Content Optimisation

Content Optimisation

Content Optimisation analyses textual content and provides characteristic keywords and semantic enrichment.

Owner/developer

Fraunhofer IAIS

Contact person(s)

For technical information:

  • Heike Horstmann
  • Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
  • Send mail

For licensing information:

What it does

Content Optimisation processes incoming textual content (e.g. from the Audio Mining SE) and extracts characteristic keywords. Subsequently, semantic enrichment based on natural language processing (NLP) is performed to connect the transcripts and keywords with additional, contextual information. The SE integrates and harmonises additional content from diverse sources. The software is intended for SMEs wanting to build second screen applications (e.g. for TV documentaries), but can also be used for various other purposes.


How it works

Content Optimisation leverages technologies for named entity recognition and spotting of entities in textual content. To accomplish this goal, it uses normed data that is available from open sources (e.g. DBPedia.org) to recognise people, organisations and/or locations in the provided textual data. Those entities will be used to annotate the data and to build up a search index. The latter enables the user to experience an intuitive search with state-of-the-art search technologies such as a faceted search approach. The search and retrieval of enriched content is accessible via a RESTful API, which enables the user to easily integrate the service into existing architecture and/or frameworks.


What you get

Content Optimisation offers a RESTful API to enrich textual content in German and English with information from open sources (i.e. DBPedia.org) using named-entity recognition (NER) and spotting technologies, and to provide an interface with search technologies such as faceted search.


Delivery model

  • SaaS

Discover more FIWARE Media & Content Enablers