GB2438646A

GB2438646A - System for content item recommendation

Info

Publication number: GB2438646A
Application number: GB0610625A
Authority: GB
Inventors: Nicolas Lhuillier; Makram Bouzid; Kevin Christopher Mercer; Jerome Picault
Original assignee: Motorola Inc
Current assignee: Motorola Solutions Inc
Priority date: 2006-05-30
Filing date: 2006-05-30
Publication date: 2007-12-05
Also published as: GB0610625D0

Abstract

An apparatus for content item recommendation comprises a user ratings store (103) which receives anonymous user ratings for content items such as television programmes from a plurality of users. An identification processor (105) determines an identity for a first user and an initial recommendation processor (109) generates a set of content item recommendations in response to the anonymous user ratings and a first user preference profile for the first user. A recommendation output (111) presents the recommendations to the first user and a feedback processor (113) receives a user preference feedback for the content item recommendations from the first user. A user preference profile processor (107) modifies the first user preference profile in response to the user preference feedback to generate a modified user preference profile. The modified user preference profile may be stored for later use. A modified recommendation processor (115) then generates a modified set of recommendations for the first user in response to the modified user preference profile.

Description

METHOD AND APPARATUS FOR CONTENT ITEM RECOMMENDATION

Field of the Invention

The invention relates to recommendation of content items and in particular, but not exclusively, to recommendation of television or radio programmes.

Background of the Invention * S. * S S S... S...

*,,,. In recent years, the availability and provision of multimedia and entertainment content has increased substantially. For example, the number of available S..

* television and radio channels has grown considerably and the 5:hh15 popularity of the Internet has provided new content distribution means. Consequently, users are increasingly provided with a plethora of different types of content from different sources. In order to identify and select the desired content, the user must typically process large amounts of information which can be very cumbersome and impractical.

Accordingly, significant resources have been invested in research into techniques and algorithms that may provide an improved user experience and assist a user in identifying and selecting content.

For example, Digital Video Recorders (DVRs) or Personal Video Recorders (PVR5) have become increasingly popular and are increasingly replacing conventional Video Cassette Recorders (VCRs) as the preferred choice for recording television broadcasts. Such DVR5 (in the following the term DVR is used to denote both DVR5 and PVR5) are typically based on storing the recorded television programs in a digital format on a hard disk or optical disc. Furthermore, DVRs can be used both for analogue television transmissions (in which case a conversion to a digital format is performed as part of the recording process) as well as for digital television transmissions (in which case the digital television data can be stored directly).

::. Increasingly, devices, such as televisions or DVR5 provide new and enhanced functions and features which provide an improved user experience. For example, televisions or DVRs : 15 can comprise functionality for providing recommendations of * television programs to the user. More specifically, such devices can comprise functionality for monitoring the viewing/recording preferences of a user. These preferences can be stored in a user preference profile and subsequently can be used to autonomously select and recommend suitable television programs for viewing or recording. E.g. a DVR may automatically record programs which are then recommended to the user, for example by inclusion of the automatically recorded programs in a listing of all the programs recorded by the DVR.

Such functionality may substantially improve the user experience. Indeed, with hundreds of broadcast channels diffusing thousands of television programs per day, the user may quickly become overwhelmed by the offering and therefore may not fully benefit from the availability of content.

Furthermore, the task of identifying and selecting suitable CMLO3976EV content becomes increasingly difficult and time-consuming.

The ability of devices to provide recommendations of television programs of potential interest to the user substantially facilitates this process.

In order to enhance the user experience, it is advantageous to personalise the recommendations to the individual user.

In this context, a recommendation consists in predicting how much a user may like a particular content item and recommending it if it is considered of sufficient interest.

The process of generating recommendations requires that user :.. preferences have been captured so that they can be used as input by the prediction algorithm.

:" 15 There are two main techniques used to collect user S. * preferences. The first approach is to explicitly obtain user preferences by the user(s) manually inputting their : preferences, for example by manually providing feedback on content items that the user(s) particularly liked or disliked. The other approach is to implicitly obtain user preferences by the system monitoring user actions to infer their preferences.

Although these techniques may be suitable for many single-user environments, they are not particularly well suited to many other environments or to multi-user environments.

For example, most of the known recommendation approaches are not ideal in the context of television viewing. A television or video recorder, such as specifically a DVR, is commonly a multi-user device and the activity of watching television is characterised by being a low effort and highly passive CMLO3976EV activity. In this context, although users ask for individual recommendations, creating individual user profiles tends not to be easy or effective.

Specifically, explicit elicitation of preferences is not effective as it is difficult for users to precisely describe their tastes. Furthermore, the user will typically consider it cumbersome and tedious to manually initialise and maintain a user preference profile.

