{"id":14,"date":"2015-09-15T14:07:08","date_gmt":"2015-09-15T14:07:08","guid":{"rendered":"http:\/\/blog.geneea.com\/?p=14"},"modified":"2026-01-29T21:30:41","modified_gmt":"2026-01-29T21:30:41","slug":"textove-zlatokopectvi","status":"publish","type":"post","link":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi","title":{"rendered":"Textov\u00e9 zlatokopectv\u00ed"},"content":{"rendered":"Dobr\u00fd hostinsk\u00fd se od t\u011bch pr\u016fm\u011brn\u00fdch odli\u0161uje v mnoha v\u011bcech, ale jednou z hlavn\u00edch je to, \u017ee zn\u00e1 sv\u00e9ho z\u00e1kazn\u00edka. V\u00ed o n\u011bm, kdy p\u0159ich\u00e1z\u00ed a zda chce ve\u010de\u0159i s v\u00ednem nebo si jen p\u0159e\u010d\u00edst noviny u kafe. V\u00ed, zda r\u00e1d poslouch\u00e1 \u017eiv\u00fd jazz nebo se rad\u0161i d\u00edv\u00e1 na hokej. V\u00ed, kdo chce jedno pivo za ve\u010der a komu m\u00e1 bez ptan\u00ed nal\u00edt dal\u0161\u00ed. Podobn\u011b je tomu u dobr\u00e9ho hoteli\u00e9ra nebo peka\u0159e.<\/span>\n

Dat je p\u0159\u00edli\u0161<\/h3>\nJen\u017ee dne\u0161n\u00ed velk\u00e9 firmy jako Tesco, McDonald\u2019s, nebo Potrefen\u00e1 husa maj\u00ed tolik z\u00e1kazn\u00edk\u016f, \u017ee je p\u0159i nejlep\u0161\u00ed v\u016fli nem\u016f\u017eou zn\u00e1t v\u0161echny.<\/strong>\u00a0Mnoh\u00e9 organizace jako \u010cesk\u00e1 televize, T-mobile nebo mBanka se se sv\u00fdmi z\u00e1kazn\u00edky \u010dasto v\u016fbec tv\u00e1\u0159\u00ed v tv\u00e1\u0159 nesetkaj\u00ed. Nav\u00edc nejde o rodinn\u00e9 podniky ale organizace s mnoha tis\u00edci zam\u011bstnanci, \u010dasto v n\u011bkolika zem\u00edch s r\u016fzn\u00fdmi \u00favazky, a p\u0159ed\u00e1v\u00e1n\u00ed osobn\u00edch zku\u0161enost\u00ed<\/strong> se z\u00e1kazn\u00edkem je tak pon\u011bkud slo\u017eit\u011bj\u0161\u00ed.\n\n\n
\"\"<\/figure>\n\n\nFirmy se proto sna\u017e\u00ed poznat sv\u00e9 z\u00e1kazn\u00edky jin\u00fdmi zp\u016fsoby. Sb\u00edraj\u00ed data o jejich chov\u00e1n\u00ed<\/strong> prost\u0159ednictv\u00edm r\u016fzn\u00fdch v\u011brnostn\u00edch karet, sout\u011b\u017e\u00ed, dotazn\u00edk\u016f a people-metr\u016f. Krom\u011b toho se ale st\u00e1le \u010dast\u011bji d\u00edvaj\u00ed i na to, jak je lid\u00e9 komentuj\u00ed na facebooku<\/strong>, co tweetnou na twitteru<\/strong> a co se o nich p\u00ed\u0161e v r\u016fzn\u00fdch online f\u00f3rech<\/strong>. Na rozd\u00edl od z\u00e1kaznick\u00fdch karet se tak mohou dozv\u011bd\u011bt nejenom o n\u00e1zorech z\u00e1kazn\u00edk\u016f sv\u00fdch, ale i o n\u00e1zorech z\u00e1kazn\u00edk\u016f konkurence, nebo dokonce t\u011bch, kte\u0159\u00ed teprve z\u00e1kazn\u00edci budou.\n\nJedna z v\u011bc\u00ed, se kterou se mus\u00ed vypo\u0159\u00e1dat, je mno\u017estv\u00ed dat<\/strong>. P\u0159ed t\u0159iceti lety si sta\u010dilo zaplatit v\u00fdst\u0159i\u017ekovou slu\u017ebu a firma se dozv\u011bd\u011bla o v\u0161em, co o n\u00ed bylo ve\u0159ejn\u011b naps\u00e1no. S p\u0159\u00edchodem blog\u016f a soci\u00e1ln\u00edch s\u00edt\u00ed, tedy takzvan\u00e9ho Webu 2.0, za\u010dalo mno\u017estv\u00ed existuj\u00edc\u00edch text\u016f nar\u016fstat exponenci\u00e1ln\u011b. Odhady se li\u0161\u00ed, ale nen\u00ed<\/span> daleko od pravdy, kdy\u017e \u0159ekneme, \u017ee mno\u017estvi existuj\u00edc\u00edch dat