WO2007034355A2 - Method and apparatus for updating user profile - Google Patents

Method and apparatus for updating user profile Download PDF

Info

Publication number
WO2007034355A2
WO2007034355A2 PCT/IB2006/053220 IB2006053220W WO2007034355A2 WO 2007034355 A2 WO2007034355 A2 WO 2007034355A2 IB 2006053220 W IB2006053220 W IB 2006053220W WO 2007034355 A2 WO2007034355 A2 WO 2007034355A2
Authority
WO
WIPO (PCT)
Prior art keywords
user
program
interest
user profile
content feature
Prior art date
Application number
PCT/IB2006/053220
Other languages
French (fr)
Other versions
WO2007034355A3 (en
Inventor
Xiaowei Shi
Freddy Snijder
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.
Publication of WO2007034355A2 publication Critical patent/WO2007034355A2/en
Publication of WO2007034355A3 publication Critical patent/WO2007034355A3/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00Commerce
    • G06Q30/02Marketing; Price estimation or determination; Fundraising
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/43Processing 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
    • H04N21/442Monitoring 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
    • H04N21/44213Monitoring of end-user related data
    • H04N21/44222Analytics of user selections, e.g. selection of programs or purchase activity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/4508Management of client data or end-user data
    • H04N21/4532Management of client data or end-user data involving end-user characteristics, e.g. viewer profile, preferences
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4661Deriving a combined profile for a plurality of end-users of the same client, e.g. for family members within a home
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4667Processing of monitored end-user data, e.g. trend analysis based on the log file of viewer selections
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/466Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H04N21/4668Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47End-user applications
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/84Generation or processing of descriptive data, e.g. content descriptors
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/41Structure of client; Structure of client peripherals
    • H04N21/4104Peripherals receiving signals from specially adapted client devices
    • H04N21/4108Peripherals receiving signals from specially adapted client devices characterised by an identification number or address, e.g. local network address
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45Management 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
    • H04N21/4508Management of client data or end-user data
    • H04N21/4524Management of client data or end-user data involving the geographical location of the client

Definitions

  • the present invention relates to an information recommendation system, and more particularly, to a method and apparatus for updating user profile in the information recommendation system.
  • a user profile in the information recommendation system is also required to change correspondingly. Therefore, how to modify the user profile in the information recommendation system dynamically based on the user's interests (preference) and recommend the user for the contents that the user is really interested in, is a problem to be resolved now.
  • a user's preference and weight of each content feature of a specific program in the user profile are modified in terms of the action that the user watches the specific program.
  • the action involves a period in which the user watches the specific program, and times that the user watches or deletes the program with a specific content feature.
  • the content feature may refer to each actor's name, the director's name contained in the program or type of the program (e.g. a literary movie, a love story movie or a horror movie and so on).
  • the content feature may be collected from information sources such as broadcast, TV or Internet and so on. Typically, it is extracted from DTV electronic program guide (EPG) that is sent to the user along with programs.
  • EPG electronic program guide
  • the information recommendation system is often used as a DTV program recommendation system for a family.
  • a family is made up of several members, and each member, as a user, usually shows a personal preference on a certain TV program.
  • the conventional information recommendation system recommends TV programs in terms of a set of preferences of all family members in a user profile.
  • a member of the family may expect to watch some TV programs alone, instead of sharing with other family members. Namely, each member as a user expects his or her own private space.
  • a method for updating a user profile comprising the steps of: monitoring an action of a user regarding a program in play; acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
  • An apparatus for updating user profile comprising: a user interaction unit, for monitoring an action of a user regarding a program in play; an interest analysis unit, for acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
  • An information recommendation system comprising: a program receiving unit, for receiving program information; a user profile management unit, for storing a user profile which comprises at least two preferences of at least one content feature for a user; a selecting unit, for selecting a program potentially preferred by the user from the program information according to the user profile and recommending the selected program to the user; a user interaction unit, for monitoring the action of the user regarding a program in play; an interest analysis unit, for acquiring the user's interest in program content according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
  • a user's at least two preferences of at least one content feature are included in the user profile according to the method for updating the user profile and the apparatus thereof in the present invention. Based on the at least two preferences, the method and the apparatus thereof not only can recommend TV programs to a group of users who enjoy the TV programs together, but also can provide TV programs to an individual user upon his own preference for his private life space.
  • Fig. 1 is a schematic diagram illustrating the configuration of an information recommendation system according to an embodiment of the present invention
  • Fig. 2 is a schematic diagram illustrating storage of each user profile of a group of users according to an embodiment of the present invention
  • Fig. 3 is a flowchart illustrating a method for recommending information to a user according to an embodiment of the present invention
  • Fig. 4 is a flowchart illustrating a method for updating a user profile according to an embodiment of the present invention.
  • Fig. 5 is a schematic diagram illustrating an application of a program recommendation system according to an embodiment of the present invention.
  • FIG. 1 is a schematic diagram illustrating the configuration of an information recommendation system according to an embodiment of the present invention.
  • the system 100 comprises a user interaction unit 103, an interest analysis unit 104, a user profile modification unit 106 and a user profile management unit 107, wherein the user profile includes a user's at least two preferences and weights of at least one content feature.
  • the content feature refers to each actor's name and director's name contained in the program, and type of the program (e.g. a literary movie, a love story movie or a horror movie and so on).
  • the content feature may be collected from information sources such as broadcast, TV, Internet or the like. Typically, it is extracted from DTV electronic program guide (EPG) that is sent to the user along with programs.
  • EPG electronic program guide
  • the content feature in the user profile may only refer to one item, such as an actor' s name.
  • the content feature in the user profile may refer to a plurality of items, and correspondingly, the result to be recommended thus is more precise.
  • the preference of content feature in the user profile for each user includes two parts: an individual preference indicating the user's preference of the programs that he or she enjoys alone, each program having a particular content feature, and a common preference indicating the user's preference of the programs that he or she watches together with others, each program having a particular content feature.
  • Table 1 shows the individual preference and the common preference for each member in a group of users.
  • Table 1 shows data about the individual preference and the common preference of every content feature for each member in the group of users.
  • the group is made up of father, mother, child 1 and child 2.
  • Each member shows different individual preference and common preference of every content feature.
  • the available TV programs include A-K, i.e. 11 features in total, wherein A is used for indicating English programs or programs mainly in English; B, C and D are used for indicating programs relating to computer, math, and chemistry respectively; E is used for indicating the programs concerning romantic movies; F and G are used for indicating cartoons and TV series respectively; H is used for indicating news programs; I is used for indicating commercial advertisements inserted between regular programs; J is used for indicating comedies, and K is used for indicating sport programs.
  • A is used for indicating English programs or programs mainly in English
  • B, C and D are used for indicating programs relating to computer, math, and chemistry respectively
  • E is used for indicating the programs concerning romantic movies
  • F and G are used for indicating cartoons and
  • Each above-mentioned preference is the user' s feeling of every content feature, and may be preset by providers with a scale, e.g. [-1, +1].
  • the figures in the table show each member's preference of a certain feature.
  • the preferences of the content feature for each member in the group of users are indicated or scaled by figures.
  • child 1 likes watching cartoon alone rather than sharing with others, and thus his or her individual preference of cartoons is set to 0.8, while the common preference is set to 0. Since he or she is not interested in either TV series or news, the corresponding values are set to 0 accordingly.
  • child 1 hates commercial advertisements, thus the preference of the feature is set to -0.6.
  • the values could be set in terms of their personal preferences.
  • the weight indicates influence, which the various content features such as actors, directors, type of programs and so on exert, over a selected result when the user selects a program.
  • weights of all actors may be the same, the weights of all types of programs may be the same, and the weights of all directors may also be the same.
  • the weights may be preset by providers within a scale, e.g. [0, 100].
  • the weights and the preferences in the user profile may be regarded as a history record for recording the programs the user watched. There is, for example, another history record for recording the times that the user watches or deletes a program having the particular content feature while the user watches the program.
  • the user interaction unit 103 is used for monitoring an action of a user on a program in play.
  • the action involves a period in which the user watches a specific TV program.
  • the user interaction unit 103 as an interactive bridge between the user and the recommendation system, receives feedback information from the user with respect to a program, which the user watches, and provides the user with a recommendation information list for the user's selection of programs to be watched.