Explicit feedback on programmes is impractical in user environments as it requires the user to be identified before the programme feedback can be recorded in order to allow the system to differentiate between the preferences of the different users. * q

Also, implicit learning of preferences tends not to be : effective as current users would need to be automatically identified and in addition implicit learning does not work well in contexts such as radio or television since the radio or television is often used as a background medium and therefore may play programmes that are not of interest to the user(s).

Known recommendation systems accordingly tend to be inflexible and/or require a significant manual involvement of the user(s). Furthermore, conventional recommenders tend to be complex and especially require complex algorithms for manipulating user rating inputs to generate personalised content item recommendations, especially in multi user environments.

CMLO3976EV Therefore, an improved system for content item recommendation would be advantageous. In particular, a system allowing an improved user experience, increased flexibility, reduced complexity, improved suitability for multi-user environments, reduced need for user inputs and/or improved performance would be advantageous.

Summary of the Invention

Accordingly, the Invention seeks to preferably mitigate, alleviate or eliminate one or more of the above mentioned disadvantages singly or in any combination. *41* * S SI..

According to a first aspect of the invention there is provided an apparatus for content item recommendation, the apparatus comprising: means for receiving anonymous user ratings for content items from a plurality of users; means for determining an identity for a first user; generating means for generating a first set of content item recommendations in response to the anonymous user ratings and a first user preference profile for the first user; means for presenting the first set of content item recommendations to the first user; means for receiving user preference feedback for the first set of content item recommendations from the first user; modifying means for modifying the first user preference profile in response to the user preference feedback to generate a modified user preference profile; and means for generating a second set of recommendations for the first user in response to the modified user preference profile.

CMLO3976EV The invention may allow an improved recommendation of content items. Specifically, the invention may e.g. provide increased flexibility and/or reduced complexity of the recommendation. The invention may allow a content recommendation in multi-user systems which can be personalised for an individual user without requiring that all user ratings are linked to specific users.

The invention may substantially facilitate the gathering of user rating data as this can be performed without requiring any identity or authentication of the user providing the : ** rating input. The invention may allow a low complexity s..

generation of content item recommendations adapted to and personalised for the specific user. The invention may allow a facilitated adaptation of the recommendations to the specific user and may specifically provide a user friendly approach to continuously improve the customisation for the S.....

individual user.

The invention may allow a facilitated operation and/or improved user experience. For example, the invention may allow a flexible and personalised recommendation without requiring substantial contribution by the individual users.

The content items may specifically be television programmes or radio programmes. The apparatus may specifically be a television, a DVR or a media server. The first user preference profile may be a personalised user preference for the first user which is not shared and/or used by any other user.

CMLO3976EV According to an optional feature of the invention, the apparatus further comprises: storage means for storing user preference profiles; retrieving means for retrieving the first user preference profile in response to the identity of the first user; and means for storing the modified user preference profile as a user preference profile belonging to the identity.

This may allow an efficient continuous adaptation of the user preference profile to the characteristics of the specific user. In particular, it may allow an efficient and : ** low complexity learning system capable of adapting to the S...

preferences of the individual user. I...

According to an optional feature of the invention, the retrieving means is arranged to retrieve a default user preference profile as the first user preference profile if S.....

:.: no user preference profile is stored for the identity.

The default user preference profile may specifically correspond to an equal preference for different categories of content items and/or may correspond to an average user preference profile of the stored user preference profiles.

This may allow an improved user experience and may in particular allow generation of recommendations for new users which can gradually be adapted to the specific preferences of the user. The feature may facilitate the initialisation and adaptation for new users.

According to an optional feature of the invention, the first user preference profile comprises a plurality of preference CMLO3976EV indications for different content item categories and the modifying means is arranged to modify the preference indication of a first content category in response to receiving a user preference feedback indication for a content item of the first set of content item recommendations belonging to the first category.

This may allow a facilitated implementation while providing accurate personalised recommendations.

According to an optional feature of the invention, the : *..* generating means comprises: grouping means for grouping the anonymous user ratings into rating groups in response to a e content item match criterion, each user rating comprising content item description data and preference data; means for receiving content item data for a plurality of content items; first recommendation means for generating a set of I.....

:. content item recommendations for each rating group in * response to the content item data and user ratings of that rating group; and second recommendation means for generating the first set of content item recommendations by combining the sets of content item recommendations for each rating group in response to the first user preference profile, the first user preference profile comprising a user preference indication for each rating group.

The invention allows a simpler personalised user preference profile to be used to personalise recommendations in a multi-user environment and allows some common processing for a plurality of users.

