WO2002043391A1 - 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
WO2002043391A1
WO2002043391A1 PCT/EP2001/013453 EP0113453W WO0243391A1 WO 2002043391 A1 WO2002043391 A1 WO 2002043391A1 EP 0113453 W EP0113453 W EP 0113453W WO 0243391 A1 WO0243391 A1 WO 0243391A1
Authority
WO
WIPO (PCT)
Prior art keywords
user
current mood
viewer
mood
profile
Prior art date
Application number
PCT/EP2001/013453
Other languages
French (fr)
Inventor
Srinivas Gutta
Miroslav Trajkovic
Antonio J. Colmenarez
Original Assignee
Koninklijke Philips Electronics N.V.
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 N.V. filed Critical Koninklijke Philips Electronics N.V.
Priority to JP2002544983A priority Critical patent/JP2004515128A/en
Priority to EP01994683A priority patent/EP1340375A1/en
Priority to KR1020027009314A priority patent/KR100876300B1/en
Publication of WO2002043391A1 publication Critical patent/WO2002043391A1/en

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
    • H04N21/45—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

Definitions

  • the present invention relates to recommenders, such as recommenders for television programming or other content, and more particularly, to a method and apparatus for making recommendations, such as recommendations of television programs or other content, based on the current mood of the user.
  • EPGs electronic program guides
  • EPGs Like printed television program guides, EPGs contain grids listing the available television programs by time and date, channel and title. Some EPGs, however, allow television viewers to sort or search the available television programs in accordance with personalized preferences. In addition, EPGs allow for on-screen presentation of the available television programs.
  • EPGs allow viewers to identify desirable programs more efficiently than conventional printed guides, they suffer from a number of limitations, which if overcome, could further enhance the ability of viewers to identify desirable programs. For example, many viewers have a particular preference towards, or bias against, certain categories of programming, such as action-based programs or sports programming. Thus, the viewer preferences can be applied to the EPG to obtain a set of recommended programs that may be of interest to a particular viewer. Thus, a number of tools have been proposed or suggested for recommending television programming.
  • the TivoTM system for example, commercially available from Tivo, Inc., of Sunnyvale, California, allows viewers to rate shows using a "Thumbs Up and Thumbs Down" feature and thereby indicate programs that the viewer likes and dislikes, respectively. In this manner, the TivoTM system implicitly derives the viewer's preferences from previous television programs that the viewer liked or did not like. Thereafter, the TiNo receiver matches the recorded viewer preferences with received program data, such as an EPG, to make recommendations tailored to each viewer.
  • Implicit television program recommenders generate television program recommendations based on information derived from the viewing history of the viewer, in a non-obtrusive manner.
  • Explicit television program recommenders on the other hand, explicitly question viewers about their preferences for program attributes, such as title, genre, actors, channel and date/time, to derive viewer profiles and generate recommendations.
  • television program recommenders identify programs that are likely of interest to a given viewer, they suffer from a number of limitations, which if overcome, could further improve the quality of the generated program recommendations.
  • conventional tools for generating television program recommendations consider a person's viewing history as a whole when generating a viewer profile and television program recommendation scores.
  • the identified programs have no particular correlation to the current interests or mood of the viewer.
  • a method and apparatus for generating a user profile in a recommendation system based on the current mood of the user.
  • the present invention thus learns the user's preferences in accordance with various moods, and thereafter utilizes such mood-based preferences to generate recommendations that are tailored to the current mood of the user.
  • the present invention detects the user's mood by processing audio or visual information, such as the facial expression of the user. Once the mood is detected, the behavior associated with a given session can be associated with the current moods of the viewer.
  • the present invention provides an electronic programming guide 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.
  • FIG. 1 illustrates a television programming recommender in accordance with the present invention
  • FIG. 2 illustrates a sample table from the program database of FIG. 1 ;
  • FIG. 3 A illustrates a sample table from a Bayesian implementation of an implicit viewer profile of FIG. 1 ;
  • FIG. 3B illustrates a sample table from a viewing history used by a decision tree (DT) recommender
  • FIG. 3C illustrates a sample table from a viewer profile generated by a decision tree (DT) recommender from the viewing history of FIG. 3B;
  • FIG. 4 is a flow chart describing an exemplary mood detection and profile update process embodying principles of the present invention.
  • FIG. 5 is a flow chart describing an exemplary mood-based recommendation process embodying principles of the present invention.
  • FIG. 1 illustrates a television programming recommender 100 in accordance with the present invention.
  • the television programming recommender 100 evaluates each of the programs in an electronic programming guide (EPG) 130 to identify programs of interest to one or more viewer(s) 140.
  • EPG electronic programming guide
  • the set of recommended programs can be presented to the viewer 140 using a set-top terminal/television 160, for example, using well known on-screen presentation techniques.
  • the present invention is illustrated herein in the context of television programming recommendations, the present invention can be applied to any automatically generated recommendations that are based on a behavior history, such as a viewing history or purchase history.
  • the television programming recommender 100 generates a user profile 300, discussed below in conjunction with FIGS. 3 A and 3C, based on the current mood of the viewer, in addition to the more conventional viewing behavior of the viewer. While a conventional recommender considers a person's viewing history as a whole when generating a viewer profile, the present invention treats the viewer's preferences as a multi-class problem, and associates each viewing session with one or more current moods of the viewer. Thus, the present invention learns the viewer's preferences in accordance with various moods, and utilizes such mood-based viewing preferences to generate program recommendations. In this manner, 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.
  • the television programming recommender 100 includes one or more audio/visual capture devices 150-1 through 150-N (hereinafter, collectively referred to as audio/visual capture devices 150) that are focused on the viewer 140.
  • the audio/visual capture devices 150 may include, for example, a pan-tilt-zoom (PTZ) camera for capturing video information or an array of microphones for capturing audio information, or both.
  • the audio or video images (or both) generated by the audio/visual capture devices 150 are processed by the television programming recommender 100, in-a manner discussed below in conjunction with FIGS. 4 and 5, to identify one or more predefined moods of the viewer 140.
  • facial expression processing techniques may be employed to analyze the face of the viewer to detect, for example, if the viewer is happy or sad.
  • audio processing techniques may be employed to analyze sounds made by the viewer to detect, for example, laughing or crying, which may suggest the current mood of the viewer.
  • the mood of the viewer may be detected, for example, when profile information is recorded, or when a recommendation is about to be generated (or both).
  • the television programming recommender 100 contains a program database 200, one or more viewer profiles 300, a mood detection and profile update process 400 and a mood-based recommendation process 500, each discussed further below in conjunction with FIGS. 2 through 5, respectively.
  • the program database 200 records information for each program that is available in a given time interval.
  • One illustrative viewer profile 300 shown in FIG. 3A, is an implicit viewer profile that is typically derived from the viewing history of the viewer, based on the set of programs that the viewer liked or disliked.
  • Another exemplary viewer profile 300', shown in FIG. 3C is generated by a decision tree recommender, based on an exemplary viewing history 360, shown in FIG. 3B.
  • the mood detection and profile update process 400 processes the video or still images (or both) generated by the audio/visual capture devices 150 to sense the current mood of the viewer and to learn the viewer's preferences when in such a mood.
  • the mood-based recommendation process 500 utilizes the mood-based viewing preferences developed by the mood detection and profile update process 400 to generate program recommendations based on the derived current mood of the viewer.
  • the television program recommender 100 may be embodied as any computing device, such as a personal computer or workstation, that contains a processor 120, such as a central processing unit (CPU), and memory 110, such as RAM and/or ROM.
