CN100423574C - Method and apparatus for generating recommendations based on current mood of user - Google Patents

Method and apparatus for generating recommendations based on current mood of user Download PDF

Info

Publication number
CN100423574C
CN100423574C CNB018040128A CN01804012A CN100423574C CN 100423574 C CN100423574 C CN 100423574C CN B018040128 A CNB018040128 A CN B018040128A CN 01804012 A CN01804012 A CN 01804012A CN 100423574 C CN100423574 C CN 100423574C
Authority
CN
China
Prior art keywords
user
program
spectators
characteristic image
expression
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.)
Expired - Fee Related
Application number
CNB018040128A
Other languages
Chinese (zh)
Other versions
CN1395798A (en
Inventor
S·古塔
M·特拉科维克
A·J·科尔梅纳雷兹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Sisvel SpA
Koninklijke Philips NV
Original Assignee
Koninklijke Philips Electronics NV
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Koninklijke Philips Electronics NV filed Critical Koninklijke Philips Electronics NV
Publication of CN1395798A publication Critical patent/CN1395798A/en
Application granted granted Critical
Publication of CN100423574C publication Critical patent/CN100423574C/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

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
    • H04N21/45—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
    • 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
    • H04N21/44222—Analytics of user selections, e.g. selection of programs or purchase activity
    • 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
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/4223—Cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • 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
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42201—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] biosensors, e.g. heat sensor for presence detection, EEG sensors or any limb activity sensors worn by the user
    • 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
    • H04N21/41—Structure of client; Structure of client peripherals
    • H04N21/422—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS]
    • H04N21/42203—Input-only peripherals, i.e. input devices connected to specially adapted client devices, e.g. global positioning system [GPS] sound input device, e.g. microphone
    • 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
    • H04N21/4508—Management of client data or end-user data
    • H04N21/4532—Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • 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
    • H04N21/454—Content or additional data filtering, e.g. blocking advertisements
    • 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
    • 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
    • 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
    • H04N21/47—End-user applications
    • H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
    • H04N21/4755—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for defining user preferences, e.g. favourite actors or genre
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00—Television systems
    • H04N7/16—Analogue secrecy systems; Analogue subscription systems
    • H04N7/162—Authorising the user terminal, e.g. by paying; Registering the use of a subscription channel, e.g. billing
    • H04N7/163—Authorising the user terminal, e.g. by paying; Registering the use of a subscription channel, e.g. billing by receiver means only

Abstract

A method and apparatus are disclosed for generating a user profile in a recommendation system based on the current mood of the user. The present invention associates each session, such as a viewing session, with one or more current moods of the user. The present invention learns the user's preferences in accordance with various moods, and utilizes such mood-based viewing preferences to generate corresponding recommendations. In one implementation, an electronic programming guide is provided that allows a viewer to select one or more programs that the viewer is likely to find attractive, based on his or her current mood.

