CN107169002A - A kind of personalized interface method for pushing and device recognized based on face - Google Patents
A kind of personalized interface method for pushing and device recognized based on face Download PDFInfo
- Publication number
- CN107169002A CN107169002A CN201710205877.8A CN201710205877A CN107169002A CN 107169002 A CN107169002 A CN 107169002A CN 201710205877 A CN201710205877 A CN 201710205877A CN 107169002 A CN107169002 A CN 107169002A
- Authority
- CN
- China
- Prior art keywords
- user
- user characteristics
- application interface
- content recommendation
- interface
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
Abstract
The invention discloses a kind of personalized interface method for pushing recognized based on face, the user's face image that user terminal calls camera to obtain when application starts is received, according to the user's face image zooming-out user characteristics;User characteristics label is set up based on the user characteristics;Application interface and content recommendation with the user characteristics tag match is obtained according to the user characteristics label, the application interface and the content recommendation are pushed to user.The invention also discloses a kind of personalized interface pusher recognized based on face.The personalized interface method for pushing and device that are recognized based on face provided using the present invention, is pushed with the application interface and content recommendation that easily and timely carry out matching with user.
Description
Technical field
The present invention relates to field of computer technology, more particularly to a kind of personalized interface method for pushing recognized based on face and
Device.
Background technology
In the prior art, application system often prepares multiple user interfaces or a variety of contents displayed on interface supply user
Selection, and interface corresponding with the preference of user and content can be provided according to preference recommendation mechanisms, such as, for for men
Family often shows the interface of male's theme, and the interface of female topic can be then shown for female user.
The essence of preference recommendation mechanisms be using user log-on message, browse information and comment, concern etc. interaction letter
Cease to do Collaborative Recommendation, i.e. personalized recommendation for user.However, being that new user or different user use same account in user
Scene, many accounts such as in Internet bar's scene using same PC terminals scene in, new user is not left in application system
Historical operating data, so the hobby of user can not be obtained, so that the recommendation of suitable user's request can not be made.
Cold start-up just can be at this time carried out, cold start-up refers to obtain the letter such as essential characteristic of user by different dimensions
Breath carries out the process of the personalized recommendation of coarseness.At this moment generally require the background information by user, or guided bone allow
User manually selects the label informations such as sex, age to set the interface to be shown first and content.
Or, can also temporarily with hot topic start substitute personalized recommendation come, wait user produce peration data after, further according to
New user's peration data updates personalized recommendation list.
Above solution is relatively complicated or can not carry out personalized recommendation in time.
The content of the invention
In order to solve the above technical problems, the embodiment of the present invention provides a kind of personalized interface method for pushing recognized based on face
And device, pushed with the application interface and content recommendation that easily and timely carry out matching with user.
What the technical scheme of the embodiment of the present invention was realized in:
The embodiment of the present invention provides a kind of personalized interface method for pushing and device recognized based on face, including:Receive and use
The user's face image that camera is obtained is called at family end when application starts, special according to the user's face image zooming-out user
Levy;
User characteristics label is set up based on the user characteristics;
Application interface and content recommendation with the user characteristics tag match is obtained according to the user characteristics label, will
The application interface and the content recommendation are pushed to user.
It is described according to the user's face image zooming-out user characteristics in such scheme, including:
Extract the age group of the user, sex, have at least one of glasses-free, current emotional user characteristics.
In such scheme, the application interface obtained according to the user characteristics label with the user characteristics tag match
And content recommendation, including:
The application interface and content recommendation for determining to match with the user characteristics according to statistic analysis result.
In such scheme, the application interface obtained according to the user characteristics label with the user characteristics tag match
And content recommendation, in addition to:
Obtained and the higher user type of the user characteristics label similarity according to the collaborative filtering based on user
Application interface and content recommendation interested.
In such scheme, application circle obtained according to the user characteristics label with the user characteristics tag match
Face and content recommendation, in addition to:Obtain special with the user according to current hotspot, current red-letter day and the user characteristics label
Levy the application interface and content recommendation of tag match.