  • the television programming recommender 100 may be embodied as any available television program recommender, such as the TivoTM system, commercially available from Tivo, Inc., of Sunnyvale, California, or the television program recommenders described in United States Patent Application Serial No. 09/466,406, filed December 17, 1999, entitled “Method and Apparatus for Recommending Television Programming Using Decision Trees," (Attorney Docket No. 700772), United States Patent Application Serial No. 09/498,271 , filed Feb.
  • FIG. 2 is a sample table from the program database 200 of FIG. 1 that records information for each program that is available in a given time interval.
  • the program database 200 contains a plurality of records, such as records 205 through 220, each associated with a given program.
  • the program database 200 indicates the date/time and channel associated with the program in fields 240 and 245, respectively.
  • the title, genre and actors for each program are identified in fields 250, 255 and 270, respectively. Additional well-known features (not shown), such as duration, and description of the program, can also be included in the program database 200.
  • FIG. 3 A is a table illustrating an exemplary implicit viewer profile 300.
  • the implicit viewer profile 300 contains a plurality of records 305-313 each associated with a different program feature.
  • the implicit viewer profile 300 provides the corresponding positive counts in fields 335 through 345, and negative counts in field 350.
  • a positive count is provided for each distinct mood that is detected by the television programming recommender 100.
  • the various positive counts indicate the number of times the viewer watched programs having each feature while in the corresponding mood.
  • the negative counts indicate the number of times the viewer did not watch programs having each feature.
  • a number of program features are classified in the user profile 300. For example, if a given viewer watched a given sports program ten times on Channel 2 in the late afternoon, while in a happy mood, then the positive counts (happy) associated with these features in the implicit viewer profile 300 would be incremented by 10 in field 345, and the negative counts would be 0 (zero). Since the implicit viewing profile 300 is based on the user's viewing history, the data contained in the profile 300 is revised over time, as the viewing history grows. Alternatively, the implicit viewer profile 300 can be based on a generic or predefined profile, for example, selected for the user based on his or her demographics. FIG.
  • FIG. 3B is a table illustrating an exemplary viewing history 360 that is maintained by a decision tree television recommender.
  • the viewing history 360 contains a plurality of records 361-369 each associated with a different program.
  • the viewing history 360 identifies various program features in fields 370-379.
  • the values set forth in fields 370-379 may be typically obtained from the electronic program guide 130. It is noted that if the electronic program guide 130 does not specify a given feature for a given program, the value is specified in the viewing history 360 using a "?".
  • FIG. 3C is a table illustrating an exemplary viewer profile 300' that may be generated by a decision tree television recommender from the viewing history 360 set forth in FIG. 3B.
  • the decision tree viewer profile 300' contains a plurality of records 381-384 each associated with a different rule specifying viewer preferences.
  • the viewer profile 300' identifies the conditions associated with the rule in field 391 and the corresponding recommendation in field 392.
  • FIG. 4 is a flow chart describing an exemplary mood detection and profile update process 400.
  • the mood detection and profile update process 400 initially performs a test during step 410 to determine if an event has occurred to trigger the updating of the viewer profile 300, such as the end of a program or the selection of a new program channel. If it is determined during step 410 that event has not occurred to trigger the updating of the viewer profile 300, then program control returns to step 410 until such an event is detected.
  • step 410 If, however, it is determined during step 410 that an event has occurred to trigger the updating of the viewer profile 300, then the current mood(s) of the viewer 140 are detected during step 420 using known facial expression analysis techniques, such as those described in "Facial Analysis from Continuous Video with Application to Human-Computer interface,” Ph.D. Dissertation, University of Illinois at Urbana-Champaign (1999); or Antonio Colmenarez et al., "A Probabilistic Framework for Embedded Face and Facial Expression Recognition,” Proc. of the IntT Conf. on Computer Vision and Pattern Recognition,” Vol. I, 592-97, Fort Collins, Colorado (1999), each incorporated by reference herein.
  • the intensity of the facial expression may be obtained, for example, in accordance with the techniques described in United States Patent Application Serial Number 09/705, 666, filed November 3, 2000, entitled “Estimation of Facial Expression Intensity Using a Bi- Directional Star Topology Hidden Markov Model,” (Attorney Docket No. 701253), assigned to the assignee of the present invention and incorporated by reference herein.
  • facial expression analysis detect the viewer's face in the field of view of the camera included in the audio/visual capture devices 150, and identify the particular facial expression exhibited by the viewer 140, such as a smile or frown. The facial expression is used to derive the current mood of the viewer 140.
  • a test is performed during step 425 to determine if the television programming recommender 100 is a Bayesian recommender or a decision tree (DT) recommender. If it is determined during step 425 that the television programming recommender 100 is a Bayesian recommender, then the positive counts corresponding to the current mood(s) of the viewer 140 are updated in the viewer profile 300 during step 430 for the program features associated with the current program. In addition, the negative counts are optionally updated in the viewer profile 300 during step 430 for the program features associated with one or more randomly selected programs that are not watched.
  • DT decision tree
  • step 425 If, however, it is determined during step 425 that the television programming recommender 100 is a decision tree (DT) recommender, then the rules in the viewer profile 300' are filtered during step 450 to identify only those rules associated with the current mood. Thereafter, the remaining rules (after filtering) are further processed to identify the rules that are satisfied by the current program. The current program is then added to the identified rules during step 470, as follows:
  • the strength can have a value of 7 for a happy mood, 1 for a sad mood and 3 for a neutral mood.
  • the viewer profile 300' of FIG. 3C can be updated during step 470 by adding the watched program to the viewing history 360 and rebuilding the profile 300'. Thereafter, program control terminates.
  • FIG. 5 is a flow chart describing the mood-based recommendation process 500 embodying principles of the present invention.
  • the mood-based recommendation process 500 utilizes the mood-based viewing preferences developed by the mood detection and profile update process 400 to generate program recommendations based on the derived current mood of the viewer.
  • the mood-based recommendation process 500 initially obtains the electronic program guide (EPG) 130 during step 510 for the time period of interest. Thereafter, the appropriate viewer profiles 300 are obtained for the viewer during step 515. The mood-based recommendation process 500 then derives the current mood of viewer during step 520 using the audio/visual capture devices 150, in the same manner described above for the mood detection and profile update process 400.
  • EPG electronic program guide
  • a test is performed during step 525 to determine if the television programming recommender 100 is a Bayesian recommender or a decision tree (DT) recommender. If it is determined during step 525 that the television programming recommender 100 is a Bayesian recommender, then a recommendation score is calculated for each program using the feature counts only for the current mood(s) during step 530.
  • DT decision tree
  • the television programming recommender 100 is a decision tree (DT) recommender
  • the rules in the viewer profile 300' are filtered during step 540 to identify only those rules associated with the current mood. Thereafter, the remaining rules (after filtering) are applied to all the programs in the time period of interest during step 550.
  • a score is retrieved for each program from field 392 of the profile 300' corresponding to the first satisfied rule in the ordered list of the profile 300'.
  • the user is presented with the calculated recommendation score for each program during step 570, before program control terminates.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Social Psychology (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Computer Security & Cryptography (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biomedical Technology (AREA)
  • Human Computer Interaction (AREA)
  • Theoretical Computer Science (AREA)
  • Neurosurgery (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Television Systems (AREA)