se zdvojn\u00e1sobuje ka\u017ed\u00fdch p\u00e1r let<\/strong>, \u010dili \u017ee za n\u00e1sleduj\u00edc\u00ed dva t\u0159i roky shrom\u00e1\u017ed\u00edme v\u00edce nov\u00fdch informac\u00edch ne\u017e za celou dosavadn\u00ed existenci lidstva. Americk\u00e1 analytick\u00e1 firma IDC odhaduje<\/a>, \u017ee v roce 2020 bude na internetu p\u0159es 40 zetta byt\u016f informac\u00ed<\/strong>, \u010dili 4 x 1022<\/sup> byt\u016f neboli 40 000 000 000 000 000 000 000 byt\u016f. Pokud bychom takov\u00e9 mno\u017estv\u00ed informac\u00ed nahr\u00e1li na CD a polo\u017eili v\u0161echna ta CD na sebe, mohli bychom spojit Zemi s M\u011bs\u00edcem 160kr\u00e1t.<\/strong> P\u0159itom cel\u00e9 d\u00edlo Shakespeara se na jedin\u00e9 CD vejde 350kr\u00e1t<\/strong>.\n\nSamoz\u0159ejm\u011b v\u011bt\u0161inu p\u0159\u00edsp\u011bvk\u016f na facebooku a diskuzn\u00edch f\u00f3rech nepsal ani Shakespeare ani Bo\u017eena N\u011bmcov\u00e1. A to je taky jeden z probl\u00e9m\u016f sou\u010dasn\u00e9 informa\u010dn\u00ed exploze \u2013 naprost\u00e1 v\u011bt\u0161ina dostupn\u00fdch text\u016f je prakticky bezcenn\u00e1<\/strong>. V t\u00e9to bezcenn\u00e9 kup\u011b se ov\u0161em \u010dasto skr\u00fdv\u00e1 d\u016fle\u017eit\u00e1 informace. Vzhledem k mno\u017estv\u00ed dat ji ov\u0161em nejde b\u011b\u017en\u00fdmi prost\u0159edky naj\u00edt.\n\nA pr\u00e1v\u011b proto se v posledn\u00ed dob\u011b za\u010dal velkou rychlost\u00ed rozv\u00edjet obor textov\u00e9 analytiky. Americk\u00fd \u010dasopis Time o n\u00ed mluvil jako o mo\u017en\u00e9 dal\u0161\u00ed \u201evelk\u00e9 v\u011bci<\/a>\u201c<\/strong> v roce 2012, The Economist mluv\u00ed o zlat\u00e9 \u017e\u00edle<\/strong>. Do textov\u00e9 analytiky investuj\u00ed firmy od gigant\u016f jako je Google, Microsoft a Facebook a\u017e po startupy ve Skandin\u00e1vii. Po cel\u00e9m sv\u011bt\u011b se tak\u00e9 zpracov\u00e1n\u00edm jazyka zab\u00fdvaj\u00ed stovky univerzit, od Stanfordu p\u0159es MIT a\u017e po Karlovu a Masarykovu univerzitu. A pak jsou tu samoz\u0159ejm\u011b arm\u00e1da a tajn\u00e9 slu\u017eby. Pojdm\u011b se ale pod\u00edvat trochu do historie.\n

Historie zpracov\u00e1n\u00ed jazyka<\/h3>\nZpracov\u00e1n\u00edm jazyka se zaob\u00edr\u00e1 v\u011bda naz\u00fdvan\u00e1 po\u010d\u00edta\u010dov\u00e1 lingvistika nebo t\u00e9\u017e strojov\u00e9 zpracov\u00e1n\u00ed jazyka. V\u011bt\u0161inou se pou\u017e\u00edv\u00e1 zkratka NLP z anglick\u00e9ho Natural Language Processing<\/strong>. Vyu\u017eit\u00ed NLP pro anal\u00fdzu dat nap\u0159\u00edklad ve firm\u00e1ch se potom \u0159\u00edk\u00e1 textov\u00e1 analytika.\n\n\n
\"\"<\/figure>\nV program\u00e1torsko-mana\u017eersk\u00e9 hant\u00fdrce se text\u016fm \u0159\u00edk\u00e1 nestrukturovan\u00e1 data<\/strong>. T\u00edm se maj\u00ed odli\u0161it od strukturovan\u00fdch dat ulo\u017een\u00fdch ve sloupe\u010dc\u00edch r\u016fzn\u00fdch datab\u00e1z\u00ed. Striktn\u011b vzato je to samoz\u0159ejm\u011b nesmysln\u00e9 pojmenov\u00e1n\u00ed. Pr\u00e1v\u011b proto, \u017ee text strukturu m\u00e1, mohou \u0161koly (\u010dasto samo\u00fa\u010deln\u011b) zkou\u0161et d\u011bti z toho, jestli jsou schopn\u00e9 ud\u011blat jazykov\u00fd rozbor. Klidn\u011b by mohli analyzovat v\u011bty typu V\u010dera m\u011b