Description

Current mood according to the user produces the method and apparatus of recommending
FIELD OF THE INVENTION
The present invention relates to recommended device,, and relate in particular to recommend method and the device that is used for according to user's current mood generation such as the recommendation of TV programme or other guide such as the recommended device that is used for TV programme or other guide.
The background of invention
Can increase by the quantity that the media that the individual obtains is selected with index speed.Owing to can increase by the channel quantity that the televiewer obtains, for example,, determine that concerning the televiewer interested TV programme has become a kind of challenge of increase along with the diversity of obtainable programme content on these channels.The televiewer determines programs of interest by analyzing the TV Guide of printing.Typically, the TV Guide of such printing comprises the form of the obtainable TV programme of listing by time and date channel and title.Because the quantity of TV programme increases, so use the guide of such printing to determine that effectively the TV programme of wanting becomes difficult more.
Recently, TV Guide can obtain with electronic format, so-called electronic program guides (EPG).As the TV Guide of printing, EPG comprises the obtainable TV programme form of listing by time and date, channel and title.But some EPG permission televiewers are according to individualized preference categories or search for obtainable TV programme.In addition, EPG allows to show on the screen of obtainable TV programme.
Although EPG allows spectators more effectively to determine the program wanted than the guide of traditional printing, they also will bear many restrictions, if overcome these restrictions, can further strengthen the ability that spectators determine the program wanted.For example, a lot of spectators have certain program category, such as the particular preferences or the prejudice of action program or sports cast.Therefore, thus spectators hobby can be applied to that EPG obtains can be by the interested one group of recommend programs of niche audience.
Therefore, many instruments have proposed or have been proposed to be used in recommending television.For example, from the Tivo Inc. of California Sani Wei Er can commercial acquisition Tivo TMSystem allows spectators to use " upwards turn over and turn over " downwards thereby the characteristic evaluating program also shows the program that spectators like and dislike respectively.By this way, Tivo TMSystem impliedly from before spectators like and the TV programme disliked draws spectators' hobby.Therefore, the Tivo receiver makes spectators' hobby of record and the TV data coupling such as EPG that receives, and recommends to be fit to each spectators thereby make.
Implicit television program recommender produces television program recommendations in not compulsory mode according to the information of watching history to draw from spectators.Direct television program recommender, on the other hand, the direct access inquiry spectators, recommend thereby draw spectators' archives and produce the hobby such as exercise question, type, performer, channel and date programs feature about them.
The television program recommender of even now is determined given spectators institute programs of interest, but they also bear many restrictions, if overcome these restrictions, then can further improve the quality that produces program commending.For example, when producing spectators' archives and television program recommendations record, the conventional tool that is used to produce TV Guide is done individual's the history of watching as a wholely to consider.Therefore, program of Que Dinging and spectators' current interest or mood do not have special correlation.Therefore, there is the method and apparatus be used to produce according to the TV Guide of spectators' current mood.
Summary of the invention
Generally speaking, a kind of method and apparatus that produces files on each of customers according to the current mood of user in commending system is disclosed.Thereby the present invention knows user's hobby according to various moods, and therefore utilizes these hobbies based on mood to produce the recommendation that is fit to user's current mood.
The present invention detects user's mood by processing audio or video information such as user's facial expression.In case mood is detected, can be associated with the current mood of spectators with the relevant behavior of section preset time.In a kind of equipment, the invention provides and a kind ofly allow spectators to select one or more spectators to find the electronic program guides of attractive program probably according to his or she current mood.
Understanding more completely of the present invention and further feature and advantage of the present invention obtain with reference to the detailed description and the accompanying drawings subsequently.
Brief description of drawings
Fig. 1 is according to the invention describes television program recommender;
Fig. 2 has described the abridged table from the program database of Fig. 1;
Fig. 3 A has described the abridged table from the Bayesian device of implicit spectators' archives of Fig. 1;
Fig. 3 B has described the abridged table of watching history that comes free decision tree (DT) recommended device to use;
The abridged table of spectators' archives that Fig. 3 C has described and produced from the historical decision tree (DT) of watching of Fig. 3 B;
Fig. 4 describes the flow chart that the exemplary mood that embodies principle of the present invention detects and the archives renewal is handled; And
Fig. 5 is the flow chart of the exemplary recommendation process based on mood that describe to embody principle of the present invention.
Describe in detail
Fig. 1 has described according to television program recommender 100 of the present invention.As shown in Figure 1, each program in the television program recommender 100 evaluation electronic program guidess (EPG) 130 is to determine one or more spectators' 140 programs of interest.One group of recommend programs can show spectators 140 by enough set-top terminal/television sets 160, for example, uses Display Technique on the known screen.Although the present invention here describes with the angle of television program recommendations, the present invention also can be applied to according to behavior history, such as watching history or buying in the historical recommendation that produces automatically.