  • the feedback information includes the action of the user.
  • the recommendation information list is shown in the following table 2:
  • the interest analysis device 104 obtains the user's interest regarding the program, wherein the interest corresponds to the content feature preset in the program. (WD - ⁇ )
  • the scale of the interest may be expressed as ' ⁇ *10 , wherein WD 1 is used
  • is used for indicating a threshold preset by a provider, for example.
  • the value of the threshold is usually set as 0.5 RD 1 , wherein RD 1 is a predetermined duration of the specific program to be played.
  • the user profile modification unit 106 modifies the individual preference, the common preference and the corresponding weight of a content feature in the user profile, to update the user profile dynamically and more precisely (See the following description in connection with Figure 3).
  • the user profile management unit 107 manages user profiles. As described above, the user profile generally includes each member's individual preference, common preference, and the corresponding weight of the content features.
  • the system further comprises a program receiving unit 101, a selecting unit 102 and an interest adjusting unit 105.
  • the program receiving unit 101 is used for receiving programs or information related to the programs, such as DTV EPG corresponding to the programs and so on.
  • the selecting unit 102 selects the user's probably favourite programs, and presents the information related to the programs that the user is likely to prefer, in the recommendation information list (See the following description in connection with Figure 4).
  • the interest adjusting unit 105 adjusts the interest obtained from the action of the user, based on the individual preference and common preference of the corresponding content feature in the user profile.
  • the scale of the interest could be adjusted by a different coefficient, which, in the range of, for example [0.1 , 1] , may be preset by providers.
  • the scale of the interest may be multiplied by a coefficient 0.9 or 1. While regarding a content feature that the user is generally unlikely to prefer (low preference), the scale of the interest may be multiplied by a coefficient 0.1 or less, to reduce the effect of the interest on the individual preference and common preference, since it seems that the user watches such a program with the content feature occasionally or in case of accompanying his or her friends.
  • the effect of the interest on the user profile will be strengthened if a special individual preference or common preference of certain content feature for the user is present in the user profile.
  • the range of the adjustment coefficient is not limited to [0.1, 1], and may be above 1.
  • the interest adjusting unit 105 is optional. Namely, based on the analyzed result from the interest analysis unit 104, the user profile modification unit 106 may modify the user profile directly.
  • each user profile of a group of users is shown in Figure 2.
  • a group made up of a plurality of users e.g. in a family made up of several members
  • each member shows his or her personal preferences on various TV programs, while all members present common preferences on certain TV programs.
  • one member is likely to enjoy some TV programs alone, and would not like to share the TV programs with other members.
  • each of the members is allotted a private storage bubble 220, 230, 240 and 250 respectively, for storing each member's individual profile together with the contents or list of the corresponding recommended TV programs.
  • All members have a common storage bubble 210 for storing each member's common profile together with the contents or list of the corresponding recommended TV programs.
  • the storage bubbles correspond to different storage elements. Alternately, the storage bubbles may correspond to different folders in the same storage element, or different files in the same storage element.
  • each member's user profile includes two parts: individual profile, such as individual profiles 225, 235, 245 and 255, and common profile 215.
  • the individual profile includes the member' s individual preference and the weight of at least one content feature.
  • the common profile includes the common preference and the weight of at least one content feature for each member in the group of users. All members' common profiles may be stored together, or separately.
  • the user profile may be established and initialized by the user. Obviously, there exists other ways to form the user profile.
  • the user profile in the recommendation system can be initialized by a manufacturer in terms of the user' s basic information (e.g. gender, age and so on).
  • a manufacturer may provide an initialization file of the user profile for different age groups as shown in table 3.
  • the user profile is a data file in a specific format, and is updated by the program provider periodically or by each member in the group of users if necessary.
  • the initialization file shown in table 3 may be regarded as a reference for the user to set individual preference and common preference.
  • the user data in the user profile is set by each member of the family using an input device, and stored into a device such as a set-top-box.
  • the user profile can be stored in various ways.
  • the user profile may be stored in a remote server held by the program provider via cable TV networks or LAN (Local Area Networks), and there provides statistics data, obtained from the samples of a plurality of families in the remote server, as a reference of the user profile.
  • information on the situations that each member in the family watches TV programs can be obtained automatically by the means of a monitor located close to the TV set, and sent to the set-too-box or transmitted to the remote server via networks for establishment of the user profile by statistics analysis.
  • Fig. 3 is a flowchart showing a method for recommending information to a user according to an embodiment of the present invention.
  • step S310 information related to a TV program is received.
  • the content feature of the TV program such as actor 1 is preset by the program provider and transmitted to the user in form of digital TV electronic program guide (EPG) along with the program.
  • EPG digital TV electronic program guide
  • step S320 a determination is made whether the content feature included in the TV program matches with the common preferences of all users (for example, all members in a family) in a group of users. Namely, no user dislikes these content features.
  • step S320 If the determination in step S320 shows that the recommendation requirement is matched, it indicates that all users in the group are interested in the TV program, and they all like sharing with other users.
  • step S330 the TV program content or list is stored into a common storage bubble for recommending to all users. For example, if a TV program including the content feature C as shown in table 1 matches the common preference of all users, the TV program content is stored into the common storage bubble.
  • step S320 determines whether the TV program content matches the common preference of an individual user.
  • step S340 If the determination in step S340 is YES, the TV program content or recommendation information is stored in the user's private storage bubble in step S360.
  • a TV program including the content feature D matches child 2's common preference, but child 1, father and mother do not like the program, so the TV program content is stored in the private storage bubble of child 2.
  • the TV program content or recommendation information stored in the user's private storage bubble in step S 360 may include an identifier for indicating that the TV program content or recommendation information is recommended according to the user's common preference. It will be appreciated by those skilled in the art that each piece of program information recommended to users may include an identifier (for example, a distinguishing colour) for indicating the ground on which the program is recommended, such as a user' s individual preference, a user' s common preference and so on. According to the identifier, the recommendation apparatus may distinguish the user' s preference. If the determination in step S340 is NO, i.e. the TV program content does not match an individual user's common preference, it is to be determined in step S350 whether the TV program content matches the individual user's individual preference. If YES, the TV program content is stored into the user's private storage bubble in step S360.
  • step S370 a determination is made whether there are still other users in the group of users. If yes, the process returns to step S340, to determine whether the TV program content matches another individual user's common preference.