According to an optional feature of the invention, the first recommendation means is arranged to match a first content item of the plurality of content items to at least a first rating group and to assign a preference value for the first content item in response to the preference data of the first rating group.

The second recommendation means may be arranged to modify : *"* the preference indication for the first rating group in e.

response to the preference data for the first rating group.

This may allow a facilitated implementation while providing ** accurate personalised recommendations.

:. According to an optional feature of the invention, the * second recommendation means is arranged to combine the sets of content item recommendations by selecting content items in response to the preference indications for each rating group.

According to an optional feature of the invention, the second recommendation means is arranged to select a number of content items included in the single set of content item recommendations for a given rating group in response to the preference indication of the given rating group.

This may allow a facilitated implementation while providing accurate personalised recommendations. Specifically, the feature may allow low complexity, personalised recommendation and/or may allow a variety of content items being recommended.

According to an optional feature of the invention, the modifying means is arranged to generate the modified user preference profile by modifying a preference indication for a ratings group in response to the user preference feedback.

: **, The user preference feedback may specifically comprise a S...

user preference feedback for a first content item of the first set of content item recommendations and the modifying means may be arranged to generate the modified user preference profile by modifying a user preference indication for a ratings group to which the first content items belongs in response to the user preference feedback.

This may allow improved recommendations and may in particular allow an adaptation of the user preference profile to the user's preferences. The feature may allow low complexity and facilitated maintenance of the user preference profile. The user preference indication may for example be modified to increase or decrease the preference and/or may be modified to prevent any content items from the set of content item recommendations for the specific rating group to be included in the final single set of content item recommendations.

According to an optional feature of the invention, the apparatus of further comprises: means for receiving a request for content item recommendations and in response determining if any user ratings have been generated since a previous grouping; and wherein the grouping means is arranged to update the grouping of user ratings to include the user ratings generated since the previous grouping.

This may allow the recommendations to continuously adapt to the preferences of the users and/or may allow an improved accuracy while allowing a low complexity and/or computational resource use.

According to another aspect of the invention, there is

S

*S0* provided a method of content item recommendation, the method

SS

comprising: receiving anonymous user ratings for content items from a plurality of users; determining an identity for a first user; generating a first set of content item recommendations in response to the anonymous user ratings and a first user preference profile for the first user; * S presenting the first set of content item recommendations to the first user; receiving user preference feedback for the first set of content item recommendations from the first user; modifying the first user preference profile in response to the user preference feedback to generate a modified user preference profile; and generating a second set of recommendations for the first user in response to the modified user preference profile.

These and other aspects, features and advantages of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

Brief Description of the Drawings

Embodiments of the invention will be described, by way of example only, with reference to the drawings, in which FIG. 1 is an illustration of an example of a device for content item recommendation in accordance with some embodiments of the invention; * .. * * a... 0'a * a

I a. * * I.. a.. a S I. S * a

I

FIG. 2 is an illustration of an example of a processor for content item recommendation in accordance with some embodiments of the invention; FIG. 3 illustrates an example of data being processed in a device for content item recommendation in accordance with some embodiments of the invention; and FIG. 4 illustrates an example of a method of content item recommendation in accordance with some embodiments of the invention.

I a * *1s1

Detailed Description of Some Embodiments of the Invention

I I.

I

The following description focuses on embodiments of the Is....

:. invention applicable to a recommendation system for * television programmes. However, it will be appreciated that the invention is not limited to this application but may be applied to many other content items including for example radio programmes, audiovisual files, music files etc. FIG. 1 is an illustration of a device for making content item recommendations. The device may for example be a DVR or a television.

The device of FIG. 1 comprises functionality for recommending content items to a user. For example, the device may recommend upcoming television programmes to the user of the device. The device uses an approach for generating recommendations which is based on anonymous user ratings which are received from a plurality of unidentified users. The device can then target the recommendations to a specific user based on a user preference profile for the individual user. The user preference profile is adapted and customised for the individual user in response to feedback from the user on the recommendations provided by the device.

Thus, the device allows user friendly operation wherein user ratings may be provided without requiring authentication of the user providing the ratings while allowing a user friendly generation and maintenance of a user preference profile that can be applied to the anonymous ratings to : ** generate a personalised list of recommendations.

Furthermore, the approach allows recommendations to take S...

into account both user group preferences as well as individual preferences. S..

The device comprises a user input 101 that can receive *5s*** :. manual inputs from one or more users of the device.

* Specifically the user input 101 can receive anonymous feedback of user preferences for various content items. As an example, a user watching or playing back a specific television programme can manually input a rating of the program.

The user input 101 is coupled to a user rating store 103.

When a user preference is received from the user input 101, a user rating record comprising the user preference measure and content item data describing the contents is stored in the user rating store 103.