internetov\u00e9 bankovnictv\u00ed banky X skute\u010dn\u011b vyto\u010dilo<\/em><\/strong> a v\u00fdsledek zapisovat m\u00edsto na tabuli do Excelu se sloupe\u010dky nadepsan\u00fdmi kdo, kdy, komu, co. Pojem nestrukturovan\u00e1 data se pou\u017e\u00edv\u00e1, proto\u017ee struktura informace nen\u00ed viditeln\u00e1 na prvn\u00ed pohled<\/strong> \u2013 zat\u00edmco lid\u00e9 rozum\u011bj\u00ed jazyku v\u00edce m\u00e9n\u011b automaticky a ani\u017e by o tom p\u0159em\u00fd\u0161leli, pro po\u010d\u00edta\u010de je to mnohem slo\u017eit\u011bj\u0161\u00ed.\n\nO po\u010d\u00edta\u010dov\u00e9m zpracov\u00e1n\u00ed jazyka se zmi\u0148oval ji\u017e Alan Turing<\/a><\/strong>, anglick\u00fd matematik, kdy\u017e navrhl test, pomoc\u00ed kter\u00e9ho by se mohlo poznat, zda je po\u010d\u00edta\u010d inteligentn\u00ed. Dnes se tomuto testu \u0159\u00edk\u00e1 Turing\u016fv test<\/a><\/strong>. Mimochodem Turing taky navrhl jeden z prvn\u00edch model\u016f po\u010d\u00edta\u010de a sehr\u00e1l hlavn\u00ed roli v prolomen\u00ed n\u011bmeck\u00fdch v\u00e1le\u010dn\u00fdch \u0161ifer. V pades\u00e1t\u00fdch letech pak n\u00e1sledovala revoluce v jazykov\u011bd\u011b zp\u016fsoben\u00e1 americk\u00fdm profesorem Noamem Chomskym<\/strong><\/a>, kter\u00fd uk\u00e1zal, \u017ee jazyk lze analyzovat exaktn\u011b pomoc\u00ed matematick\u00fdch struktur a pravidel, kter\u00e1 jsou nav\u00edc v z\u00e1kladu shodn\u00e1 pro v\u0161echny jazyky.\n\nVelk\u00e1 \u010d\u00e1st v\u00fdzkumu v po\u010d\u00edta\u010dov\u00e9m zpracov\u00e1n\u00ed jazyka byla financov\u00e1na arm\u00e1dou<\/strong>, jak v USA tak v Sov\u011btsk\u00e9m svazu. V roce 1954 p\u0159elo\u017eil syst\u00e9m vyvinut\u00fd spole\u010dn\u011b firmou IBM a Georgetownskou univerzitou p\u0159es 60 rusk\u00fdch v\u011bt z ru\u0161tiny do angli\u010dtiny.<\/strong> Auto\u0159i syst\u00e9mu byli natolik optimisti\u010dt\u00ed, \u017ee tvrdili, \u017ee strojov\u00fd p\u0159eklad bude do t\u0159\u00ed a\u017e p\u011bti let zvl\u00e1dnut\u00fd probl\u00e9m (zde<\/a> si lze p\u0159e\u010d\u00edst p\u016fvodn\u00ed tiskovou zpr\u00e1vu).. V\u00fdsledky se ov\u0161em nedostavily, nad\u0161en\u00ed vyst\u0159\u00eddala skepse a s n\u00ed p\u0159i\u0161el i konec masivn\u00edch investic do v\u00fdzkumu (anal\u00fdza od Johna Hutchinsa<\/a> s 50-let\u00fdm odstupem).\n\nK v\u00fdznamn\u011bj\u0161\u00edmu pokroku do\u0161lo a\u017e b\u011bhem 80. let, kdy ov\u0161em p\u016fvodn\u00ed syst\u00e9my s ru\u010dn\u011b psan\u00fdmi pravidly nahradily syst\u00e9my statistick\u00e9, kter\u00e9 se samy u\u010d\u00ed.<\/strong> V popul\u00e1rn\u00edm tisku se \u010dasto mluv\u00ed o neuronov\u00fdch s\u00edt\u00edch, ale syst\u00e9m\u016f existuje v\u00edce druh\u016f. \u010casto se jazyk nap\u0159\u00edklad modeluje v algebraick\u00fdch prostorech o tis\u00edc\u00edch dimenz\u00ed, kter\u00e9 se r\u016fzn\u011b deformuj\u00ed a prom\u00edtaj\u00ed do jin\u00fdch prostor\u016f. Spo\u010d\u00edt\u00e1n\u00ed podobnosti v\u00fdznamu dvou v\u011bt je pak do zna\u010dn\u00e9 m\u00edry podobn\u00e9 spo\u010d\u00edt\u00e1n\u00ed vzd\u00e1lenosti dvou m\u011bst na map\u011b.\n\nTyto syst\u00e9my se u\u010d\u00ed z dat<\/strong>. T\u011bch dat v\u011bt\u0161inou pot\u0159ebuj\u00ed hodn\u011b a nav\u00edc se \u201espr\u00e1vn\u00fdmi odpov\u011b\u010fmi\u201c.