  • Fig. 4 is a flowchart showing a method for updating a user profile according to an embodiment of the present invention.
  • a user profile is established.
  • the user profile includes two parts, an individual profile and a common profile, which include a user's individual preferences and common preferences of a plurality of content features and the corresponding weights respectively (as shown in table 1).
  • a detailed description is made to specific preferences and weights of related content features in an application No. 200410095756.5 titled " a method and apparatus for updating user profile," Chinese patent, filed with Chinese Patent Office on November 18, 2004 by KONINKLIJKE PHILIPS ELECTRONICS N. V., which is incorporated by reference herein.
  • step 420 action of the user on a program in play is monitored.
  • the program in play may be one selected from a recommendation information list by the user.
  • the action includes a program recommendation information source, from which the played program the user is watching originates, for example, from a private storage bubble or from a common storage bubble.
  • the action may further include the duration of a program having one or more preset particular content features, and times that the user watches or deletes a program having the particular content feature while the user watches the program.
  • the program in play is movie A
  • the type of movie A e.g. literary movie
  • the program may further include other one or more content features, such as actor 1, actor 2 and so on.
  • the content features may be preset by program providers and transmitted to users in form of digital TV electronic program guide (EPG) along with programs.
  • EPG digital TV electronic program guide
  • step 470 If the determination is YES, it indicates that an individual user prefers the TV program content, and it is to determine the user corresponding to the private storage bubble (e.g. father) in step 470. In step 480, the individual preference of the user (father) is modified.
  • the modification process may be referred to the application No. 200410095756.5 filed by KONINKLIJKE PHILIPS ELECTRONICS N.V, which is incorporated by reference herein.
  • the predetermined duration is set to 2 hours ( RD 1 )
  • the threshold is set to 0.5 hours ( ⁇ )
  • the father spends 1.5 hours( WD 1 ) in watching the program.
  • the father's interest in the program is calculated to be 5 by the
  • RD 1 preference adjusting coefficient is 0.01
  • the father's adjusted individual preference for the sport program is calculated to be 0.85 (0.8+0.01*5) based on the interest.
  • Step S470 is an optional step.
  • each user' s individual preference may be stored into the private storage bubble of the user in the group of users . If it is determined in step S430 that the recommendation information of the TV program, which the user is watching, is from a private storage bubble, the process proceeds to step S480 directly, to modify the individual preference stored in the private storage bubble.
  • step S430 If the TV program content, which the user is watching, does not exist in a private storage bubble in step S430, it indicates that the TV program content exists in a common storage bubble, and it is required to acquire the interests of all users and modify the individual preference or common preference of each user in the group.
  • step S440 it is determined whether the user is watching the TV program content by means of a private device. The determination of a private device is described hereafter with reference to Fig.5.
  • step S480 the user's individual interest is determined in step S480, and the user's individual preference is modified according to the individual interest in step S490.
  • step S440 it is determined that the user is not watching the TV program by means of a private device, it indicates that there may be several users watching the TV program from the common storage bubble by using a common device.
  • the interest of the user group is further required to be calculated, so as to make further modification to the common preference of each user in the group.
  • step S450 the interest of the group is calculated.
  • a method for estimating total interests of a group of users is described in detail in an patent application No. 200510073942.3, titled “a method and apparatus for estimating the total interests of a group of users", filed with Chinese Patent Office in May 27, 2005 by KONINKLIJKE PHILIPS ELECTRONICS N.V, which is incorporated by reference herein.
  • the interest may be expressed as i *10 , wherein WD 1 is the period in
  • is a preset threshold which may be provided by providers in advance, and generally as 0.5 RD 1 , where RD 1 indicates the predetermined duration of the specific program.
  • the interest is adjusted according to the common preference of the corresponding content feature in user profile of each user.
  • the interest may be adjusted with a different coefficient, wherein the coefficient may be preset by providers with a scale, e.g. [0.1,1].
  • TV series A is as an example.
  • a content feature for the TV series i.e. actor 1
  • the common preference in a user profile is 0.8, thus it indicates that the user likes the content feature actor 1 or is interested in the content feature actor 1 usually.
  • a higher coefficient may be used to adjust the interest. For example, if the interest is 5 initially and the coefficient is 0.9, the adjusted interest of the user with respect to actor 1 becomes 4.5. A small adjustment is made, and thus the interest has a reduced influence on the user profile to a very limited extent.
  • step S470 the common preference of each user in the group of users is modified according to the determined interest. The whole process for updating user profile of the present invention is completed.
  • Step S460 is an optional step. Namely, in step S470, the common preference of each user in the group may be modified according to the user's action.
  • Fig. 5 is a schematic diagram illustrating an application of a program recommendation system according to an embodiment of the present invention. As shown in the figure, in a group made up of a plurality of users, for example, in a family made up of several members, each member has his or her own private space, such as bedroom, and all members share a public space, such as living room.
  • Each room has its particular content receiving devices, such as TV sets 510, 520, 530 and 550 for receiving TV programs, CD player 540 for receiving audio contents and so on. All devices may be connected to a family server 560, which stores TV programs, audio contents or list and recommendation information. When a member wants to watch TV programs or listen to audio contents by a receiving device, he or she may download the related contents by establishing a connection to the server 560.
  • All devices may be connected to a family server 560, which stores TV programs, audio contents or list and recommendation information.
  • the server 560 stores device information 565 as well, for managing all receiving devices connected thereto.
  • the device information includes device ID, device name, device location (room) and device owner (or a member who uses the device most frequently) and other information. For example, it may be known from the device information that the TV set 530 with device ID 003 is located in bedroom 2, and the owner of the room is child 1.
  • a receiving device such as a TV set in the bedroom of each member, is used by the member individually, and a TV set in the living room may be used by several members.
  • the TV set with device ID 003 is usually used by child 1 individually, thus the watched TV programs may be preferred by child 1, and possibly are what child 1 does not want to share with other family members or are what other family members do not like.
  • the TV set with device ID 001 is usually used by one or more of the members together, i.e. the father, the mother, child 1 and child 2, and hence the watched TV programs shall be what all members like or what one member likes and wants to share with other family members.
  • a device usually used by an individual user is referred to be a private device, and a device usually used by two or more users is referred to be a public device.
  • the device ID of a device connected to the server 560 it may be determined which device is being used for a user to watch a TV program, and determined whether it is a private device or a public device.
  • a user profile may include various other preferences, in addition to individual preferences and common preferences. Namely, a user profile may include more than two preferences for different purposes, for example, a portion for personal privacy and different common preferences of a content feature for different groups of users.

