This application claims the benefit of Korean Provisional Patent Application Nos. 10-2014-0034388, 10-2014-0034395 and 10-2014-0034391 filed with the Korean Intellectual Property Office on Mar. 25, 2014, and Korean Patent Application Nos. 10-2015-0032779, 10-2015-0032783 and 10-2015-0032785 filed with the Korean Intellectual Property Office on Mar. 9, 2015, the disclosure of which is incorporated herein by reference in their entirety.
1. Technical Field
The present invention relates to recommending a service by use of a user description, more specifically to providing a recommendation description for providing a service suitable for a user through a user description.
2. Background Art
As a vast amount of data has become easily accessible owing to the advancement of the Internet and network technologies, customized analyses of expanded data, such as big data, have been risen to a new issue. That is, rather than accessing the data itself, selecting and supplying valuable data for each individual's purpose has become more important for the differentiation of a service. Exposure to a large amount of data is rather less preferred, and providing higher quality data at a right time at a right place secures a greater number loyal users. In order to differentiate the service among a countlessly large number of similar services, the service needs to be customized by analyzing a variety of contexts of users.
The present invention provides an apparatus and a method for recommending a service that can provide a recommendation description in order to provide a service customized for a user by use of a user description.
An aspect of the present invention provides an apparatus for recommending a service, which includes: a user description providing unit configured for storing a user description; a communication interface configured for receiving a request for recommendation of a service; and a recommendation engine configured for obtaining the user description corresponding to the request for recommendation of a service from the user description providing unit and generating a recommendation description by referring to the user description, wherein the user description includes at least one of UserProfileType, PersonProfileType, OrganizationProfileType, DeviceProfileType, GroupedProfileType, UsageHistoryTyp, EventType, interactionAtomType, artefactType, observableType, stateType, PreferenceType, EmotionType, VocabularySetType, ScheduleType, ActivityType, IntentionType, LanguageType, SpecialtyType, AccessibilityType, SocialInformationType and ObjectSharingType.
The UsageHistoryType may include multimediaExperienceType and DetailedUserInteractionType.
The PreferenceType may include at least one of AudioPresentationPreferencesType, DisplayPresentationPreferencesType, GraphicsPresentationPreferencesType, ServicePreferenceType, AudioPresentationPreferencesInfoType, TranslationPreferenceType, InterestedMediaType and WebLinkPreferencesType.
The LanguageType may include at least one of NameType, CompetenceReferenceType, LanguageRegionType, Type, ReadingLevelType, WritingLevelType, SpeakingLevelType and ListeningLevelType.
The CompetenceReferenceType may include CompetenceTestNameType, CompetenceLevelType, CompetenceTestURIType and CompetenceTestDateType.
The ScheduleType may include EventType, wherein the EventType may include at least one of SharedUser, RecurrenceInfoType, AlarmTimeType, AlarmFormatType and descriptionMethodType.
The apparatus for recommending a service may further include a service description providing unit configured for storing a service description, wherein the recommendation engine is configured for generating the recommendation description by referring to the service description and the user description corresponding to the request for recommendation of a service, and wherein the service description may include at least one of Service General Description, FormatType, ServiceTargetInformationType, ServiceTargetModelType, VocabularySetType, ServiceInterfaceType, RequiredInputDataType, InternalServicesType, InternalServiceType, LosslessAudioDBType, LossyAudioDBType, VideoDBType, ServiceObjectType and ObjectType.
The apparatus for recommending a service may further include a context description providing unit configured for storing a context description, wherein the recommendation engine is configured for generating the recommendation description by referring to the context description and the user description corresponding to the request for recommendation of a service, and wherein the context description may include at least one of ContextDescriptionType, ContextIdentificationType, DeviceCharacteristicsType, NewworkInfoType, LocationType, WeatherType, OtherEnvironmentalInfoType, AudioEnvironment, RecordingEnvironmentType and ContextPriorityType.
