method based on artificial intelligence, device, storage equipment and computer equipment.Wherein, if method includes: that the positive mental attitude index is higher than the second preset threshold, the history life data of first user are obtained；The first evaluation information of first user is determined according to history life data；Obtain the second evaluation information that first user inputs in terminal device；The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains the narration information of the user, and the narration information includes the positive incentive story between the user and finance product；Create the corresponding link of the narration information；When detecting that the corresponding advertisement of the link is browsed by second user, the corresponding narration information of the link is shown；When detecting that the narration information has been browsed, pop-up registration message request.
Description
Technical field
The invention belongs to field of artificial intelligence more particularly to a kind of finance product popularization sides based on artificial intelligence
Method, device, storage medium and computer equipment.
Background technique
With the development of science and technology also when the river rises the boat goes up for the income level of people, various financings have been emerged in large numbers on the market and have been produced
Product, however the way of promotion of finance product is more single, for example, the popularization of finance product is generally by the same webpage representation
The characteristics of relevant information of finance product, relevant information mainly includes finance product, however the financing of the same webpage representation produces
The relevant information of product is more identical, the relevant information of the finance product can not be done corresponding transformation in conjunction with different user, because
This can not carry out promoting in conjunction with user's feature and cause to promote low efficiency.
Summary of the invention
In view of this, the finance product promotion method that the embodiment of the invention provides a kind of based on artificial intelligence, device, depositing
Storage media and terminal device can not be carried out with solving the way of promotion presence of finance product in the prior art in conjunction with user's feature
Popularization causes the problem of promoting low efficiency.
The first aspect of the embodiment of the present invention provides a kind of finance product promotion method based on artificial intelligence, comprising:
The face image for obtaining the first user extracts the first facial feature information of the face image；
Calculate the second face of at least one face image in first facial feature information and sample face data library
The similarity value of characteristic information；
It is special by obtaining first face if calculated all similarity values are above the first preset threshold
Micro- expression in reference breath determines the positive mental attitude index of first user；
If the forward direction mental attitude index is higher than the second preset threshold, the history life number of first user is obtained
According to；
The first evaluation information of first user is determined according to history life data；
Obtain the second evaluation information that first user inputs in terminal device；
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains
The narration information of the user, the narration information include the positive incentive story between the user and finance product；
Create the corresponding link of the narration information；
When detecting that the corresponding advertisement of the link is browsed by second user, the corresponding story letter of the link is shown
Breath；
When detecting that the narration information has been browsed, pop-up registration message request.
The second aspect of the embodiment of the present invention provides a kind of finance product popularization device based on artificial intelligence, comprising:
First obtains module, and for obtaining the face image of the first user, the first face for extracting the face image is special
Reference breath；
Computing module is schemed for calculating at least one face in first facial feature information and sample face data library
The similarity value of second facial feature information of picture；
Determining module passes through acquisition if being above the first preset threshold for calculated all similarity values
Micro- expression in first facial feature information determines the positive mental attitude index of first user；
Second obtains module, if being higher than the second preset threshold for the positive mental attitude index, obtains described the
The history life data of one user；
Analysis module, for determining the first evaluation information of first user according to history life data；
Third obtains module, the second evaluation information inputted for obtaining first user in terminal device；
Fusion treatment module, the keyword for keyword and second evaluation information to first evaluation information
Fusion treatment is carried out, the narration information of the user is obtained, the narration information includes between the user and finance product
Positive incentive story；
Creation module, for creating the corresponding link of the narration information；
Display module, for showing the link when detecting that the corresponding advertisement of the link is browsed by second user
Corresponding narration information；
Display module, for when detecting that the narration information has been browsed, message request to be registered in pop-up.
The third aspect of the embodiment of the present invention provides a kind of computer equipment, comprising: memory, processor and storage
In the memory and the computer program that can run on the processor, the processor execute the computer program
When perform the steps of
The face image for obtaining the first user extracts the first facial feature information of the face image；
Calculate the second face of at least one face image in first facial feature information and sample face data library
The similarity value of characteristic information；
It is special by obtaining first face if calculated all similarity values are above the first preset threshold
Micro- expression in reference breath determines the positive mental attitude index of first user；
If the forward direction mental attitude index is higher than the second preset threshold, the history life number of first user is obtained
According to；
The first evaluation information of first user is determined according to history life data；
Obtain the second evaluation information that first user inputs in terminal device；
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains
The narration information of the user, the narration information include the positive incentive story between the user and finance product；
Create the corresponding link of the narration information；
When detecting that the corresponding advertisement of the link is browsed by second user, the corresponding story letter of the link is shown
Breath；
When detecting that the narration information has been browsed, pop-up registration message request.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the computer program performs the steps of when being executed by processor
The face image for obtaining the first user extracts the first facial feature information of the face image；
Calculate the second face of at least one face image in first facial feature information and sample face data library
The similarity value of characteristic information；
It is special by obtaining first face if calculated all similarity values are above the first preset threshold
Micro- expression in reference breath determines the positive mental attitude index of first user；
If the forward direction mental attitude index is higher than the second preset threshold, the history life number of first user is obtained
According to；
The first evaluation information of first user is determined according to history life data；
Obtain the second evaluation information that first user inputs in terminal device；
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains
The narration information of the user, the narration information include the positive incentive story between the user and finance product；
Create the corresponding link of the narration information；
When detecting that the corresponding advertisement of the link is browsed by second user, the corresponding story letter of the link is shown
Breath；
When detecting that the narration information has been browsed, pop-up registration message request.