\u00a0Nap\u0159\u00edklad b\u011b\u017en\u00fd syst\u00e9m pro strojov\u00fd p\u0159eklad se \u201etr\u00e9nuje\u201c na statis\u00edc\u00edch p\u0159elo\u017een\u00fdch v\u011bt a fr\u00e1z\u00ed. Podobn\u011b syst\u00e9m, kter\u00fd bude t\u0159\u00eddit emaily na st\u00ed\u017enosti a dotazy pot\u0159ebuje nejd\u0159\u00edve \u201evid\u011bt\u201c stovky a\u017e tis\u00edce email\u016f spr\u00e1vn\u011b rozt\u0159\u00edd\u011bn\u00fdch.\n

Jak to (skoro) funguje<\/h3>\nP\u0159edstavte si nap\u0159\u00edklad syst\u00e9m pro monitoring zpr\u00e1v, jakousi modern\u00ed v\u00fdst\u0159i\u017ekovou slu\u017ebu. Z\u00e1kazn\u00edk, t\u0159eba automobilka, bude cht\u00edt dost\u00e1vat pravideln\u00e9 zpr\u00e1vy o tom, co se na r\u016fzn\u00fdch zpravodajsk\u00fdch serverech, blog\u00e1ch, facebooku atd. p\u00ed\u0161e o jej\u00edch autech i autech konkurence. Takov\u00fd syst\u00e9m bude pou\u017e\u00edvat neust\u00e1le aktualizovanou datab\u00e1zi web\u016f<\/strong> podobnou t\u00e9, jakou\u00a0pou\u017e\u00edvaj\u00ed vyhled\u00e1va\u010de jako Google nebo Seznam. Z t\u00e9 bude pravideln\u011b \u010derpat nov\u011b publikovan\u00e9 informace. U ka\u017ed\u00e9 str\u00e1nky pak bude muset rozpoznat jazyk a t\u00e9ma (zda jde o recenzi auta, nebo o recept na b\u00e1bovku). \u010casto bude text t\u0159eba \u201evy\u010distit\u201c<\/strong>, proto\u017ee mnoh\u00e9 koment\u00e1\u0159e jsou ps\u00e1ny ve sp\u011bchu, obsahuj\u00ed chyby, jsou bez diakritiky, atd. Taky je t\u0159eba odstranit reklamy, odkazy na jin\u00e9 \u010dl\u00e1nky atd. Z videa je t\u0159eba z\u00edskat obsah pomoc\u00ed syst\u00e9mu pro<\/span> rozpozn\u00e1v\u00e1n\u00ed \u0159e\u010di<\/span>. Pak se v textu naleznou jm\u00e9na produkt\u016f, firem, osob, atd. a vztahy mezi nimi (Sylvester Stallone p\u0159ijel ve sv\u00e9m mercedesu<\/em>). Podobn\u011b je d\u016fle\u017eit\u00e9, jak se text o t\u011bchto produktech a firm\u00e1ch vyjad\u0159uje, takzvan\u00fd sentiment<\/strong>. To je samoz\u0159ejm\u011b jednodu\u0161\u0161\u00ed u kr\u00e1tk\u00e9ho\u00a0tweetu ne\u017e u n\u011bkolikastr\u00e1nkov\u00e9ho rozhovoru<\/span>. Taky\u00a0je d\u016fle\u017eit\u00e9 v\u011bd\u011bt, \u017ee \u010dl\u00e1nek se pochvaln\u011b vyjad\u0159uje o akceleraci a vybaven\u00ed, ale negativn\u011b o cen\u011b a spot\u0159eb\u011b. A tak d\u00e1le.\n\nKrom\u011b anal\u00fdzy jednotliv\u00fdch str\u00e1nek je pak t\u0159eba taky analyzovat v\u0161echny jako celek: zobrazit celkov\u00e9 statistiky, identifikovat nov\u00e1 nosn\u00e1 t\u00e9mata, trendy (spolehlivost je na francouzsk\u00e9m facebooku vn\u00edm\u00e1na l\u00e9pe ne\u017e p\u0159ed rokem, ale na anglick\u00e9m h\u016f\u0159e). No a v\u0161e je t\u0159eba spr\u00e1vn\u011b zobrazit, aby tomu z\u00e1kazn\u00edk rozum\u011bl, a aby mu to pomohlo l\u00e9pe d\u011blat jeho pr\u00e1ci, v tomto p\u0159\u00edpad\u011b l\u00e9pe vyr\u00e1b\u011bt a prod\u00e1vat auta<\/strong>.