WO2008103546A1 - Method and apparatus for personalisation of applications - Google Patents

Method and apparatus for personalisation of applications Download PDF

Info

Publication number
WO2008103546A1
WO2008103546A1 PCT/US2008/053030 US2008053030W WO2008103546A1 WO 2008103546 A1 WO2008103546 A1 WO 2008103546A1 US 2008053030 W US2008053030 W US 2008053030W WO 2008103546 A1 WO2008103546 A1 WO 2008103546A1
Authority
WO
WIPO (PCT)
Prior art keywords
application
user
personalisation
profile data
user preference
Prior art date
Application number
PCT/US2008/053030
Other languages
French (fr)
Inventor
Jerome Picault
Jean Millerat
Myriam Ribiere
Original Assignee
Motorola, Inc.
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
Priority to GB0703166A priority Critical patent/GB2446618B/en
Priority to GB0703166.9 priority
Application filed by Motorola, Inc. filed Critical Motorola, Inc.
Publication of WO2008103546A1 publication Critical patent/WO2008103546A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/16Analogue secrecy systems; Analogue subscription systems
    • H04N7/173Analogue secrecy systems; Analogue subscription systems with two-way working, e.g. subscriber sending a programme selection signal
    • H04N7/17309Transmission or handling of upstream communications
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43Querying
    • G06F16/435Filtering based on additional data, e.g. user or group profiles
    • G06F16/437Administration of user profiles, e.g. generation, initialisation, adaptation, distribution
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/953Querying, e.g. by the use of web search engines
    • G06F16/9535Search customisation based on user profiles and personalisation
    • 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
    • H04N21/454Content or additional data filtering, e.g. blocking advertisements
    • 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
    • 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

Abstract

A plurality of personalisation servers (120) comprise a receiver (301, 303) for receiving application non-specific psychological profile data for a user from any remote device (103) out of a plurality of remote devices (103). A rule processor (307) provides a set of application specific rules relating psychological profile data values to user preferences for a user application where the application specific rules are associated with a first application. A preference processor (305) generates a user preference for the user in response to the psychological profile data and the application specific rules, and an application processor (309) adapts the operation of the first application in response to the user preference. A transmitter then transmits the application output data to the remote device (103). Each of the remote devices (103) comprises functionality for transmitting psychological profile data to any personalisation device (101) out of the personalisation devices (101).

Description

METHOD AND APPARATUS FOR PERSONALISATION OF APPLICATIONS

Field of the invention

The invention relates to a method and apparatus for personalisation of applications and in particular, but not exclusively, to personalisation of recommending applications recommending content items such as television programmes, music etc.

Background of the Invention

In recent years, the availability and provision of multimedia and entertainment content has increased substantially. For example, the number of available television and radio channels has grown considerably and the 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.

Similarly, an increasing number of services and applications with many different options and customisation features are becoming available to the user.

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, personalising services etc .

In order to enhance the user experience, it is advantageous to personalise applications and e.g. recommendations to the individual user as much as possible. 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 data by the prediction algorithm.

Furthermore, people increasingly use a wide range of electronic devices for different purposes and with different capabilities (e.g. cell phone, PDA, MP3 players, set-top boxes, personal computers, etc.) All these devices are running more and more complex applications with many applications using some element of personalisation to provide a better or simplified user experience .

Personalisation technology usually involves the application developing a user profile which contains the user's preferences determined e.g. based on the previous behaviour of the user. A prediction algorithm then uses the preferences to infer suitable personalisation actions.

User models for determining user preferences tend to focus on aspects which are easy to measure and evaluate technically such as use demographics or previous user operations and selections. E.g. Conventional recommender systems recommend content after having determined (through explicit or implicit methods) that feature X of a product or content Y is of interest to the user or by using correlations e.g. in product consumption between different users. Thus, the criteria used for generating recommendations are based on "descriptive" and objective attributes of the content to be filtered.

Furthermore, the user preference is typically generated to provide exactly the information needed by the specific prediction algorithm and is structured in the specific format required by the prediction algorithm. Indeed, the user preference profile generation and the prediction algorithm are normally closely integrated and developed together .

However, such an approach has the disadvantage that it does not provide a practical reuse of user data and requires the user to specifically interact with an application in order to personalise the application.

E.g. preferences generated for one web site application cannot directly be used for another web site. Moreover, if users want to use multiple services with personalised features, they have to generate a dedicated user profile for each service. However, this is very complex and impractical as a large number of services are normally accessed by a typical user.

Furthermore, some systems have been proposed where reuseability is achieved by generating very complex user profiles and storing these centrally. However, these systems tend to be complex and impractical and tend to require very large user profiles and/or algorithms which are standardised to a very detailed level. Accordingly they tend to be difficult to integrate with existing systems and applications and often require major architectural changes.

Hence, in contrast to the world of human interactions where people can automatically and flexibly adapt to the specifics of other people involved in the interaction, the technical domain requires that the input personalisation data for a specific application meets the specific requirements and data formats implemented by that algorithm. Accordingly, in the technical domain there exists a problem in enabling a variety of applications to interface to the same device or client without this being specifically designed therefor. Furthermore, generating a specific standardised interface tends to require a high complexity in order to provide an accurate personalisation for a range of different applications .

Furthermore, in order to provide accurate personalisation, existing personalisation approaches tend to use very complex algorithms, which are often based on years of research. This complexity arises both in relation to user data gathering and the algorithm used for generating the personalisation prediction. However, despite such complexity, the accuracy of the prediction/ personalisation tends to be suboptimal. Hence, an improved system would be advantageous and in particular a personalisation system allowing increased flexibility, facilitated operation, improved user experience, reduced complexity, improved personalisation accuracy, improved reuse and/or improved personalisation operation 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.

According to a first aspect of the invention there is provided a personalisation apparatus comprising: receiving means for receiving application non-specific psychological profile data for a user; means for providing a set of application specific rules relating psychological personality data values to user preferences, the application specific rules being associated with a first application; preference means for generating a user preference for the user in response to the psychological profile data and the application specific rules; and application means for adapting the operation of the first application in response to the user preference.

The invention may allow personalisation of an application while allowing this application to be accessible by a variety of different clients and/or devices. A user preference may be determined from application nonspecific psychological profile data which depends only on the user and not on any characteristics of the application. Accordingly, the psychological profile data may be used to personalise a variety of different applications and specifically the apparatus may allow personalisation of the application without requiring any application specific user data. Furthermore, the invention may allow accurate personalisation for the specific application as the psychological personality data provides a strong indication of characteristics of the user which are often strongly correlated with typical user preferences. Furthermore, the combination of application non-specific psychological profile data and application specific rules allows the personalisation to closely reflect not only the user but also the specific characteristics of the application.

The invention may address the problem of how a given client/device can access a variety of different applications while maintaining low complexity and obtaining a high degree of accurate personalisation.

The application non-specific psychological profile data may be data which is generic, shared and/or application independent. Specifically, non-specific psychological profile data may depend only on characteristics of the user and may specifically reflect only personality characteristics of the user.

The psychological profile data may comprise an indication of at least one personality category for the user out of a plurality of predefined personality categories and or personality parameter values for the user for a plurality of predefined personality parameters. The predefined personality categories and/or predefined personality parameters may be commonly defined for all users.

The user preference may be a combined user preference comprising a plurality of individual user preferences for different features/parameters. The application specific rules may contain one or more application specific rules.

According to another aspect of the invention, there is provided a system comprising: a plurality of personalisation servers, each server comprising: receiving means for receiving application non-specific psychological profile data for a user from any remote device out of a plurality of remote devices, means for providing a set of application specific rules relating psychological profile data values to user preferences for a user application, the application specific rules being associated with a first application, preference means for generating a user preference for the user in response to the psychological profile data and the application specific rules, application means for adapting the operation of the first application in response to the user preference, and means for transmitting application output data to a remote device of the plurality of remote devices; and the plurality of remote devices, each remote device comprising: means for transmitting psychological profile data to any personalisation device out of the plurality of personalisation devices, and means for receiving application output data from the personalisation device.

According to another aspect of the invention, there is provided a method of personalising an application, the method comprising: receiving application non-specific psychological profile data for a user; providing a set of application specific rules relating psychological personality data values to user preferences, the application specific rules being associated with a first application; generating a user preference for the user in response to the psychological profile data and the application specific rules; and adapting the operation of the first application in response to the user preference.

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 illustrates an example of a communication system in accordance with some embodiments of the invention;

FIG. 2 illustrates an example of an interaction between an application server 101 and a client device in accordance with some embodiments of the invention;

FIG. 3 illustrates an example of an application server in accordance with some embodiments of the invention;

FIG. 4 illustrates an example of a client device in accordance with some embodiments of the invention; and FIG. 5 illustrates method of personalising an application in accordance with some embodiments of the invention.

Detailed Description of Some Embodiments of the Invention

FIG. 1 illustrates an example of a communication system in accordance with some embodiments of the invention. The system comprises a number of personalisation servers/ application servers 101 and a number of remote devices/ client devices 103. Each of the application servers 101 executes a different application to provide a different service to users of the client devices 103. Any application server 101 may be accessed by any of the client devices 103. For example, one application server 101 may perform a recommendation application which can generate content recommendations for e.g. television programmes and radio programmes, another application server 103 may perform a news provision application which provides a current news update, another application server 101 may execute a shopping application allowing a user to browse a catalogue and select and purchase specific items therefrom etc.

Each of the application servers 101 may be accessed by any of the client devices 103. Thus, depending on the current user activity, the client device 103 can access the appropriate application server 101 to obtain the desired service. For example, in order to have a television programme recommended, a first client device 103 may access a first application server 101 and in order to be provided with the latest news the same client device 103 may access a second application server 101. In the system, all the applications executed by the application servers 101 can be personalised to specifically suit the characteristics of the user accessing the application using the client device 103. For example, the television programme recommendations can be targeted to the user, the news may be provided in a format which is particular attractive to the user and the items for sale can be ordered such that items most likely to be of interest to the user will be presented first.

In the specific example, the client devices 103 and application servers 101 communicate wirelessly for example over a Wireless Local Area Network (WLAN) . However, it will be appreciated that in other embodiments other means of communication may be used. For example, all the client devices 103 and application servers 101 may be coupled together via the Internet.

In the human domain, provision of personalised information can easily be achieved. For example, if a person telephones a shop, the shopkeeper can quickly ask questions that allow him to identify which products may be of specific interest to the person.

However, in the technical domain such personalisation becomes significantly more difficult and specifically the interaction and reuse of personality information between different applications becomes difficult. In order to ensure efficient operation with accurate personalisation conventional systems tend to use user preference profiles that are specifically developed for the individual application. Although this approach allows efficient personalisation, it is very cumbersome in scenarios where many different applications may be accessed by the same user. This is becoming an increasing problem as the number of applications and services accessed via the electronic domain is becoming increasingly varied and popular .

The system of FIG. 1 provides a solution wherein application non-specific psychological profile data for the individual user is stored in the client device 103 of that user. The psychological profile data represents a psychological profile of the user which is unrelated to any specific application or user interaction but rather represents the user's general psychological profile. Specifically, a user may be assigned a set of scores on predefined psychological dimensions which enables discrimination between different users.

This psychological profile data is accordingly completely independent of any characteristics or requirements of any specific application. Furthermore, it provides a relatively accurate but concise representation of many individual characteristics of the user. Furthermore, this psychological profile of the user can be represented by relatively little data thereby allowing a very low complexity implementation with low computational and memory requirements.

In the system, a client device 103 may transmit the psychological profile data to an application server 101 when accessing an application executed by that server 101. The application server 101 applies a set of application specific rules to the received psychological profile data in order to determine likely user preferences for the user. For example, for a user having psychological profile data indicating a high level of neuroticism, a high preference value for horror films may be generated by a television programme recommendation application server 101.

The application server 101 then modifies the operation of the application to match the specific user preferences derived from the psychological profile data and the application specific rules thereby resulting in a personalisation of the application (for example, a recommendation of a horror film may be generated) .

Thus, in contrast to existing systems, the client device 103 does not provide a user preference profile which is used for personalisation but rather provides generic and common psychological profile data reflecting a generic characterisation of a personality of the user rather than of his preferences.

As the psychological profile data is application independent, it can be used by the client device 103 when accessing any of the application servers 101. Furthermore, as psychological profile information is used this can easily be generated separately and independently of any application. Furthermore, as such psychological data has been shown to be a strong indication of user preferences in many cases a highly efficient personalisation of the individual application can be achieved. Also, this personalisation may efficiently take the specific characteristics and properties of the individual application into account by the application of application specific rules. Furthermore, these application specific rules can in many embodiments be relatively simple thereby leading to a very low complexity implementation. Also, as the application specific rules relates only to the specific application, these can be developed individually for each application and thus a highly complex system allowing large number of different client devices 103 to access a large number of different and independent application servers 101 can be provided without requiring a complex and cumbersome coordination or common development of the individual application servers 101.

The described approach may in particular provide a generic method associating a psychological category including personality traits or a set of scores on a predefined set of psychological dimensions to a user in order to enable a simple personalised interaction with potentially any kind of application.

FIG. 2 illustrates an example of an interaction between an application server 101 and a client device 103 in accordance with some embodiments of the invention.

FIG. 3 illustrates an example of an application server 101 in accordance with some embodiments of the invention. The application server 101 comprises a transceiver 301 which is arranged to communicate with the client devices 101 (the remote devices) over a suitable communication network which in the present example is the wireless network. The transceiver 301 is coupled to a profile data processor 303 which is arranged to receive the application non-specific psychological profile data for the user. Specifically, in the example, the profile data processor 303 receives the psychological profile data from a client device 101 together with a request for an output from the application. For example, the client devise 101 may request a content item recommendation and include the psychological profile data in the request message.

The profile data processor 303 is coupled to a preference processor 305 which is further coupled to a rule processor 307. The rule processor 307 provides the set of application specific rules to the preference processor 305. The application specific rules relate psychological personality data values to user preferences. For example, the rules may specify that if the psychological personality data indicates that the user belongs to a specific predefined psychological category, a specific user preference should be included in a user preference profile. The preference processor 305 applies these rules to the psychological profile data in order to generate at least one user preference. In the specific example, the preference processor 305 generates a user preference profile comprising a plurality of user preferences being determined in response to different elements of the psychological profile data.

It will be appreciated that in some embodiments only a single application specific rule may be used. The preference processor 305 is coupled to an application processor 309 which is further coupled to the transceiver 301. The application processor 309 executes the specific application of the application server 101. Furthermore, the application processor 309 adapts the operation of the application in response to the user preference. For example, a television programme recommendation application would modify its operation to provide an increased bias for a specific type of television programmes for which the user preference indicates that the user has a high preference. The output data of the application is then transmitted back to the client device of 103 by the transceiver 301.

Thus, the user of the client devise 101 may request a specific application to be executed and in response receive personalised data without needing to provide any specific input for the specific application. For example, a user may request a television programme recommendation and be provided with a recommendation that is particularly suitable for him without having to enter any specific user information.

It will be appreciated that in different embodiments, the psychological profile data may be based on different psychological characteristics. However, in the system of FIG. 2, the psychological profile data is based on general and predefined psychological classifications/ characteristics which have been developed in the psychological sciences to characterise human personalities . For example, Jung suggested that a person's ability to process different information is limited by their particular personality stereotype of which there are sixteen fundamental types. For example, people can be either Extroverts or Introverts, depending on the direction of their activity; Thinking, Feeling, Sensing, Intuitive, according to their own information pathways; Judging or Perceiving, depending on the method in which they process received information. More specifically Jung suggested the following classification:

— Extroverts vs. Introverts: Extroverts are directed towards the objective world whereas Introverts are directed towards the subjective world.

— Sensing vs. Intuition: Sensing is an ability to deal with information on the basis of its physical qualities and how it is affected by other information. Intuition is an ability to deal with the information on the basis of its hidden potential and its possible existence.

— Thinking vs. Feeling: Thinking is an ability to deal with information on the basis of its structure and its function. Feeling is an ability to deal with information on the basis of its initial energetic condition and its interactions.

— Perceiving vs. Judging: Perceiving types are motivated into activity by the changes in a situation. Judging types are motivated into activity by their decisions resulting from the changes in a situation.

Based on this classification, the four pairs of preferences define eight different ways of dealing with information, which in turn result in sixteen psychological stereotypes:

ENTp, ISFp, ESFj, INTj, ENFj, ISTj, ESTp, INFp, ESFp, INTp, ENTj, ISFj, ESTj, INFj, ENFp and ISTp,

where E - Extrovert, I - Introvert, S - Sensing, N - Intuitive, T - Thinking, F - Feeling, j - Judging, p - Perceiving. So, ENTp for example would be Extrovert, Intuitive, Thinking and Perceiving type.

In the last decade, the psychology scientific community has approached a consensus on a general taxonomy of personality traits, known as the "Big Five" personality parameters or dimensions. These dimensions do not represent a particular theoretical perspective but are derived from analyses of the natural-language terms people use to describe themselves and others. Rather than replacing all previous systems, the Big Five taxonomy serves an integrative function because it can represent the various and diverse systems of personality description in a common framework.

Researchers have shown that it is possible to define 5 replicable, broad dimensions of personality, and they can be summarized by the broad concepts of: extraversion, agreeableness, conscientiousness, neuroticism and openness to experience. Contrary to Jung' s approach, the Big-Five approach does not classify people in a fixed set of classes. Rather, Big-Five related tests provide a numeric value for each of the five dimensions defined above.

Several tests are known for determining a value for each of these five dimensions and for classifying a person into a specific category (such as the sixteen categories defined by Jung) . Typically, such tests involve a user filling out a questionnaire by responding to a number of test questions or selecting between different options.

In some embodiments, the psychological profile data comprises an indication of at least one personality category for the user out of a plurality of predefined personality categories. Specifically, the predefined personality categories may correspond to specific general personality stereotypes such as e.g. the sixteen stereotypes defined by Jung. In the following, such a stereotype will be referred to as a ψ-stereotype (or psychographic stereotype) .

In some embodiments, the psychological profile data comprises personality parameter values for the user for a plurality of predefined personality parameters (or personality dimensions) . For example, the psychological profile data can comprise a user specific value for each of the Big Five personality traits. Specifically, the term ψ-profile (or psychographic profile) is used to denote a characterization of individual users based on a list of scores on a predefined set of psychological dimensions . Thus, the psychological profile data comprises data which follows standard psychological profiling dimensions which are common and standardised and which accordingly can allow a relatively precise personalisation and a broad re-use .

As an example, a ψ-profile may be determined for a user by asking the user to fill in a psychological questionnaire on the client device 103. The device then uses predetermined relations to determine values for the specific parameters (e.g. for the Big Five, a numerical value will be assigned to the psychological parameters/ dimensions E [extraversion] , A [agreableness] , C [conscientiousness], N [neuroticism] and O [openness to experience] ) .

Alternatively or additionally, a user may be assigned a ψ-stereotype in a similar fashion, i.e. by filing out a predefined questionnaire for which there is a pre- established relationship between the user choices and the corresponding ψ-stereotype. The characterization of the user using a ψ-stereotype tends to be less precise than when using a ψ-profile.

The application specific rules are used to relate the general and generic user characterisation provided by the personality profile data to specific user preferences that are specifically applicable to the individual application.

Indeed, for many applications, a general personality characterisation provides a strong indication of the user's specific preferences. For example, extraversion relates to an individuals' ability to engage the environment. Extraverts typically display high levels of sociability, participation, and positive self-esteem and are characterized as sociable, lively, active, assertive, carefree, dominant, venturesome and sensation-seeking. Neuroticism identifies the degree to which an individual perceives the world as threatening, problematic and distressing. First-order traits are: anxious, depressed, guilt feelings, low self-esteem, tense, irrational, shy, moody and emotional. Psychotism points to an individual's level of egocentricity, autonomy, social deviance, and impulsivity; these people are characterized as: aggressive, cold, egocentric, impersonal, impulsive, antisocial, unempathic, creative and tough-minded.

Such observations allow the developer of the individual application to generate application specific rules relating the user characteristics to specific application specific user preferences that are relevant for the individual application.

For example, the application specific rules can comprise a rule which sets the user preference to a predetermined user preference if the personality parameter values are within predetermined intervals. For example, for a ψ- profile comprising a number of personality parameters values (referred to as personality_scores) , a rule may be specified as:

personality _ scorel ≥ aγ

=^> preferencea ≥ λ personality _ scoren ≥ an i.e. if the first personality score is above a first threshold, the second personality score is above a second threshold etc then a specific user preference is set to be higher than a given predetermined value λ.

As another example, for ψ-stereotype psychological profile data, the first rule processor 307 may store an entire user preference profile for each of the possible ψ-stereotypes . Thus, the preference processor 305 can simply compare the received user ψ-stereotype to the stored values and retrieve the user preference profile for the matching stereotype.

As another example, the application specific rules can comprise a user preference value given as a function of a correlation between the personality parameters values and reference personality parameters values for the user preference value. For example, a high preference value for a specific type of content items may be associated with a specific ψ-profile and the corresponding preference value for the current user may be determined depending on how closely his ψ-profile matches the specific ψ-profile.

It will be appreciated that the application developer can use the application specific rules to customise the generic psychological profile data to the specific characteristics and requirements for the specific application. The application developer can for example develop the application specific rules based on expert (sociologists and psychologists) reports and/or specific user studies.

FIG. 4 illustrates an example of a client device 103 in accordance with some embodiments of the invention.

The client device 103 comprises transceiver 401 which is arranged to communicate with any of the application servers 101 over the air interface. The transceiver 401 is coupled to a transmit controller 403 which is arranged to cause a request message to be transmitted to the application server 101 requesting that the specific application is executed and that output data is provided to the client device 103.

The transmit controller 403 is coupled to a profile data controller 405 which is further coupled to a profile data store 407. The profile data store 407 comprises psychological profile data stored for the individual user of the client device 103. When the transmit controller 403 transmits the request message, the profile data controller 405 retrieves the stored psychological profile data from the profile data store 407 and provides it to the transmit controller 403. The transmit controller 403 includes the psychological profile data in the request message which is transmitted to the application server 101.

The transceiver 401 furthermore comprises a receiver that receives the response message generated by the application server 101 and which comprises the output data from the execution of the application. In the example, the output data is fed to a presentation processor 407 which is coupled to a user interface 409. The user interface 409 can for example comprise a display and a keyboard. The presentation processor 401 processes the received output data and presents it to the user via the user interface 409. For example, for a content item recommendation application, the presentation processor 409 may control the display to provide an indication of the recommended content item.

The client device 103 may send different request messages depending on which specific service is required. For example, a different request message may be sent to a content item recommendation application then to a shopping application. However, the client device 103 is arranged to transmit the same psychological profile data to any of the application servers 101.

In the example of FIG. 4, the client device 103 furthermore comprises a profile data controller 413 coupled to the user interface 409 and the profile data store 407. The profile data controller 413 monitors the user pattern for the user and generates, modifies or adapts the psychological profile data in response to this user pattern.

Specifically, in the example, the ψ-profile or the ψ- stereotype may be learnt over time by analyzing user behaviour data. For example, a classification algorithm may be used based on training data constituted by a set of people with known ψ-profile or the ψ-stereotype and known application (s) behaviours. By comparing the behaviour of the current user to the training data, it is possible to generate a good estimate of the user' s ψ- profile or ψ-stereotype . In some cases, this method may be less accurate than using a questionnaire but can be used as a complement to the questionnaire method. E.g. the user behaviour inference technique may be used with a shorter version of a questionnaire thereby inconveniencing the user less.

In the described examples, the user preferences were generated by application specific rules. In some embodiments, the user preferences may furthermore be generated in response to application non-specific rules which relate psychological profile data values to user preferences. Thus, in some embodiments, the user preferences may be generated from both application- specific and application non-specific rules. For example, a set of generic rules (applicable to several applications) can be used to generate some user preferences whereas other user preferences are generated from the application specific rules. The personalisation of the application may then be performed in response to a combined user preference comprising all the individual user preferences.

Such an approach may facilitate application development and may allow some generic rules to be used. For example, the modality of the presentation of output data may be determined based on a generic rule, e.g. a specific personality category is associated with a visual presentation whereas another personality category is associated with a spoken presentation. This generic rule may be used for different applications, e.g. a content item recommendation application may generate the content item recommendations based on the application specific rules whereas the application non-specific rules are used to determine how the resulting recommendation is provided to the user (e.g. visually or by audio) .

The application non-specific rules may for example be developed on the basis of (sociologists and psychologists) reports and/or specific user studies.

In some embodiments, the application servers 101 can retrieve the non-specific rules from a remote server (not shown) . This remote server can serve a plurality of application servers 101 such that the same rules can be used by more than one application server 101. This may allow a practical way of achieving a facilitated application development while maintaining a high degree of flexibility in the personalisation of each application .

The application non-specific rules may correspond to the application specific rules and follow the same principles, syntax and/or protocol. For example the application non-specific rules can comprise a rule which sets the user preference to a predetermined user preference if the personality parameter values are within predetermined intervals. For example, for a ψ-profile comprising a number of personality parameters values (referred to as personality_scores) , a rule may be specified as:

personality _ scorel ≥ ax preferencea ≥ λ personality _ scoren ≥ an i.e. if the first personality score is above a first threshold, the second personality score is above a second threshold etc then a specific user preference is set to be higher than a given predetermined value λ.

As a specific example, a generic rule can be used to reflect that e.g. "Thinkers" prefer to obtain information from experts whereas "Feelers" prefer to obtain information from a community, e.g.:

C Vx from Community, receptiveuser (x) = high user e Feelers => <

[ Vx from Experts, receptiveuser(x) = low

Such a rule can e.g. be used by a decision-support system to display the right information in order to help the users select an item to purchase from an online store.

As another example, a generic rule may indicate that users with a high value for "Confidence" and "Openness" is allowed to be provided with recommendations that deviate significantly from core preferences, e.g:

Vrec,confidenceLevel(rec) > a ∞ l/ openness (user) => allowed (rec)

It will be appreciated that the personalisation of the application can include many features and aspects including for example content item filtering, modification of a user interface and in particular the kind and details of the information presented, the modalities that are the most appropriate to the current user etc.

In some cases where the presentation to the user is adapted at the client device 103, the application server 101 may be arranged to transmit control data for the presentation output and the client device 103 may be arranged to adapt the presentation according to the control data.

In the following, some examples of specific use cases for the described principles are given.

One of the application servers 101 may for example execute a content item recommendation application where the application means generates one or more content item recommendations in response to the user preference. The content item recommendations may for example provide recommendations for television programmes, radio programmes, songs etc.

Thus, in this example the application processor 309, comprise functionality for filtering a large number of potential content items depending on the user preference in order to select one or more content items which are likely to be of particular interest to the user.

Thus, the system may utilise the fact that a correlation exists between the personality of the user and the preferred content items. For example, tests have indicated that people scoring high on neuroticism have a strong interest in information/news television and 'downbeat' music whereas those scoring high on psychoticism showed a stronger preference for graphically violent horror movies (e.g. Alien) and less interest in typical television content such as situation-comedy (e.g. Cosby Show), and both romance (e.g. Dirty Dancing) and comedy movies (e.g. Crocodile Dundee). Similarly, tests have found a correlation between personality and music preferences and Internet content preferences where extraverts tends to prefer leisure services (erotic websites, random surfing) whereas users scoring high on neuroticism had a negative association with information services (work-related information, studies-related information) .

The user preference generated from the psychological profile data can be used to determine preferences for the individual content items. However, alternatively or additionally it may also be used to determine a distribution variety of the generated recommendations. E.g. the diversity of information/content items proposed to the user may be adjusted depending on the psychological profile data. For example those scoring high on openness may be proposed more risky recommendations than those scoring low, or may even be proposed randomly chosen content items in order to introduce more diversity of the recommended content.

Specifically, the application specific rules can set a user preference to indicate a high preference for an increased variety if the psychological profile data matches a predetermined psychological profile. If so, the content item recommendation is biased towards an increased variety of content items being recommended. As another example, the content item recommendation may

(at least partly) be based on the user preferences of a group of people rather than only on the individual user.

For example, in user-based collaborative filtering, the computation of recommendations is based on a group of similarly minded users. However, traditionally similarity is only based on objective (measurable) criteria such as the analysis of purchase history or ratings entered by the user. This captures only one dimension of similarity between users and does not capture all the subtleties of consumers. In some embodiments, the psychological profile data may alternatively or additionally be used to determine a group of similarly minded users. For example, a number of users may be grouped together if their psychological profile data meets a given similarity criterion. For example, all users having the same ψ- stereotype can be grouped together. A group user preference is then calculated using individual user preferences of these users and the content item recommendation is generated accordingly.

The described approach can also be used as a complement/enhancement of existing personalisation techniques. For example, the psychological profile data may be used to generate an initial user preference profile which is subsequently adapted by a learning algorithm based on the user's behaviour.

E.g. a solution for bootstrapping a user profile is to use stereotypes. When a new user registers for a personalised application, the ψ-stereotype of that user can be used to select a predetermined reference user preference profile suitable for users having that ψ- stereotype. This reference user preference profile can then be used as an initial user preference profile which can subsequently be updated based on user inputs reflecting the user's behaviour. For example, the user preference profile may be updated such that the preference value for the types of content items that are selected by the user is increased whereas the preference value for content items that are not selected by the user is decreased.

In some embodiments, the personalisation of the application may comprise adapting an avatar employed by the application. For example, an avatar may be selected from a group of predetermined avatars depending on the ψ- stereotype or profile of the user. An avatar is a character that represents the user and which can be personalised and used for interacting with a system (for instance in a game or with friends on the web (chat) ) . Furthermore, the described approach would allow computerized avatars to mimic the user's personality in order to deliver more satisfying interaction experiences.

FIG. 5 illustrates method of personalising an application in accordance with some embodiments of the invention.

The method starts in step 501 wherein application nonspecific psychological profile data for a user is received.

Step 501 is followed by step 503 wherein a set of application specific rules relating psychological personality data values to user preferences is provided. The application specific rules are associated with a first application.

Step 503 is followed by step 505 wherein a user preference for the user is generated in response to the psychological profile data and the application specific rules .

Step 505 is followed by step 507 wherein the operation of the first application is adapted in response to the user preference .

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.

The invention can be implemented in any suitable form 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

1. A personalisation apparatus comprising receiving means for receiving application non- specific psychological profile data for a user; means for providing a set of application specific rules relating psychological personality data values to user preferences, the application specific rules being associated with a first application; preference means for generating a user preference for the user in response to the psychological profile data and the application specific rules; and application means for adapting the operation of the first application in response to the user preference.
2. The personalisation apparatus of claim 1 wherein the psychological profile data comprises an indication of at least one personality category for the user out of a plurality of predefined personality categories.
3. The personalisation apparatus of claim 1 wherein the psychological profile data comprises personality parameter values for the user for a plurality of predefined personality parameters.
4. The personalisation apparatus of claim 3 wherein the application specific rules comprise a rule setting the user preference to a predetermined user preference if the personality parameter values are within predetermined intervals.
5. The personalisation apparatus of claim 3 wherein the application specific rules comprise a user preference value given as a function of a correlation between the personality parameters values and reference personality parameters values for the user preference value.
6. The personalisation apparatus of claim 1 further comprising means for providing a set of application nonspecific rules relating psychological profile data values to user preferences; and wherein the preference means is further arranged to generate the user preference in response to the application non-specific rules.
7. The personalisation apparatus of claim 6 further comprising means for receiving the application nonspecific rules from a remote server serving a plurality of personalisation apparatuses.
8. The personalisation apparatus of claim 1 wherein the application is a content item recommendation application and the application means is arranged to generate a content item recommendation in response to the user preference .
9. The personalisation apparatus of claim 8 wherein the application specific rules comprise setting the user preference to indicate a preference for an increased variety of content items if the psychological profile data meets a criterion; and the application means is arranged to bias the content item recommendation towards an increased variety of content items in response to the user preference being indicative of the preference for the increased variety of content items.
10. The personalisation apparatus of claim 8 wherein the application means is arranged to generate the content item recommendation in response to a group user preference and the apparatus comprises means for generating the group user preference by combining user preferences of users having psychological profile data meeting a similarity criterion.
11. The personalisation apparatus of claim 1 wherein the user preference is a presentation user preference and the application means is arranged to adapt a user presentation of output data of the application in response to the user preference.
12. The personalisation apparatus of claim 1 wherein the application means is arranged to adapt an avatar employed by the application in response to the user preference.
13. The personalisation apparatus of claim 1 wherein the application means comprises: means for adapting the operation of the application in response to a user preference profile; means for generating an initial user preference profile in response to the user preference; and means for updating the user preference profile in response to a user input.
14. The personalisation apparatus of claim 1 wherein the receiving means is arranged to receive a request from a remote device, the request comprising the psychological profile data; and the application means is arranged to execute the application in response to the request and to transmit application output data to the remote device.
15. A system comprising: a plurality of personalisation servers, each server comprising receiving means for receiving application nonspecific psychological profile data for a user from any remote device out of a plurality of remote devices, means for providing a set of application specific rules relating psychological profile data values to user preferences for a user application, the application specific rules being associated with a first application, preference means for generating a user preference for the user in response to the psychological profile data and the application specific rules, application means for adapting the operation of the first application in response to the user preference, and means for transmitting application output data to a remote device of the plurality of remote devices; and the plurality of remote devices, each remote device comprising : means for transmitting psychological profile data to any personalisation device out of the plurality of personalisation devices, and means for receiving application output data from the personalisation device.
16. The system of claim 15 wherein at least one of the remote devices is arranged to transmit the same psychological profile data to personalisation devices associated with different applications.
17. The system of claim 15 wherein at least one of the remote devices comprises means for monitoring a user pattern of a user of the remote device and means for determining the psychological profile data in response to the user pattern.
18. A method of personalising an application, the method comprising: receiving application non-specific psychological profile data for a user; providing a set of application specific rules relating psychological personality data values to user preferences, the application specific rules being associated with a first application; generating a user preference for the user in response to the psychological profile data and the application specific rules; and adapting the operation of the first application in response to the user preference.
PCT/US2008/053030 2007-02-19 2008-02-05 Method and apparatus for personalisation of applications WO2008103546A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
GB0703166A GB2446618B (en) 2007-02-19 2007-02-19 Method and apparatus for personalisation of applications
GB0703166.9 2007-02-19

Publications (1)

Publication Number Publication Date
WO2008103546A1 true WO2008103546A1 (en) 2008-08-28

Family

ID=37908863

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2008/053030 WO2008103546A1 (en) 2007-02-19 2008-02-05 Method and apparatus for personalisation of applications

Country Status (2)

Country Link
GB (1) GB2446618B (en)
WO (1) WO2008103546A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020032564A1 (en) * 2018-08-08 2020-02-13 Samsung Electronics Co., Ltd. Electronic device and method for providing one or more items in response to user speech

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998047249A2 (en) * 1997-04-16 1998-10-22 News Datacom Limited Passenger aircraft entertainment system
WO2000031656A2 (en) * 1998-11-19 2000-06-02 Andersen Consulting, Llp A system, method and article of manufacture for effectively interacting with a network user
US20040128301A1 (en) * 2002-12-31 2004-07-01 Marcus Thint Method and apparatus for automatic updating of user profiles
US20050188220A1 (en) * 2002-07-01 2005-08-25 Mikael Nilsson Arrangement and a method relating to protection of end user data

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1762095A1 (en) * 2004-06-17 2007-03-14 Philips Electronics N.V. Personalized summaries using personality attributes

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1998047249A2 (en) * 1997-04-16 1998-10-22 News Datacom Limited Passenger aircraft entertainment system
WO2000031656A2 (en) * 1998-11-19 2000-06-02 Andersen Consulting, Llp A system, method and article of manufacture for effectively interacting with a network user
US20050188220A1 (en) * 2002-07-01 2005-08-25 Mikael Nilsson Arrangement and a method relating to protection of end user data
US20040128301A1 (en) * 2002-12-31 2004-07-01 Marcus Thint Method and apparatus for automatic updating of user profiles

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020032564A1 (en) * 2018-08-08 2020-02-13 Samsung Electronics Co., Ltd. Electronic device and method for providing one or more items in response to user speech

Also Published As

Publication number Publication date
GB2446618A (en) 2008-08-20
GB0703166D0 (en) 2007-03-28
GB2446618B (en) 2009-12-23

Similar Documents

Publication Publication Date Title
US9665832B2 (en) Estimating affective response to a token instance utilizing a predicted affective response to its background
US10387898B2 (en) Crowd-based personalized recommendations of food using measurements of affective response
Bobadilla et al. Recommender systems survey
US10572679B2 (en) Privacy-guided disclosure of crowd-based scores computed based on measurements of affective response
US9697288B2 (en) Active and passive personalization techniques
Tintarev et al. Explaining recommendations: Design and evaluation
Boksem et al. Brain responses to movie trailers predict individual preferences for movies and their population-wide commercial success
JP6291481B2 (en) Determining the subsequent part of the current media program
RU2611260C2 (en) Method and device to provide recommendations of multimedia resources
Ribeiro et al. Multiobjective pareto-efficient approaches for recommender systems
Pu et al. Evaluating recommender systems from the user’s perspective: survey of the state of the art
US8818931B2 (en) Comparative expertise level-based discovery system and method
Nagy et al. Imagined affordance: Reconstructing a keyword for communication theory
Quijano-Sanchez et al. Social factors in group recommender systems
US8589434B2 (en) Recommendations based on topic clusters
Cremonesi et al. Investigating the persuasion potential of recommender systems from a quality perspective: An empirical study
Herlocker Understanding and improving automated collaborative filtering systems
US20170213274A1 (en) Intent prediction based recommendation system using data combined from multiple channels
DE102015113942A1 (en) Rating of holiday destinations based on affective response
US9026484B2 (en) Personal taste assessment method and system
Konstan et al. Recommender systems: from algorithms to user experience
Ramanathan et al. Consuming with others: Social influences on moment-to-moment and retrospective evaluations of an experience
Herlocker et al. Explaining collaborative filtering recommendations
Masthoff Group recommender systems: aggregation, satisfaction and group attributes
US7072846B1 (en) Clusters for rapid artist-audience matching

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 08729027

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase in:

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 08729027

Country of ref document: EP

Kind code of ref document: A1