In the embodiment of the present invention, at least one in first facial feature information and sample face data library is calculated first
The similarity value of second facial feature information of face image；If it is default that calculated all similarity values are above first
Threshold value then determines the positive mental attitude of first user by micro- expression in acquisition first facial feature information
Index；If the forward direction mental attitude index is higher than the second preset threshold, the history life number of first user is obtained
According to, and the first evaluation information of first user is determined according to history data of living；Then, in conjunction with first user
The second evaluation information of terminal device input and first evaluation information obtain comprising the user and finance product it
Between positive incentive story narration information；Finally, creating the corresponding link of the narration information；When detect it is described link pair
When the advertisement answered is browsed by second user, the corresponding narration information of the link is shown；When detecting that the narration information is clear
When having look at, pop-up registration message request.As it can be seen that the narration information in the present invention be according to the first evaluation information of the first user and
What the second evaluation information generated, the characteristics of first evaluation information and second evaluation information embody the first user, because
This can generate different narration informations in conjunction with the characteristics of different user, fetch invitation second by the corresponding chain of narration information and use
Family registration, the advertisement that second user browses to be it is relevant to the personal touch of the first user, in other words, it is same second use
Family or different second users, be all based on the advertisement that the first different users sees it is different, so avoid popularization
Mode it is single, improve the efficiency of popularization, and the characteristics of advertisement is the first user and the combination of finance product, therefore solve
The way of promotion of finance product causes to promote asking for low efficiency in the presence of that can not promote in conjunction with user feature in the prior art
Topic.
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 finance product promotion method in the embodiment of the present invention based on artificial intelligence；
Fig. 2 is the implementation process signal for the finance product promotion method based on artificial intelligence that the embodiment of the present invention one provides
Figure；
Fig. 3 is the schematic diagram that the finance product provided by Embodiment 2 of the present invention based on artificial intelligence promotes device；
Fig. 4 is that finance product provided by Embodiment 2 of the present invention based on artificial intelligence promotes showing for computing module in device
It is intended to；
Fig. 5 is that the finance product provided by Embodiment 2 of the present invention based on artificial intelligence promotes the second computing unit in device
Schematic diagram；
Fig. 6 is the schematic diagram for the computer equipment that the embodiment of the present invention three provides.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Embodiment one
Finance product promotion method provided by the invention based on artificial intelligence, can be applicable in the application environment such as Fig. 1,
Wherein, computer equipment is communicated by network with server.Wherein, computer equipment/client can be, but not limited to respectively
Kind personal computer, laptop, smart phone, tablet computer and portable wearable device.Server can be with independently
The server cluster of server either multiple servers composition realize.
Fig. 2 shows the implementation processes for the finance product promotion method based on artificial intelligence that the embodiment of the present invention one provides
Schematic diagram.Specifically comprise the following steps S101 to step as shown in Fig. 2, being somebody's turn to do the finance product promotion method based on artificial intelligence
S110。
S101, the face image for obtaining the first user, extract the first facial feature information of the face image.
For example, terminal device is scanned the face of the first user, face image is obtained, by the facial image information
It is sent to server, server extracts the first facial feature information of the face image.
S102, calculate at least one face image in first facial feature information and sample face data library second
The similarity value of facial feature information.
As an embodiment of the present invention, wherein the facial feature information includes the position of facial feature localization information, face
Confidence breath etc., face include eyebrow, eyes, ear, nose and mouth.Optionally, in order to filter out face value from the first user
Higher user, the face image in sample face data library refer to the face being stored in advance in sample face data library
Image, the face image in sample face data library can be the face image of star, it is to be understood that the face of star
Portion's image face value is higher, and by step S102, higher first user of face value can be tentatively filtered out from the first user,
Attract other clients since the face image for showing first user may be needed when promoting, filter out face value compared with
The first high user can achieve better promotion effect.
It should be noted that at least one face in calculating first facial feature information and sample face data library
During the similarity value of second facial feature information of image, can be determined according to first facial feature information first
The attributes such as gender, the age of one user, and then according to face corresponding with the attribute in above-mentioned attribute selection sample face data library
Portion's image and then the calculating for carrying out similarity value avoid face higher first user of value script since gender, age etc. belong to
Different faces in property differ greatly, and the occurrence of do not come out by preliminary screening；That is, if the first user and sample face
The attributes such as the gender of the face image in portion's database and age are consistent, then the first facial feature information and the second face feature are believed
If breath is similar, illustrate the first user compared with the face image (for example, face image of star) in sample face data library
Similar, the face value of first user may be higher at this time, on the contrary, then the face value of the first user may be undesirable.It illustrates
Bright: there are the 8 male's face images and 8 female face images between 20-25 years old in sample face data library, then according to
One facial feature information determine the first user be women and the age be between 20-25 years old after, only calculate separately the first face spy
The similarity value of the second facial feature information of at least one of reference breath and 8 female face images.
It is described to calculate second of at least one face image in first facial feature information and sample face data library
The similarity value of facial feature information, comprising:
S201 positions the face of face area in the face image of first user, obtains location information.
S202, determined according to the location information first user face location information.
Wherein, the location information of face can be coordinate information.
S203, the face area for dividing first user according to the positional information face in area locating for each organ
Domain.
The present embodiment searches corresponding organ (i.e. eyebrow, eyes, ear, nose and mouth by way of positioning feature point
Bar).Firstly, the average shape of the human face characteristic point in initial face iconic model is placed in the face image of the first user
Face location is believed by the characteristic point of the image in region locating for each organ in face in the face image of the first user of comparison
Characteristic point information corresponding with the organ in initial face iconic model is ceased, the adjustment of characteristic point position is constantly carried out, iteration is more
Final characteristic point position is obtained after secondary, the location information of face as in the face image of the first user.Wherein, initial face figure
As model can refer to the model that can show each organ in face image in face and its locating region, for example,
The initial face iconic model includes a 2D faceform, includes a face mask on the 2D faceform, described
Face mask includes five organs (i.e. eyebrow, eyes, ear, nose and mouth), this five organs are corresponding in 2D faceform
Position on, each organ has an average shape, and the average shape is made of several characteristic points, each average
(characteristic point position locating for the characteristic point of each average shape is Different Organs on this feature point position to the characteristic point of shape
Coordinate average value) set constitutive characteristic point information.During the adjustment of features described above point position, if the first user
The device in the characteristic point information and initial face iconic model of the image in region locating for each organ in face image in face
The corresponding characteristic point information of official, then will be locating for each organ in the face image of the first user in face on separate direction
The characteristic point position of the image in region is carried out to close to the corresponding characteristic point position of the organ in the initial face iconic model
Adjustment, until within the scope of the distance between two characteristic point positions reach predeterminated position threshold value, the specific calculation that is iterated
Details are not described herein for method.
S204, the image for extracting region locating for each organ.
S205, the characteristic information for extracting each organ respectively from the image in region locating for each organ.
S206, the characteristic information of each organ in the characteristic information of each organ and initial face iconic model is carried out
Comparison, obtains the analog information of each organ of face area in the face image of the first user.
S207, each organ of face area in the face image of first user is generated according to the analog information
Five features vector.
For S204-S207, extracting type includes conventional method (SIFT feature, HOG feature, LBP feature and color characteristic
Deng) and depth convolution generate characteristic information, and by all characteristic informations merge generate a feature vector；The feature letter
Breath includes position, size, shape, color and the texture of organ.For example, the analog information of A image B organ is A image B organ
With the similarity of B organ in initial face iconic model, meanwhile, which can be presented as A image B organ and initial face
The distance between B organ value (referring to subsequent step S304) in iconic model, distance is closer, illustrates A image B organ and initial face
B organ similarity is higher in portion's iconic model.Wherein, the distance value can be Euclidean distance.
S208, the five features vector of the five features vector and face image in sample face data library is subjected to phase
It is calculated like degree, obtains the face of face image in each organ and sample face data library of the face image of the first user
Similarity between feature vector, and by the similarity be recorded as first user face image and the sample face
The similarity value of face image in database.
It should be noted that the analog information of the same organ is closer in two human face regions, illustrate this two faces
In the organ similarity it is higher.Wherein, each organ of the face image of the first user and face in sample face data library
The manner of comparison that cosine similarity can be used in similarity S between the five features vector of portion's image calculates:
S=ab/ (| | a | | | | b | |)；
Wherein, a is the feature vector of organ in the face image of the first user, and b is sample face data Ku Zhong face figure
The feature vector of the face of picture.S value illustrates that the similarity degree of the two is higher closer to 1.
Optionally, the five features vector of face image in the five features vector and sample face data library is carried out
Similarity calculation obtains five of face image in each organ and sample face data library of the face image of the first user
Similarity between official's feature vector, specifically includes:
S301, obtain sample face data library in face image five features.
Wherein, can be preset in sample face data library multiple public praises preferably or the higher amusement circles star of face value
And/or the face image of sports star, each face image are associated with corresponding five features, it can be from the sample
The five features of the face image of the preferable amusement circles star of the public praise and/or sports star is obtained in this face data library.
S302, the five features is arranged in the way of who object, obtains sample face data library
In multiple face images five features corresponding to multiple five features vectors.
Wherein, the five features is carried out arranging in the way of who object includes: according to sample face data library
In select personage, the face of each personage are arranged.For example, multiple face of sports star Bryant are obtained after arranging
Multiple feature vectors, wherein the feature of the feature vector a of eyebrow, the feature vector b of eyes, the feature vector c of ear, nose
The feature vector e of vector d and mouth.
S303, according to the multiple five features vector, calculate multiple face images in sample face data library
The averaged feature vector of face's organ.
Wherein, averaged feature vector is a vector for characterizing the multiple feature vector.Specifically calculating average characteristics
When vector, it can be calculated according to the weight of face's organ each in each sample face.It should be noted that each face image
There are multiple feature vectors, the averaged feature vector in the present embodiment refers to the corresponding multiple spies of multiple organs in a face image
Levy the averaged feature vector of vector.For example, the calculation formula of the averaged feature vector in the present embodiment can be f=β * a+ γ * b
+ δ * c+ ε * d+ ξ * e, wherein β, γ, δ, ε and ξ be respectively feature vector a, the feature vector b of eyes, ear feature vector c,
The corresponding weight of feature vector e of the feature vector d and mouth of nose.
S304, obtain the first user face image averaged feature vector, according to the face image of first user
Averaged feature vector and sample face data library in multiple samples face's organ averaged feature vector, be calculated
In each organ of the face image of first user and sample face data library between the five features vector of face image
Similarity.
For S304, in the calculating process of the averaged feature vector of the face image of the first user and sample face data library
The calculating process of the averaged feature vector of face's organ is similar in multiple samples, and details are not described herein.
It can be calculated, be obtained similar between two averaged feature vectors according to the calculation formula of above-mentioned cosine similarity
Degree.Alternatively, the averaged feature vector of the face image of the first user is first calculated by the calculation formula of distance between vector
With in sample face data library in each star the averaged feature vector of face's organ distance value, then according to average characteristics to
The similarity of face image in face image and sample face data library of the distance between the amount value to calculate the first user.It can be with
Understand, the distance value is bigger, and similarity is smaller.The distance value can be ranked up, to the distance value from small
To being ranked up greatly, by preceding N, (e.g., the corresponding sample face of preceding 3) a distance value is as candidate face.
In the present embodiment, human face five-sense-organ it is similar differentiate from people to the basic classification of face feature (the face), into
Row accurate detailed analysis, comparison, can provide the similarity degree between different people or image between each human face for user,
It is people's face similarity degree that embodiment can also be integrated in turn.In addition, individual existing face comparative analysis applications are only extracted from itself
After be compared, do not consider its influence of the size position to its perception effect in entirety.For example, two eyes size shapes
The identical people of shape, but there is a big difference for eye distance, and conventional method will be considered that the eyes of two people like then in the present embodiment
In view of the difference of eye distance, it is believed that this organ of eyes is not like therefore the present embodiment then considers more in two people's face
It is perfect, comprehensive.The present embodiment can determine each part feelings similar to contrast sample's in the face of the first user as a result,
Condition improves the accuracy of human face analysis and comprehensive.
If 103, calculated all similarity values are above the first preset threshold, by obtaining first face
Micro- expression in portion's characteristic information determines the positive mental attitude index of first user.
Wherein, the example above is accepted, if finding in sample face data library similar to the face of the first user
Degree is higher than the face image of the first preset threshold, then by obtaining micro- expression in first facial feature information to determine
State the positive mental attitude index of the first user.The forward direction mental attitude index is used to characterize the image of the face of the first user
The positive degree of makings is greater than by determining that positive mental attitude index filters out positive mental attitude index from the first user
First user of provisional index value, to be conducive to increase the success rate that finance product is promoted.
Optionally, the forward direction by obtaining micro- expression in first facial feature information to determine first user
Mental attitude index specifically includes:
401, each micro- expression in the first facial feature information is obtained.
Wherein, micro- expression include but is not limited to it is glad, angry, detest, contempt, indignation and worry etc..
402, the positive value of each micro- expression and the weight of the positive value are calculated；
403, the weight of the positive value based on each micro- expression and the positive value, according to mental attitude index meter
Calculate the positive mental attitude index that first user is calculated in function.
For 402 and 403, for example, micro- expression of the first user is got as glad and worry, wherein glad positive value
It is 90, the positive value of worry is -20, and the weight of glad positive value is 50%, and the weight of the positive value of worry is 20%, then
The positive mental attitude index of first user is equal to [90*0.8+ (- 20) * 0.2]/100=0.68, it should be noted that
The value range of positive mental attitude index is 0 to 1, and positive mental attitude index then shows the essence of the first user closer to 1
Refreshing looks are more positive.
If 104, the positive mental attitude index is higher than the second preset threshold, the history for obtaining first user is raw
Live data.
Wherein, history life data may include but be not limited to the first user in mobile terminal and/or the upper netting index of computer end
According to, such as the behavioural informations such as previous search, browsing, consumption of user.Example is applied as of the invention one, it can be by first
The Internet data of customer mobile terminal and/or computer end is crawled and is clustered, to obtain the relevant history life data.
The specific implementation for crawling and clustering is not limited thereto.
105, the first evaluation information of first user is determined according to history life data.
106, the second evaluation information that first user inputs in terminal device is obtained.
107, fusion treatment is carried out to the keyword of the keyword of first evaluation information and second evaluation information,
The narration information of the user is obtained, the narration information includes the positive incentive story between the user and finance product.
For 105 to 107, wherein the first evaluation information can be the preliminary assessment information to first user, and second
Evaluation information can be the self-assessment information of user.Wherein, preliminary assessment information can be goes through according to the first user
History life data obtain, and preliminary assessment information can be " having deep love for moving ", " character is rectified ", " sociable ", " English proficiency
By force " etc..For example, the second evaluation information, which can be the first user, receives input self-assessment letter in terminal (e.g., mobile terminal)
After the prompting message of breath, input is completed, is retransmited to server.Wherein, the prompting message of self-assessment information can with but it is unlimited
In following format: " distinguished user please give one self-assessment of do-it-yourself, send to preferably promote xxx finance product
Mode is xxx, be thanks！".Further, after the prompting message for receiving input self-assessment information, first uses the first user
The operation that family can be inputted on website at the terminal, is also possible to be inputted in application program on mobile terminals
Operation can also be that any other can complete the scene of input operation at the terminal, and this is not restricted.Second self-assessment
Information may include the evaluation information of some label types and/or the evaluation information of interesting plot.Wherein, the evaluation information of label type includes
But be not limited to sunlight, it is optimistic, bear hardships and stand hard work, have adventurous spirit；The evaluation of interesting plot includes but is not limited to that the first user is purchasing
Buy variation in life caused by finance product front and back.The positive incentive story can buy finance product for the first user
The positive story in the front of promotion on individual wealth, the promotion in quality of the life and/or the promotion on profile afterwards.
Wherein, narration information can be text information (can be the corresponding link of HTML), and being also possible to image information (can
To be the corresponding link of HTML), it is also possible to audio-frequency information, video information, can also be that other include the story of plot
Information.When narration information is text information, the number of words of story, which can be, to be preset, such as the number of words no more than 300；When event
When thing information is H5 page info, the reading time of the H5 page can be preset, such as can specify that the reading time is no more than 3
Minute；When narration information is audio/video information, the playout length of audio/video information can be preset, such as no more than 5 points
Clock.
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains
The narration information of the user, specifically includes:
Word cutting processing is carried out to first evaluation information and second evaluation information, extracts first evaluation information
With the keyword in second evaluation information, the keyword is subjected to fusion treatment.
As an embodiment of the present invention, narration information can be user for example, by the data page of user or its
Social movement is presented in the predetermined region of his page, additional information associated with finance product is presented, is used second
Increase in the news stream at family or instant dynamic or protrudes in another way.It can be in social networking system or social networking system
The social movement of upper popularization.
108, the corresponding link of the narration information is created.
109, when detecting that the corresponding advertisement of the link is browsed by second user, the corresponding story letter of the link is shown
Breath.
It should be noted that the second user is the target user that the first user promotes the advertisement.
