CN105721936B - A kind of intelligent television program recommendation system based on context aware - Google Patents
A kind of intelligent television program recommendation system based on context aware Download PDFInfo
- Publication number
- CN105721936B CN105721936B CN201610038269.8A CN201610038269A CN105721936B CN 105721936 B CN105721936 B CN 105721936B CN 201610038269 A CN201610038269 A CN 201610038269A CN 105721936 B CN105721936 B CN 105721936B
- Authority
- CN
- China
- Prior art keywords
- user
- face
- program
- image
- recognition
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44213—Monitoring of end-user related data
- H04N21/44218—Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26258—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for generating a list of items to be played back in a given order, e.g. playlist, or scheduling item distribution according to such list
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4667—Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The embodiment of the invention discloses a kind of intelligent television program recommendation system based on context aware, wherein, the system includes：Television headend subsystem, for obtaining the recommendation program list of inter-related task from high in the clouds；User's identification system, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture, obtain the characteristic parameter and recognition result of user, program is ranked up according to the characteristic parameter of user and recognition result, the forward program that will sort recommends user, user data upload is identified to high in the clouds, while is supplied to television headend subsystem to use from the recommendation program list of high in the clouds acquisition inter-related task；And show recognition result and recommend program list.In embodiments of the present invention, emotional information during collection user viewing TV and the feedback information to TV programme in all directions, and it is adapted to optimal the rendition list of user's viewing for customer group structure according to these information, Consumer's Experience can be improved, user is viewed and admired TV programme more pleasantly.
Description
Technical field
The present invention relates to television program recommendations technical field, more particularly to a kind of intelligent television program based on context aware
Commending system.
Background technology
Application of the middle identification technology on TV platform in recent years oneself through obtaining the favor of main manufacturer, 2012
January, Samsung first elect TV App Store and open the Smart TV epoch, are integrated with speech identifying function, and the television set carries in addition
A high-definition camera, it is possible to provide gesture and the function of face recognition.In addition, other manufacturers on product except releasing this base
In outside the application of identification technology, while also begin to calculate the research and development of Related product in enterprising rack of TV platform of oneself.
Current context aware applications, it is the situation of presence for unique user mostly.For TV user, perceive
Unique user can then ignore the context information of other users；In the case where multi-user watches TV, if the program recommended is only
Meet the interest of unique user, then be able to not can recommend to meet the TV programme of most people.
TV of the prior art can not be identified using image processing techniques and identify the identity of user, it is impossible to drawn and worked as
The corresponding emotional information of preceding user's expression, the interest model of user can not be more established according to the emotional information using user, it is right
User makes optimal recommendation.
Recognizer and proposed algorithm of the prior art all in local runtime, are thus needed in the equipment of local
Corresponding hardware module is added, can so increase the unnecessary cost of intelligent television, the trend phase lightening with intelligent television
Run counter to, while local device can not handle substantial amounts of video flowing and image data immediately.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, and the invention provides a kind of Mobile solution operation assistant's
Implementation method and its device, can collect in all directions user watch TV when emotional information and the feedback letter to TV programme
Breath, and the optimal the rendition list watched according to these information for the suitable user of customer group structure, can improve Consumer's Experience, make
User views and admires TV programme more pleasantly.
In order to solve the above problems, the present invention proposes a kind of intelligent television program recommendation system based on context aware,
The system includes：
Television headend subsystem, for obtaining the recommendation program list of inter-related task from high in the clouds；
User's identification system, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture,
The characteristic parameter and recognition result of user is obtained, program is ranked up according to the characteristic parameter of user and recognition result, will be arranged
The forward program of sequence recommends user, and user data upload is identified to high in the clouds, while obtains inter-related task from high in the clouds
Program list is recommended to be supplied to television headend subsystem to use；And show recognition result and recommend program list.
Preferably, the user's identification system includes：
Data acquisition module, for inputting the user data of television headend subsystem and whole identification service；
Network communication module, inter-related task is obtained for user data upload to be identified to high in the clouds, while from high in the clouds
Recommendation program list be supplied to television headend subsystem use；
Recognizer module, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture,
Obtain the characteristic parameter and recognition result of user；
Recommending module, program is ranked up for the characteristic parameter according to user and recognition result, it is forward by sorting
Program recommends user；
Interface display module, for showing recognition result and recommending program list.
