Academic Journals Database
Disseminating quality controlled scientific knowledge

Use of cluster analysis for documents processing in retrieval system

Author(s): Shcherbatov I. А. | Belyaev I. О.

Journal: Vestnik Astrahanskogo Gosudarstvennogo Tehničeskogo Universiteta. Seriâ: Upravlenie, Vyčislitelʹnaâ Tehnika i Informatika
ISSN 2072-9502

Volume: 2;
Issue: Astrakhan State Technical University, Russia;
Start page: 161;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: information retrieval system | accuracy of search | search quality | cluster analysis | genetic algorithm

The role of information retrieval systems becomes every year more and more actual. The e-information doubles each 7–9 years, therefore, the solution of the problem of obtaining relevant information from large volume of data is very important. The main stages of creation of the information retrieval system are described. The news from a portal for 2011 is used as practical material. The problems arising in processing a large amount of data are described; the mechanisms of their solution are proposed. Search quality is evaluated by two key parameters: the accuracy and completeness. The most important factor is response time. The mechanism of reduction of the response time without loss of search quality is offered. This mechanism is based on the synthesis of cluster analysis and genetic algorithm.
RPA Switzerland

RPA Switzerland

Robotic process automation


Tango Jona
Tangokurs Rapperswil-Jona