In a specific embodiment, it may be required in third party's webpage, social networking system webpage or other pages
Show advertisement.Can be in the private part of the page, such as the banner region at the top of the page, the column in the side of the page
In, show extensively in the GUI of the page, in pop-up window, at the top of content of the page or the other places about the page
It accuses.Alternatively or additionally, advertisement can be shown in or game interior in application.Advertisement can be shown in private pages, this
With regard to needing to interact or watch advertisement with advertisement before the accessible page of user, using application program or object for appreciation game.For example,
The circle of friends that user can be shared by the first user watches advertisement.
Second user can be interacted with advertisement in any suitable manner.User can click or select in another way wide
It accuses, and advertisement can guide second user (or the browser that uses of second user or other application) to associated with advertisement
The page.In the page associated with advertisement, user can take other movement, such as buy financing associated with advertisement and produce
Product or service relevant to the finance product receive associated with advertisement information, or when subscription is associated with advertisement
Thing communication.Advertisement with audio or video can be played by selecting the component (similar " broadcast button ") of advertisement.
Advertisement may include the social networking system function that user can interact.For example, advertisement can permit the second use
Family fetches " praising " with the associated icon of endorsement or corresponding chain by selection or approves advertisement.Similarly, the first user can
To share advertisement or event associated with advertisement with second user.
110, when detecting that the narration information has been browsed, pop-up registration message request.
Optionally, after message request is registered in pop-up, further includes:
111, the first quantity and described second for browsing the narration information second user that first user shares is obtained
The second quantity of the finance product is registered in user；
112, the value that shares one's experience of first user is calculated based on first quantity and the second quantity；
113, the mapping pass of the value that shares one's experience according to and scheduled the share one's experience value and electronics reward amount
System, the electronics for calculating first user reward amount.
For 111 to 113, wherein sharing can be sharing to wechat, the social softwares such as microblogging, such as shares and arrive wechat
Circle of friends calculate primary, be shared with some wechat good friend and also calculate once, being shared with some wechat group and calculating again once (or can be regarded as more
It is secondary).Second quantity can be the number-of-registration for inviting good friend, refer to and register corresponding link by sending to good friend, successfully infuse
The corresponding APP of advertisement or finance product that volume the present embodiment is related to etc..For example, the number that user shares is f, invite good friend's
Number-of-registration is g, then the electronics reward amount of the first user is equal to λ * f+ μ * g, and wherein λ and μ is preset weight.
The embodiment of the present invention extracts the first face feature of the face image by the face image of the first user of acquisition
Information；Calculate the second face feature of at least one face image in first facial feature information and sample face data library
The similarity value of information；If calculated all similarity values are above the first preset threshold, by obtaining described the
Micro- expression in one facial feature information determines the positive mental attitude index of first user；If the positive spiritual face
Looks index is higher than the second preset threshold, then obtains the history life data of first user；According to history life data
Determine the first evaluation information of first user；Obtain the second evaluation information that first user inputs in terminal device；
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains the user
Narration information, the narration information includes positive incentive story between the user and finance product；Create the story
The corresponding link of information；When detecting that the corresponding advertisement of the link is browsed by second user, show that the link is corresponding
Narration information；When detecting that the narration information has been browsed, pop-up registration message request.As it can be seen that this programme can combine
The characteristics of different user, generates different narration informations, avoids the single of the way of promotion, improves the efficiency of popularization, solves
The way of promotion of finance product causes to promote asking for low efficiency in the presence of that can not promote in conjunction with user's feature in the prior art
Topic.
Finance product promotion method based on artificial intelligence should be understood that the size of the serial number of each step in above-described embodiment simultaneously
The successive of execution sequence is not meant that, the execution sequence of each process should be determined by its function and internal logic, without coping with this hair
The implementation process of bright embodiment constitutes any restriction.
Embodiment two
Referring to FIG. 3, it illustrates provided by Embodiment 2 of the present invention, the finance product based on artificial intelligence promotes device 3
Schematic diagram.The finance product based on artificial intelligence promotes device 3, comprising: the first acquisition module 30, computing module 31,
Determining module 32, second obtains module 33 and analysis module 34, and third obtains module 35, fusion treatment module 36, creation module
37, display module 38 and display module 39.Wherein, the concrete function of each module is as follows:
First acquisition module 30 extracts the first face of the face image for obtaining the face image of the first user
Characteristic information；
Computing module 31, for calculating at least one face in first facial feature information and sample face data library
The similarity value of second facial feature information of image；
Determining module 32, if being above the first preset threshold for calculated all similarity values, by obtaining
Micro- expression in first facial feature information is taken to determine the positive mental attitude index of first user；
Second obtains module 33, if being higher than the second preset threshold for the positive mental attitude index, obtain described in
The history life data of first user；
Analysis module 34, for determining the first evaluation information of first user according to history life data；
Third obtains module 35, the second evaluation information inputted for obtaining first user in terminal device；
Fusion treatment module 36, the key for keyword and second evaluation information to first evaluation information
Word carries out fusion treatment, obtains the narration information of the user, and the narration information includes between the user and finance product
Positive incentive story；
Creation module 37, for creating the corresponding link of the narration information；
Display module 38, for showing the chain when detecting that the corresponding advertisement of the link is browsed by second user
Connect corresponding narration information；
Display module 39, for when detecting that the narration information has been browsed, message request to be registered in pop-up.
Optionally, referring to FIG. 4, computing module 31 includes:
Positioning unit 310, the face for face area in the face image to first user position, and obtain
Location information；
Determination unit 311, the location information of the face for determining first user according to the location information；
Division unit 312, it is every in the face of the face area for dividing first user according to the positional information
Region locating for a organ；
First extraction unit 313, for extracting the image in region locating for each organ；
Second extraction unit 314 extracts each device from the image in region locating for each organ for extracting respectively
The characteristic information of official；
Comparison unit 315, for by each organ in the characteristic information of each organ and initial face iconic model
Characteristic information compares, and obtains the analog information of each organ of face area in the face image of the first user；
Generation unit 316, face area in the face image for generating first user according to the analog information
Each organ five features vector；
Computing unit 317, for the face of face image in the five features vector and sample face data library are special
It levies vector and carries out similarity calculation, obtain face in each organ and sample face data library of the face image of the first user
Similarity between the five features vector of portion's image, and by the similarity be recorded as the face image of first user with
The similarity value of face image in sample face data library.
Optionally, referring to FIG. 5, computing unit 317 includes:
Subelement 3170 is obtained, for obtaining the five features of the face image in sample face data library；
It arranges subelement 3171 and obtains face for arranging the five features in the way of who object
Multiple five features vectors corresponding to the five features of multiple face images in database；
First computation subunit 3172, for calculating the sample face data according to the multiple five features vector
The averaged feature vector of face's organ of multiple face images in library；
Second computation subunit 3173, the averaged feature vector of the face image for obtaining the first user, according to described
In the averaged feature vector of the face image of first user and sample face data library in multiple samples face's organ it is flat
Face image in each organ and sample face data library of the face image of the first user is calculated in equal feature vector
Five features vector between similarity.
Optionally it is determined that module 32 includes:
Acquiring unit, for obtaining each micro- expression in the first facial feature information；
Third computing unit, for calculating the positive value of each micro- expression and the weight of the positive value；
4th computing unit, for according to the positive value of each micro- expression and the weight of the positive value, according to
Mental attitude index calculates the positive mental attitude index that first user is calculated in function.
Optionally, the finance product based on artificial intelligence promotes device 3, further includes:
Third obtains module, for obtaining the first number for browsing the narration information second user that first user shares
The second quantity of the finance product is registered in amount and the second user；
It shares one's experience and is worth computing module, for first user to be calculated based on first quantity and the second quantity
The value that shares one's experience；
Electronics rewards amount computing module, for value and the scheduled value that shares one's experience of sharing one's experience according to
With the mapping relations of electronics reward amount, the electronics for calculating first user rewards amount.
The specific restriction for promoting device about the finance product based on artificial intelligence may refer to above for based on people
The restriction of the finance product promotion method of work intelligence, details are not described herein.The above-mentioned finance product based on artificial intelligence promotes dress
Modules in setting can be realized fully or partially through software, hardware and combinations thereof.Above-mentioned each module can be in the form of hardware
It is embedded in or independently of the storage that in the processor in computer equipment, can also be stored in a software form in computer equipment
In device, the corresponding operation of the above modules is executed in order to which processor calls.
Embodiment three
In the present embodiment, a kind of computer equipment is provided, which can be server, internal structure
Figure can be as shown in Figure 6.The computer equipment includes processor, the memory, network interface sum number connected by system bus
According to library.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory of the computer equipment includes
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 the data being related in the finance product promotion method based on artificial intelligence.The computer is set
Standby network interface is used to communicate with external terminal by network connection.To realize when the computer program is executed by processor
A kind of finance product promotion method based on artificial intelligence.
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 are realized in above-described embodiment when executing computer program based on artificial
The step of finance product promotion method of intelligence, such as step 101 shown in Fig. 2 is to step 110.Alternatively, processor executes meter
Realize that the finance product in above-described embodiment based on artificial intelligence promotes the function of each module/unit of device when calculation machine program,
Such as module 30 shown in Fig. 3 is to the function of module 39.To avoid repeating, which is not described herein again.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program realizes the step of finance product promotion method in above-described embodiment based on artificial intelligence when being executed by processor, such as
Step 101 shown in Fig. 2 is to step 110.Alternatively, being realized when computer program is executed by processor in above-described embodiment based on people
The finance product of work intelligence promotes the function of each module/unit of device, such as module 30 shown in Fig. 3 is to the function of module 39.
To avoid repeating, which is not described herein again.
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 by the present invention,
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 finance product promotion method based on artificial intelligence characterized by comprising
The face image for obtaining the first user extracts the first facial feature information of the face image；
Calculate the second face feature of at least one face image in first facial feature information and sample face data library
The similarity value of information；
If calculated all similarity values are above the first preset threshold, by obtaining the first face feature letter
Micro- expression in breath determines the positive mental attitude index of first user；
If the forward direction mental attitude index is higher than the second preset threshold, the history life data of first user are obtained；
The first evaluation information of first user is determined according to history life data；
Obtain the second evaluation information that first user inputs in terminal device；
The keyword of keyword and second evaluation information to first evaluation information carries out fusion treatment, obtains described
The narration information of user, the narration information include the positive incentive story between the user and finance product；
Create the corresponding link of the narration information；
When detecting that the corresponding advertisement of the link is browsed by second user, the corresponding narration information of the link is shown；
When detecting that the narration information has been browsed, pop-up registration message request.
2. the finance product promotion method according to claim 1 based on artificial intelligence, which is characterized in that calculate described the
The similarity value of second facial feature information of at least one face image in one facial feature information and sample face data library,
Include:
The face of face area in the face image of first user are positioned, location information is obtained；
The location information of the face of first user is determined according to the location information；
Region locating for each organ in the face of the face area of first user is divided according to the positional information；
Extract the image in region locating for each organ；
Extract the characteristic information of each organ respectively from the image in region locating for each organ；
The characteristic information of each organ and the characteristic information of each organ in initial face iconic model are compared, obtained
The analog information of each organ of face area in the face image of first user；
The five features of each organ of face area in the face image of first user is generated according to the analog information
Vector；
The five features vector of face image in the five features vector and sample face data library is subjected to similarity calculation,
Obtain the five features vector of face image in each organ and sample face data library of the face image of the first user
Between similarity, and by the similarity be recorded as first user face image and sample face data library in
The similarity value of face image.