Preferably, the user data includes user's head portrait, user emotion information and managing operation history.
Preferably, the recognizer module includes：
Recognition of face submodule, for using the movable information in symmetric difference method detection video flowing and picture, root
Face datection is carried out according to cluster of the face complexion in YCrCb color spaces；
Emotion identification submodule, for detecting the emotional characteristics of face in the movable information in video flowing and picture, obtain
Obtain recognition result.
Preferably, the recognition of face submodule is used to carry out Face datection using rule-based projection algorithm.
Preferably, the data acquisition module is additionally operable to preset the personal like of user, increases whenever there is new user
New user profile can be added when adding to television system.
In embodiments of the present invention, in all directions collect user watch TV when emotional information and the feedback to TV programme
Information, and the optimal the rendition list watched according to these information for the suitable user of customer group structure, can improve Consumer's Experience,
User is set to view and admire TV programme more pleasantly.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the structure composition signal of the intelligent television program recommendation system based on context aware of the embodiment of the present invention
Figure.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other under the premise of creative work is not made
Embodiment, belong to the scope of protection of the invention.
Fig. 1 is the structure composition signal of the intelligent television program recommendation system based on context aware of the embodiment of the present invention
Figure, as shown in figure 1, the system includes：
Television headend subsystem 1, for obtaining the recommendation program list of inter-related task from high in the clouds；
User's identification system 2, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture,
The characteristic parameter and recognition result of user is obtained, program is ranked up according to the characteristic parameter of user and recognition result, will be arranged
The forward program of sequence recommends user, and user data upload is identified to high in the clouds, while obtains inter-related task from high in the clouds
Program list is recommended to be supplied to television headend subsystem to use；And show recognition result and recommend program list.
User's identification system 2 includes：
Data acquisition module 20, for inputting the user data of television headend subsystem and whole identification service；
Network communication module 21, related appoint is obtained for user data upload to be identified to high in the clouds, while from high in the clouds
The recommendation program list of business is supplied to television headend subsystem to use；
Recognizer module 22, for carrying out recognition of face and mood knowledge to the movable information in video flowing and picture
Not, the characteristic parameter and recognition result of user is obtained；
Recommending module 23, program is ranked up for the characteristic parameter according to user and recognition result, will sorted forward
Program recommend user；
Interface display module 24, for showing recognition result and recommending program list.
In embodiments of the present invention, user data includes user's head portrait, user emotion information and user's history operation note
Record.
Wherein, camera can be opened, closed by data acquisition module 20, TV embeds face detection function
Use, the operation such as video flowing and photo interception.
Data acquisition module 20 is additionally operable to preset the personal like of user, can when having new user to increase
To add new user profile to television system：Including user's face feature, program preferences value, viewing time preference value etc., this
A little information can all form a customer data base, reach the effect that comprehensive multi-user recommends program.
In specific implementation, recognizer module 22 includes：
Recognition of face submodule, for using the movable information in symmetric difference method detection video flowing and picture, root
Face datection is carried out according to cluster of the face complexion in YCrCb color spaces；Wherein, entered using rule-based projection algorithm
Row Face datection, single face can be detected, the plurality of human faces under complex environment can also be detected；
Emotion identification submodule, for detecting the emotional characteristics of face in the movable information in video flowing and picture, obtain
Obtain recognition result.
, can be according to similarity recognition method, by face to be identified and face database after face characteristic is extracted
Image is compared, you can determines face.Here the method for Weighted Similarity is taken to judge face to be measured and sample face
Similarity, i.e.,：
Wherein, d represents the similarity of face to be measured and face sample in storehouse；N is characterized number of components；tiFor face to be measured
Characteristic vector；RiFor the characteristic vector of sample face in face database；wiIdentification contribution is added according to each feature
Weighted value.