Abstract

The present invention provides a method for updating a user profile, comprising the steps of monitoring the action of a user regarding a program in play; acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest. The present invention can not only recommend to a group of users with TV programs preferred by all of them, but also recommend a favorite program preferred by each individual member.

Description

METHOD AND APPARATUS FOR UPDATING USER PROFILE
FIELD OF THE INVENTION
The present invention relates to an information recommendation system, and more particularly, to a method and apparatus for updating user profile in the information recommendation system.
BACKGROUND OF THE INVENTION
With the development of modern communication technology, people may acquire massive information at any moment. However, people are often at a loss when facing the rapid expansion of information, there is, therefore, an urgent need for a tool, e.g. individual information recommendation system, to help people quickly search what they are really interested in.
In order to meet the constant change of the user's interests, a user profile in the information recommendation system is also required to change correspondingly. Therefore, how to modify the user profile in the information recommendation system dynamically based on the user's interests (preference) and recommend the user for the contents that the user is really interested in, is a problem to be resolved now.
At present, a user's preference and weight of each content feature of a specific program in the user profile are modified in terms of the action that the user watches the specific program. The action involves a period in which the user watches the specific program, and times that the user watches or deletes the program with a specific content feature.
The content feature may refer to each actor's name, the director's name contained in the program or type of the program (e.g. a literary movie, a love story movie or a horror movie and so on). The content feature may be collected from information sources such as broadcast, TV or Internet and so on. Typically, it is extracted from DTV electronic program guide (EPG) that is sent to the user along with programs.
The information recommendation system is often used as a DTV program recommendation system for a family. Generally, a family is made up of several members, and each member, as a user, usually shows a personal preference on a certain TV program. There is a need for a program for all members who are likely to enjoy the program together (shared life space), and also a need for a specific TV program for a member who would like to watch it alone (private life space).
The conventional information recommendation system recommends TV programs in terms of a set of preferences of all family members in a user profile. However, a member of the family may expect to watch some TV programs alone, instead of sharing with other family members. Namely, each member as a user expects his or her own private space.
Therefore, there is a need for an improved method and apparatus for updating user profile and an information recommendation system thereof, which not only can recommend TV programs to all family members who enjoy the TV programs together, but also can provide TV programs to each member upon his own preference.
OBJECT AND SUMMARY OF THE INVENTION
It is an object of the present invention to provide a method and apparatus for updating user profile and an information recommendation system thereof, which not only can recommend TV programs to a group of users who enjoy the TV programs together, but also can provide TV programs to an individual user upon his own preference.
A method for updating a user profile according to an embodiment of the present invention, comprising the steps of: monitoring an action of a user regarding a program in play; acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
An apparatus for updating user profile according to an embodiment of the present invention, the apparatus comprising: a user interaction unit, for monitoring an action of a user regarding a program in play; an interest analysis unit, for acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
An information recommendation system according to an embodiment of the present invention, comprising: a program receiving unit, for receiving program information; a user profile management unit, for storing a user profile which comprises at least two preferences of at least one content feature for a user; a selecting unit, for selecting a program potentially preferred by the user from the program information according to the user profile and recommending the selected program to the user; a user interaction unit, for monitoring the action of the user regarding a program in play; an interest analysis unit, for acquiring the user's interest in program content according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
It may be concluded that a user's at least two preferences of at least one content feature are included in the user profile according to the method for updating the user profile and the apparatus thereof in the present invention. Based on the at least two preferences, the method and the apparatus thereof not only can recommend TV programs to a group of users who enjoy the TV programs together, but also can provide TV programs to an individual user upon his own preference for his private life space.
Other objects and attainments together with a fuller understanding of the invention will become apparent and appreciated by referring to the following description and claims taken in conjunction with the accompanying drawings.
BRIEF DESCRIPTION OF THE DRAWINGS
Fig. 1 is a schematic diagram illustrating the configuration of an information recommendation system according to an embodiment of the present invention;
Fig. 2 is a schematic diagram illustrating storage of each user profile of a group of users according to an embodiment of the present invention;
Fig. 3 is a flowchart illustrating a method for recommending information to a user according to an embodiment of the present invention;
Fig. 4 is a flowchart illustrating a method for updating a user profile according to an embodiment of the present invention; and
Fig. 5 is a schematic diagram illustrating an application of a program recommendation system according to an embodiment of the present invention.
Throughout the above drawings, the same reference numerals indicate similar or corresponding features or functions.
DETAILED DESCRIPTION OF THE INVENTION Fig. 1 is a schematic diagram illustrating the configuration of an information recommendation system according to an embodiment of the present invention.
The system 100 comprises a user interaction unit 103, an interest analysis unit 104, a user profile modification unit 106 and a user profile management unit 107, wherein the user profile includes a user's at least two preferences and weights of at least one content feature.
The content feature refers to each actor's name and director's name contained in the program, and type of the program (e.g. a literary movie, a love story movie or a horror movie and so on). The content feature may be collected from information sources such as broadcast, TV, Internet or the like. Typically, it is extracted from DTV electronic program guide (EPG) that is sent to the user along with programs.
The content feature in the user profile may only refer to one item, such as an actor' s name. Alternatively, the content feature in the user profile may refer to a plurality of items, and correspondingly, the result to be recommended thus is more precise.
According to an embodiment of the present invention, the preference of content feature in the user profile for each user includes two parts: an individual preference indicating the user's preference of the programs that he or she enjoys alone, each program having a particular content feature, and a common preference indicating the user's preference of the programs that he or she watches together with others, each program having a particular content feature. Table 1 shows the individual preference and the common preference for each member in a group of users.
Table 1:
Figure imgf000006_0001
Figure imgf000007_0001
Table 1 shows data about the individual preference and the common preference of every content feature for each member in the group of users. The group is made up of father, mother, child 1 and child 2. Each member shows different individual preference and common preference of every content feature. The available TV programs include A-K, i.e. 11 features in total, wherein A is used for indicating English programs or programs mainly in English; B, C and D are used for indicating programs relating to computer, math, and chemistry respectively; E is used for indicating the programs concerning romantic movies; F and G are used for indicating cartoons and TV series respectively; H is used for indicating news programs; I is used for indicating commercial advertisements inserted between regular programs; J is used for indicating comedies, and K is used for indicating sport programs.
Each above-mentioned preference is the user' s feeling of every content feature, and may be preset by providers with a scale, e.g. [-1, +1].
The figures in the table show each member's preference of a certain feature. Namely, the preferences of the content feature for each member in the group of users are indicated or scaled by figures. For example, child 1 likes watching cartoon alone rather than sharing with others, and thus his or her individual preference of cartoons is set to 0.8, while the common preference is set to 0. Since he or she is not interested in either TV series or news, the corresponding values are set to 0 accordingly. Moreover, child 1 hates commercial advertisements, thus the preference of the feature is set to -0.6. As for other members in the family, the values could be set in terms of their personal preferences. The weight indicates influence, which the various content features such as actors, directors, type of programs and so on exert, over a selected result when the user selects a program. In other words, which factor such as actors, type of programs, directors and so on, is taken into consideration when the user selects his or her favourite program. Furthermore, the weights of all actors may be the same, the weights of all types of programs may be the same, and the weights of all directors may also be the same. Similarly, the weights may be preset by providers within a scale, e.g. [0, 100].