The user rating record can for example store the user preference as a number between 1 and 10, the genre of the television programme, the title of the television programme, the duration of the television programme, people involved in the television programme (such as actors or directors) etc. The device is a multi-user device that may be used by many different users. Furthermore, the user preferences are inputted without any identification of the specific user that is providing the data. Accordingly, the user rating records stored in the user rating store 103 are anonymous user ratings and the records do not comprise any information of the identity of the user who provided the input. Hence, * it is not feasible to generate content item recommendations which are personalised to an individual user based only on the stored user ratings. Rather, such an approach provides :. 15 recommendations which can be customised for the whole group * .:. of users using the device.

The device furthermore comprises an identification processor :. 105 which can determine an identity for a first user for which a list of recommendations is to be generated. The identity may be any indication, information or data that allows a specific user preference profile suitable for the first user to be identified. Specifically, the identity may be for a single user or may be for a group of users to which the first user belongs.

For example, prior to the generation of recommendations for a specific user, the user can authenticate with the device in order to be identified. The identification may for example be by clicking on a dedicated button on a remote control, selecting an appropriate icon or a menu on the television screen, entering an identity code or any other identification mechanism (e.g. biometric).

The identification processor 105 is coupled to a user preference profile processor 107 which is fed the determined user identity.

The user preference profile processor 107 comprises functionality for storing and retrieving user preference profiles. Each stored user preference profile is associated with a specific user identity and when the user preference profile processor 107 receives the user identity from the identification processor 105 it can proceed to retrieve the S...

corresponding user preference profile from the user preference profile store. *..

The device furthermore comprises an initial recommendation processor 109 which is coupled to the user rating store 103 and the user preference profile processor 107. If the first user requests a recommendation of content items, the initial recommendation processor 105 receives the corresponding user preference profile from the user preference profile processor 107. It then proceeds to generate a list of content item recommendations in response to the user preference profile and the anonymous user ratings stored in the user rating store 103.

It will be appreciated that the initial recommendation processor 109 may use any suitable method for generating recommendations in response to the user ratings and user preference profiles. For example, the initial recommendation processor 109 may have a number of predetermined content categories defined (for example corresponding to movies, sports, soaps etc). The initial recommendation processor 109 may in advance determine the rating for each of these categories based on the user ratings. Thus, the initial recommendation processor 109 may have a common rating for each category which corresponds to the user group rating for this category.

The initial recommendation processor 109 may then receive data corresponding to a number of content items that are eligible for being recommended to the user. The rating of each of these content items may initially be found by determining if they belong to any of the predetermined categories and if so assigning them the rating of this category. S..

Similarly, the user preference profile may comprise a number of predetermined content item categories with a preference indication for each category. Thus, additionally, each eligible content item can be compared to the categories of the user preference profile and the user group rating can be modified depending on the rating indicated by the user preference profile. For example, the rating of the user preference profile for the category to which the content item belong can be added to the rating determined in response to the user ratings.

It will be appreciated that in such an example, the same content item categories may be used for the user ratings and for the user preference profile but that this is not necessary.

Such an approach allows for a very flexible, efficient and accurate recommendation. Specifically, the device can use all the information provided by the anonymous user ratings while at the same time allowing the user preference profile to override any group preferences in favour of the individual' s preferences.

The initial recommendation processor 109 can then simply select the content items which have achieved the highest rating for recommendation.

The initial recommendation processor 109 is coupled to a :.:::. recommendation output 111 which is fed the list of S...

recommendations. The recommendation output 111 can present this list to the user in any suitable form. For example, for a television application, the recommendation output 115 can S..

display a list of upcoming television programs that are considered of particular interest for the currently authenticated user. Likewise, for a DVR the recommendation output 115 can present a list of recommended television programmes to the user and/or can automatically record the recommended content items.

The device furthermore comprises a feedback processor 113 which is coupled to the user input 101 and which can receive user preference feedback from the user for the list of content item recommendations. Specifically, the feedback processor 113 can receive user preference feedback for the specific content items that are recommended to the user. The user may e.g. indicate that he would like more content items recommended which are similar to a specific content item, that he would like fewer content items recommended which are similar to a specific content item or that he does not want any content items recommended which are similar to the specific content item. As an example, the user can provide feedback on the list of recommendations by selecting a recommendation and using for instance buttons labelled "More like this", "Less of this" or "Not for me".

The feedback processor 113 is coupled to the user preference profile processor 107 which is fed the feedback information.

In response, the user preference profile processor 107 updates the user preference profile for the first user to reflect the user feedback. * I. * I * S... *S..

As a specific example, if the user pressed the button :. 15 labelled "More like this" for a given content item, the * rating of the category in the user preference profile to *..