According to a feature of the present invention, television program recommender 100 also according to spectators' current mood, except more traditional the watching according to spectators produces files on each of customers 300 below the behavior, discuss with Fig. 3 A and 3C hereinafter by these archives.Although traditional recommended device is regarded a people's the history of watching as an integral body when producing spectators' archives, the present invention regards spectators' hobby as multistage problem, and makes each watch the period to be associated with one or more current moods of spectators.Therefore, the present invention learns spectators' hobby according to various moods, and utilizes such based on watching hobby to produce program commending.By this way, provide the electronic program guides of selecting the program of one or more spectators' most probables discovery attractions according to his or her current mood permission spectators.
As shown in Figure 1, television program recommender 100 comprises that one and a plurality of spectators' of focusing on 140 audio/video deriving means 150-1 is to 150-N (hereinafter, being called audio/video deriving means 150 jointly).Audio/video deriving means 150 can comprise that for example being used to obtain video information De Shake takes the photograph-angle lapping-zoom (PTZ) video camera or be used to obtain the microphone array of audio-frequency information or all comprise.
Handle by television program recommender 100 by the audio or video image (or all comprising) that audio/video deriving means 150 produces, thus identification spectators' 140 one or more predetermined mood, in the mode of hereinafter discussing with Figure 4 and 5.As discussed below, to be used for detecting spectators be happiness or sadness to the facial expression treatment technology expression that can be used to analyze spectators.In addition, audio signal processing technique can be used to analyze the sound that is sent by spectators, is used for detecting spectators and laughs at or cry, and this can hint current spectators' mood.For example when archive information is recorded, or when taking place simultaneously (or both) spectators' mood can be detected when a recommendation will be produced.
As shown in Figure 1, television program recommender 100 comprises program database 200, one or more spectators' files 300, mood detects and archives upgrade processing 400 and based on the recommendation process 500 of mood, each part hereinafter respectively with Fig. 2 to 5 argumentation that links together.Usually, program database 200 is recorded in the information of obtainable each program of section preset time.As shown in Figure 3A, illustrative spectators archives 300 are the spectators' archives that imply, and according to the program set that former spectators like or dislike, these archives typically draw from spectators' the history of watching.Shown in Fig. 3 C, another exemplary spectators' archives 300 ' produced by the decision tree recommended device watch historical 360 according to exemplary shown in Fig. 3 B.
Mood detection and archives upgrade handles 400 video or the still images of handling by 150 generations of audio/video deriving means (or the both comprises), thereby feels spectators' current mood and know the hobby of spectators when such mood.Utilize by the hobbies of watching that mood detects and archives renewal processing 400 produces based on the recommendation process 500 of mood, thereby produce program commending according to the spectators' that draw current mood based on mood.
Television program recommender 100 can be used any calculation element, realizes such as personal computer or work station, and it comprises such as the processor 120 of center processing unit (CPU) with such as the memory 110 of RAM and/or ROM.In addition, television program recommender 100 can be with the Tivo of the commercial acquisition of Tivo Inc. of any California Sani Wei Er TMSystem or the exercise question of applying on December 17th, 1999 are the U.S. Patent Application Serial Number 09/466 of " method and apparatus that uses the decision tree recommending television ", 406 (acting on behalf of case No.700772), the exercise question of application on February 4th, 2000 is the U.S. Patent application of submitting in " Bayesian television program recommender " (agent docket No.700690) and on July 27th, 2000 the 09/627th, 139, exercise question is the television program recommender that " three kinds mode media recommend method and system " (agent docket No.700913) describes, perhaps their combination in any is modified to carry out feature of the present invention and function here.
Fig. 2 is that it is recorded in the information of obtainable each program of section preset time from the abridged table of the program database 200 of Fig. 1.As shown in Figure 2, program database 200 comprises a plurality of records, and such as record 205 to 220, each record is relevant with given program.Concerning each program, date and channel that program database 200 expression is associated with program in field 240 and 245 respectively.In addition, the exercise question of each program, type and performer determine in field 250,255 and 270 respectively.Additional well-known characteristic (not shown) also can be included in the program database 200 such as the explanation of duration and program.
Fig. 3 A is a form of describing exemplary implicit spectators' archives 300.As shown in Figure 3, implicit spectators' archives 300 comprise a plurality of record 305-313, and each writes down with different programs features and is associated.In addition, to each feature that occurs in the row 330, implicit spectators' archives 300 are provided at the forward counting of the correspondence in the field 335 to 345 and the negative counting in the field 350.According to a feature of the present invention, forward counting is provided for each distinct expression that is detected by television program recommender 100.Various forward countings are represented spectators watch the time of the program with each feature when the mood of correspondence numeral.Negative counting expression spectators do not watch the time figure of the program with each feature.
To each positive and negative program example (program of promptly watching He not watching), the number of programs feature is classified in files on each of customers 300.For example, if watch given sports cast ten times at channel 2 when given spectators are later in the afternoon, be glad mood at this moment, then the forward counting (happiness) that is associated with these features in implicit spectators' archives 300 will increase by 10 in field 345, and negative counting will be 0 (zero).Because implicit spectators' archives 300 can be according to common or predetermined archives, for example, according to his or his statistics select by the user.
