Sophia Search Limited is an Irish software company, founded in 2007.
Sophia builds contextually aware Enterprise Search solution products, that enable organizations to intelligently discover knowledge from unstructured content based on context so that it can be recovered, consolidated and optimized. (The information may be on the Internet, or stored privately in files in a company or database, or a combination of these.)
The technology works for a range of natural languages and so does not require reconfiguration. There is no external meta-data required: no ontology, no dictionary, no thesaurus, no Resource Description Framework augmenting and improving other search engines. Using a proprietary set of algorithms, the content enrichment process automatically creates semantic metadata for information.
Sophia is based on a model of Linguistics (called Semiotics), the metadata discovered and extracted by Sophia's Contextual Discovery Engine (CDE) is exposed as XML through RESTful web services.
Contents |
Sophia began life as a campus company in the University of Ulster and Saint Petersburg State University currently maintaining offices in Belfast, Northern Ireland, and San Jose, California. It also has an R&D base in St Petersburg, Russia. It is privately funded; having raised the largest ever private investment round, via an Angel Investor(s), in Northern Ireland history.
The name Sophia is taken from the Greek word for Wisdom
The Company's mission is to improve the 'findability' of content within organizations.
Its core product, the Sophia Digital Librarian, automatically enriches each document with semantic metadata (such as Topic, concepts, document tags & semantic tags). This Metadata can then be leveraged by other tools, such as search and content management systems, in order to radically improve the findability of information. The tool has a key focus on discovery of new information. The Sophia Digital Librarian does not rely on Taxonomies, ontologies, thesauri or any type of background knowledge nor does it require any training. It is built on a model of Linguistics called Semiotics, which explains how humans understand the meaning of signs, symbols and text.
This knowledge can be used to in conjunction with existing search tools, such as MS FAST, Google Search Appliance and Lucene/Solr to search semantically and to significantly improve the findability of indexed content. It can also be used to enrich content held within Content Management Systems (CMS) such as SharePoint, Documentum, and MarkLogic.
The company has won a number of awards for its products including: