SEMPRIA-Search: the cognitive search engine

higher recall, precision and comfort - through automatic understanding of language and domain languages

With the ever growing bodies of data in intranets and on the Internet, a fundamental problem of traditional search engines becomes all the more apparent. The traditional search engine is not able to understand the search query or the searched documents on a semantic level. Only phrases that are identical to the query or very similar on the surface level can be found. This is why documents that would be a perfect match on the semantic level cannot be found if divergent wording and phrasing is used. Millions of examples exist for that particular problem. The following is one of them. (Reload this page to make 12 so-called concept trips.)

Example of cognitive semantic search.

The answer to this problem is the cognitive search engine SEMPRIA-Search. It is a development that departs from semantic search. SEMPRIA-Search uses modern language technology and AI. The search query and the indexed documents are understood on a semantic level. Wording and phrasing becomes almost irrelevant, as divergent wording can be countered with knowledge of synonyms (different phrasing can be countered with paraphrased texts). Varied terminology is treated with knowledge of hierarchies and jargon. SEMPRIA-Search can explain every found match and each inference step. SEMPRIA-Search finds the relevant documents more precisely and more completely and presents the matches comprehensively.

SEMPRIA was funded by a federal ministry.Prize for innovation in information technology.