Fig. 3 B describes exemplary historical 360 the form of watching, and it is kept by the decision tree television recommender.Shown in Fig. 3 B, watch historical 360 to comprise a plurality of record 361-369, each is associated with different program.In addition, to each program, watch the historical 360 various programs features of determining among the field 370-379.The value that occurs in field 370-379 can typically obtain from electronic program guides 130.Note, if electronic program guides 130 does not specify a given feature to given program, this value in watching history 360 with one "? " expression.
Fig. 3 C be describe exemplary spectators' archives 300 ' table, it can occur from Fig. 3 B watches historical 360 to be produced by the decision tree television recommender.Shown in Fig. 3 C, a plurality of record 381-384 of decision tree spectators archives 300 ' comprise, each is associated with the rule of different definite spectators' hobby.In addition, to each rule of definition in row 390, the condition that the corresponding recommendation in rule in spectators' archives 300 ' identification and the field 391 and the field 392 is associated.
More detailed argumentation to the generation of the spectators' archives in the decision tree commending system, see the U.S. Patent Application Serial Number 09/466 of the exercise question of for example application on December 17th, 1999 for " using the method and apparatus of decision tree recommending television ", 406 (agent docket No.700772) here quote as a reference.
Fig. 4 is a flow chart of describing exemplary mood detection and archives renewal processing 400.As shown in Figure 4, thereby mood detects and archives upgrade and handle 400 and carry out test in step 410 at first and determine whether an incident renewal of startup spectators archives 300 has taken place, such as at the end of program or the selection of program channel newly.If determine that in step 410 thereby incident also not have to take place to start the renewal of spectators' archives 300, then program is controlled and is turned back to step 410 and be detected up to such incident.
But, if determine that in step 410 thereby the renewal of spectators' archives 300 has taken place to start an incident, then current spectators' 140 mood is detected with known facial expression analysis technology in step 420, such as University of Illinois at Urbana-Champaign (1999), the technology of describing in Ph.D.Dissertation " the face analysis of continuous videos " with application program of people and computer interface; Or Proc.Of the Int ' l Conf.on Computer Vision andPattern Recognition, Fort Collins, Colorado (1999), Vol.I, the technology that Antonio Colmenarez etc. " face that is used for embedding and the statistical framework of human facial expression recognition " described among the 592-97, they are here quoted as a reference.Can obtain the intensity of facial expression, for example, according to U.S. Patent Application Serial Number 09/705 in application on November 3rd, 2000,666 exercise questions are " using the estimation of the facial expression intensity of two-way Star topology markov pattern ", (agent docket 701253) transfers assignee of the present invention and also here quotes as a reference.Usually, the face of the spectators in the viewing areas of the video camera of facial expression analysis detection in being included in audio/video deriving means 150, and identification is by the special facial expression of spectators' 140 displayings, such as smiling or frowning.Facial expression is used to draw spectators 140 current mood.
Thereby during step 425, carry out test and determine that television program recommender 100 is Bayes's recommended device or decision tree (DT) recommended device.If determine that in step 425 television program recommender 100 is Bayes's recommended devices, then the forward counting corresponding to spectators 140 current mood is updated to the programs feature that is associated in preceding program in spectators' archives 300 during step 430.In addition, negative counting optionally is updated to the programs feature that is associated with one or more elective programs of not watching in step 430 spectators archives 300.
But, if determine that during step 425 television program recommender 100 is decision tree (DT) recommended devices, thus then step 450 spectators archives 300 ' in rule-based filtering only discern the rule that is associated with current mood.Therefore, Sheng Xia rule (filter back) thus the rule of current program is satisfied in further processed identification.Then be added in the recognition rule at the current program of step 470, as follows:
Figure C0180401200101
Wherein, intensity has 7 value to the mood of happiness, and the mood of sadness is had 1 value, and the mood of neutrality is had 3 value.Perhaps, spectators' archives 300 of Fig. 3 C ' can be during step 470 are by adding the program that watch and reconstructing file 300 ' upgrade to watching in historical 360.Therefore, program control stops.
Fig. 5 is the flow chart based on the recommendation process 500 of mood that describe to embody principle of the present invention.Utilize by the hobby of watching that mood detects and archives renewal processing 400 produces to come based on the recommendation process 500 of mood based on the spectators' current mood generation program commending that draws based on mood.
As shown in Figure 5, during step 510, based on the recommendation process 500 initial electronic program guidess (EPG) that obtain for the interested time period of mood.Therefore, during step 515, spectators are obtained suitable spectators' archives 300.During step 520, based on 500 of the recommendation process of mood to detect with aforementioned mood and archives upgrade and handle the current mood that 400 identical modes are used audio/video deriving means acquisition spectators.
During step 525, determine that television program recommender 100 is Bayes's recommended device or decision tree (DT) recommended device thereby carry out test.If determine that in step 525 television program recommender 100 is Bayes's recommended devices, then at step 530 use characteristic counting only to current mood to each program calculated recommendation mark.
But, if determine that in step 525 television program recommender 100 is decision tree (DT) recommended devices, then in step 540 spectators' archives 300 ' in rule be filtered, thereby only discern those rules relevant with current mood.Therefore, remaining rule (filtering the back) is applied at all programs of interested time period during step 550.Corresponding to archives 300 ' the tabulation of order in first rule that satisfies, mark to from archives 300 ' each program of field 392 be resumed.
Finally, in step 570, before program control stopped, the user was provided to the recommender score to each program calculating.
Be to be understood that only having illustrated with improvement with the embodiment that describes of illustrating do not depart from the scope of the present invention principle of the present invention and aim here, those skilled in the art can realize various modifications.

