ontology based content management for digital tv services
Post on 03-Feb-2016
35 Views
Preview:
DESCRIPTION
TRANSCRIPT
Ontology Based Content Management for Digital TV
Services
Benjamin LuiChinese University of Hong
Kong benjamin_lui@hotmail.com
Dickson K. W. CHIUSenior Member, IEEE
Dickson Computer SystemsHong Kong
dicksonchiu@ieee.org
Haiyang Hu, Hua Hu, Yi Zhuang
Zhejiang Gongshang University, China{hhy, huhua, zhuang}@mail.zjgsu.edu.cn
Ontology for DTV
CMS SOKM 2009- 2
Introduction
Content management systems (CMS) are widely used in various industries.
Semantic gap – discrepancy between the way video contents are coded digitally and the way they are experienced by human users.
General Problems: classification => searching DTV problems
Subscribe channels through set-top boxes Single direction Limited ability in providing recommendations
Ontology for DTV
CMS SOKM 2009- 3
Agent-based Solution Overview
Proactively search channels or VOD contents for users based on different categories
Recommend channels based on channel classifications, user subscription, and profile preferences for up-sale
Notify users of new interesting contents Provide statistical reports of users subscription
in both vertical and horizontal domains service provider can review the business needs and
then look for new potential contents
*** Use ontology
Ontology for DTV
CMS SOKM 2009- 4
Simplified Ontology forContent Annotation
Ontology for DTV
CMS SOKM 2009- 5
Partial Ontology Listing for Multimedia Content annotation
<owl:Ontology rdf:about="#Content"> <rdfs:comment>Simplified Content Ontology</rdfs:comment> <owl:Class rdf:ID="Content" /> <owl:Class rdf:ID="Genre" /> <owl:Class rdf:ID="Category"> <rdfs:subClassOf rdf:resource="#Genre" /> ... </owl:Class> <owl:ObjectProperty rdf:ID="hasGenre"> <rdfs:domain rdf:resource="#Content" /> <rdfs:range rdf:resource="#Genre" /> </owl:ObjectProperty> ... <owl:DatatypeProperty rdf:ID="class"> <!-- Enumeration --!> <rdfs:domain rdf:resource="#Genre"/> <rdfs:range> <owl:DataRange> <owl:oneOf> <rdf:List> <rdf:rest> <rdf:List> <rdf:rest><rdf:List> <rdf:rest><rdf:List> <rdf:rest rdf:resource="http://www.w3.org/1999/02/22-rdf-syntax-ns#nil"/> <rdf:first rdf:datatype="http://www.w3.org/2001/XMLSchema#string">I</rdf:first></rdf:List></rdf:rest>…<rdf:first rdf:datatype="http://www.w3.org/2001/XMLSchema#string">III</rdf:first></rdf:List> </owl:oneOf></owl:DataRange></rdfs:range> </owl:DatatypeProperty> …</owl:Ontology>
Ontology for DTV
CMS SOKM 2009- 6
Semantic basede-Marketplace Conceptual Model
concert =>
music & performance
fighting vs. Kung-fu
Ontology for DTV
CMS SOKM 2009- 7
Process Model of the CMS
Ontology for DTV
CMS SOKM 2009- 8
Understanding Requirements from Ontologies
Match key requirement issues like class, category, language as genre
For each issue, check if a direct mapping to a genre based on an agreed ontology is possible.
If not, the agent tries to see if sets of relating genres can be mapped by well-known graph search algorithms.
If the user accepts the new genre, new contents are recommended.
Further the agent refines the issue with new search criteria. Another set of related genres can be extracted.
Eventually more and more content matched users’ interests can be provided.
Ontology for DTV
CMS SOKM 2009- 9
System Implementation Architecture
Ontology for DTV
CMS SOKM 2009- 10
Advantages of Using Ontology
Traditional CMS Contributions of Ontology
Match-making
Match-making often ineffective because of rigid definition of contents (e.g., categories) predefined by service providers
Shared and agreed ontology provides common, flexible, and extensible definitions of multimedia contents for match-making and subsequent business processes
Difficult to specify unclear types of multimedia content out of predefined categories
Complicated use requirements can be decomposed into simple genres for elicitation of options
Ontology for DTV
CMS SOKM 2009- 11
Advantages of Using Ontology (cont)
Traditional CMS Contributions of Ontology
Recom-mendation
Often only possible within the same category
Ontology helps elicit alternatives for recommendation
Pre-defined formulae for every type of multimedia contents are needed for evaluation
Ontology help recommendation by evaluating offers in terms of flexible overall scaling
Business analysis
Simple data mining: mainly depends on viewership of single channel / program
Ontology help analyze the viewership of related channels and programs to achieve a better marketing strategy (Segmentation of contents and users)
Ontology for DTV
CMS SOKM 2009- 12
Conclusions Ontology applied to an agent-based CMS system of
DTV service. Conceptual model for the content searching and
subscription Ontology helps improve mutual understanding
between users and service providers Relationship of contents can be extracted
effectively for cross-sale and business analysis
Ontology for DTV
CMS SOKM 2009- 13
Future Work
Formal models Elicitation of semantic distances Enhancement of ontology-based matchmaking and
recommendation algorithms Ontology-based cross-sale and up-sale Mobile clients and location / context-sensitive
recommendations
top related