No matter how expression changes, and eye center point is too big all without occurring relative to the distance of nose, eyebrow each point
Change, also, the area shared by eyebrow is also almost unchanged, therefore larger weighted value is assigned to it；And eye center point is relative
It can be changed in face center and corners of the mouth distance with the change of expression, so being assigned to less weighted value to it.So
For can on the basis of without loss of generality, what part solution expression shape change was brought says goodbye to error.
Emotion identification submodule detects the emotional characteristics of face in the movable information in video flowing and picture, is identified
As a result process includes：
Step 1, eigenface is calculated；
If facial image I (x, y) is two-dimentional NxN gray level images, N is used2Dimensional vector Γ is represented.Facial image training set is
{Γi| i=1 ..., M }, wherein M is total number of images in training set, and the average vector of this M width image is：
Each face ΓiWith average face Ψ difference value vector ΦiFor：
Φi=Γi-Ψ；I=1 ..., M
The covariance matrix of training image is represented by：
C=AAT
Wherein A=[Φ1..., ΦM]。
Eigenface is made up of covariance matrix C orthogonal eigenvectors.For NxN facial images, covariance matrix C's is big
Small is N2*N2, it is highly difficult to solve characteristic value and characteristic vector to it, and a kind of instead method is that solution M*M is less
Matrix.The characteristic vector of M*M matrix Ls is calculated first
vi(i=1 ..., M), wherein, L=ATA
The characteristic vector u of Matrix Ci(i=1 ..., M) is by difference value vector Φi(i=1 ..., M) and vi(i=1 ..., M) line
Property combines to obtain：
U=[u1..., uM]=[Φ1..., ΦM][v1..., vM]=AV
In fact, m (m<M) individual eigenface is sufficiently used for recognition of face.Therefore, the spy of L preceding m eigenvalue of maximum is only taken
Sign vector calculates eigenface.M is by threshold value θλIt is determined that：
Step 2, the recognition of face of feature based face；
The face recognition process of feature based face is made up of two stages:Training stage and cognitive phase.In the training stage,
Each oneself knows face ΓkIt is mapped on the subspace by eigenface, obtains m dimensional vectors Ωk。
Ωk=UT(Γk-Ψ)；K=1 ..., Nc
Wherein NcFor known number.Distance threshold value θcIt is defined as follows：
Here, the projection matrix U that principal component is formed has following features：
Minimize the reconstruction error of all samples：
Maximize variance of the sample set in low dimension projective：Ui=argmax | ∑i|ΓiUT|2|
ΓiLow dimension projective ΩiCovariance matrix Q=∑siΩiΩi TIt is a diagonal matrix, therefore principal component analysis disappears
Except the correlation of primitive character.
In cognitive phase, image Γ to be identified is mapped to eigenface space first, obtains vectorial Ω：
Ω=UTΓ-Ψ
Ω and each face collection distance definition is：
In order to distinguish face and non-face, also need to calculate original image Γ and eigenface space reconstruction image ΓkBetween
Distance ε：
ε2=| | Γ-Γk||2, wherein Γk=U Ω+Ψ
Face classification rule is as follows：
If ε >=θc, then the image inputted is not facial image.
If ε ＜ θc, and for any k, εk≥θc, then the image inputted includes unknown face.
If ε ＜ θc, and for any k, εk＜ θc, then the image that inputs includes k-th of face in image library.
Here directly do not apply to recognition of face using principal component as a kind of feature, but utilize PCA
A kind of simple and effective dimension reduction method is provided for ICA and LDA algorithm.
In recommending module 23 carries out program recommendation process, it is assumed that the rating characteristic vector of user is x=(xtrt, wcrc,
wmgrmg, were, wara, wsrs)T；Wherein：rt, rc, rmg, re, ra, rsRepresent user to viewing time, channel, program major class respectively
Hobby value and mood, the matching degree of age and sex；wt, wc, wmg, we, wa, ws, represent corresponding weight.Assuming that E generations
Recommendation index of the table to specific program, that is,：E=wtrt+wcrc+wmgrmg+were+wara+wsrs。
Proposed algorithm by system according to program recommendation index height, program is ranked up, it is forward by sorting
Program recommends user, you can obtains and the program of user is recommended.