* which this content item belongs is increased. If the user pressed the button labelled "Less like this", the rating of the category is reduced. If the user pressed the button labelled "Not for me" the rating of the category may be set to ban any content items belonging to this category from being included in the recommendation lists.

The user preference profile processor 107 then stores the modified user preference profile such that it can be used for future recommendations.

Furthermore, the user preference profile processor 107 is coupled to a modified recommendation processor 115 which is arranged to generate a modified list of recommendations by using the modified user preference profile. The modified recommendation processor 115 is coupled to the recommendation output at 111 which can present the modified recommendation list to the user.

It will be appreciated that the modified recommendation processor 115may operate similarly or identically to the initial recommendation processor 109. Indeed, the initial recommendation processor 109 and the modified recommendation processor 115 are for clarity presented as separate entities in FIG. 1 but will typically be the same entity operated sequentially with different user profile data. Thus, the two elements may be implemented by the same hardware and/or software such as for example by the same algorithm or executable code used with the different user preference profiles as an input. It will furthermore be appreciated, :. 15 that the generation and presentation of the modified list of * recommendations may be performed when receiving of the user S..

feedback and/or may for example be performed the next time a list of recommendations is requested by the user.

SS * S * * S

The device thus allows a dynamic adaptation of the user preference profile to more accurately reflect the individual user's preferences. Furthermore, the adaptation may be performed by a user friendly operation which reduces the inconvenience to the user and which specifically can reduce the adaptation to areas wherein the individual user preferences deviate from those of the user group as a whole.

Such adaptation may also allow an efficient and user-friendly initialisation for a new user. Thus, whenever a recommendation of content items is requested, the device can retrieve the user preference profile stored for that user and can store the modified user preference profile which takes into account the user preference feedback for the recommendation list. When a user is provided with a recommendation for the first time, a default user preference profile is used and this is modified in accordance with the user preference feedback from the user. The modified user preference profile is then stored. This process is repeated every time a new recommendation list is generated and accordingly the user preference profile increasingly accurately reflects the individual user's preferences.

The default user preference profile can specifically correspond to a user preference profile which has an equal preference for all content items. E.g. the same (neutral) rating may initially be assigned to all content categories :. 15 of the user preference profile. Thus, by using a default * user preference profile, an initial content item *** recommendation list is generated that conforms to the preferences of the user group as a whole. The user can then proceed to customise this to reflect the differences between his personal preferences and those of the user group.

In the following, a specific example of how the recommendation lists may be generated is described. The example will be described with reference to the initial recommendation processor 109 but it will be appreciated that it equally applies to the modified recommendation processor (which effectively may be the same entity).

The described approach is highly flexible yet allows a high degree of personalisation. Specifically, the initial recommendation processor 109 uses a two-stage approach wherein user ratings are first clustered and personalisation is then achieved in response to user preferences for the clusters of content items. This approach may provide an efficient implementation with high flexibility and is in particularly useful for multi-user environments wherein anonymous user ratings are received from a plurality of users.

The initial recommendation processor 109 comprises a grouping processor 201 which is arranged to cluster or group user rating records stored in the user ratings store 103 into groups of user ratings. The grouping of the user rating records is performed in response to a content item match :,:::. criterion which may be any suitable match criterion that allows a grouping of content items into groups having desirable common characteristics. The match criterion may be a simple similarity criterion for specific characteristics S..

* of the user ratings or may e.g. be a complex clustering algorithm. S. *S * S S * S

For example, the content item match criterion may require that a content characteristic, such as a genre or actor, is the same for all the content items in a given group.

Additionally or alternatively, the content item match criterion may require that user preferences for content items in the same group are the same or similar. For example, the grouping processor 201 can generate groups as content items corresponding to for example movies the users like, movies the users do not like, actors the users like, actors the users do not like, etc. In more complex embodiments, the grouping processor 201 may for example group the content items by using a clustering algorithm such as a k-means or isodata clustering algorithm.

A k-means clustering algorithm initially defines k clusters with given initial parameters. The user rating records are then matched to the k clusters. The parameters for each cluster are then recalculated based on the user rating records that have been assigned to each cluster. The algorithm then proceeds to reallocate the user rating records to the k clusters in response to the updated parameters for the clusters. If these operations are I.:..' iterated a sufficient number of times, the clustering Is.' converges resulting in k groups of content items having similar properties.

S S..

The device furthermore comprises a first recommendation processor 203 which is coupled to the grouping processor 201. In addition, the first recommendation processor 203 is coupled to a content item processor 205. The content item processor 205 receives information of various content items which are eligible to be recommended to a user.

For example, the content item processor 205 can be provided with information of the television programmes that are to be received within a given time interval. Specifically the content item processor 205 can receive an Electronic Programme Guide (EPG) that indicates the television programmes that will be transmitted in, say, the next week.

In addition to the time and titles of the television programmes, the EPG can contain further meta-data such as an indication of the genre, actors, directors etc. As another example, the content item processor 205 may alternatively or additionally be provided with information of television programmes that has been recorded by e.g. a DVR.

The first recommendation processor 203 is arranged to generate recommendations for each of the user rating groups which were determined by the grouping processor 201. Thus, the first recommendation processor 203 processes each user rating group independently of the other user rating groups.

For each user rating group, a list of recommendations is generated. * I.

Specifically, for each user rating group, the first recommendation processor 203 compares each of the potential content items from the content item processor 205 to the * characteristics of the user rating group. If the match is sufficiently close, the content item is considered to belong to this group and is accordingly considered to have a rating that can be determined from the user ratings of the group.

As a simple example, for a given user rating group, a user preference value can be set to correspond to the average of all the user preference values for the user rating records associated with group. Thus, if the content item is found to match a group, it is included in the list of recommendations for that group and is assigned the rating of the group.

Thus, the first recommendation processor 203 generates a number of recommendation lists with each list comprising a number of content items that are considered to have characteristics matching the group.

Hence, when generating recommendations, the device retrieves the list of content available for the time period being considered (for instance via the EPG) and uses the groups to compute recommendations. For each piece of content, this is done by determining the closest group (e.g. using a similarity or distance function) and computing the recommendations for that group using a content matching algorithm and the programme ratings of this group. This process results in obtaining one list of recommendations per group. These lists may e.g. be sorted first by the confidence level of the prediction, for instance using a threshold, and then by the actual value of the prediction. I... * U

The first recommendation processor 203 is coupled to a is, 15 second recommendation processor 207. The second recommendation processor 207 is arranged to generate a single list of recommended content items by combining the list of content items generated by the first recommendation I. Si : * * processor 203. The second recommendation processor 207 is furthermore coupled to a user preference profile processor 107 and can receive the individual user preference profile for the first users from this.

Specifically, if the user already has an individual user preference profile (for instance created at bootstrap or during previous usage of the system), the second recommendation processor 207 obtains this profile.

Otherwise, the second recommendation processor 207 may receive a default user preference profile.

In the example, the user preference profile comprises preference data indicative of an individual user preference for the user rating groups. The user preference profile is thus associated with the user rating groups and does not indicate specific preferences for individual content items, or individual content item characteristics. Rather, it provides a user preference indication for each rating group.

The user preference profile can for example indicate that a specific user rating group is rated highly by the user whereas another user rating group is not rated very highly.

The combination of the recommendation lists for the different groups is then performed taking this rating into account. * S* * * S *5S5

As an example, the second recommendation processor 207 selects content items from the individual lists to be included in the final list depending on the ratings which S..

are assigned to the content items of the group lists. *

*e**** * * As a specific example, the second recommendation processor 207 can select a number of content items from each group list where the number of content items that are selected from each group depends on the rating of that group in the user preference profile. For example, if the user preference profile indicates a high preference a first number of content items is selected (e.g. five content items may be selected), if the user preference profile indicates a lower preference a lower number of content items is selected (e.g. three content items may be selected), if the user preference profile indicates an even lower preference an even lower number of content items is selected (e.g. one content items may be selected). If the user preference profile indicates a dislike for the group, no content items are selected.

In some embodiments, the user preference profile may be used to more gradually bias the different rating groups.

Specifically, a rating or preference for the group can be determined in response to the preference indication in the user preference profile and the rating determined from the content items in the rating group. For example, the user preference indication of the user preference profile for a given user rating group may be used to bias the rating or ratings determined from the user rating records by the first recommendation means. Specifically, if the user preference profile indicates a preference for a given group or cluster, ::::. the rating(s) of this group may be increased, whereas if the ** user preference profile indicates a negative preference for a given group or cluster, the rating(s) of this group may be : decreased. The modified ratings can then be used to select the number of content items taken from each group.

The selection of the content items for the single list may for example be by selecting the highest rated content items of each list and/or the content items that most closely match the group characteristics. In some embodiments, the single lists may have an equal rating for all recommended content items and the content items for the final list may simply be randomly selected.

FIG. 3 illustrates an example of how data may be processed by the initial recommendation processor 109.

The device receives content item data 301 for example in the form of an EPG. The content item data 301 is compared to the rating groups 303 to generate a plurality of lists 305. In the specific example, one list of recommendations 305 is generated for each rating group. In the example, a first list corresponds to recommended sports programs, a second list corresponds to recommended soaps and a third list corresponds to recommended movies. The individual lists 305 are then processed with reference to the specific individualised user preference profile 307 that is associated with the user for which the recommendations are generated. As a result, a single list of recommendations 309 is generated. This list is highly personalised for the individual user although it is also based on anonymous user ratings from a plurality of users. In the example, the user preference profile 307 may indicate that the user has a high preference for sports programs, does not like soaps, and has a medium preference for movies. Accordingly, the final list has a high number of sport programmes, a lower number of *s.

movies and no soaps recommended.

S..... * S

In the example, the generation of recommended content item lists for each user rating group is based entirely on information which is not specific to the individual user for which the recommendation list is generated but rather is associated with the entire group of users that use the device. Thus, the second recommendation processor 207 uses an individual user preference profile to modify the user group preferences and characteristics to more closely adapt to that of the individual user. However, this processing is performed without requiring that all the data is processed or sorted for the individual user. Thus, a low complexity, flexible and accurate content item recommendation is achieved. Specifically, in some embodiments, the grouping of user ratings and the content item recommendations for each user rating group may be common for all users with the only individual personalisation being introduced by the second recommendation processor 207 in response to the user preference profile.

The list generated by the second recommendation processor 207 can be fed to the recommendation output 111 to be presented to the user. The user then provides feedback which is used to update the user preference profile. Specifically, the user may indicate a specific like or dislike for a specific content item on the list of recommendations, and the user preference profile processor 107 can proceed to increase or decrease the preference indication for the user *::::* rating group to which this content item belongs. The modified user preference profile can then be stored and can be used for generation of a list of recommendations the next S..

* time this is requested by the user. Alternatively or additionally, the modified user preference profile may be used immediately to generate an updated list of recommendations. For example, the selection of content items from the plurality of lists corresponding to the individual rating groups can be repeated with the modified user preference profile without necessitating any repetition of the processing required to generate the rating group lists.

In some embodiments, the user rating groups are stored for each individual user and the grouping into the user rating groups may be different for different users. In such an example, after providing feedback on the recommended list, the user may decide to store the final configuration of user rating groups for later reuse. In such a case, the new groups can replace the previously stored groupings.

FIG. 4 illustrates an example of a method of content item recommendation in accordance with some embodiments of the invention.

The method initiates in step 401 wherein anonymous user ratings for content items are received from a plurality of users.

Step 401 is followed by step 403 wherein an identity for a first user is determined.

Step 403 is followed by step 405 wherein a first set of content item recommendations is generated in response to the :. 15 anonymous user ratings and a first user preference profile * for the first user. ***

Step 405 is followed by step 407 wherein the first set of content item recommendations is presented to the first user.

Step 407 is followed by step 409 wherein user preference feedback is received for the first set of content item recommendations from the first user.

Step 409 is followed by step 411 wherein the first user preference profile is modified in response to the user preference input to generate a modified user preference profile.

Step 411 is followed by step 413 wherein a second set of recommendations is generated for the first user in response to the modified user preference profile.

It will be appreciated that the above description for clarity has described embodiments of the invention with reference to different functional units and processors.

However, it will be apparent that any suitable distribution of functionality between different functional units or processors may be used without detracting from the invention. For example, functionality illustrated to be performed by separate processors or controllers may be performed by the same processor or controllers. Hence, references to specific functional units are only to be seen as references to suitable means for providing the described :.::. functionality rather than indicative of a strict logical or *::::* physical structure or organization. S.

The invention can be implemented in any suitable form *55 * including hardware, software, firmware or any combination of these. The invention may optionally be implemented at least partly as computer software running on one or more data processors and/or digital signal processors. The elements and components of an embodiment of the invention may be physically, functionally and logically implemented in any suitable way. Indeed the functionality may be implemented in a single unit, in a plurality of units or as part of other functional units. As such, the invention may be implemented in a single unit or may be physically and functionally distributed between different units and processors.

Although the present invention has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Rather, the scope of the present invention is limited only by the accompanying claims. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognize that various features of the described embodiments may be combined in accordance with the invention. In the claims, the term comprising does not exclude the presence of other elements or steps.

Furthermore, although individually listed, a plurality of means, elements or method steps may be implemented by e.g. a single unit or processor. Additionally, although individual features may be included in different claims, these may :.:::. possibly be advantageously combined, and the inclusion in different claims does not imply that a combination of features is not feasible and/or advantageous. Also the inclusion of a feature in one category of claims does not * imply a limitation to this category but rather indicates that the feature is equally applicable to other claim categories as appropriate. Furthermore, the order of features in the claims does not imply any specific order in which the features must be worked and in particular the order of individual steps in a method claim does not imply that the steps must be performed in this order. Rather, the steps may be performed in any suitable order.

Claims

CLAIMS

1. An apparatus for content item recommendation, the apparatus comprising: means for receiving anonymous user ratings for content items from a plurality of users; means for determining an identity for a first user; generating means for generating a first set of content item recommendations in response to the anonymous user ratings and a first user preference profile for the first user; means for presenting the first set of content item ::::. recommendations to the first user; means for receiving user preference feedback for the first set of content item recommendations from the first * S * user; S..

* modifying means for modifying the first user preference profile in response to the user preference feedback to generate a modified user preference profile; and means for generating a second set of recommendations for the first user in response to the modified user preference profile.

2. The apparatus of claim 1 further comprising: storage means for storing user preference profiles; retrieving means for retrieving the first user preference profile in response to the identity of the first user; and means for storing the modified user preference profile as a user preference profile belonging to the identity.

3. The apparatus of claim 2 wherein the retrieving means is arranged to retrieve a default user preference profile as the first user preference profile if no user preference profile is stored for the identity.

4. The apparatus of claim 3 wherein the default user preference profile corresponds to an equal preference for all content item categories.

5. The apparatus of any previous claim wherein the first user preference profile comprises a plurality of preference indications for different content item categories and the modifying means is arranged to modify the preference indication of a first content category in response to receiving a user preference feedback indication for a content item of the first set of content item * recommendations belonging to the first category.

6. The apparatus of any previous claim wherein the generating means comprises: grouping means for grouping the anonymous user ratings into rating groups in response to a content item match criterion, each user rating comprising content item

description data and preference data;

means for receiving content item data for a plurality of content items; first recommendation means for generating a set of content item recommendations for each rating group in response to the content item data and user ratings of that rating group; and second recommendation means for generating the first set of content item recommendations by combining the sets of content item recommendations for each rating group in response to the first user preference profile, the first user preference profile comprising a user preference indication for each rating group.

7. The apparatus of claim 6 wherein the first recommendation means is arranged to match a first content item of the plurality of content items to at least a first rating group and to assign a preference value for the first content item in response to the preference data of the first rating group.

8. The apparatus of claim 7 wherein the second recommendation means is arranged to modify the preference indication for the first rating group in response to the preference value for the first rating group.

9. The apparatus of claim 7 or 8 wherein the second : recommendation means is arranged to combine the sets of content item recommendations by selecting content items in response to the preference indications for each rating group.

10. The apparatus of the claims 6 to 9 wherein the second recommendation means is arranged to select a number of content items included in the single set of content item recommendations for a given rating group in response to the preference indication of the given rating group.

11. The apparatus of any of the previous claims 6 to 10 wherein the modifying means is arranged to generate the modified user preference profile by modifying a preference indication for a ratings group in response to the user preference feedback.

12. The apparatus of claim 11 wherein the user preference feedback comprises a user preference feedback for a first content item of the first set of content item recommendations and the modifying means is arranged to generate the modified user preference profile by modifying a user preference indication for a ratings group to which the first content item belongs in response to the user preference feedback.

13. The apparatus of any of the previous claims 6 to 12 I...

wherein the content item match criterion comprises a content match criterion. S..

14. The apparatus of any of the previous claims 6 to 13 wherein the content item match criterion comprises a user preference indication match criterion.

15. The apparatus of any of the previous claims 6 to 14 arranged to generate content item recommendations for a plurality of users and the rating groups are common to a plurality of users 16. The apparatus of any of the previous claims 6 to 15 further comprising: means for receiving a request for content item recommendations and in response determining if any user ratings have been generated since a previous grouping; and wherein the grouping means is arranged to update the grouping of user ratings to include the user ratings generated since the previous grouping.

17. The apparatus of any of the previous claims 6 to 16 further comprising means for storing the rating groups and wherein the first and second recommendation means is arranged to use rating groups from a previous generation of user recommendations.

18. The apparatus of any previous claim wherein the means for receiving content item data is arranged to extract at least some of the content item data from an Electronic S...

Programme Guide. :. 15

* 19. A method of content item recommendation, the method

SSS

comprising: receiving anonymous user ratings for content items from a plurality of users; determining an identity for a first user; generating a first set of content item recommendations in response to the anonymous user ratings and a first user preference profile for the first user; presenting the first set of content item recommendations to the first user; receiving user preference feedback for the first set of content item recommendations from the first user; modifying the first user preference profile in response to the user preference feedback to generate a modified user preference profile; and generating a second set of recommendations for the first user in response to the modified user preference profile.

20. A computer program product enabling the carrying out of a method according to claim 19. * S. * I I *SS. S... * * *SSS *S * I * S.. S..

I

S

* SS S S I * S S. SI * S I * S