Claims (13)

1. one kind produces the method for recommending to one or more projects, may further comprise the steps:
Use video camera (150-1; 150-N) obtain the image of user (140);
Use processor (400) that described image is carried out facial expression analysis with face that detects the user (140) in the viewing areas of gamma camera and the characteristic image character of discerning the facial expression of the described face of expression; And
According to the recommendation of the characteristic image character generation of being discerned at least one project.
2. the method for claim 1, this method is applied to a television program recommender, and described method comprises the steps:
-from the source of electronic program guides (130), obtain a plurality of
-use one group of top set terminal/television machine (160) to show recommendation to the user.
3. the process of claim 1 wherein that described one or more project is program, interior perhaps product.
4. the files on each of customers (300) of user (140) of method select to produce to(for) the user in a plurality of projects said method comprising the steps of:
Monitor a user's (140) of one or more projects selection;
The gamma camera that use focuses on this user obtains a user's (140) image; And
Use processor (400) that described image is carried out facial expression analysis with face that detects the user (140) in the viewing areas of gamma camera and the characteristic image character of discerning the facial expression of the described face of expression; And
The expression of the characteristic image character that record is associated with described project selection in memory is to be used to produce described archives.
5. the method for claim 4, wherein said files on each of customers (300) is associated with content of TV program recommended device (100).
6. the method for claim 4, the step of the expression that the described project of wherein said record is selected also comprises the step that increases the one or more positive feature counts that are associated with described project and described current characteristic image character.
7. the method for claim 4 is wherein determined described current characteristic image character by the described user of inquiry (140).
8. the method for claim 4, wherein said one or more projects are program, interior perhaps product.
9. one kind produces the system of recommending to one or more projects, and this system comprises:
Gamma camera (150-1; 150-N), be used to obtain the information of user (140);
With first device (400) of gamma camera coupling, described image is carried out facial expression analysis with face that detects the user (140) in the viewing areas of gamma camera and the characteristic image character of discerning the facial expression of the described face of expression; And
With second device of the first device coupling, according to the recommendation of the characteristic image character generation of being discerned at least one project.
10. the system of claim 9 comprises:
-be coupled to the electronic program guides source (130) of described second device, be used to provide described
-one group of top set terminal/television machine (160) is coupled to described second device, is used for showing recommendation to the user.
11. select to produce the system of the files on each of customers (300) of user (140) for the user in a plurality of projects for one kind, described system comprises:
Monitoring arrangement is used to monitor the user's (140) of one or more projects selection;
Focus on user's gamma camera, be used to obtain user's (140) a image;
Processor (400) carries out facial expression analysis with face that detects the user (140) in the viewing areas of gamma camera and the characteristic image character of discerning a facial expression of the described face of expression to described image; And
Storage arrangement, the expression of the characteristic image character that record is associated with described project selection is to be used to produce described archives.
12. the system of claim 11,
Wherein said processor (120) further is configured to increase and described project and the described one or more positive feature counts that is associated when characteristic image character.
13. the system of claim 11, wherein said one or more projects are program, interior perhaps product.
CNB018040128A 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on current mood of user Expired - Fee Related CN100423574C (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US71826000A 2000-11-22 2000-11-22
US09/718,260 2000-11-22

Publications (2)

Publication Number Publication Date
CN1395798A CN1395798A (en) 2003-02-05
CN100423574C true CN100423574C (en) 2008-10-01

Family

ID=24885424

Family Applications (1)

Application Number Title Priority Date Filing Date
CNB018040128A Expired - Fee Related CN100423574C (en) 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on current mood of user

Country Status (5)

Country Link
EP (1) EP1340375A1 (en)
JP (1) JP2004515128A (en)
KR (1) KR100876300B1 (en)
CN (1) CN100423574C (en)
WO (1) WO2002043391A1 (en)

Families Citing this family (57)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1661399A1 (en) * 2003-08-29 2006-05-31 Koninklijke Philips Electronics N.V. User-profile controls rendering of content information
KR20050117829A (en) * 2004-06-11 2005-12-15 삼성전자주식회사 Automatic service selection method and apparatus according to the physical condition of user, and terminal therewith
JP2007041988A (en) * 2005-08-05 2007-02-15 Sony Corp Information processing device, method and program
CN100455012C (en) * 2005-09-12 2009-01-21 中兴通讯股份有限公司 Television program recommending device and method thereof
JP2007215046A (en) * 2006-02-10 2007-08-23 Sharp Corp Information processor, information processing method, information processing program, and recording medium
US20080263591A1 (en) * 2007-04-23 2008-10-23 Microsoft Corporation Content viewing session
JP5042883B2 (en) * 2008-02-28 2012-10-03 株式会社日立製作所 Content recommendation device and content recommendation method
FR2931332A1 (en) * 2008-05-16 2009-11-20 Alcatel Lucent Sas METHOD AND SYSTEM FOR ESTABLISHING A PROGRAM GUIDE IN A DEMAND-BASED VIDEOS SERVICE BASED ON THE USER'S MOOD
US8658576B1 (en) 2009-10-21 2014-02-25 Encore Wire Corporation System, composition and method of application of same for reducing the coefficient of friction and required pulling force during installation of wire or cable
JP2011166572A (en) * 2010-02-12 2011-08-25 Nec Personal Products Co Ltd Apparatus for estimation of program preference, image viewing system, program viewing confirmation method, and program
US9123061B2 (en) 2010-03-24 2015-09-01 Disney Enterprises, Inc. System and method for personalized dynamic web content based on photographic data
US10289898B2 (en) 2010-06-07 2019-05-14 Affectiva, Inc. Video recommendation via affect
CN101958138A (en) * 2010-06-08 2011-01-26 宇龙计算机通信科技(深圳)有限公司 Music data storage method and device and music play terminal
US8640021B2 (en) * 2010-11-12 2014-01-28 Microsoft Corporation Audience-based presentation and customization of content
KR101789619B1 (en) * 2010-11-22 2017-10-25 엘지전자 주식회사 Method for controlling using voice and gesture in multimedia device and multimedia device thereof
CN102098567B (en) * 2010-11-30 2013-01-16 深圳创维－Rgb电子有限公司 Interactive television system and control method thereof
TW201225649A (en) * 2010-12-07 2012-06-16 Acer Inc Television system and interaction method thereof
EP2678820A4 (en) * 2011-02-27 2014-12-03 Affectiva Inc Video recommendation based on affect
US8887095B2 (en) * 2011-04-05 2014-11-11 Netflix, Inc. Recommending digital content based on implicit user identification
US20130061257A1 (en) * 2011-09-02 2013-03-07 Sony Corporation Verbally communicating facially responsive television apparatus
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
CN103137043B (en) * 2011-11-23 2015-07-15 财团法人资讯工业策进会 Advertisement display system and advertisement display method in combination with search engine service
US9100685B2 (en) 2011-12-09 2015-08-04 Microsoft Technology Licensing, Llc Determining audience state or interest using passive sensor data
CN102523502A (en) * 2011-12-15 2012-06-27 四川长虹电器股份有限公司 Intelligent television interaction system and interaction method
CN102402765B (en) * 2011-12-27 2017-07-28 北京京东尚科信息技术有限公司 Electronic commerce recommending method based on user's Expression analysis
US9352371B1 (en) 2012-02-13 2016-05-31 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