The weights and the preferences in the user profile may be regarded as a history record for recording the programs the user watched. There is, for example, another history record for recording the times that the user watches or deletes a program having the particular content feature while the user watches the program.
The user interaction unit 103 is used for monitoring an action of a user on a program in play. For example, the action involves a period in which the user watches a specific TV program. The user interaction unit 103, as an interactive bridge between the user and the recommendation system, receives feedback information from the user with respect to a program, which the user watches, and provides the user with a recommendation information list for the user's selection of programs to be watched. The feedback information includes the action of the user.
The recommendation information list is shown in the following table 2:
Table 2
Figure imgf000008_0001
Based on the action of the user described above, the interest analysis device 104 obtains the user's interest regarding the program, wherein the interest corresponds to the content feature preset in the program. (WD -θ)
The scale of the interest may be expressed as ' *10 , wherein WD1 is used
for indicating a period in which the user watches a specific program, and θ is used for indicating a threshold preset by a provider, for example. The value of the threshold is usually set as 0.5 RD1 , wherein RD1 is a predetermined duration of the specific program to be played.
Based on the interest corresponding to the content feature in the program, the user profile modification unit 106 modifies the individual preference, the common preference and the corresponding weight of a content feature in the user profile, to update the user profile dynamically and more precisely (See the following description in connection with Figure 3).
The user profile management unit 107 manages user profiles. As described above, the user profile generally includes each member's individual preference, common preference, and the corresponding weight of the content features.
The system further comprises a program receiving unit 101, a selecting unit 102 and an interest adjusting unit 105.
The program receiving unit 101 is used for receiving programs or information related to the programs, such as DTV EPG corresponding to the programs and so on.
Based on the received information related to the programs and the individual preference and common preference in the user profile, the selecting unit 102 selects the user's probably favourite programs, and presents the information related to the programs that the user is likely to prefer, in the recommendation information list (See the following description in connection with Figure 4).
The interest adjusting unit 105 adjusts the interest obtained from the action of the user, based on the individual preference and common preference of the corresponding content feature in the user profile. The scale of the interest could be adjusted by a different coefficient, which, in the range of, for example [0.1 , 1] , may be preset by providers.
For example, regarding a content feature that the user usually prefers (high preference), the scale of the interest may be multiplied by a coefficient 0.9 or 1. While regarding a content feature that the user is generally unlikely to prefer (low preference), the scale of the interest may be multiplied by a coefficient 0.1 or less, to reduce the effect of the interest on the individual preference and common preference, since it seems that the user watches such a program with the content feature occasionally or in case of accompanying his or her friends.
Obviously, the effect of the interest on the user profile will be strengthened if a special individual preference or common preference of certain content feature for the user is present in the user profile. Namely, the range of the adjustment coefficient is not limited to [0.1, 1], and may be above 1.
In the present invention, the interest adjusting unit 105 is optional. Namely, based on the analyzed result from the interest analysis unit 104, the user profile modification unit 106 may modify the user profile directly.
The storage of each user profile of a group of users according to an embodiment of the present invention is shown in Figure 2. In a group made up of a plurality of users, e.g. in a family made up of several members, each member shows his or her personal preferences on various TV programs, while all members present common preferences on certain TV programs. In addition, one member is likely to enjoy some TV programs alone, and would not like to share the TV programs with other members.
In order to manage the user profiles for the group of users effectively, in a family made up of four members according to an embodiment of the present invention, each of the members is allotted a private storage bubble 220, 230, 240 and 250 respectively, for storing each member's individual profile together with the contents or list of the corresponding recommended TV programs. All members have a common storage bubble 210 for storing each member's common profile together with the contents or list of the corresponding recommended TV programs.
It will be appreciated by those skilled in the art that the storage bubbles correspond to different storage elements. Alternately, the storage bubbles may correspond to different folders in the same storage element, or different files in the same storage element.
That is to say, each member's user profile includes two parts: individual profile, such as individual profiles 225, 235, 245 and 255, and common profile 215. The individual profile includes the member' s individual preference and the weight of at least one content feature. The common profile includes the common preference and the weight of at least one content feature for each member in the group of users. All members' common profiles may be stored together, or separately.
The user profile may be established and initialized by the user. Obviously, there exists other ways to form the user profile. For example, the user profile in the recommendation system can be initialized by a manufacturer in terms of the user' s basic information (e.g. gender, age and so on).
For example, a manufacturer may provide an initialization file of the user profile for different age groups as shown in table 3. The user profile is a data file in a specific format, and is updated by the program provider periodically or by each member in the group of users if necessary. The initialization file shown in table 3 may be regarded as a reference for the user to set individual preference and common preference.
Table 3
Figure imgf000011_0001
According to an embodiment of the present invention, the user data in the user profile is set by each member of the family using an input device, and stored into a device such as a set-top-box.
It will be appreciated by those skilled in the art that the user profile can be stored in various ways. For example, the user profile may be stored in a remote server held by the program provider via cable TV networks or LAN (Local Area Networks), and there provides statistics data, obtained from the samples of a plurality of families in the remote server, as a reference of the user profile. Alternately, information on the situations that each member in the family watches TV programs can be obtained automatically by the means of a monitor located close to the TV set, and sent to the set-too-box or transmitted to the remote server via networks for establishment of the user profile by statistics analysis. Fig. 3 is a flowchart showing a method for recommending information to a user according to an embodiment of the present invention.
As shown in Fig. 3, firstly in step S310, information related to a TV program is received. The content feature of the TV program, such as actor 1, is preset by the program provider and transmitted to the user in form of digital TV electronic program guide (EPG) along with the program.
Then in step S320, a determination is made whether the content feature included in the TV program matches with the common preferences of all users (for example, all members in a family) in a group of users. Namely, no user dislikes these content features.
If the determination in step S320 shows that the recommendation requirement is matched, it indicates that all users in the group are interested in the TV program, and they all like sharing with other users. In step S330, the TV program content or list is stored into a common storage bubble for recommending to all users. For example, if a TV program including the content feature C as shown in table 1 matches the common preference of all users, the TV program content is stored into the common storage bubble.
If the determination in step S320 is NO, it indicates that there are users in the group who do not like the TV program content, and then in step S340, a determination is made whether the TV program content matches the common preference of an individual user.
If the determination in step S340 is YES, the TV program content or recommendation information is stored in the user's private storage bubble in step S360. For example, a TV program including the content feature D matches child 2's common preference, but child 1, father and mother do not like the program, so the TV program content is stored in the private storage bubble of child 2.
The TV program content or recommendation information stored in the user's private storage bubble in step S 360 may include an identifier for indicating that the TV program content or recommendation information is recommended according to the user's common preference. It will be appreciated by those skilled in the art that each piece of program information recommended to users may include an identifier (for example, a distinguishing colour) for indicating the ground on which the program is recommended, such as a user' s individual preference, a user' s common preference and so on. According to the identifier, the recommendation apparatus may distinguish the user' s preference. If the determination in step S340 is NO, i.e. the TV program content does not match an individual user's common preference, it is to be determined in step S350 whether the TV program content matches the individual user's individual preference. If YES, the TV program content is stored into the user's private storage bubble in step S360.