\n\nTakov\u00fdto syst\u00e9m, kter\u00fd by pln\u011b automaticky a spolehliv\u011b fungoval nap\u0159\u00ed\u010d t\u00e9maty a jazyky, je st\u00e1le je\u0161t\u011b hudbou budoucnosti, ale mnoh\u00e9 jeho \u010d\u00e1sti jsou dostupn\u00e9 ji\u017e dnes<\/strong>. Nap\u0159\u00edklad ka\u017ed\u00fd si m\u016f\u017ee vyzkou\u0161et anal\u00fdzu jednotliv\u00fdch dokument\u016f pomoc\u00ed IBM Watson<\/a> pro angli\u010dtinu. V\u011bt\u0161ina lid\u00ed si asi taky v\u0161imla, \u017ee kdy\u017e hled\u00e1me na anglick\u00e9m Googlu<\/strong> pou\u017eit\u00e1 auta pomoc\u00ed dotazu \u201eused vehecles\u201c, tak Google oprav\u00ed p\u0159eklep a navrhne hled\u00e1n\u00ed spr\u00e1vn\u00e9ho \u201eused vehicles\u201c, najde i str\u00e1nky, kde bude \u201evehicle\u201c jen v jednotn\u00e9m \u010d\u00edsle, a hlavn\u011b najde i str\u00e1nky, kde se bude m\u00edsto \u201evehicle\u201c pou\u017e\u00edvat b\u011b\u017en\u011bj\u0161\u00ed \u201ecar\u201c. Podobn\u011b t\u0159eba youtube um\u00ed automaticky p\u0159idat titulky k anglick\u00fdm film\u016fm.\n\nJak to bylo d\u00e1l? T\u011b\u0161te se na dal\u0161\u00ed d\u00edl Textov\u00e9ho zlatokopectv\u00ed! \ud83d\ude42","protected":false},"excerpt":{"rendered":"

Dobr\u00fd hostinsk\u00fd se od t\u011bch pr\u016fm\u011brn\u00fdch odli\u0161uje v mnoha v\u011bcech, ale jednou z hlavn\u00edch je to, \u017ee zn\u00e1 sv\u00e9ho z\u00e1kazn\u00edka. V\u00ed o n\u011bm, kdy p\u0159ich\u00e1z\u00ed a zda chce ve\u010de\u0159i s v\u00ednem nebo si jen p\u0159e\u010d\u00edst noviny u kafe. V\u00ed, zda r\u00e1d poslouch\u00e1 \u017eiv\u00fd jazz nebo se rad\u0161i d\u00edv\u00e1 na hokej. V\u00ed, kdo chce jedno pivo…<\/p>\n","protected":false},"author":8,"featured_media":104,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[350],"tags":[],"class_list":["post-14","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-informace"],"yoast_head":"\nTextov\u00e9 zlatokopectv\u00ed - Geneea News<\/title>\n<meta name=\"description\" content=\"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Textov\u00e9 zlatokopectv\u00ed - Geneea News\" \/>\n<meta property=\"og:description\" content=\"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi\" \/>\n<meta property=\"og:site_name\" content=\"Geneea News\" \/>\n<meta property=\"article:published_time\" content=\"2015-09-15T14:07:08+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-01-29T21:30:41+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1140\" \/>\n\t<meta property=\"og:image:height\" content=\"640\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Jiri Hana\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Jiri Hana\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi\"},\"author\":{\"name\":\"Jiri Hana\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#\\\/schema\\\/person\\\/01da37c1e642ddff7af2d03f9d7b908d\"},\"headline\":\"Textov\u00e9 zlatokopectv\u00ed\",\"datePublished\":\"2015-09-15T14:07:08+00:00\",\"dateModified\":\"2026-01-29T21:30:41+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi\"},\"wordCount\":1807,\"publisher\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2015\\\/09\\\/zlatokopectvi.jpg\",\"articleSection\":[\"Informace\"],\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi\",\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi\",\"name\":\"Textov\u00e9 zlatokopectv\u00ed - Geneea News\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2015\\\/09\\\/zlatokopectvi.jpg\",\"datePublished\":\"2015-09-15T14:07:08+00:00\",\"dateModified\":\"2026-01-29T21:30:41+00:00\",\"description\":\"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#primaryimage\",\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2015\\\/09\\\/zlatokopectvi.jpg\",\"contentUrl\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2015\\\/09\\\/zlatokopectvi.jpg\",\"width\":1140,\"height\":640},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/cs\\\/textove-zlatokopectvi#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/geneea.com\\\/news\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Textov\u00e9 zlatokopectv\u00ed\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#website\",\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/\",\"name\":\"Geneea News\",\"description\":\"Learn more about what's happening at Geneea: new NLP features, newest case studies, tutoring projects, conferences we attended, etc.\",\"publisher\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/geneea.com\\\/news\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#organization\",\"name\":\"Geneea News\",\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/cropped-geneea-logo-50pc.png\",\"contentUrl\":\"https:\\\/\\\/geneea.com\\\/news\\\/wp-content\\\/uploads\\\/2022\\\/02\\\/cropped-geneea-logo-50pc.png\",\"width\":242,\"height\":64,\"caption\":\"Geneea News\"},\"image\":{\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#\\\/schema\\\/logo\\\/image\\\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/geneea.com\\\/news\\\/#\\\/schema\\\/person\\\/01da37c1e642ddff7af2d03f9d7b908d\",\"name\":\"Jiri Hana\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g\",\"caption\":\"Jiri Hana\"},\"url\":\"https:\\\/\\\/geneea.com\\\/news\\\/author\\\/jiri-hana\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Textov\u00e9 zlatokopectv\u00ed - Geneea News","description":"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi","og_locale":"en_US","og_type":"article","og_title":"Textov\u00e9 zlatokopectv\u00ed - Geneea News","og_description":"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.","og_url":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi","og_site_name":"Geneea News","article_published_time":"2015-09-15T14:07:08+00:00","article_modified_time":"2026-01-29T21:30:41+00:00","og_image":[{"width":1140,"height":640,"url":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg","type":"image\/jpeg"}],"author":"Jiri Hana","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Jiri Hana","Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#article","isPartOf":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi"},"author":{"name":"Jiri Hana","@id":"https:\/\/geneea.com\/news\/#\/schema\/person\/01da37c1e642ddff7af2d03f9d7b908d"},"headline":"Textov\u00e9 zlatokopectv\u00ed","datePublished":"2015-09-15T14:07:08+00:00","dateModified":"2026-01-29T21:30:41+00:00","mainEntityOfPage":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi"},"wordCount":1807,"publisher":{"@id":"https:\/\/geneea.com\/news\/#organization"},"image":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#primaryimage"},"thumbnailUrl":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg","articleSection":["Informace"],"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi","url":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi","name":"Textov\u00e9 