3. the finance product promotion method according to claim 2 based on artificial intelligence, which is characterized in that by the face
The five features vector of face image carries out similarity calculation in feature vector and sample face data library, obtains the first user's
Similarity packet in each organ of face image and sample face data library between the five features vector of face image
It includes:
Obtain the five features of the face image in sample face data library；
The five features is arranged in the way of who object, obtains multiple face images in sample face data library
Five features corresponding to multiple five features vectors；
According to the multiple five features vector, face's organ of multiple face images in sample face data library is calculated
Averaged feature vector；
The averaged feature vector for obtaining the face image of the first user, according to the average characteristics of the face image of first user
The averaged feature vector of vector and face's organ in multiple samples in sample face data library, is calculated the first user's
Similarity in each organ of face image and sample face data library between the five features vector of face image.
4. the finance product promotion method according to claim 1 based on artificial intelligence, which is characterized in that by obtaining institute
Micro- expression in the first facial feature information is stated to determine the positive mental attitude index of first user, comprising:
Obtain each micro- expression in the first facial feature information；
Calculate the positive value of each micro- expression and the weight of the positive value；
The weight of positive value and the positive value based on each micro- expression, calculates function meter according to mental attitude index
Calculation obtains the positive mental attitude index of first user.
5. the finance product promotion method according to any one of claims 1 to 4 based on artificial intelligence, which is characterized in that
After message request is registered in pop-up, further includes:
It obtains and is infused in the first quantity and the second user that browsed the narration information second user that first user shares
Second quantity of the volume finance product；
The value that shares one's experience of first user is calculated based on first quantity and the second quantity；
According to the mapping relations of share one's experience value and scheduled the share one's experience value and electronics reward amount, calculate
The electronics of first user rewards amount.
6. a kind of finance product based on artificial intelligence promotes device characterized by comprising
First obtains module, for obtaining the face image of the first user, extracts the first face feature letter of the face image
Breath；
Computing module, for calculating at least one face image in first facial feature information and sample face data library
The similarity value of second facial feature information；
Determining module, if being above the first preset threshold for calculated all similarity values, described in obtaining
Micro- expression in first facial feature information determines the positive mental attitude index of first user；
Second obtains module, if being higher than the second preset threshold for the positive mental attitude index, obtains described first and uses
The history life data at family；
Analysis module, for determining the first evaluation information of first user according to history life data；
Third obtains module, the second evaluation information inputted for obtaining first user in terminal device；
Fusion treatment module, the keyword for keyword and second evaluation information to first evaluation information carry out
Fusion treatment, obtains the narration information of the user, and the narration information includes the forward direction between the user and finance product
Motivate story；
Creation module, for creating the corresponding link of the narration information；
Display module, for showing that the link is corresponded to when detecting that the corresponding advertisement of the link is browsed by second user
Narration information；
Display module, for when detecting that the narration information has been browsed, message request to be registered in pop-up.
7. the finance product according to claim 6 based on artificial intelligence promotes device, which is characterized in that computing module packet
It includes:
Positioning unit, the face for face area in the face image to first user position, and obtain positioning letter
Breath；
Determination unit, the location information of the face for determining first user according to the location information；
Division unit, each organ institute in the face of the face area for dividing first user according to the positional information
Locate region；
First extraction unit, for extracting the image in region locating for each organ；
Second extraction unit, for extracting the feature for extracting each organ respectively from the image in region locating for each organ
Information；
Comparison unit, for by the characteristic information of each organ in the characteristic information of each organ and initial face iconic model
It compares, obtains the analog information of each organ of face area in the face image of the first user；
Generation unit, each device of face area in the face image for generating first user according to the analog information
The five features vector of official；
Computing unit, for by the five features vector of face image in the five features vector and sample face data library into
Row similarity calculation obtains face image in each organ and sample face data library of the face image of the first user
Similarity between five features vector, and by the similarity be recorded as first user face image and the sample
The similarity value of face image in face data library.
8. the finance product according to claim 7 based on artificial intelligence promotes device, which is characterized in that computing unit packet
It includes:
Subelement is obtained, for obtaining the five features of the face image in sample face data library；
Subelement is arranged to obtain in face data library for arranging the five features in the way of who object
Multiple five features vectors corresponding to the five features of multiple face images；
First computation subunit, for calculating multiple in sample face data library according to the multiple five features vector
The averaged feature vector of face's organ of face image；
Second computation subunit, the averaged feature vector of the face image for obtaining the first user, according to first user
Face image averaged feature vector and sample face data library in multiple samples face's organ average characteristics to
Amount, the face that face image in each organ and sample face data library of the face image of the first user is calculated are special
Levy the similarity between vector.