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

Method and apparatus for generating recommendations based on current mood of user
Field of the Invention
The present invention relates to recommenders, such as recommenders for television programming or other content, and more particularly, to a method and apparatus for making recommendations, such as recommendations of television programs or other content, based on the current mood of the user.
Background of the Invention
The number of media options available to individuals is increasing at an exponential pace. As the number of channels available to television viewers has increased, for example, along with the diversity of the programming content available on such channels, it has become increasingly challenging for television viewers to identify television programs of interest. Historically, television viewers identified television programs of interest by analyzing printed television program guides. Typically, such printed television program guides contained grids listing the available television programs by time and date, channel and title. As the number of television programs has increased, it has become increasingly difficult to effectively identify desirable television programs using such printed guides.
More recently, television program guides have become available in an electronic format, often referred to as electronic program guides (EPGs). Like printed television program guides, EPGs contain grids listing the available television programs by time and date, channel and title. Some EPGs, however, allow television viewers to sort or search the available television programs in accordance with personalized preferences. In addition, EPGs allow for on-screen presentation of the available television programs.
While EPGs allow viewers to identify desirable programs more efficiently than conventional printed guides, they suffer from a number of limitations, which if overcome, could further enhance the ability of viewers to identify desirable programs. For example, many viewers have a particular preference towards, or bias against, certain categories of programming, such as action-based programs or sports programming. Thus, the viewer preferences can be applied to the EPG to obtain a set of recommended programs that may be of interest to a particular viewer. Thus, a number of tools have been proposed or suggested for recommending television programming. The Tivo™ system, for example, commercially available from Tivo, Inc., of Sunnyvale, California, allows viewers to rate shows using a "Thumbs Up and Thumbs Down" feature and thereby indicate programs that the viewer likes and dislikes, respectively. In this manner, the Tivo™ system implicitly derives the viewer's preferences from previous television programs that the viewer liked or did not like. Thereafter, the TiNo receiver matches the recorded viewer preferences with received program data, such as an EPG, to make recommendations tailored to each viewer.
Implicit television program recommenders generate television program recommendations based on information derived from the viewing history of the viewer, in a non-obtrusive manner. Explicit television program recommenders, on the other hand, explicitly question viewers about their preferences for program attributes, such as title, genre, actors, channel and date/time, to derive viewer profiles and generate recommendations.
While such television program recommenders identify programs that are likely of interest to a given viewer, they suffer from a number of limitations, which if overcome, could further improve the quality of the generated program recommendations. For example, conventional tools for generating television program recommendations consider a person's viewing history as a whole when generating a viewer profile and television program recommendation scores. Thus, the identified programs have no particular correlation to the current interests or mood of the viewer. A need therefore exists for a method and apparatus for generating television program recommendations that is responsive to the current mood of the viewer.
Summary of the Invention Generally, 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 thus learns the user's preferences in accordance with various moods, and thereafter utilizes such mood-based preferences to generate recommendations that are tailored to the current mood of the user. The present invention detects the user's mood by processing audio or visual information, such as the facial expression of the user. Once the mood is detected, the behavior associated with a given session can be associated with the current moods of the viewer. In one implementation, the present invention provides an electronic programming guide 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.
A more complete understanding of the present invention, as well as further features and advantages of the present invention, will be obtained by reference to the following detailed description and drawings.
Brief Description of the Drawings
FIG. 1 illustrates a television programming recommender in accordance with the present invention; FIG. 2 illustrates a sample table from the program database of FIG. 1 ;
FIG. 3 A illustrates a sample table from a Bayesian implementation of an implicit viewer profile of FIG. 1 ;
FIG. 3B illustrates a sample table from a viewing history used by a decision tree (DT) recommender; FIG. 3C illustrates a sample table from a viewer profile generated by a decision tree (DT) recommender from the viewing history of FIG. 3B;
FIG. 4 is a flow chart describing an exemplary mood detection and profile update process embodying principles of the present invention; and
FIG. 5 is a flow chart describing an exemplary mood-based recommendation process embodying principles of the present invention.
Detailed Description
FIG. 1 illustrates a television programming recommender 100 in accordance with the present invention. As shown in FIG. 1, the television programming recommender 100 evaluates each of the programs in an electronic programming guide (EPG) 130 to identify programs of interest to one or more viewer(s) 140. The set of recommended programs can be presented to the viewer 140 using a set-top terminal/television 160, for example, using well known on-screen presentation techniques. While the present invention is illustrated herein in the context of television programming recommendations, the present invention can be applied to any automatically generated recommendations that are based on a behavior history, such as a viewing history or purchase history.