Each hobby value and matching degree can give corresponding numerical value with the method for statistics, and example is used as using the hobby value of time
Son.
System will be set to 24 periods for one day, a length of 1h during each period.Assuming that user sees in timing statisticses section
The total degree of TV is n times, is fallen i-th (1<=i<=24) number of individual period is Ni, then user watched TV in the i periods
Hobby value be Rti=Ni/N。
In embodiments of the present invention, in the case where multi-user watches TV, if the program recommended only meets single use
The interest at family, then it can recommend to meet the TV programme of most people.It take into account the situation that a variety of users watch TV, energy
It is enough to be watched and recorded according to the history of user in the case where multi-user watches TV, the default preference value of user and user's
Emotional information, so as to more rationally recommend program to user.
It can be identified by image processing techniques and identify the identity of user, draw the corresponding feelings of active user's expression
Thread information, and the interest model of user is established according to the emotional information using user, optimal recommendation is made to user.
Substantial amounts of video flowing and image data are sent into high in the clouds additionally by cloud computing technology faster to be located
Reason, can so allow user faster or immediately to receive the result of identification and the TV programme list of recommendation.
In embodiments of the present invention, in all directions collect user watch TV when emotional information and the feedback to TV programme
Information, and the optimal the rendition list watched according to these information for the suitable user of customer group structure, can improve Consumer's Experience,
User is set to view and admire TV programme more pleasantly.
One of ordinary skill in the art will appreciate that all or part of step in the various methods of above-described embodiment is can
To instruct the hardware of correlation to complete by program, the program can be stored in a computer-readable recording medium, storage
Medium can include：Read-only storage (ROM, Read Only Memory), random access memory (RAM, Random
Access Memory), disk or CD etc..
In addition, the intelligent television program recommendation system based on context aware provided above the embodiment of the present invention is carried out
It is discussed in detail, specific case used herein is set forth to the principle and embodiment of the present invention, above example
Explanation be only intended to help understand the present invention method and its core concept；Meanwhile for those of ordinary skill in the art,
According to the thought of the present invention, there will be changes in specific embodiments and applications, in summary, in this specification
Appearance should not be construed as limiting the invention.
Claims (6)
1. a kind of intelligent television program recommendation system based on context aware, it is characterised in that the system includes：
Television headend subsystem, for obtaining the recommendation program list of inter-related task from high in the clouds；
User's identification system, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture, obtain
Program, is ranked up, sequence is leaned on by the characteristic parameter and recognition result of user according to the characteristic parameter of user and recognition result
Preceding program recommends user, and user data upload is identified to high in the clouds, while the recommendation of inter-related task is obtained from high in the clouds
Program list is supplied to television headend subsystem to use；And show recognition result and recommend program list；
The user's identification system includes data acquisition module, network communication module, recognizer module, recommending module and interface
Display module；
The recognizer module includes recognition of face submodule and Emotion identification submodule, the Emotion identification submodule detection
The emotional characteristics of face in movable information in video flowing and picture, obtaining the process of recognition result includes：
Step 1, eigenface is calculated；
If facial image I (x, y) is two-dimentional NxN gray level images, N is used2Dimensional vector Γ represents that facial image training set is { Γi|i
=1 ..., M }, wherein M is total number of images in training set,
The average vector of this M width image is：
Each face ΓiWith average face Ψ difference value vector ΦiFor：Φi=Γi-Ψ；I=1 ..., M,
The covariance matrix of training image is represented by：C=AAT, wherein A=[Φ1..., ΦM],
Eigenface is made up of covariance matrix C orthogonal eigenvectors, and for NxN facial images, covariance matrix C size is
N2*N2, by solving M*M less matrixes come solution matrix C characteristic value and characteristic vector,
Calculate the characteristic vector v of M*M matrix Lsi(i=1 ..., M), wherein, L=ATA,
The characteristic vector u of Matrix Ci(i=1 ..., M) is by difference value vector Φi(i=1 ..., M) and vi(i=1 ..., M) is linear
Combination obtains：U=[u1..., uM]=[Φ1..., ΦM][v1..., vM]=AV,
The characteristic vector of L preceding m eigenvalue of maximum is only taken to calculate eigenface；
Step 2, the recognition of face of feature based face, the face recognition process of feature based face is by training stage and cognitive phase two
Individual stage composition；
In the training stage, each oneself knows face ΓkIt is mapped on the subspace being made up of eigenface, obtains m dimensional vectors Ωk, Ωk
=UT(Γk-Ψ)；K=1 ..., Nc, wherein NcFor known number,
In cognitive phase, image Γ to be identified is mapped to eigenface space first, obtains vectorial Ω：Ω=UTΓ-Ψ, away from
From threshold value θcIt is defined as：
Ω and each face collection distance definition is：K=1 ... Nc,
Calculate original image Γ and eigenface space reconstruction image ΓkThe distance between ε：ε2=| | Γ-Γk||2, wherein Γk
=U Ω+Ψ,
Face classification rule is as follows：If ε >=θc, then the image inputted is not facial image；If ε ＜ θc, and for any k, εk≥
θc, then the image inputted includes unknown face；If ε ＜ θc, and for any k, εk＜ θc, then the image inputted includes image library
In k-th of face.