It is described according to the user's face image zooming-out user characteristics in such scheme, including:
The high frequency subgraph and low frequency subgraph of the user's face image are obtained based on wavelet transformation;
User characteristics described in LBP operator extractions is used to the high frequency subgraph and low frequency subgraph.
The embodiment of the present invention provides a kind of personalized interface pusher recognized based on face, and described device includes:
Extraction unit, for receiving the user's face image that user terminal calls camera to obtain when application starts, and root
According to the user's face image zooming-out user characteristics;
Unit is set up, for setting up user characteristics label based on the user characteristics;
Push unit, for obtaining the application interface with the user characteristics tag match according to the user characteristics label
And content recommendation, the application interface and the content recommendation are pushed to user.
In such scheme, the extraction unit is additionally operable to:
Extract the age group of the user, sex, have at least one of glasses-free, current emotional user characteristics.
In such scheme, the push unit is additionally operable to:
The application interface and content recommendation for determining to match with the user characteristics according to statistic analysis result.
In such scheme, the push unit is additionally operable to:Obtained and used with described according to the collaborative filtering based on user
The higher user type of family feature tag similarity application interface and content recommendation interested.
In such scheme, the push unit is additionally operable to:According to current hotspot, current red-letter day and the user characteristics mark
Label obtain the application interface and content recommendation with the user characteristics tag match.
In such scheme, the extraction unit is additionally operable to:
The high frequency subgraph and low frequency subgraph of the user's face image are obtained based on wavelet transformation;
User characteristics described in LBP operator extractions is used to the high frequency subgraph and low frequency subgraph.
The personalized interface method for pushing and device that are recognized based on face that the embodiment of the present invention is provided, are started according to application
During user's face image zooming-out user characteristics to set up user characteristics label;According to the user characteristics label obtain with
The application interface and content recommendation of the user characteristics tag match, using the program, can easily and timely be carried out and user
The application interface and content recommendation matched is pushed.
Brief description of the drawings
Fig. 1 is the implementation process figure for the personalized interface method for pushing that the embodiment of the present invention is recognized based on face;
Fig. 2 is the composition structural representation for the personalized interface pusher that the embodiment of the present invention is recognized based on face.
Embodiment
In order to more fully hereinafter understand the features of the present invention and technology contents, below in conjunction with the accompanying drawings to the reality of the present invention
Now it is described in detail, appended accompanying drawing purposes of discussion only for reference, not for limiting the present invention.
Fig. 1 is the implementation process figure for the personalized interface method for pushing that the embodiment of the present invention is recognized based on face, such as Fig. 1 institutes
Show, the personalized interface method for pushing provided in an embodiment of the present invention recognized based on face is included:
Step 101, the user's face image that user terminal calls camera to obtain when application starts is received, and according to user
Face-image extracts user characteristics.
Step 102, user characteristics label is set up based on user characteristics.
Step 103, the application interface and content recommendation with user characteristics tag match are obtained according to user characteristics label, will
Application interface and content recommendation are pushed to user.
In the technical scheme of the embodiment of the present invention, user terminal gets the facial image of the user of currently used terminal
Afterwards, image can be sent to the server on backstage, the user characteristics in image is extracted by server, it is then special according to the user
The content determined in corresponding displaying interface and interface is levied, finally by the content push in the displaying interface of determination and interface
To user terminal, user terminal just can be shown to the user of currently used terminal.
So, after user's cold start-up logs in triggering, just corresponding interface and content recommendation can be provided according to recognition of face,
For example, the different homepages for logging in homepage face, female's frequency books being provided for female user are provided for different sexes, for year
Light male user provides the homepage of male frequency books;Different fonts, size and face can be provided for the user of different age group
Color, automatically will be using font amplification for old user;Adjusted in real time according to various social hotspots and the situation of festivals or holidays
And change, provide the beautiful interface of color and bigger font to old user in festivals or holidays.Or, can for male user
To show a whole set of interface that male user is exclusive, not only pattern is exclusive male interface at the interface, and the content in interface
It is also male's content interested;The thematic page of boy student is provided for 10-20 Sui male user and young men user is provided happiness
Network serialized content recommendation that love is read etc..Content in interface laid out above and interface can be real-time by server
Push, it is ageing higher.