According to one feature of the present invention, the television programming recommender 100 generates a user profile 300, discussed below in conjunction with FIGS. 3 A and 3C, based on the current mood of the viewer, in addition to the more conventional viewing behavior of the viewer. While a conventional recommender considers a person's viewing history as a whole when generating a viewer profile, the present invention treats the viewer's preferences as a multi-class problem, and associates each viewing session with one or more current moods of the viewer. Thus, the present invention learns the viewer's preferences in accordance with various moods, and utilizes such mood-based viewing preferences to generate program recommendations. In this manner, 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.
As shown in FIG. 1, the television programming recommender 100 includes one or more audio/visual capture devices 150-1 through 150-N (hereinafter, collectively referred to as audio/visual capture devices 150) that are focused on the viewer 140. The audio/visual capture devices 150 may include, for example, a pan-tilt-zoom (PTZ) camera for capturing video information or an array of microphones for capturing audio information, or both. The audio or video images (or both) generated by the audio/visual capture devices 150 are processed by the television programming recommender 100, in-a manner discussed below in conjunction with FIGS. 4 and 5, to identify one or more predefined moods of the viewer 140. As discussed below, facial expression processing techniques may be employed to analyze the face of the viewer to detect, for example, if the viewer is happy or sad. In addition, audio processing techniques may be employed to analyze sounds made by the viewer to detect, for example, laughing or crying, which may suggest the current mood of the viewer. The mood of the viewer may be detected, for example, when profile information is recorded, or when a recommendation is about to be generated (or both).
As shown in FIG. 1, the television programming recommender 100 contains a program database 200, one or more viewer profiles 300, a mood detection and profile update process 400 and a mood-based recommendation process 500, each discussed further below in conjunction with FIGS. 2 through 5, respectively. Generally, the program database 200 records information for each program that is available in a given time interval. One illustrative viewer profile 300, shown in FIG. 3A, is an implicit viewer profile that is typically derived from the viewing history of the viewer, based on the set of programs that the viewer liked or disliked. Another exemplary viewer profile 300', shown in FIG. 3C, is generated by a decision tree recommender, based on an exemplary viewing history 360, shown in FIG. 3B. The mood detection and profile update process 400 processes the video or still images (or both) generated by the audio/visual capture devices 150 to sense the current mood of the viewer and to learn the viewer's preferences when in such a mood. The mood-based recommendation process 500 utilizes the mood-based viewing preferences developed by the mood detection and profile update process 400 to generate program recommendations based on the derived current mood of the viewer.
The television program recommender 100 may be embodied as any computing device, such as a personal computer or workstation, that contains a processor 120, such as a central processing unit (CPU), and memory 110, such as RAM and/or ROM. In addition, the television programming recommender 100 may be embodied as any available television program recommender, such as the Tivo™ system, commercially available from Tivo, Inc., of Sunnyvale, California, or the television program recommenders described in United States Patent Application Serial No. 09/466,406, filed December 17, 1999, entitled "Method and Apparatus for Recommending Television Programming Using Decision Trees," (Attorney Docket No. 700772), United States Patent Application Serial No. 09/498,271 , filed Feb. 4, 2000, entitled "Bayesian TV Show Recommender," (Attorney Docket No. 700690) and United States Patent Application Serial No. 09/627,139, filed July 27, 2000, entitled "Three- Way Media Recommendation Method and System," (Attorney Docket No. 700913), or any combination thereof, as modified herein to carry out the features and functions of the present invention.
FIG. 2 is a sample table from the program database 200 of FIG. 1 that records information for each program that is available in a given time interval. As shown in FIG. 2, the program database 200 contains a plurality of records, such as records 205 through 220, each associated with a given program. For each program, the program database 200 indicates the date/time and channel associated with the program in fields 240 and 245, respectively. In addition, the title, genre and actors for each program are identified in fields 250, 255 and 270, respectively. Additional well-known features (not shown), such as duration, and description of the program, can also be included in the program database 200.
FIG. 3 A is a table illustrating an exemplary implicit viewer profile 300. As shown in FIG. 3, the implicit viewer profile 300 contains a plurality of records 305-313 each associated with a different program feature. In addition, for each feature set forth in column 330, the implicit viewer profile 300 provides the corresponding positive counts in fields 335 through 345, and negative counts in field 350. According to a feature of the present invention, a positive count is provided for each distinct mood that is detected by the television programming recommender 100. The various positive counts indicate the number of times the viewer watched programs having each feature while in the corresponding mood. The negative counts indicate the number of times the viewer did not watch programs having each feature. For each positive and negative program example (i.e., programs watched and not watched), a number of program features are classified in the user profile 300. For example, if a given viewer watched a given sports program ten times on Channel 2 in the late afternoon, while in a happy mood, then the positive counts (happy) associated with these features in the implicit viewer profile 300 would be incremented by 10 in field 345, and the negative counts would be 0 (zero). Since the implicit viewing profile 300 is based on the user's viewing history, the data contained in the profile 300 is revised over time, as the viewing history grows. Alternatively, the implicit viewer profile 300 can be based on a generic or predefined profile, for example, selected for the user based on his or her demographics. FIG. 3B is a table illustrating an exemplary viewing history 360 that is maintained by a decision tree television recommender. As shown in FIG. 3B, the viewing history 360 contains a plurality of records 361-369 each associated with a different program. In addition, for each program, the viewing history 360 identifies various program features in fields 370-379. The values set forth in fields 370-379 may be typically obtained from the electronic program guide 130. It is noted that if the electronic program guide 130 does not specify a given feature for a given program, the value is specified in the viewing history 360 using a "?".
