Methods for searching with semantic similarity scores in one or more ontologies

<strong>Technology</strong><br>

The invention provides techniques for indexing and searching in databases using ontologies. Categories or individual documents within the database that are annotated to the terms of the ontology can be searched and prioritized using statistical models to test for significance of the similarity scores of queries against the database. The database can be any repository of documents such as books, articles, internal company documentation, or web pages.<br><br> An ontology provides a classification of the entities within a domain. Each entity is said to make up a term of the ontology. Furthermore, an ontology must specify the semantic relationships between the entities. <br><br> A p-value for query results is provided which serves as an index and ranking according to the semantic relevance. The invention provides a rapidly computing of the exact distribution of similarity scores in ontologies, which makes it practicable to index large corpora of information and to keep the index up to date by regularly recalculating the score distribution in a time- and cost-efficient way. <br><br> <b>Benefits:</b><br> <ul> <li>Fast score distribution computation</li> <li>Possible searching in multiple ontologies</li> </ul> <p><strong>IP Rights</strong><br> US Patent Application US 2011 0040766 A1<br> European Patent Application EP 2465054 A1 </p> <p><strong>Origin</strong><br> Charité Universitätsmedizin Berlin, Germany</p>

Weitere Informationen: PDF

ipal GmbH
Tel.: +49 (0)30/2125-4820

Ansprechpartner
Dr. Dirk Dantz