Another aspect of the present invention provides a method for recommending a service, the service being recommended by an apparatus for recommending a service. The method for recommending a service in accordance with an embodiment of the present invention includes: receiving a request for recommendation of a service; obtaining a user description corresponding to the request for recommendation of a service; and generating a recommendation description by referring to the user description, wherein the user description may include at least one of UserProfileType, PersonProfileType, OrganizationProfileType, DeviceProfileType, GroupedProfileType, UsageHistoryTyp, EventType, interactionAtomType, artefactType, observableType, stateType, PreferenceType, EmotionType, VocabularySetType, ScheduleType, ActivityType, IntentionType, LanguageType, SpecialtyType, AccessibilityType, SocialInformationType and ObjectSharingType.
The UsageHistoryType may include multimediaExperienceType and DetailedUserInteractionType.
The PreferenceType may include at least one of AudioPresentationPreferencesType, DisplayPresentationPreferencesType, GraphicsPresentationPreferencesType, ServicePreferenceType, AudioPresentationPreferencesInfoType, TranslationPreferenceType, InterestedMediaType and WebLinkPreferencesType.
The LanguageType may include at least one of NameType, CompetenceReferenceType, LanguageRegionType, Type, ReadingLevelType, WritingLevelType, SpeakingLevelType and ListeningLevelType.
The CompetenceReferenceType may include CompetenceTestNameType, CompetenceLevelType, CompetenceTestURIType and CompetenceTestDateType.
The ScheduleType may include EventType, wherein the EventType may include at least one of SharedUser, RecurrenceInfoType, AlarmTimeType, AlarmFormatType and descriptionMethodType.
The method for recommending a service may further include obtaining a service description corresponding to the request for recommendation of a service, wherein in the generating of the recommendation description by referring to the user description, the recommendation description is generated by referring to the user description and the service description, wherein the service description may include at least one of Service General Description, FormatType, ServiceTargetInformationType, ServiceTargetModelType, VocabularySetType, ServiceInterfaceType, RequiredInputDataType, InternalServicesType, InternalServiceType, LosslessAudioDBType, LossyAudioDBType, VideoDBType, ServiceObjectType and ObjectType.
The method for recommending a service may further include obtaining a context description corresponding to the request for recommendation of a service, wherein in the generating of the recommendation description by referring to the user description, the recommendation description is generated by referring to the user description and the context description, and wherein the context description may include at least one of ContextDescriptionType, ContextIdentificationType, DeviceCharacteristicsType, NewworkInfoType, LocationType, WeatherType, OtherEnvironmentalInfoType, AudioEnvironment, RecordingEnvironmentType and ContextPriorityType.
Since there can be a variety of permutations and embodiments of the present invention, certain embodiments will be illustrated and described with reference to the accompanying drawings. This, however, is by no means to restrict the present invention to certain embodiments, and shall be construed as including all permutations, equivalents and substitutes covered by the ideas and scope of the present invention.
When one element is described to “send” or “transmit” a signal to another element, it shall be construed that the signal is sent or transmitted to the other element by having the one element directly connected to the other element but also by, unless explicitly described otherwise, possibly having another element interposed between the one element and the other element.
Referring to
The communication interface 110 is connected with a service providing apparatus 50 through a communication network to receive a request for recommendation of a service from the service providing apparatus 50 and send the request to the recommendation engine 120. Here, the request for recommendation of a service may include an identification information of a user who will receive the service.
Moreover, upon receiving a recommendation description from the recommendation engine 120, the communication interface 110 transmits the recommendation description to the service providing apparatus 50, which is an apparatus that provides a specific service to the user. For example, the service providing apparatus 50 may be any device, such as a user terminal or a server providing a service to the user terminal, which is connected with the communication interface 110 through a communication network.