FIG. 3C is a table illustrating an exemplary viewer profile 300' that may be generated by a decision tree television recommender from the viewing history 360 set forth in FIG. 3B. As shown in FIG. 3C, the decision tree viewer profile 300' contains a plurality of records 381-384 each associated with a different rule specifying viewer preferences. In addition, for each rule identified in column 390, the viewer profile 300' identifies the conditions associated with the rule in field 391 and the corresponding recommendation in field 392. For a more detailed discussion of the generating of viewer profiles in a decision tree recommendation system, see, for example, United States Patent Application Serial No. 09/466,406, filed December 17, 1999, entitled "Method and Apparatus for Recommending Television Programming Using Decision Trees," (Attorney Docket No. 700772), incorporated by reference above. FIG. 4 is a flow chart describing an exemplary mood detection and profile update process 400. As shown in FIG. 4, the mood detection and profile update process 400 initially performs a test during step 410 to determine if an event has occurred to trigger the updating of the viewer profile 300, such as the end of a program or the selection of a new program channel. If it is determined during step 410 that event has not occurred to trigger the updating of the viewer profile 300, then program control returns to step 410 until such an event is detected.
If, however, it is determined during step 410 that an event has occurred to trigger the updating of the viewer profile 300, then the current mood(s) of the viewer 140 are detected during step 420 using known facial expression analysis techniques, such as those described in "Facial Analysis from Continuous Video with Application to Human-Computer interface," Ph.D. Dissertation, University of Illinois at Urbana-Champaign (1999); or Antonio Colmenarez et al., "A Probabilistic Framework for Embedded Face and Facial Expression Recognition," Proc. of the IntT Conf. on Computer Vision and Pattern Recognition," Vol. I, 592-97, Fort Collins, Colorado (1999), each incorporated by reference herein. The intensity of the facial expression may be obtained, for example, in accordance with the techniques described in United States Patent Application Serial Number 09/705, 666, filed November 3, 2000, entitled "Estimation of Facial Expression Intensity Using a Bi- Directional Star Topology Hidden Markov Model," (Attorney Docket No. 701253), assigned to the assignee of the present invention and incorporated by reference herein. Generally, facial expression analysis detect the viewer's face in the field of view of the camera included in the audio/visual capture devices 150, and identify the particular facial expression exhibited by the viewer 140, such as a smile or frown. The facial expression is used to derive the current mood of the viewer 140. A test is performed during step 425 to determine if the television programming recommender 100 is a Bayesian recommender or a decision tree (DT) recommender. If it is determined during step 425 that the television programming recommender 100 is a Bayesian recommender, then the positive counts corresponding to the current mood(s) of the viewer 140 are updated in the viewer profile 300 during step 430 for the program features associated with the current program. In addition, the negative counts are optionally updated in the viewer profile 300 during step 430 for the program features associated with one or more randomly selected programs that are not watched.
If, however, it is determined during step 425 that the television programming recommender 100 is a decision tree (DT) recommender, then the rules in the viewer profile 300' are filtered during step 450 to identify only those rules associated with the current mood. Thereafter, the remaining rules (after filtering) are further processed to identify the rules that are satisfied by the current program. The current program is then added to the identified rules during step 470, as follows:
New Score = Current Score + x Indicated Strength
Total # Programs Covered by Rule where, the strength can have a value of 7 for a happy mood, 1 for a sad mood and 3 for a neutral mood. Alternatively, the viewer profile 300' of FIG. 3C can be updated during step 470 by adding the watched program to the viewing history 360 and rebuilding the profile 300'. Thereafter, program control terminates.
FIG. 5 is a flow chart describing the mood-based recommendation process 500 embodying principles of the present invention. The mood-based recommendation process 500 utilizes the mood-based viewing preferences developed by the mood detection and profile update process 400 to generate program recommendations based on the derived current mood of the viewer.
As shown in FIG. 5, the mood-based recommendation process 500 initially obtains the electronic program guide (EPG) 130 during step 510 for the time period of interest. Thereafter, the appropriate viewer profiles 300 are obtained for the viewer during step 515. The mood-based recommendation process 500 then derives the current mood of viewer during step 520 using the audio/visual capture devices 150, in the same manner described above for the mood detection and profile update process 400.
A test is performed during step 525 to determine if the television programming recommender 100 is a Bayesian recommender or a decision tree (DT) recommender. If it is determined during step 525 that the television programming recommender 100 is a Bayesian recommender, then a recommendation score is calculated for each program using the feature counts only for the current mood(s) during step 530.
If, however, it is determined during step 525 that the television programming recommender 100 is a decision tree (DT) recommender, then the rules in the viewer profile 300' are filtered during step 540 to identify only those rules associated with the current mood. Thereafter, the remaining rules (after filtering) are applied to all the programs in the time period of interest during step 550. A score is retrieved for each program from field 392 of the profile 300' corresponding to the first satisfied rule in the ordered list of the profile 300'. Finally, the user is presented with the calculated recommendation score for each program during step 570, before program control terminates.
It is to be understood that the embodiments and variations shown and described herein are merely illustrative of the principles of this invention and that various modifications may be implemented by those skilled in the art without departing from the scope and spirit of the invention.