Wherein, in step 101, obtain user's head image and extract the detailed process of user characteristics and be:Pass through camera
User's face image is obtained, recognition of face then is carried out to image;When carrying out recognition of face to image, obtained based on wavelet transformation
Take the high frequency subgraph and low frequency subgraph of family face-image;It is special using LBP operator extractions user to high frequency subgraph and low frequency subgraph
Levy.
Specifically, high frequency subgraph is obtained by Haar wavelet decomposition facial images;Recycle the textural characteristics of high frequency subgraph
By illumination effect it is small the characteristics of, obtain the statistic histogram of each subgraph using LBP enlargement oprator computings, and by making after weight cascade
For the characteristic vector of face, to improve robustness of the recognition of face to illumination;In the characteristic extraction procedure of gender classification,
Using the multiresolution analysis characteristic of wavelet transformation, the low frequency subgraph of single order and second order is obtained by wavelet decomposition facial image,
It is same that the statistic histogram that computing obtains subgraph is carried out to low frequency subgraph with LBP operators, artwork is transported with LBP operators
The statistic histogram for obtaining artwork is calculated, the statistic histogram cascade obtained by subgraph and artwork is special as final classification chart picture
Levy.
The program preferably combines face integral structure characteristic and local detail feature, improves the same of classification stability
When solve based on the gender classification under small sample training storehouse, and reduce calculating and carrying cost, can meet increasingly
Requirement of the movement and embedded platform of popularization to memory space and computation complexity.
In step 101, according to age group of the user characteristics of user's face Graph Extraction including user, sex, there is anophthalmia
Mirror and current emotional.According to the characteristics of image obtained by recognition of face, according to characteristics of image set in advance and user characteristics
Between corresponding relation, the following feature of user can be obtained:Age group (less than 20,30-40 etc.), sex (man, female, not
Know), whether wear glasses, mood (happiness, anger, sorrow, calmness etc.).In step 102, user characteristics mark is set up based on above user characteristics
Label.
In step 103, using user characteristics label as input, according to statistic analysis result and collaborative filtering, obtain
Go out the interface shown to user and content, right rear line is shown, and does detailed explanation to this process below.
In step 103, the application interface and content recommendation with user characteristics tag match are obtained according to user characteristics label
When, the application interface and content recommendation with user characteristics tag match can be determined according to statistic analysis result.
Here statistic analysis result refers to according to existing data, to different user to content and the interest level at interface
Analyze obtained result.Here the data analyzed include:Obtained data and root is investigated in hobby to user
The data of the reflection user preferences obtained according to the historical behavior of user.
Such as, the user for determining 20~30 years old according to the statistical analysis to data likes interface a, user's happiness of 30~40 years old
Joyous interface b, so, if it is determined that the age of active user is 23 years old, it is possible to recommend interface a to the user.Certainly here only
It is illustrated, all may be used for the relation between the different elements and user characteristics in multiple interfaces and interface with single interface
To carry out statistical analysis, and then interface to active user can be recommended according to the feature of active user.
Here the granularity that statistical analysis is divided to user characteristics is often larger, in order to further increase user tag and boundary
The accuracy of face matching, can determine user interface interested, specifically by collaborative filtering according to the label of user
Ground, is answered according to the collaborative filtering acquisition based on user and the higher user type of user characteristics label similarity are interested
With interface and content recommendation.
The principle of collaborative filtering based on user is:By the historical behavior data of user find user to commodity or
The hobby of content, and these hobbies are measured and given a mark.The historical behavior data of user herein include purchase commodity, received
Hide commodity, perhaps sharing contents in comment.Afterwards, according to different user to identical commodity or the attitude and fancy grade meter of content
Calculate the relation between user, and progress commodity or commending contents between the user for having identical hobby.If for example, two use of A, B
Family all have purchased x, y, tri- books of z, and give the favorable comment of five-pointed star, then A and B just belong to the use with identical hobby
Family, the books w that can have seen A recommends user B.Same reason, using the collaborative filtering based on user, can be obtained
Take with the higher user with active user with identical hobby of active user's type similarity, it is and latter user is interested
Application interface and content recommendation recommend active user.