zlatokopectv\u00ed - Geneea News","isPartOf":{"@id":"https:\/\/geneea.com\/news\/#website"},"primaryImageOfPage":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#primaryimage"},"image":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#primaryimage"},"thumbnailUrl":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg","datePublished":"2015-09-15T14:07:08+00:00","dateModified":"2026-01-29T21:30:41+00:00","description":"Objevte, jak textov\u00e1 analytika pom\u00e1h\u00e1 naj\u00edt cenn\u00e9 poznatky v obrovsk\u00e9m mno\u017estv\u00ed textu \u2013 od z\u00e1kaznick\u00fdch zp\u011btn\u00fdch vazeb a\u017e po firemn\u00ed data.","breadcrumb":{"@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#primaryimage","url":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg","contentUrl":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2015\/09\/zlatokopectvi.jpg","width":1140,"height":640},{"@type":"BreadcrumbList","@id":"https:\/\/geneea.com\/news\/cs\/textove-zlatokopectvi#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/geneea.com\/news"},{"@type":"ListItem","position":2,"name":"Textov\u00e9 zlatokopectv\u00ed"}]},{"@type":"WebSite","@id":"https:\/\/geneea.com\/news\/#website","url":"https:\/\/geneea.com\/news\/","name":"Geneea News","description":"Learn more about what's happening at Geneea: new NLP features, newest case studies, tutoring projects, conferences we attended, etc.","publisher":{"@id":"https:\/\/geneea.com\/news\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/geneea.com\/news\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/geneea.com\/news\/#organization","name":"Geneea News","url":"https:\/\/geneea.com\/news\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/geneea.com\/news\/#\/schema\/logo\/image\/","url":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2022\/02\/cropped-geneea-logo-50pc.png","contentUrl":"https:\/\/geneea.com\/news\/wp-content\/uploads\/2022\/02\/cropped-geneea-logo-50pc.png","width":242,"height":64,"caption":"Geneea News"},"image":{"@id":"https:\/\/geneea.com\/news\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/geneea.com\/news\/#\/schema\/person\/01da37c1e642ddff7af2d03f9d7b908d","name":"Jiri Hana","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/9763e6bb29d017c7d64e51704541d429c4203c159ff1f336be9728247ed7e023?s=96&d=mm&r=g","caption":"Jiri Hana"},"url":"https:\/\/geneea.com\/news\/author\/jiri-hana"}]}},"_links":{"self":[{"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/posts\/14","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/comments?post=14"}],"version-history":[{"count":8,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/posts\/14\/revisions"}],"predecessor-version":[{"id":2316,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/posts\/14\/revisions\/2316"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/media\/104"}],"wp:attachment":[{"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/media?parent=14"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/categories?post=14"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/geneea.com\/news\/wp-json\/wp\/v2\/tags?post=14"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}