Technology Overview

Designed to yield only highly relevant answers, Collexis software allows a system to be queried not only for relevant documents, but also for experts on a particular topic, or even for organizations or departments that are active in a particular field of interest. First and foremost, the results of a Collexis query are relevant.

 

Collexis software mines text and performs detailed analyses of entire document collections. Collexis is based on the principle of Fingerprinting. In humans, a fingerprint, although small, is a unique representation of a person. Collexis creates a Fingerprint of each piece of information (such as an MS-Word document, an e-mail, a PowerPoint presentation, or a web site) using the knowledge residing in a thesaurus or multiple thesauri. A thesaurus is a specialized vocabulary (“repository of knowledge”) of a particular domain such as medicine, law, or finance. Collexis not only creates Fingerprints from all content, but also from the search information. This information can be a few words, a sentence, or a complete document.