In embodiments of the present invention, it can also be obtained according to current hotspot, current red-letter day and user characteristics label with using
The application interface and content recommendation of family feature tag matching.
Specifically, application interface and content recommendation are adjusted in real time according to various social hotspots and the situation of festivals or holidays
And change, provide color to old user with reference to user characteristics label in some festivals or holidays such as National Day, the Spring Festival, the Double Ninth Festival beautiful
Interface and the interface that is consistent with festivals or holidays.
The personalized interface method for pushing recognized based on face that the embodiment of the present invention is provided, according in application start-up course
User's face image zooming-out user characteristics to set up user characteristics label;Obtained and user characteristics mark according to user characteristics label
The application interface and content recommendation of matching are signed, using the program, application circle matched with user can be easily and timely carried out
Face and content recommendation are pushed.
As shown in Fig. 2 the personalized interface pusher provided in an embodiment of the present invention recognized based on face is included:
Extraction unit 201, for receiving the user's face image that user terminal calls camera to obtain when application starts, and
According to user's face image zooming-out user characteristics.
Unit 202 is set up, for setting up user characteristics label based on user characteristics.
Push unit 203, for obtaining and the application interface of user characteristics tag match and pushing away according to user characteristics label
Content is recommended, application interface and content recommendation are pushed to user.
Wherein, extraction unit 201, which obtains user's head image and extracts the detailed process of user characteristics, is:Pass through camera
User's face image is obtained, recognition of face then is carried out to image;When carrying out recognition of face to image, obtained based on wavelet transformation
Take the high frequency subgraph and low frequency subgraph of family face-image;It is special using LBP operator extractions user to high frequency subgraph and low frequency subgraph
Levy.
Specifically, high frequency subgraph is obtained by Haar wavelet decomposition facial images using the principle of wavelet transformation;Recycle
The textural characteristics of high frequency subgraph by illumination effect it is small the characteristics of, the statistics Nogata of each subgraph is obtained using LBP enlargement oprator computings
Figure, and by the characteristic vector after weight cascade as face, to improve robustness of the recognition of face to illumination;Know in face gender
In another characteristic extraction process, using the multiresolution analysis characteristic of wavelet transformation, one is obtained by wavelet decomposition facial image
Rank and the low frequency subgraph of second order, it is same that the statistic histogram that computing obtains subgraph is carried out to low frequency subgraph with LBP operators, use
LBP operators carry out the statistic histogram that computing obtains artwork to artwork, and the statistic histogram obtained by subgraph and artwork is cascaded and made
For final classifying image features.
The program preferably combines face integral structure characteristic and local detail feature, improves the same of classification stability
When solve based on the gender classification under small sample training storehouse, and reduce calculating and carrying cost, can meet increasingly
Requirement of the movement and embedded platform of popularization to memory space and computation complexity.
Extraction unit 201 according to the age group of the user characteristics of user's face Graph Extraction including user, sex, have anophthalmia
Mirror and current emotional.Specifically, according to the characteristics of image obtained by recognition of face, according to characteristics of image set in advance with using
Corresponding relation between the feature of family, can obtain the following feature of user:Age group (less than 20,30-40 etc.), sex (man,
It is female, unknown), whether wear glasses, mood (happiness, anger, sorrow, calmness etc.).Afterwards, unit 202 is set up to build based on above user characteristics
Vertical user characteristics label.
In push unit 203 is additionally operable to the application interface matched according to statistic analysis result determination with user characteristics and recommended
Hold.
Here statistic analysis result refers to according to existing data, to different user to content and the interest level at interface
Analyze obtained result.Here the data analyzed include:Obtained data and root is investigated in hobby to user
The data of the reflection user preferences obtained according to the historical behavior of user.
Here the granularity that statistical analysis is divided to user characteristics is often larger, in order to further increase user tag and boundary
The accuracy of face matching, push unit 203 can determine that user is interested by collaborative filtering according to the label of user
Interface, specifically, push unit 203 according to based on user collaborative filtering obtain with user characteristics label similarity compared with
High user type application interface and content recommendation interested.