Claims

CLAIMS:
1. A method for recommending one or more items, comprising the steps of: obtaining a list of available items (130); determining a current mood of a user (140); and generating a recommendation score for at least one of said available items (130) based on said current mood.
2. The method of claim 1, wherein said current mood is determined using facial expression processing techniques.
3. The method of claim 1 , wherein said current mood is determined using audio and/or video processing techniques.
4. The method of claim 1 , wherein said current mood is determined by querying said user (140).
5. The method of claim 1 , wherein said one or more items are programs, content or products.
6. A method for generating a user profile (300) indicating preferences of a user (140), comprising the steps of: monitoring one or more items that are selected by said user (140); determining a current mood of a user (140) during said selection; and recording an indication of said current mood with said item selection in said profile.
7. The method of claim 6, wherein said user profile (300) is associated with a program content recommender (100).
8. The method of claim 6, wherein said step of recording an indication of said item selection further comprises the step of incrementing one or more positive feature counts associated with said item and said current mood.
9. The method of claim 6, wherein said current mood is determined by querying said user (140).
10. The method of claim 6, wherein said one or more items are programs, content or products.
11. A system (100) for recommending one or more items, comprising: a memory (110) for storing computer readable code; and a processor (120) operatively coupled to said memory (110), said processor (120) configured to: obtain a list of available items (130); - ι determine a current mood of a user (140); and generate a recommendation score for at least one of said available items (130) based on said current mood.
12. The system (100) of claim 11 , wherein said current mood is determined using audio and/or video processing techniques.
13. The system (100) of claim 11, wherein said current mood is determined by querying said user (140).
14. A system (100) for generating a user profile (300) indicating preferences of a user (140), comprising: a memory (110) for storing computer readable code; and a processor (120) operatively coupled to said memory (110), said processor (120) configured to: monitor one or more items that are selected by said user (140); determine a current mood of a user (140) during said selection; and record an indication of said current mood with said item selection in said profile.
15. The system ( 100) of claim 14, wherein said processor ( 120) is further configured to increment one or more positive feature counts associated with said item and said current mood.
16. The system (100) of claim 14, wherein said one or more items are programs, content or products.
PCT/EP2001/013453 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on current mood of user WO2002043391A1 (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2002544983A JP2004515128A (en) 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on a user's current mood
EP01994683A EP1340375A1 (en) 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on current mood of user
KR1020027009314A KR100876300B1 (en) 2000-11-22 2001-11-16 Method and apparatus for generating recommendations based on a user's current mood