CA2775700C (en) 2012-05-04 2013-07-23 Microsoft Corporation Determining a future portion of a currently presented media program
CN103383597B (en) * 2012-05-04 2017-07-28 微软技术许可有限责任公司 Method for media program to be presented
US11328843B1 (en) 2012-09-10 2022-05-10 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
CN103024521B (en) * 2012-12-27 2017-02-08 深圳Tcl新技术有限公司 Program screening method, program screening system and television with program screening system
KR20140094125A (en) * 2013-01-21 2014-07-30 삼성전자주식회사 display apparatus and method of providing customer-built information using the apparatus
KR20140096935A (en) * 2013-01-29 2014-08-06 이종식 Smart device having a user interface based on human emotion or tendency and user interface method
US10056742B1 (en) 2013-03-15 2018-08-21 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
KR20150062647A (en) 2013-11-29 2015-06-08 삼성전자주식회사 Image processing apparatus and control method thereof
DK178068B1 (en) * 2014-01-21 2015-04-20 Bang & Olufsen As Mood based recommendation
CN104811801A (en) * 2015-04-23 2015-07-29 天脉聚源(北京)传媒科技有限公司 Method and device for automatic switching of channels
CN106294489B (en) * 2015-06-08 2022-09-30 北京三星通信技术研究有限公司 Content recommendation method, device and system
FR3037757B1 (en) * 2015-06-18 2018-11-16 Spideo METHOD AND SYSTEM FOR RECOMMENDING A CONTENT USER FROM PARAMETER (S) ACTIVATED BY THE USER FROM A CORRESPONDING INTERFACE.
CN106327234A (en) * 2015-07-02 2017-01-11 中兴通讯股份有限公司 Information recommendation method and apparatus
CN106658202A (en) * 2015-10-30 2017-05-10 中国移动通信集团公司 Method and equipment for triggering interaction application
CN105898411A (en) * 2015-12-15 2016-08-24 乐视网信息技术（北京）股份有限公司 Video recommendation method and system and server
CN105578277A (en) * 2015-12-15 2016-05-11 四川长虹电器股份有限公司 Intelligent television system for pushing resources based on user moods and processing method thereof
CN105721936B (en) * 2016-01-20 2018-01-16 中山大学 A kind of intelligent television program recommendation system based on context aware
CN106331109A (en) * 2016-08-26 2017-01-11 天津通信广播集团有限公司 Method for realizing intelligent recommendation system of visual information in digital television
CN106445365A (en) * 2016-09-12 2017-02-22 上海斐讯数据通信技术有限公司 Method for adjusting emotions and intelligent terminal
KR20180057096A (en) * 2016-11-21 2018-05-30 삼성전자주식회사 Device and method to perform recognizing and training face expression
CN108234591B (en) * 2017-09-21 2021-01-05 深圳市商汤科技有限公司 Content data recommendation method and device based on identity authentication device and storage medium
CN109327736B (en) * 2018-10-25 2021-01-26 合肥澳视智能科技有限公司 Program recommendation method based on program viewing expression and user information
CN109542624B (en) * 2018-11-23 2021-09-28 中国农业银行股份有限公司 Resource allocation method and device for application change
US11589094B2 (en) 2019-07-22 2023-02-21 At&T Intellectual Property I, L.P. System and method for recommending media content based on actual viewers
KR20210015410A (en) * 2019-08-02 2021-02-10 삼성전자주식회사 Display apparatus and Method for controlling the display apparatus thereof
CN111414883A (en) * 2020-03-27 2020-07-14 深圳创维－Rgb电子有限公司 Program recommendation method, terminal and storage medium based on face emotion
CN111417017A (en) * 2020-04-28 2020-07-14 安徽国广数字科技有限公司 IPTV program recommendation method and system based on human body identification
US11641506B2 (en) * 2020-11-11 2023-05-02 Rovi Guides, Inc. Systems and methods for providing media recommendations
US11849177B2 (en) * 2020-11-11 2023-12-19 Rovi Guides, Inc. Systems and methods for providing media recommendations
CN113992991A (en) * 2021-10-27 2022-01-28 四川启睿克科技有限公司 Voiceprint recognition-based video recommendation system and method
CN115866339A (en) * 2022-12-07 2023-03-28 深圳创维－Rgb电子有限公司 Television program recommendation method and device, intelligent device and readable storage medium