In step S370, a determination is made whether there are still other users in the group of users. If yes, the process returns to step S340, to determine whether the TV program content matches another individual user's common preference.
If there are no other users yet, the process is completed.
Fig. 4 is a flowchart showing a method for updating a user profile according to an embodiment of the present invention.
Firstly, in step S410, a user profile is established. The user profile includes two parts, an individual profile and a common profile, which include a user's individual preferences and common preferences of a plurality of content features and the corresponding weights respectively (as shown in table 1). A detailed description is made to specific preferences and weights of related content features in an application No. 200410095756.5 titled " a method and apparatus for updating user profile," Chinese patent, filed with Chinese Patent Office on November 18, 2004 by KONINKLIJKE PHILIPS ELECTRONICS N. V., which is incorporated by reference herein.
Next in step 420, action of the user on a program in play is monitored. The program in play may be one selected from a recommendation information list by the user. The action includes a program recommendation information source, from which the played program the user is watching originates, for example, from a private storage bubble or from a common storage bubble. The action may further include the duration of a program having one or more preset particular content features, and times that the user watches or deletes a program having the particular content feature while the user watches the program.
For example, the program in play is movie A, and the type of movie A (e.g. literary movie) is a preset content feature. The program may further include other one or more content features, such as actor 1, actor 2 and so on. The content features may be preset by program providers and transmitted to users in form of digital TV electronic program guide (EPG) along with programs. Next in step S430, a determination is made whether the recommendation information of the TV program, which the user is watching, is from a private storage bubble.
If the determination is YES, it indicates that an individual user prefers the TV program content, and it is to determine the user corresponding to the private storage bubble (e.g. father) in step 470. In step 480, the individual preference of the user (father) is modified. The modification process may be referred to the application No. 200410095756.5 filed by KONINKLIJKE PHILIPS ELECTRONICS N.V, which is incorporated by reference herein.
For a sport program, for example, the predetermined duration is set to 2 hours ( RD1 ), the threshold is set to 0.5 hours (θ) , and the father spends 1.5 hours( WD1 ) in watching the program. The father's interest in the program is calculated to be 5 by the
equation ' *10 . If the father's initial individual preference is 0.8 and the
RD1 preference adjusting coefficient is 0.01, the father's adjusted individual preference for the sport program is calculated to be 0.85 (0.8+0.01*5) based on the interest.
Step S470 is an optional step. According to an embodiment of the present invention, each user' s individual preference may be stored into the private storage bubble of the user in the group of users . If it is determined in step S430 that the recommendation information of the TV program, which the user is watching, is from a private storage bubble, the process proceeds to step S480 directly, to modify the individual preference stored in the private storage bubble.
If the TV program content, which the user is watching, does not exist in a private storage bubble in step S430, it indicates that the TV program content exists in a common storage bubble, and it is required to acquire the interests of all users and modify the individual preference or common preference of each user in the group. In step S440, it is determined whether the user is watching the TV program content by means of a private device. The determination of a private device is described hereafter with reference to Fig.5.
If it is determined that the user is watching the TV program by means of a private device, it indicates that the owner of the private device is watching the TV program and is interested in the TV program. Then, the owner of the private device will be determined in step 470. Next, the user's individual interest is determined in step S480, and the user's individual preference is modified according to the individual interest in step S490.
If in step S440, it is determined that the user is not watching the TV program by means of a private device, it indicates that there may be several users watching the TV program from the common storage bubble by using a common device. The interest of the user group is further required to be calculated, so as to make further modification to the common preference of each user in the group.
In step S450, the interest of the group is calculated. A method for estimating total interests of a group of users is described in detail in an patent application No. 200510073942.3, titled "a method and apparatus for estimating the total interests of a group of users", filed with Chinese Patent Office in May 27, 2005 by KONINKLIJKE PHILIPS ELECTRONICS N.V, which is incorporated by reference herein.
(WD -θ)
The interest may be expressed as i *10 , wherein WD1 is the period in
which a user watches a specific program, θ is a preset threshold which may be provided by providers in advance, and generally as 0.5 RD1 , where RD1 indicates the predetermined duration of the specific program.
In step 460, the interest is adjusted according to the common preference of the corresponding content feature in user profile of each user. The interest may be adjusted with a different coefficient, wherein the coefficient may be preset by providers with a scale, e.g. [0.1,1].
Here TV series A is as an example. With respect to a content feature for the TV series, i.e. actor 1, the common preference in a user profile is 0.8, thus it indicates that the user likes the content feature actor 1 or is interested in the content feature actor 1 usually. In this case, a higher coefficient may be used to adjust the interest. For example, if the interest is 5 initially and the coefficient is 0.9, the adjusted interest of the user with respect to actor 1 becomes 4.5. A small adjustment is made, and thus the interest has a reduced influence on the user profile to a very limited extent.
Finally, in step S470, the common preference of each user in the group of users is modified according to the determined interest. The whole process for updating user profile of the present invention is completed.
Step S460 is an optional step. Namely, in step S470, the common preference of each user in the group may be modified according to the user's action. Fig. 5 is a schematic diagram illustrating an application of a program recommendation system according to an embodiment of the present invention. As shown in the figure, in a group made up of a plurality of users, for example, in a family made up of several members, each member has his or her own private space, such as bedroom, and all members share a public space, such as living room.
Each room has its particular content receiving devices, such as TV sets 510, 520, 530 and 550 for receiving TV programs, CD player 540 for receiving audio contents and so on. All devices may be connected to a family server 560, which stores TV programs, audio contents or list and recommendation information. When a member wants to watch TV programs or listen to audio contents by a receiving device, he or she may download the related contents by establishing a connection to the server 560.
In addition to a mass of TV programs or audio contents or list, the server 560 stores device information 565 as well, for managing all receiving devices connected thereto. As shown in table 4, the device information includes device ID, device name, device location (room) and device owner (or a member who uses the device most frequently) and other information. For example, it may be known from the device information that the TV set 530 with device ID 003 is located in bedroom 2, and the owner of the room is child 1.
Table 4
Figure imgf000016_0001
Generally, a receiving device, such as a TV set in the bedroom of each member, is used by the member individually, and a TV set in the living room may be used by several members. For example, the TV set with device ID 003 is usually used by child 1 individually, thus the watched TV programs may be preferred by child 1, and possibly are what child 1 does not want to share with other family members or are what other family members do not like. The TV set with device ID 001 is usually used by one or more of the members together, i.e. the father, the mother, child 1 and child 2, and hence the watched TV programs shall be what all members like or what one member likes and wants to share with other family members.
According to an embodiment of the present invention, a device usually used by an individual user is referred to be a private device, and a device usually used by two or more users is referred to be a public device. According to the device ID of a device connected to the server 560, it may be determined which device is being used for a user to watch a TV program, and determined whether it is a private device or a public device.
It will be appreciated by those skilled in the art that, in the method and apparatus for updating user profile as disclosed in the present invention, a user profile may include various other preferences, in addition to individual preferences and common preferences. Namely, a user profile may include more than two preferences for different purposes, for example, a portion for personal privacy and different common preferences of a content feature for different groups of users.
It is to be understood by those skilled in the art that various improvements and modifications may be made to the method and system for updating use profiles as disclosed in the present invention without departing from the basis of the present invention, the scope of which is to be defined by the appended claims herein.

Claims

CLAIMS:
1. A method for updating a user profile, comprising the steps of:
(a) monitoring an action of a user regarding a program in play;
(b) acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and
(c) modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
2. The method of claim 1, wherein the at least two preferences comprise an individual preference and a common preference, the individual preference indicating the user's preference for enjoying the program having the content feature alone, and the common preference indicating the user's preference for sharing the program having the content feature.
3. The method of claim 1, wherein the action of the user comprises selecting the program from a recommendation list, and wherein the step (c) comprises the step of modifying one of the at least two preferences of the content feature corresponding to the source of the recommendation list in the user profile according to the source of the recommendation list and the interest.
4. The method of claim 1, wherein the action of the user comprises playing the program by using a specific device, and wherein the step (c) comprises the step of modifying one of the at least two preferences of the content feature corresponding to the property of the specific device in the user profile according to the property of the specific device and the interest.
5. The method of claim 1, further comprising the step of adjusting the interest according to the at least two preferences of the corresponding content feature in the user profile, and wherein the step (c) comprises the step of modifying one of the at least two preferences of the content feature corresponding to the action of the user in the user profile according to the adjusted interest.
6. An apparatus for updating a user profile, the apparatus comprising: a user interaction unit, for monitoring an action of a user regarding a program in play; an interest analysis unit, for acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
7. The apparatus of claim 6, wherein the at least two preferences comprise an individual preference and a common preference, the individual preference indicating the user's preference for enjoying the program having the content feature alone, and the common preference indicating the user's preference for sharing the program having the content feature.
8. The apparatus of claim 6, wherein the action of the user comprises selecting the program from a recommendation list, and wherein the user profile modification unit is configured to modify one of the at least two preferences of the content feature corresponding to the source of the recommendation list in the user profile according to the source of the recommendation list and the interest.
9. The apparatus of claim 6, wherein the action of the user comprises playing the program by using a specific device, and wherein the user profile modification unit is configured to modify one of at least two preferences of the content feature corresponding to the property of the specific device in the user profile according to the property of the specific device and the interest.
10. The apparatus of claim 6, further comprising an interest adjusting unit for adjusting the interest according to the at least two preferences of the corresponding content feature in the user profile, and wherein the user profile modification unit is configured to modify one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the adjusted interest.
11. An information recommendation system, comprising: a program receiving unit, for receiving program information; a user profile management unit, for storing a user profile which comprises at least two preferences of at least one content feature for a user; a selecting unit, for selecting a program potentially preferred by the user from the program information according to the user profile and recommending the selected program to the user; a user interaction unit, for monitoring an action of the user regarding a program in play; an interest analysis unit, for acquiring the user's interest in the program according to the action of the user, the interest regarding a content feature of the program, and a user profile modification unit, for modifying one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the interest.
12. The system of claim 11, further comprising an interest adjusting unit for adjusting the interest according to the at least two preferences of the corresponding content feature in the user profile, and wherein the user profile modification unit is configured to modify one of at least two preferences of the content feature corresponding to the action of the user in the user profile according to the adjusted interest.
PCT/IB2006/053220 2005-09-23 2006-09-12 Method and apparatus for updating user profile WO2007034355A2 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN200510106907.7 2005-09-23
CN200510106907 2005-09-23

Publications (2)

Publication Number Publication Date
WO2007034355A2 true WO2007034355A2 (en) 2007-03-29
WO2007034355A3 WO2007034355A3 (en) 2010-12-23

Family

ID=37889187

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/IB2006/053220 WO2007034355A2 (en) 2005-09-23 2006-09-12 Method and apparatus for updating user profile

Country Status (1)

Country Link
WO (1) WO2007034355A2 (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012089899A1 (en) * 2010-12-29 2012-07-05 Nokia Corporation Method and apparatus for providing recommendations based on preloaded models
WO2012146831A3 (en) * 2011-04-28 2012-12-20 Nokia Corporation Method and apparatus for extracting explicit profile representation through adaptive recommender system
CN105959735A (en) * 2016-04-29 2016-09-21 乐视控股(北京)有限公司 On-line program recommending method and server
CN110809190A (en) * 2018-08-06 2020-02-18 Tcl集团股份有限公司 Method and device for matching user roles based on smart television and server
CN110913249A (en) * 2018-09-18 2020-03-24 深圳市茁壮网络股份有限公司 Program recommendation method and system

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7085747B2 (en) * 2001-09-26 2006-08-01 J Koninklijke Philips Electronics, Nv. Real-time event recommender for media programming using “Fuzzy-Now” and “Personal Scheduler”

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
None

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2012089899A1 (en) * 2010-12-29 2012-07-05 Nokia Corporation Method and apparatus for providing recommendations based on preloaded models
WO2012146831A3 (en) * 2011-04-28 2012-12-20 Nokia Corporation Method and apparatus for extracting explicit profile representation through adaptive recommender system
EP2702515A2 (en) * 2011-04-28 2014-03-05 Nokia Corp. Method and apparatus for extracting explicit profile representation through adaptive recommender system
EP2702515A4 (en) * 2011-04-28 2014-11-05 Nokia Corp Method and apparatus for extracting explicit profile representation through adaptive recommender system
CN105959735A (en) * 2016-04-29 2016-09-21 乐视控股(北京)有限公司 On-line program recommending method and server
CN110809190A (en) * 2018-08-06 2020-02-18 Tcl集团股份有限公司 Method and device for matching user roles based on smart television and server
CN110809190B (en) * 2018-08-06 2021-12-31 Tcl科技集团股份有限公司 Method and device for matching user roles based on smart television and server
CN110913249A (en) * 2018-09-18 2020-03-24 深圳市茁壮网络股份有限公司 Program recommendation method and system

Also Published As

Publication number Publication date
WO2007034355A3 (en) 2010-12-23

Similar Documents

Publication Publication Date Title
US9712586B2 (en) Prioritization in a continuous video playback experience
US8789108B2 (en) Personalized video system
US9924218B2 (en) Information processing apparatus, information processing method, program, and information sharing system
US9294816B2 (en) Methods and systems for predicting user viewing preferences based on detected events
US20110161242A1 (en) Systems and methods for searching and browsing media in an interactive media guidance application
US20070074245A1 (en) Virtual channels
US20130347033A1 (en) Methods and systems for user-induced content insertion
CA2977959A1 (en) Methods and systems for recommending media content
JP2013539893A (en) Method and apparatus for recommending and bookmarking media programs
RU2420908C2 (en) Method and apparatus for generating recommendation for content element
US20150156529A1 (en) Systems and methods for selectively transmitting user interaction information based on biometric information
CN106471819B (en) System and method for improving accuracy in a media asset recommendation model
US11842040B2 (en) Systems and methods for automatic formatting of images for media assets based on user profile
AU2022200691B2 (en) Systems and methods for automatic formatting of images for media assets based on user profile
US11172270B2 (en) Systems and methods for discovery of, identification of, and ongoing monitoring of viral media assets
US9591359B2 (en) Systems and methods for automatic formatting of images for media assets based on prevalence
US20140081992A1 (en) Systems and methods for providing customized descriptions related to media assets
WO2007034355A2 (en) Method and apparatus for updating user profile
US20160378308A1 (en) Systems and methods for identifying an optimal image for a media asset representation
RU2532703C2 (en) Biased recommender system
JP2010130051A (en) System of distributing content directed to individual
US20190327516A1 (en) System and method for classifying recorded content for deletion
JP2006236341A (en) Information search method and its device
US10448072B1 (en) Systems and methods for increasing a likelihood of media asset consumption using recommendation chains

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 06795994

Country of ref document: EP

Kind code of ref document: A2