Upon receiving the request for recommendation of a service, the recommendation engine 120 generates a recommendation description used for providing a service suitable for the user. The recommendation engine 120 obtains a user description from the user description providing unit 130, a service description from the service description providing unit and a context description from the context description providing unit 150. The recommendation engine 120 analyzes the obtained user description, service description and context description according to a predetermined pattern and generates the recommendation description. The recommendation description is a set of recommended information elements provided to applications in a structural, efficient, compact fashion when a customer requests for a service in a specific environment. The recommendation description may include information extracted from the user description, context description and service description, information indicating a logical relation between the user/context/service descriptions and metadata. The recommendation engine 120 that generates the recommendation description may have various ranges of complexity and performance. The recommendation description may have a general format that is independent from applications. Here, the recommendation engine 120 may generate the recommendation description according to a pattern known through, for example, the MPEG-UP standard. The recommendation engine 120 transmits the recommendation description to the service providing apparatus 50 through the communication interface 110.
The user description providing unit 130 stores the user description and provides the description to the recommendation engine 120. For example, the recommendation engine 120 sends a request for user description, including the identification information of the user, to the user description providing unit 130, and the user description providing unit 130 sends the user description corresponding to the identification information of the user to the recommendation engine 120.
The user description includes UserProfileType, PersonProfileType, OrganizationProfileType, DeviceProfileType, GroupedProfileType, UsageHistoryTyp, EventType, interactionAtomType, artefactType, observableType, multimediaExperienceType, stateType, PreferenceType, WebLinkPreferenceType, ServicePreferencesType, AudioPresentationPreferencesInfoType, TranslationPreferencesType, EmotionType, VocabularySetType, EmotionGroupType, ScheduleType, ScheduleEventType, ActivityType, IntentionType, LanguageType, LanguageCompetenceReferenceType, CompetenceLevelType, SpecialtyType, AccessibilityType, SocialInformationType and ObjectSharingType.
The UserProfileType describes basic entity information of the user. The semantics of the UserProfileType is shown in Table 1 below.
The PersonProfileType describes a person entity. The PersonProfileType can be used to describe individual basic properties of human being. The semantics of PersonProfileType are shown in Table 2 below.
The semantics of the OrganizationProfileType is shown in Table 3 below.
The DeviceProfileType includes various information on the user device. The semantics of the DeviceProfileType are shown in Table 4 below.
The GroupedProfileType can be used to describe basic attributes of a group which is a set of users. The semantics of the GroupedProfileType are shown in Table 5 below.
The UsageHistoryType describes the history of actions on specific area by a user, including usage history of media contents, movement of user, pattern in online social network. etc. The semantics of the UsageHistoryType are shown in Table 6 below.
The EventType describes information on an event. The semantics of the EventType are shown in Table 7 below.
The interactionAtomType describes observables and artefacts. The semantics of the interactionAtomType are shown in Table 8 below.
The artefactType describes a specific multimedia object, e.g. tags, annotations, voice, generated or selected by the user while in a specific state.
The observableType describes a specific multimedia object that the user may decide to use. An observable may be any multimedia object visible to the user in a specific state (e.g. an image in the graphic interface). The semantics of the observableType is shown in Table 9 below.
The semantics of the multimediaExperienceType is shown in Table 10.
Table 11 shows the semantics of the stateType.
The PreferenceType describes the preference related to the various services. Table 12 shows the semantics of the PreferenceType.
The semantics of the WebLinkPreferencesType are shown in Table 13 below.
Table 14 shows the semantics of the ServicePreferenceType.
The semantics of the AudioPresentationPreferencesInfoType are shown in Table 15.
The semantics of the TranslationPreferencesType are shown in Table 16 below.
The EmotionType can be used to represents user's subjective notion and feeling. It can be described user's emotion including its changes over time. The emotion can be acquired by some direct input of user or inference results from sensor data. The semantics of the EmotionType are shown in Table 17.
The DynamicEmotionVocabularySetType can include VocabularySetType to describe the fundamental emotions according to a set of definite criteria. The complete set of vocabularies for representing emotions does not exist. Therefore, the DynamicEmotionVocabularySetType can include vocabulary that can be temporarily used to define the set of emotion vocabularies.
The VocabularySetType can be used to describe the fundamental vocabularies according to a set of definite criteria. The semantics of the VocabularySetType are shown in Table 18.
Moreover the user description includes EmotionGroupType. The EmotionGroupType can be used to describe and specify detailed information about emotion state of this user according to a specific duration. The semantics of the EmotionGroupType are shown in Table 19.
Moreover, the user description includes ScheduleType. The ScheduleType represents a plan for events related to the user. Table 20 show the semantics of the ScheduleType.
Table 21 shows the semantics of the ScheduleEventType.
The semantics of the AcitvityType are shown in Table 22 below.
The semantics of the IntentionType are shown in Table 23.
The LanguageType can be used to describe properties of a specific language that this user can use. The semantics of the LanguageType are shown in Table 24 below.
LanguageCompetenceReferenceType describes user's competence for a specific language in the common test. The semantics of LanguageCompetenceReferenceType are shown in Table 25.
The semantics of the CompetenceLevelType are shown in Table 26.
Moreover, the user description includes SpecialtyType. The SpecialtyType can be used to describe a value specific to a particular user. The semantics of the SpecialtyType are shown in Table 27.
The AccessibilityType can be used to describe the characteristics of a user's disabilitydisability. The semantics of the AccessibilityType are shown in Table 28.
SocialInformationType can be used to describe information on the social communities provided by a given service. The semantics of the SocialInformationType are shown in Table 29.
The semantics of ObjectSharingType are shown in Table 30.
The service description providing unit 140 stores the service description and provides the service description to the recommendation engine 120. For example, the recommendation engine 120 sends a request for service description to the service description providing unit 140, and the service description providing unit 140 sends the service description according to the request for service description to the recommendation engine 120. The service description may include information on which user is targeted for each service.
The service description includes Service General Description, FormatType, ServiceTargetInformationType, ServiceTargetModelType, VocabularySetType, ServiceInterfaceType, RequiredInputDataType, InternalServicesType, InternalServiceType, LosslessAudioDBType, LossyAudioDBType, VideoDBType, ServiceObjectType and ObjectType.
ServiceGeneralInformationType describes general information about service. The semantics of ServiceGeneralInformationType are shown in Table 31 below.
Moreover, the service description includes FormatType. FormatType specifies media formats supported by the service. All the media types supported by the service shall be listed with this type. Table 32 below shows the semantics of FormatType.
The semantics of the ServiceTargetInformationType are shown in Table 33.
ServiceTargetModelType includes information corresponding to a decision making model to describe an intention of a specific service provider. Decision making can be regarded as the cognitive process resulting in the selection of a course of action among several alternative scenarios. Every decision making process produces a final choice which can be an action or an opinion of choice. Each service provider has own domain knowledge about every phase of its business, and need to make distinct strategies to try to develop into a highly profitable business. For this, it might be important for service provider to segment users considering usage data and statistical analysis of user for providing target services.
First of all, an approach is proposed to describe a decision tree to represent the decision making model. As mentioned earlier, the structure of service description is proposed, and the service target description, which is the second part in the service description, is proposed. Since one of the purposes of the recommendation description is to suggest proper service according to the user's intention, the service description describes its service target in its description. In this element, a DecisionModel child element, which includes information about a decision model uniquely made by a specific service provider, is newly defined. The semantics of the ServiceTargetModelType are shown in Table 34.
The semantics of the VocabularySetType are shown in Table 35.
ServiceInterfacesType specifies Service Interfaces provided by the service. Table 36 shows the semantics of ServiceInterfacesType.
ServiceInterfaceType describes the type the service interface supported by the service using an MPEG-7 Classification Scheme. Terms for the ServiceInterfaceType may be specified by the ServiceInterfaceTypeCS(urn:mpeg:mpeg-ud:cs:2014:01-SD-NS:serviceInterfaceTypeCS). The semantics of the ServiceInterfaceType are shown in Table 37.
Moreover, the service description includes RequiredInputDataType. RequiredInputDataType specifies what kind of input data is needed to utilize the service. The semantics of RequiredInputDataType are shown in Table 38.
InternalServicesType lists internal services within a service. Table 39 shows the semantics of InternalServicesType
InternalServiceType specifies each service within a service. The semantics of InternalServiceType are shown in Table 40.
The semantics of LosslessAudioDBType are shown in Table 41.
The semantics of LossyAudioDBType are shown in Table 42.
The semantics of VideoDBType are shown in Table 43.
The semantics of ServiceObjectType are shown in Table 44 below.
The semantics of ObjectType are shown in Table 45.
The context description providing unit 150 stores the context description and provides the context description to the recommendation engine 120. The context description is information describing the current environment in which the user is situated.
The context description includes ContextDescriptionType, ContextIdentificationType, DeviceCharacteristicsType, NewworkInfoType, LocationType, WeatherType, OtherEnvironmentalInfoType, AudioEnvironment, RecordingEnvironmentType and ContextPriorityType.
The semantics of ContextDescriptionType are shown in Table 46 below.
The semantics of ContextIdentificationType are shown in Table 47.
The semantics of DeviceCharacteristicsType are shown in Table 48.
NetworkInfoType describes the static and dynamic information of the available network around user. The semantics of NetworkInfoType are shown in Table 49.
Moreover, the context description includes LocationType. The semantics of LocationType are shown in Table 50.
WeatherType include Temperature, Precipitation, wind and Humidity elements. The semantics of WeatherType are shown in Table 51.
The semantics of OtherEnvironmentalInfoType are shown in Table 52.
The semantics of AudioEnvironmentType are shown in Table 53.
The semantics of RecordingEnvironmentType are shown in Table 54.
The semantics of ContextPriorityType are shown in Table 55.
Referring to
In step 220, the apparatus 100 for recommending a service obtains a user description, a service description and a context description corresponding to the request for recommendation of a service. For example, the apparatus 100 for recommending a service may request the user description providing unit 130, the service description providing unit 140 and the context description providing unit 150 for the user description, the service description and the context description, respectively, and obtain the user description, the service description and the context description, respectively. Here, the user description may includeUserProfileType, PersonProfileType, OrganizationProfileType, DeviceProfileType, GroupedProfileType, UsageHistoryTyp, EventType, interactionAtomType, artefactType, observableType, multimediaExperienceType, stateType, PreferenceType, WebLinkPreferenceType, ServicePreferencesType, AudioPresentationPreferencesInfoType, TranslationPreferencesType, EmotionType, VocabularySetType, EmotionGroupType, ScheduleType, ScheduleEventType, ActivityType, IntentionType, LanguageType, LanguageCompetenceReferenceType, CompetenceLevelType, SpecialtyType, AccessibilityType, SocialInformationType and ObjectSharingType.
In step 230, the apparatus 100 for recommending a service generates a recommendation description corresponding to the user description, the service description and the context description. For example, the apparatus 100 for recommending a service may generate the recommendation description based on a pattern available in the MPEG-UD standard and the like.
In step 240, the apparatus 100 for recommending a service sends the recommendation description to the service providing apparatus 50. Therefore, the service providing apparatus 50 may provide a service that is suitable for the user by referring to the recommendation description.
The apparatus 100 for recommending a service in accordance with an embodiment of the present invention may be implemented in a computer system.
An embodiment of the present invention may be implemented as, for example, a computer-readable recording medium, in a computer system. As shown in
Hitherto, certain embodiments of the present invention have been described, and it shall be appreciated that a large number of permutations and modifications of the present invention are possible without departing from the intrinsic features of the present invention by those who are ordinarily skilled in the art to which the present invention pertains. Accordingly, the disclosed embodiments of the present invention shall be appreciated in illustrative perspectives, rather than in restrictive perspectives, and the scope of the technical ideas of the present invention shall not be restricted by the disclosed embodiments. The scope of protection of the present invention shall be interpreted through the claims appended below, and any and all equivalent technical ideas shall be interpreted to be included in the claims of the present invention.
Number | Date | Country | Kind |
---|---|---|---|
10-2014-0034388 | Mar 2014 | KR | national |
10-2014-0034391 | Mar 2014 | KR | national |
10-2014-0034395 | Mar 2014 | KR | national |
10-2015-0032779 | Mar 2015 | KR | national |
10-2015-0032783 | Mar 2015 | KR | national |
10-2015-0032785 | Mar 2015 | KR | national |