The principle of collaborative filtering based on user is:By the historical behavior data of user find user to commodity or
The hobby of content, and these hobbies are measured and given a mark.The historical behavior data of user herein include purchase commodity, received
Hide commodity, perhaps sharing contents in comment.Afterwards, according to different user to identical commodity or the attitude and fancy grade meter of content
Calculate the relation between user, and progress commodity or commending contents between the user for having identical hobby.
In addition, push unit 203 is additionally operable to be obtained and user according to current hotspot, current red-letter day and user characteristics label
The application interface and content recommendation of feature tag matching.
Specifically, application interface and content recommendation are adjusted in real time according to various social hotspots and the situation of festivals or holidays
And change, provide color to old user with reference to user characteristics label in some festivals or holidays such as National Day, the Spring Festival, the Double Ninth Festival beautiful
Interface and the interface that is consistent with festivals or holidays.
The personalized interface pusher recognized based on face that the embodiment of the present invention is provided, according in application start-up course
User's face image zooming-out user characteristics to set up user characteristics label;Obtained and used with described according to the user characteristics label
The application interface and content recommendation of family feature tag matching, using the program, can easily and timely carry out matching with user
Application interface and content recommendation push.
In practical application, extraction unit 201, set up unit 202 and push unit 203 can by be based on face identification
On personalized interface pusher central processing unit (CPU, Central Processing Unit), microprocessor (MPU,
Micro Processor Unit), digital signal processor (DSP, Digital Signal Processor) or scene can compile
Journey gate array (FPGA, Field Programmable Gate Array) etc. is realized.
It should be understood by those skilled in the art that, embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the shape of the embodiment in terms of the present invention can use hardware embodiment, software implementation or combine software and hardware
Formula.Moreover, the present invention can be used can use storage in one or more computers for wherein including computer usable program code
The form for the computer program product that medium is implemented on (including but is not limited to magnetic disk storage and optical memory etc.).
The present invention is the flow with reference to method according to embodiments of the present invention, equipment (system) and computer program product
Figure and/or block diagram are described.It should be understood that can be by every first-class in computer program instructions implementation process figure and/or block diagram
Journey and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for real
The device for the function of being specified in present one flow of flow chart or one square frame of multiple flows and/or block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
The foregoing is only a preferred embodiment of the present invention, is not intended to limit the scope of the present invention.
Claims (12)
1. a kind of personalized interface method for pushing recognized based on face, it is characterised in that methods described includes:
The user's face image that user terminal calls camera to obtain when application starts is received, is carried according to the user's face image
Take user characteristics;
User characteristics label is set up based on the user characteristics;
Application interface and content recommendation with the user characteristics tag match is obtained according to the user characteristics label, will be described
Application interface and the content recommendation are pushed to user.
2. according to the method described in claim 1, it is characterised in that described special according to the user's face image zooming-out user
Levy, including:
Extract the age group of the user, sex, have at least one of glasses-free, current emotional user characteristics.
3. method according to claim 2, it is characterised in that described to be obtained and the user according to the user characteristics label
The application interface and content recommendation of feature tag matching, including:
The application interface and content recommendation for determining to match with the user characteristics according to statistic analysis result.
4. method according to claim 3, it is characterised in that described to be obtained and the user according to the user characteristics label
The application interface and content recommendation of feature tag matching, in addition to:
The user type sense higher with the user characteristics label similarity is obtained according to the collaborative filtering based on user emerging
The application interface and content recommendation of interest.
5. the method according to any one of Claims 1-4, it is characterised in that described to be obtained according to the user characteristics label
The application interface and content recommendation with the user characteristics tag match are taken, in addition to:According to current hotspot, current red-letter day and
The user characteristics label obtains the application interface and content recommendation with the user characteristics tag match.
6. method according to claim 5, it is characterised in that described special according to the user's face image zooming-out user
Levy, including:
The high frequency subgraph and low frequency subgraph of the user's face image are obtained based on wavelet transformation;
User characteristics described in LBP operator extractions is used to the high frequency subgraph and low frequency subgraph.