2. the intelligent television program recommendation system based on context aware as claimed in claim 1, it is characterised in that the user
Identifying system includes：
Data acquisition module, for inputting the user data of television headend subsystem and whole identification service；
Network communication module, pushing away for inter-related task is obtained for user data upload to be identified to high in the clouds, while from high in the clouds
Recommending program list is supplied to television headend subsystem to use；
Recognizer module, for carrying out recognition of face and Emotion identification to the movable information in video flowing and picture, obtain
The characteristic parameter and recognition result of user；
Recommending module, program is ranked up for the characteristic parameter according to user and recognition result, by the forward program that sorts
Recommend user；
Interface display module, for showing recognition result and recommending program list.
3. the intelligent television program recommendation system based on context aware as claimed in claim 2, it is characterised in that the user
Data include user's head portrait, user emotion information and managing operation history.
4. the intelligent television program recommendation system based on context aware as claimed in claim 2, it is characterised in that the identification
Algoritic module includes：
Recognition of face submodule, for detecting the movable information in video flowing and picture using symmetric difference method, according to people
Cluster of the face colour of skin in YCrCb color spaces carries out Face datection；
Emotion identification submodule, for detecting the emotional characteristics of face in the movable information in video flowing and picture, known
Other result.
5. the intelligent television program recommendation system based on context aware as claimed in claim 4, it is characterised in that the face
Identify that submodule is used to carry out Face datection using rule-based projection algorithm.
6. the intelligent television program recommendation system based on context aware as claimed in claim 2, it is characterised in that the data
Acquisition module is additionally operable to preset the personal like of user, can add when having new user to increase to television system
Add new user profile.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610038269.8A CN105721936B (en) | 2016-01-20 | 2016-01-20 | A kind of intelligent television program recommendation system based on context aware |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610038269.8A CN105721936B (en) | 2016-01-20 | 2016-01-20 | A kind of intelligent television program recommendation system based on context aware |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105721936A CN105721936A (en) | 2016-06-29 |
| CN105721936B true CN105721936B (en) | 2018-01-16 |
Family
ID=56148004
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610038269.8A Active CN105721936B (en) | 2016-01-20 | 2016-01-20 | A kind of intelligent television program recommendation system based on context aware |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105721936B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE112016007435T5 (en) * | 2016-12-14 | 2019-07-25 | Mitsubishi Electric Corporation | STATE ESTIMATION DEVICE |
| CN107424019A (en) | 2017-08-15 | 2017-12-01 | 京东方科技集团股份有限公司 | The art work based on Emotion identification recommends method, apparatus, medium and electronic equipment |
| CN107784114A (en) * | 2017-11-09 | 2018-03-09 | 广东欧珀移动通信有限公司 | Recommendation method, apparatus, terminal and the storage medium of facial expression image |
| CN108347628B (en) * | 2018-01-10 | 2020-05-29 | 维沃移动通信有限公司 | Method for prompting member activation, mobile terminal and server |
| CN108645495A (en) * | 2018-05-03 | 2018-10-12 | 温州三特食品科技有限公司 | A kind of intelligence can trace electronic scale |
| CN109327737B (en) * | 2018-11-14 | 2021-04-16 | 深圳创维－Rgb电子有限公司 | Television program recommendation method, terminal, system and storage medium |