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 (1)

Publication Number Publication Date
WO2002043391A1 true WO2002043391A1 (en) 2002-05-30

Family

ID=24885424

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2001/013453 WO2002043391A1 (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)

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005022910A1 (en) * 2003-08-29 2005-03-10 Koninklijke Philips Electronics N.V. User-profile controls rendering of content information
EP1610479A2 (en) * 2004-06-11 2005-12-28 Samsung Electronics Co., Ltd. Method of and apparatus for automatically selecting broadcast service according to physiological state of user
WO2008134171A2 (en) * 2007-04-23 2008-11-06 Microsoft Corporation Content viewing session
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
WO2012064565A2 (en) 2010-11-12 2012-05-18 Microsoft Corporation Audience-based presentation and customization of content
WO2012138667A1 (en) 2011-04-05 2012-10-11 Netflix, Inc. Recommending digital content based on implicit user identification
WO2012158234A3 (en) * 2011-02-27 2013-03-21 Affectiva, Inc. Video recommendation based on affect
CN103942243A (en) * 2013-01-21 2014-07-23 三星电子株式会社 Display apparatus and method for providing customer-built information using the same
DK178068B1 (en) * 2014-01-21 2015-04-20 Bang & Olufsen As Mood based recommendation
US9123061B2 (en) 2010-03-24 2015-09-01 Disney Enterprises, Inc. System and method for personalized dynamic web content based on photographic data
US9200234B1 (en) 2009-10-21 2015-12-01 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
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
US9390714B2 (en) 2010-11-22 2016-07-12 Lg Electronics Inc. Control method using voice and gesture in multimedia device and multimedia device thereof
WO2016203178A1 (en) * 2015-06-18 2016-12-22 Spideo Method and system for recommending content to a user based on one or more parameters that can be activated by the user from a corresponding interface
US10056742B1 (en) 2013-03-15 2018-08-21 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
US10289898B2 (en) 2010-06-07 2019-05-14 Affectiva, Inc. Video recommendation via affect
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
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
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
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
US12015251B1 (en) 2022-08-22 2024-06-18 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant

Families Citing this family (36)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
JP5042883B2 (en) * 2008-02-28 2012-10-03 株式会社日立製作所 Content recommendation device and content recommendation method
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
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
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
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
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
CA2775700C (en) 2012-05-04 2013-07-23 Microsoft Corporation Determining a future portion of a currently presented media program
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
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
KR20150062647A (en) 2013-11-29 2015-06-08 삼성전자주식회사 Image processing apparatus and control method thereof
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
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
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
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 (5)

* Cited by examiner, † Cited by third party
Title
EDWARDS A D N: "Progress in sign language recognition", WORKSHOP PROCEEDINGS, GESTURE AND SIGN LANGUAGE IN HUMAN-COMPUTER INTERACTION, BIELEFELD, GERMANY, 17-19 SEPT. 1997, 1998, Berlin, Germany, Springer-Verlag, Germany, pages 13 - 21, XP008001046, ISBN: 3-540-64424-5 *
GUTTA S ET AL: "TV CONTENT RECOMMENDER SYSTEM", PROCEEDINGS SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI 2000), AUSTIN, TX, USA, 30 July 2000 (2000-07-30) - 3 August 2000 (2000-08-03), pages 1121 - 1122, XP001031541 *
HANSEN J P ET AL: "Eye-gaze control of multimedia systems", PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTIONS (HCI INTERNATIONAL'95), SYMBIOSIS OF HUMAN AND ARTIFACT. FUTURE COMPUTING AND DESIGN FOR HUMAN-COMPUTER INTERACTION, TOKYO, JAPAN, 9-14 JULY 1995, 1995, Amsterdam, Netherlands, Elsevier, Netherlands, pages 37 - 42 Vol.A, XP008001050, ISBN: 0-444-81795-6 *
KANEKO M ET AL: "Processing of face images and its applications", IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, MARCH 1999, INST. ELECTRON. INF. & COMMUN. ENG, JAPAN, vol. E82-D, no. 3, pages 589 - 600, XP001032065, ISSN: 0916-8532 *
NAKATSU R ET AL: "Emotion recognition and its application to computer agents with spontaneous interactive capabilities", HUMAN-COMPUTER INTERACTION: ERGONOMICS AND USER INTERFACES. PROCEEDINGS OF HCI INTERNATIONAL '99 (8TH INTERNATIONAL CONFERENCE ON HUMAN-COMPUTER INTERACTION), 1999, Mahwah, NJ, USA, Lawrence Erlbaum Associates, USA, pages 142 - 146 vol.2, XP008001048, ISBN: 0-8058-3391-9 *

