"8"^^ . "2014-12-31+01:00"^^ . "2531"^^ . "8"^^ . "\"V sou\u010Dasn\u00E9 dob\u011B jsou podnikatel\u00E9 a mana\u017Ee\u0159i vystaveni v\u0161udyp\u0159\u00EDtomn\u00E9mu informa\u010Dn\u00EDmu smogu. Z toho p\u0159irozen\u011B vypl\u00FDv\u00E1 nar\u016Fstaj\u00EDc\u00ED v\u00FDznam metod spadaj\u00EDc\u00EDch do oblasti \"\"business intelligence\"\". V sou\u010Dasnosti se v\u0161ak pou\u017E\u00EDvanj\u00ED metody, kter\u00E9 jen velmi obt\u00ED\u017En\u011B zvl\u00E1daj\u00ED obrovsk\u00E9 a nestrukturovan\u00E9 datov\u00E9 (textov\u00E9) zdroje jak\u00FDmi je na p\u0159\u00EDklad Internet, jeho\u017E v\u00FDznam dnes st\u00E1le roste. K dosa\u017Een\u00ED tohoto hlavn\u00EDho c\u00EDle projektu je nutn\u00E9 nal\u00E9zt a ov\u011B\u0159it dostate\u010Dn\u011B spolehliv\u00E9 metody umo\u017E\u0148uj\u00EDc\u00ED pro ka\u017Ed\u00FD textov\u00FD dokument strojov\u011B nal\u00E9zt (sestavit) kontext, tedy mnohadimenzion\u00E1ln\u00ED (z\u0159ejm\u011B strukturovanou) lingvistickou charakteristiku reprezentuj\u00EDc\u00ED obsah dokumentu. Pro zpracov\u00E1n\u00ED v\u00EDcejazy\u010Dn\u00FDch zdroj\u016F vyvineme p\u0159\u00EDstupy, kter\u00E9 nebudou z\u00E1visl\u00E9 na jazyku zdroje, nebudou vy\u017Eadovat dodate\u010Dn\u00E9 n\u00E1stroje z\u00E1visl\u00E9 na pou\u017Eit\u00E9m jazyku (jako nap\u0159. synonymick\u00E9 slovn\u00EDky). V na\u0161em pojet\u00ED bude kontext dynamick\u00FD, klasifikace dokumentu tedy nebude z\u00E1visl\u00E1 jen na posuzovan\u00E9m dokumentu ale i na korpusu; roz\u0161\u00ED\u0159en\u00ED korpusu tak m\u016F\u017Ee zp\u016Fsobit zm\u011Bnu v klasifikaci dokumentu.\""@cs . . "At this time all managers and businessmen are exposed to the everpresent information pollution. This is why tools of business intelligence are of great importance, nevertheless the current methods can hardly cope with large and unstructured data (text) sources like, for example, world wide web (WWW) that currently becomes more and more important. To achieve this main goal we have to find and verify satisfactorily reliable methods for automatic extraction of a main context of a document, i.e., multidimensional (possibly structured) linguistic characterization representing the contents of the document. To cope with the multilingual sources we have to develop approaches that would not be dependent of the language of the source and that would not need additional language dependent tools (like e.g. dictionaries of synonyms). In our conception, the context will be dynamic, which means that a classification of a document will not be dependent only on the document in question but also on the corpus; an expansion of a corpus can result in a change of a document classification."@en . . . "0"^^ . . "2531"^^ . . . . . . . "1"^^ . "2012-01-01+01:00"^^ . . . . "Metody podpory mana\u017Eersk\u00E9ho rozhodov\u00E1n\u00ED zalo\u017Een\u00E9 na anal\u00FDze textov\u00FDch informa\u010Dn\u00EDch zdroj\u016F"@cs . "0"^^ . "Methods Supporting Managerial Desision-Making Based on the Analysis of Text Information Sources"@en . "decision support; business intelligence; text mining; unstructured information sources; context extracti"@en .