| CN110166836B (en) * | 2019-04-12 | 2022-08-02 | 深圳壹账通智能科技有限公司 | Television program switching method and device, readable storage medium and terminal equipment |
| CN115223236A (en) * | 2021-04-19 | 2022-10-21 | 华为技术有限公司 | Device control method and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1395798A (en) * | 2000-11-22 | 2003-02-05 | 皇家菲利浦电子有限公司 | Method and apparatus for generating recommendations based on current mood of user |
| CN102427553A (en) * | 2011-09-23 | 2012-04-25 | Tcl集团股份有限公司 | Method and system for playing television programs, television set and server |
| CN103402142A (en) * | 2013-07-11 | 2013-11-20 | 深圳创维数字技术股份有限公司 | Program list pushing method and device |
| CN104363474A (en) * | 2014-11-14 | 2015-02-18 | 四川长虹电器股份有限公司 | Multiuser-based smart television program recommending system and method |
-
2016
- 2016-01-20 CN CN201610038269.8A patent/CN105721936B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1395798A (en) * | 2000-11-22 | 2003-02-05 | 皇家菲利浦电子有限公司 | Method and apparatus for generating recommendations based on current mood of user |
| CN102427553A (en) * | 2011-09-23 | 2012-04-25 | Tcl集团股份有限公司 | Method and system for playing television programs, television set and server |
| CN103402142A (en) * | 2013-07-11 | 2013-11-20 | 深圳创维数字技术股份有限公司 | Program list pushing method and device |
| CN104363474A (en) * | 2014-11-14 | 2015-02-18 | 四川长虹电器股份有限公司 | Multiuser-based smart television program recommending system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105721936A (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105721936B (en) | A kind of intelligent television program recommendation system based on context aware | |
| Nagrani et al. | Seeing voices and hearing faces: Cross-modal biometric matching | |
| US11222196B2 (en) | Simultaneous recognition of facial attributes and identity in organizing photo albums | |
| CN105426850B (en) | Associated information pushing device and method based on face recognition | |
| Lovato et al. | Faved! biometrics: Tell me which image you like and I'll tell you who you are | |
| US7684651B2 (en) | Image-based face search | |
| JP2020522077A (en) | Acquisition of image features | |
| WO2019076227A1 (en) | Human face image classification method and apparatus, and server | |
| EP2915101A1 (en) | Method and system for predicting personality traits, capabilities and suggested interactions from images of a person | |
| Zhao et al. | Video classification and recommendation based on affective analysis of viewers | |
| Guo et al. | Assessment model for perceived visual complexity of painting images | |
| CN111931592A (en) | Object recognition method, device and storage medium | |
| US11521013B2 (en) | Systems and methods for providing personalized product recommendations using deep learning | |
| CN110232331B (en) | Online face clustering method and system | |
| Ren et al. | Semantic facial descriptor extraction via axiomatic fuzzy set | |
| Zafeiriou et al. | Probabilistic slow features for behavior analysis | |
| Maddumala | Big Data-Driven Feature Extraction and Clustering Based on Statistical Methods. | |
| CN113779283B (en) | Fine-grained cross-media retrieval method with deep supervision and feature fusion | |
| Zhang et al. | Affective abstract image classification and retrieval using multiple kernel learning | |
| Monteiro et al. | Design and evaluation of classifier for identifying sign language videos in video sharing sites | |
| Lienhard et al. | How to predict the global instantaneous feeling induced by a facial picture? | |
| Dantcheva et al. | Assessment of female facial beauty based on anthropometric, non-permanent and acquisition characteristics | |
| Schauerte et al. | Web-based learning of naturalized color models for human-machine interaction | |
| Guntuku et al. | Evaluating visual and textual features for predicting user ‘likes’ | |
| Khan | Detection of emotions from video in non-controlled environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |