Semantic Search for IPTV Content
KT Corporation (formerly Korea Telecom), is the leading South Korean integrated telecommunication service provider. KT has an information and communications business, and has the largest portion of the South Korean local telephone and high-speed Internet business. Megapass is a broadband telecommunication service offered by KT, featuring Interactive TV, TV-VOD (Video on Demand) and including movies and popular television programs, remote domestic video monitoring, SMS messaging, and local service ‘directory’ information.
To provide viewers with a semantic search mechanism that will allow them locate and access more IPTV content. Currently users search for less than 10% of all available content
Since the launch of the service in 2007, content providers have realized the need for semantic search to expose more IPTV content (more than 70,000 VOD contents) and match it with the user’s preferences and needs
- Analyze content to provide more relevant search results
- Metadata Enrichment based on Web mining (director, actor/actress, synopsis…)
- Multi-genre classification based on Association Rule Classifier
- Topic extraction based on ontology and synonyms (from WordNet)
To better understand and answer the information needs of their customers, KT was looking for an ontology that represented video categories/genres and emotional lexicon. KT also needed NLP-based semantic query analysis. Furthermore, the solution should provide support multiple devices and a semantic search open API.
The Solution: Semantic Search
KT has implemented a semantic search system with the following features
- Consonant-based query completion (a solution specific to Korean hieroglyphs)
- Semantic-based query expansion.
- Natural language query analysis based on VOD metadata: title, genre, actor/actress, director, etc
- Semantic search based on an ontology including emotional words, topics, etc
- Result filtering by user profile (user’s service grade)
- Result ranking by user intention and statistics about VOD contents
KT uses a number of OWLIM licenses as RDF database and reasoning service (supporting full OWL2 RL inference), to guarantee the required performance and resilience parameters.
KT conceptual diagram of Interactive TV service:
KT provides semantic VOD search service for IPTV and various smart mobile devices using OWLIM as semantic repository. We found that BigOWLIM is suitable for our service, as it has shown good performance for its price compared with other products in the actual simulation tests. Best of all, OWLIM could be easily tested, installed and used thanks to open library, detailed guidelines, and lots of samples etc. By and large, our experience is that OWLIM is a very powerful and reliable high-performance semantic repository.”
– Joo Won Sung, Senior Researcher, Central R&D Laboratory, KT.