Cited By (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005022910A1 (en) * 2003-08-29 2005-03-10 Koninklijke Philips Electronics N.V. User-profile controls rendering of content information
EP1610479A2 (en) * 2004-06-11 2005-12-28 Samsung Electronics Co., Ltd. Method of and apparatus for automatically selecting broadcast service according to physiological state of user
EP1610479A3 (en) * 2004-06-11 2006-01-18 Samsung Electronics Co., Ltd. Method of and apparatus for automatically selecting broadcast service according to physiological state of user
WO2008134171A2 (en) * 2007-04-23 2008-11-06 Microsoft Corporation Content viewing session
WO2008134171A3 (en) * 2007-04-23 2009-03-12 Microsoft Corp Content viewing session
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
WO2009150347A1 (en) * 2008-05-16 2009-12-17 Alcatel Lucent Method and system for setting up an on-demand video service program guide based on the mood of the user
US9200234B1 (en) 2009-10-21 2015-12-01 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
US10276279B1 (en) 2009-10-21 2019-04-30 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
US10580551B1 (en) 2009-10-21 2020-03-03 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
US9458404B1 (en) 2009-10-21 2016-10-04 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
US11783963B1 (en) 2009-10-21 2023-10-10 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
US11456088B1 (en) 2009-10-21 2022-09-27 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
US10062475B1 (en) 2009-10-21 2018-08-28 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
US11101053B1 (en) 2009-10-21 2021-08-24 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
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
EP2638702A4 (en) * 2010-11-12 2014-04-16 Microsoft Corp Audience-based presentation and customization of content
WO2012064565A2 (en) 2010-11-12 2012-05-18 Microsoft Corporation Audience-based presentation and customization of content
EP2638702A2 (en) * 2010-11-12 2013-09-18 Microsoft Corporation Audience-based presentation and customization of content
US9390714B2 (en) 2010-11-22 2016-07-12 Lg Electronics Inc. Control method using voice and gesture in multimedia device and multimedia device thereof
WO2012158234A3 (en) * 2011-02-27 2013-03-21 Affectiva, Inc. Video recommendation based on affect
EP2695038A4 (en) * 2011-04-05 2014-09-24 Netflix Inc Recommending digital content based on implicit user identification
WO2012138667A1 (en) 2011-04-05 2012-10-11 Netflix, Inc. Recommending digital content based on implicit user identification
EP2695038A1 (en) * 2011-04-05 2014-02-12 Netflix, Inc. Recommending digital content based on implicit user identification
US10777338B1 (en) 2012-02-13 2020-09-15 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
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
US10102947B1 (en) 2012-02-13 2018-10-16 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
US10418156B1 (en) 2012-02-13 2019-09-17 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
US10943713B1 (en) 2012-02-13 2021-03-09 Encore Wire Corporation Method of manufacture of electrical wire and cable having a reduced coefficient of friction and required pulling force
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
CN103942243A (en) * 2013-01-21 2014-07-23 三星电子株式会社 Display apparatus and method for providing customer-built information using the same
EP2757799A1 (en) * 2013-01-21 2014-07-23 Samsung Electronics Co., Ltd Display apparatus and method for providing customer-built information using the same
US11522348B1 (en) 2013-03-15 2022-12-06 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
US10847955B1 (en) 2013-03-15 2020-11-24 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
US10680418B1 (en) 2013-03-15 2020-06-09 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
US11444440B1 (en) 2013-03-15 2022-09-13 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
US10056742B1 (en) 2013-03-15 2018-08-21 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant
DK178068B1 (en) * 2014-01-21 2015-04-20 Bang & Olufsen As Mood based recommendation
WO2016203178A1 (en) * 2015-06-18 2016-12-22 Spideo Method and system for recommending content to a user based on one or more parameters that can be activated by the user from a corresponding interface
FR3037757A1 (en) * 2015-06-18 2016-12-23 Spideo METHOD AND SYSTEM FOR RECOMMENDING A CONTENT USER FROM PARAMETER (S) ACTIVATED BY THE USER FROM A CORRESPONDING INTERFACE.
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
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
US12015251B1 (en) 2022-08-22 2024-06-18 Encore Wire Corporation System, method and apparatus for spray-on application of a wire pulling lubricant

Also Published As

Publication number Publication date
KR20020070490A (en) 2002-09-09
EP1340375A1 (en) 2003-09-03
KR100876300B1 (en) 2008-12-31
CN100423574C (en) 2008-10-01
CN1395798A (en) 2003-02-05
JP2004515128A (en) 2004-05-20

Similar Documents

Publication Publication Date Title
KR100876300B1 (en) Method and apparatus for generating recommendations based on a user's current mood
EP1337914B1 (en) Method and apparatus for obtaining auditory and gestural feedback in a recommendation system
US7441260B1 (en) Television program recommender with automatic identification of changing viewer preferences
US20020178440A1 (en) Method and apparatus for automatically selecting an alternate item based on user behavior
KR100838098B1 (en) Method and apparatus for automatic generation of query search terms for a program recommender
US20020075320A1 (en) Method and apparatus for generating recommendations based on consistency of selection
US20060225088A1 (en) Generation of implicit tv recommender via shows image content
WO2002080551A1 (en) Method and apparatus for generating recommendations for a plurality of users
JP2004515979A (en) Method and apparatus for selective updating of a user profile
WO2002037851A2 (en) Method and apparatus for generating television program recommendations based on prior queries
EP1435048A2 (en) Filtering of recommendations employing personal characteristics of users
EP1516489A1 (en) Anticipatory content augmentation
EP1634442B1 (en) Transformation of recommender scores depending upon the viewed status of tv shows

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): CN JP KR

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR

REEP Request for entry into the european phase

Ref document number: 2001994683

Country of ref document: EP

WWE Wipo information: entry into national phase

Ref document number: 2001994683

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2002 544983

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 1020027009314

Country of ref document: KR

WWE Wipo information: entry into national phase

Ref document number: 018040128

Country of ref document: CN

WWP Wipo information: published in national office

Ref document number: 1020027009314

Country of ref document: KR

121 Ep: the epo has been informed by wipo that ep was designated in this application
WWP Wipo information: published in national office

Ref document number: 2001994683

Country of ref document: EP