7. a kind of personalized interface pusher recognized based on face, it is characterised in that described device includes:
Extraction unit, for receiving the user's face image that user terminal calls camera to obtain when application starts, and according to institute
State user's face image zooming-out user characteristics;
Unit is set up, for setting up user characteristics label based on the user characteristics;
Push unit, for obtaining and the application interface of the user characteristics tag match and pushing away according to the user characteristics label
Content is recommended, the application interface and the content recommendation are pushed to user.
8. device according to claim 7, it is characterised in that the extraction unit is additionally operable to:
Extract the age group of the user, sex, have at least one of glasses-free, current emotional user characteristics.
9. device according to claim 8, it is characterised in that the push unit is additionally operable to:
The application interface and content recommendation for determining to match with the user characteristics according to statistic analysis result.
10. device according to claim 9, it is characterised in that the push unit is additionally operable to:According to the association based on user
Obtain interior with the higher user type of user characteristics label similarity application interface interested and recommendation with filter algorithm
Hold.
11. the device according to any one of claim 7 to 10, it is characterised in that the push unit is additionally operable to:According to work as
Preceding focus, current red-letter day and the user characteristics label obtain the application interface and recommendation with the user characteristics tag match
Content.
12. device according to claim 11, it is characterised in that the extraction unit is additionally operable to:
The high frequency subgraph and low frequency subgraph of the user's face image are obtained based on wavelet transformation;
User characteristics described in LBP operator extractions is used to the high frequency subgraph and low frequency subgraph.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205877.8A CN107169002A (en) | 2017-03-31 | 2017-03-31 | A kind of personalized interface method for pushing and device recognized based on face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205877.8A CN107169002A (en) | 2017-03-31 | 2017-03-31 | A kind of personalized interface method for pushing and device recognized based on face |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107169002A true CN107169002A (en) | 2017-09-15 |
Family
ID=59849001
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710205877.8A Pending CN107169002A (en) | 2017-03-31 | 2017-03-31 | A kind of personalized interface method for pushing and device recognized based on face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107169002A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108429816A (en) * | 2018-03-27 | 2018-08-21 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108509041A (en) * | 2018-03-29 | 2018-09-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for executing operation |
CN108595651A (en) * | 2018-04-27 | 2018-09-28 | 深圳码隆科技有限公司 | Customized information display methods, device and user terminal based on recognition of face |
CN109191184A (en) * | 2018-08-14 | 2019-01-11 | 微梦创科网络科技(中国)有限公司 | Advertisement placement method and system based on image recognition |
CN109920174A (en) * | 2019-01-23 | 2019-06-21 | 平安科技(深圳)有限公司 | Book borrowing and reading method, apparatus, electronic equipment and storage medium |
CN110321477A (en) * | 2019-05-24 | 2019-10-11 | 平安科技(深圳)有限公司 | Information recommendation method, device, terminal and storage medium |
WO2020015152A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技(深圳)有限公司 | Method and device for setting system theme, computer apparatus, and storage medium |
CN111743546A (en) * | 2019-03-26 | 2020-10-09 | 康泰医学系统(秦皇岛)股份有限公司 | Interface display method, device, medium and equipment of oximeter |
CN117591697A (en) * | 2024-01-19 | 2024-02-23 | 成都亚度克升科技有限公司 | Text recommendation method and system based on artificial intelligence and video processing |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103677516A (en) * | 2013-11-27 | 2014-03-26 | 青岛海信电器股份有限公司 | Interface generating method and device of terminal |
CN103955691A (en) * | 2014-05-08 | 2014-07-30 | 中南大学 | Multi-resolution LBP textural feature extracting method |
CN104202718A (en) * | 2014-08-05 | 2014-12-10 | 百度在线网络技术(北京)有限公司 | Method and device for providing information for user |