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
Eye-gaze control of multimedia systems. HANSEN J P ET AL.PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTIONS (HCI INTERNATIONAL'95),Vol.A . 1995
Eye-gaze control of multimedia systems. HANSEN J P ET AL.PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTIONS (HCI INTERNATIONAL'95),Vol.A . 1995 *
Processing of face images and its applications. KANEKO M ET AL.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,Vol.E82-D No.3. 1999
Processing of face images and its applications. KANEKO M ET AL.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,Vol.E82-D No.3. 1999 *
TV CONTENT RECOMMENDER SYSTEM. GUTTA S ET AL.PROCEEDINGS SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE. 2000
TV CONTENT RECOMMENDER SYSTEM. GUTTA S ET AL.PROCEEDINGS SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE. 2000 *

Also Published As

Publication number Publication date
CN1395798A (en) 2003-02-05
KR20020070490A (en) 2002-09-09
KR100876300B1 (en) 2008-12-31
JP2004515128A (en) 2004-05-20
EP1340375A1 (en) 2003-09-03
WO2002043391A1 (en) 2002-05-30

Similar Documents

Publication Publication Date Title
CN100423574C (en) Method and apparatus for generating recommendations based on current mood of user
EP1337914B1 (en) Method and apparatus for obtaining auditory and gestural feedback in a recommendation system
CN100499794C (en) Method and apparatus for selective updating of a user profile
US7240355B1 (en) Subscriber characterization system with filters
EP2051509B1 (en) Program recommendation system, program view terminal, program view program, program view method, program recommendation server, program recommendation program, and program recommendation method
JP5482206B2 (en) Information processing apparatus, information processing method, and program
CN1460371A (en) Method and apparatus for automatically selecting alternate item based on user behavior
US20060225088A1 (en) Generation of implicit tv recommender via shows image content
US20110219042A1 (en) Method and apparatus for generating meta data of content
KR20040037246A (en) Program recommendation method and system utilizing a viewing history of commercials
US20020186867A1 (en) Filtering of recommendations employing personal characteristics of users
KR101068657B1 (en) Transformation of recommender scores depending upon the viewed status of ?? shows
KR100730309B1 (en) A method of real-time audience response collection and reporting
CN115278370A (en) Television program recommendation method and system, smart television and medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: Holland Ian Deho Finn

Patentee after: KONINKLIJKE PHILIPS N.V.

Address before: Holland Ian Deho Finn

Patentee before: KONINKLIJKE PHILIPS ELECTRONICS N.V.

CP01 Change in the name or title of a patent holder
TR01 Transfer of patent right

Effective date of registration: 20180118

Address after: Italy Knowles

Patentee after: S.I.SV.EL SOCIETA' ITALIANA PER LO SVILUPPO DELL'ELETTRONICA S.P.A.

Address before: Holland Ian Deho Finn

Patentee before: KONINKLIJKE PHILIPS N.V.

TR01 Transfer of patent right
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20081001

Termination date: 20201116

CF01 Termination of patent right due to non-payment of annual fee