|
|
|
SemanticRank Algorithm
SemanticRank algorithm of hakia is comprised of innovative solutions from the disciplines
of Ontological Semantics (OntoSem), Fuzzy Logic, Computational Linguistics, and Mathematics.
The purpose of the algorithm is to rank search results in the order relevancy.
As shown above, a pool of relevant paragraphs come from the QDEX system for a given query terms.
Then, the final relevancy is determined by the SemanticRank algorithm based on an advanced sentence analysis and concept match between the query and the best sentence of each paragraph. Among other things, morphological and syntactic analyses are also performed. In this operation, there is no keyword matching or Boolean algebra involved.
Among the criteria, the credibility and age (of the Web page) are also taken into account via proprietary measurements. Popularity of keywords by means of link referrals is not used, which eliminates the possibilities of (1) meaningless results ranking high, and (2) manipulation of results by fictitious page design.
SemanticRank algorithm operates independently from the rest of the system, and is extremely fast to be deployed on the fly. It works best with the output of the QDEX system, that ensures base-line relevancy and uniterrupted text (or paragraph) representing a Web page.
|
|
|
|