US20170053170A1 (en) * | 2012-10-10 | 2017-02-23 | Shahrzad Rafati | Intelligent Video Thumbnail Selection and Generation |
-
2017
- 2017-03-31 CN CN201710205877.8A patent/CN107169002A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20170053170A1 (en) * | 2012-10-10 | 2017-02-23 | Shahrzad Rafati | Intelligent Video Thumbnail Selection and Generation |
CN103677516A (en) * | 2013-11-27 | 2014-03-26 | 青岛海信电器股份有限公司 | Interface generating method and device of terminal |
CN103955691A (en) * | 2014-05-08 | 2014-07-30 | 中南大学 | Multi-resolution LBP textural feature extracting method |
CN104202718A (en) * | 2014-08-05 | 2014-12-10 | 百度在线网络技术(北京)有限公司 | Method and device for providing information for user |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108429816A (en) * | 2018-03-27 | 2018-08-21 | 百度在线网络技术(北京)有限公司 | Method and apparatus for generating information |
CN108509041A (en) * | 2018-03-29 | 2018-09-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for executing operation |
CN108595651A (en) * | 2018-04-27 | 2018-09-28 | 深圳码隆科技有限公司 | Customized information display methods, device and user terminal based on recognition of face |
WO2020015152A1 (en) * | 2018-07-18 | 2020-01-23 | 平安科技(深圳)有限公司 | Method and device for setting system theme, computer apparatus, and storage medium |
CN109191184A (en) * | 2018-08-14 | 2019-01-11 | 微梦创科网络科技(中国)有限公司 | Advertisement placement method and system based on image recognition |
CN109920174A (en) * | 2019-01-23 | 2019-06-21 | 平安科技(深圳)有限公司 | Book borrowing and reading method, apparatus, electronic equipment and storage medium |
CN111743546A (en) * | 2019-03-26 | 2020-10-09 | 康泰医学系统(秦皇岛)股份有限公司 | Interface display method, device, medium and equipment of oximeter |
CN110321477A (en) * | 2019-05-24 | 2019-10-11 | 平安科技(深圳)有限公司 | Information recommendation method, device, terminal and storage medium |
WO2020238023A1 (en) * | 2019-05-24 | 2020-12-03 | 平安科技(深圳)有限公司 | Information recommendation method and apparatus, and terminal and storage medium |
CN117591697A (en) * | 2024-01-19 | 2024-02-23 | 成都亚度克升科技有限公司 | Text recommendation method and system based on artificial intelligence and video processing |
CN117591697B (en) * | 2024-01-19 | 2024-03-29 | 成都亚度克升科技有限公司 | Text recommendation method and system based on artificial intelligence and video processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107169002A (en) | A kind of personalized interface method for pushing and device recognized based on face | |
US10049308B1 (en) | Synthesizing training data | |
WO2021238631A1 (en) | Article information display method, apparatus and device and readable storage medium | |
US10255681B2 (en) | Image matting using deep learning | |
CN109635680B (en) | Multitask attribute identification method and device, electronic equipment and storage medium | |
CN108073910B (en) | Method and device for generating human face features | |
US9607010B1 (en) | Techniques for shape-based search of content | |
US20200112756A1 (en) | Content data recommendation method and apparatus based on identity verification apparatus, and storage medium | |
CN104636371B (en) | Information recommendation method and equipment | |
CN107193962B (en) | Intelligent map matching method and device for Internet promotion information | |
US10360623B2 (en) | Visually generated consumer product presentation | |
CN110390033B (en) | Training method and device for image classification model, electronic equipment and storage medium | |
US10083521B1 (en) | Content recommendation based on color match | |
CN105493078B (en) | Colored sketches picture search | |
JP2012089171A (en) | Generation of contextual image-containing advertisements | |
CN111212303A (en) | Video recommendation method, server and computer-readable storage medium | |
CN110298245B (en) | Interest collection method, interest collection device, computer equipment and storage medium | |
KR102111720B1 (en) | Method for design recommending using cloud literary work analysis | |
CN108846792A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
US11010636B2 (en) | Systems and methods for providing personalized product recommendations using deep learning | |
CN107590267A (en) | Information-pushing method and device, terminal and readable storage medium storing program for executing based on picture | |
US20150235264A1 (en) | Automatic entity detection and presentation of related content | |
US10558745B2 (en) | Information processing apparatus and non-transitory computer readable medium | |
CN111881901A (en) | Screenshot content detection method and device and computer-readable storage medium | |
CN113761253A (en) | Video tag determination method, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170915 |