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 any one of 5 the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 5 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209202.XA CN110097470A (en) | 2019-03-19 | 2019-03-19 | Finance product promotion method, device and computer equipment based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910209202.XA CN110097470A (en) | 2019-03-19 | 2019-03-19 | Finance product promotion method, device and computer equipment based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097470A true CN110097470A (en) | 2019-08-06 |
Family
ID=67442947
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910209202.XA Pending CN110097470A (en) | 2019-03-19 | 2019-03-19 | Finance product promotion method, device and computer equipment based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097470A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021143234A1 (en) * | 2020-01-17 | 2021-07-22 | 北京市商汤科技开发有限公司 | Information delivering method and apparatus, electronic device, storage medium, and computer program |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004021798A (en) * | 2002-06-19 | 2004-01-22 | Nec Corp | Advertisement design collection system, device and method for collecting advertisement design and advertisement design collection processing program |
| CN102437968A (en) * | 2010-09-29 | 2012-05-02 | 腾讯科技（深圳）有限公司 | Method and device for publishing representing informationdata |
| CN104915857A (en) * | 2015-05-27 | 2015-09-16 | 裴峤 | Interactive mobile advertisement putting system base on user personalization and return mechanism |
| CN105303151A (en) * | 2014-06-30 | 2016-02-03 | 深圳Tcl新技术有限公司 | Human face similarity detection method and apparatus |
| CN106815309A (en) * | 2016-12-20 | 2017-06-09 | 北京奇虎科技有限公司 | A kind of image method for pushing, device and mobile terminal |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
| US20180005272A1 (en) * | 2016-06-30 | 2018-01-04 | Paypal, Inc. | Image data detection for micro-expression analysis and targeted data services |
| CN107563336A (en) * | 2017-09-07 | 2018-01-09 | 廖海斌 | Human face similarity degree analysis method, the device and system of game are matched for famous person |
| CN107895146A (en) * | 2017-11-01 | 2018-04-10 | 深圳市科迈爱康科技有限公司 | Micro- expression recognition method, device, system and computer-readable recording medium |
| CN109360024A (en) * | 2018-10-24 | 2019-02-19 | 北京汇银丰网络技术有限公司 | A kind of merchandise information processing method and social shopping platform based on social activity |
-
2019
- 2019-03-19 CN CN201910209202.XA patent/CN110097470A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004021798A (en) * | 2002-06-19 | 2004-01-22 | Nec Corp | Advertisement design collection system, device and method for collecting advertisement design and advertisement design collection processing program |
| CN102437968A (en) * | 2010-09-29 | 2012-05-02 | 腾讯科技（深圳）有限公司 | Method and device for publishing representing informationdata |
| CN105303151A (en) * | 2014-06-30 | 2016-02-03 | 深圳Tcl新技术有限公司 | Human face similarity detection method and apparatus |
| CN104915857A (en) * | 2015-05-27 | 2015-09-16 | 裴峤 | Interactive mobile advertisement putting system base on user personalization and return mechanism |
| US20180005272A1 (en) * | 2016-06-30 | 2018-01-04 | Paypal, Inc. | Image data detection for micro-expression analysis and targeted data services |
| CN106815309A (en) * | 2016-12-20 | 2017-06-09 | 北京奇虎科技有限公司 | A kind of image method for pushing, device and mobile terminal |
| CN106980819A (en) * | 2017-03-03 | 2017-07-25 | 竹间智能科技（上海）有限公司 | Similarity judgement system based on human face five-sense-organ |
| CN107563336A (en) * | 2017-09-07 | 2018-01-09 | 廖海斌 | Human face similarity degree analysis method, the device and system of game are matched for famous person |
| CN107895146A (en) * | 2017-11-01 | 2018-04-10 | 深圳市科迈爱康科技有限公司 | Micro- expression recognition method, device, system and computer-readable recording medium |
| CN109360024A (en) * | 2018-10-24 | 2019-02-19 | 北京汇银丰网络技术有限公司 | A kind of merchandise information processing method and social shopping platform based on social activity |
Non-Patent Citations (2)
| Title |
|---|
| 郭秩禹: "《试论广告代言人的作用——以无印良品为例》", 《现代营销(信息版)》, no. 2, pages 228 * |
| 高红阳 等: ""国内商业保险视频广告的内容分析"", 《广告大观(理论版)》, no. 6, pages 64 - 74 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021143234A1 (en) * | 2020-01-17 | 2021-07-22 | 北京市商汤科技开发有限公司 | Information delivering method and apparatus, electronic device, storage medium, and computer program |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sridhar et al. | Include: A large scale dataset for indian sign language recognition | |
| WO2021169637A1 (en) | Image recognition method and apparatus, computer device and storage medium | |
| Liu et al. | The path of film and television animation creation using virtual reality technology under the artificial intelligence | |
| Paasonen | Online pornography: Ubiquitous and effaced | |
| CN111339404A (en) | Content popularity prediction method and device based on artificial intelligence and computer equipment | |
| CN111898031A (en) | Method and device for obtaining user portrait | |
| CN112131472A (en) | Information recommendation method and device, electronic equipment and storage medium | |
| US20140328536A1 (en) | Automatic Analysis of Individual Preferences For Attractiveness | |
| KR20180077959A (en) | Method and apparatus of recommending contents | |
| CN114201516B (en) | User portrait construction method, information recommendation method and related devices | |
| CN110032685A (en) | Feeding optimization | |
| Tang et al. | Memories are one-to-many mapping alleviators in talking face generation | |
| Davis et al. | Memory for artwork is predictable | |
| CN113704509B (en) | Multimedia recommendation method and device, electronic equipment and storage medium | |
| Shi et al. | Face-based age estimation using improved Swin Transformer with attention-based convolution | |
| CN115130493A (en) | Face deformation recommendation method, device, equipment and medium based on image recognition | |
| Pang et al. | Auditing cross-cultural consistency of human-annotated labels for recommendation systems | |
| Yilma et al. | Together Yet Apart: Multimodal Representation Learning for Personalised Visual Art Recommendation | |
| CN110097470A (en) | Finance product promotion method, device and computer equipment based on artificial intelligence | |
| Yang et al. | Understanding image impressiveness inspired by instantaneous human perceptual cues | |
| Yang et al. | Finding badly drawn bunnies | |
| CN116701706A (en) | Data processing method, device, equipment and medium based on artificial intelligence | |
| Liu et al. | A3GAN: An attribute-aware attentive generative adversarial network for face aging | |
| Zhang | [Retracted] Educational Psychology Analysis Method for Extracting Students’ Facial Information Based on Image Big Data | |
| CN113434633B (en) | Social topic recommendation method, device, equipment and storage medium based on head portrait |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190806 |
|
| WD01 | Invention patent application deemed withdrawn after publication |