{"id":33865,"date":"2019-10-31T21:55:06","date_gmt":"2019-10-31T18:55:06","guid":{"rendered":"https:\/\/prohoster.info\/blog\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing\/"},"modified":"2019-10-31T21:55:06","modified_gmt":"2019-10-31T18:55:06","slug":"microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","status":"publish","type":"post","link":"https:\/\/prohoster.info\/cs\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","title":{"rendered":"Microsoft otev\u0159el k\u00f3d knihovny vektorov\u00e9ho vyhled\u00e1v\u00e1n\u00ed pou\u017e\u00edvan\u00e9 v Bingu","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Spole\u010dnost Microsoft publikovala<\/a><\/noindex> p\u016fvodn\u00ed texty knihovny strojov\u00e9ho u\u010den\u00ed SPTAG<\/a><\/noindex> (Space Partition Tree And Graph) s implementac\u00ed algoritmu p\u0159ibli\u017en\u00e9ho vyhled\u00e1v\u00e1n\u00ed nejbli\u017e\u0161\u00edho souseda<\/a><\/noindex>. Knihovna byla vyvinuta<\/a><\/noindex> ve v\u00fdzkumn\u00e9 divizi Microsoft Research a centru pro v\u00fdvoj vyhled\u00e1vac\u00edch technologi\u00ed (Microsoft Search Technology Center). V praxi se SPTAG pou\u017e\u00edv\u00e1 v vyhled\u00e1va\u010di Bing k ur\u010den\u00ed nejrelevantn\u011bj\u0161\u00edch v\u00fdsledk\u016f s p\u0159ihl\u00e9dnut\u00edm k kontextu vyhled\u00e1vac\u00edch dotaz\u016f. K\u00f3d je naps\u00e1n v jazyce C++ a distribuov\u00e1no<\/a><\/noindex> je licencov\u00e1n pod licenc\u00ed MIT. Je podporov\u00e1na kompilace pro Linux a Windows. Je k dispozici obal pro jazyk Python.<\/p>\n

I kdy\u017e my\u0161lenky na vyu\u017eit\u00ed vektorov\u00fdch \u00falo\u017ei\u0161\u0165 ve vyhled\u00e1va\u010d\u00edch existuj\u00ed ji\u017e dlouho, jejich implementaci na praxi br\u00e1n\u00ed vysok\u00e1 n\u00e1ro\u010dnost operac\u00ed s vektory a omezen\u00ed \u0161k\u00e1lovatelnosti. Kombinace metod hloubkov\u00e9ho strojov\u00e9ho u\u010den\u00ed s algoritmy p\u0159ibli\u017en\u00e9ho vyhled\u00e1v\u00e1n\u00ed nejbli\u017e\u0161\u00edho souseda umo\u017enila dos\u00e1hnout v\u00fdkonnosti a \u0161k\u00e1lovatelnosti vektorov\u00fdch syst\u00e9m\u016f na \u00farove\u0148 p\u0159ijatelnou pro velk\u00e9 vyhled\u00e1va\u010de. Nap\u0159\u00edklad v Bingu pro vektorov\u00fd index o velikosti v\u00edce ne\u017e 150 miliard vektor\u016f doba v\u00fdb\u011bru nejrelevantn\u011bj\u0161\u00edch v\u00fdsledk\u016f \u010din\u00ed 8 ms.<\/p>\n

Knihovna obsahuje n\u00e1stroje pro vytv\u00e1\u0159en\u00ed indexu a organizaci vyhled\u00e1v\u00e1n\u00ed vektor\u016f, stejn\u011b jako sadu n\u00e1stroj\u016f pro podporu distribuovan\u00e9ho online vyhled\u00e1v\u00e1n\u00ed, pokr\u00fdvaj\u00edc\u00edho velmi velk\u00e9 sb\u00edrky vektor\u016f. Jsou nab\u00edzeny<\/a><\/noindex> n\u00e1sleduj\u00edc\u00ed moduly: index builder pro indexaci, searcher pro vyhled\u00e1v\u00e1n\u00ed pomoc\u00ed indexu, distribuovan\u00e9ho v clusteru n\u011bkolika uzl\u016f, server pro spu\u0161t\u011bn\u00ed zpracovatel\u016f na uzlech, Aggregator pro spojen\u00ed n\u011bkolika server\u016f do jednoho celku a klient pro odes\u00edl\u00e1n\u00ed dotaz\u016f. Podporuje se p\u0159id\u00e1v\u00e1n\u00ed nov\u00fdch vektor\u016f do indexu a odstra\u0148ov\u00e1n\u00ed vektor\u016f v re\u00e1ln\u00e9m \u010dase.<\/p>\n

Knihovna p\u0159edpokl\u00e1d\u00e1, \u017ee zpracov\u00e1van\u00e1 a prezentovan\u00e1 data ve sb\u00edrce jsou uspo\u0159\u00e1d\u00e1na jako propojen\u00e9 vektory, kter\u00e9 lze porovn\u00e1vat na z\u00e1klad\u011b eukleidovsk\u00fdch<\/a><\/noindex> (L2) nebo kosinov\u00fdch<\/a><\/noindex> vzd\u00e1lenost\u00ed. P\u0159i vyhled\u00e1vac\u00edm dotazu se vr\u00e1t\u00ed vektory, jejich\u017e vzd\u00e1lenost od p\u016fvodn\u00edho vektoru je minim\u00e1ln\u00ed. V SPTAG jsou k dispozici dv\u011b metody organizace vektorov\u00e9ho prostoru: SPTAG-KDT (K-\u00fahlov\u00fd strom (kd-tree<\/a><\/noindex>) a graf relativn\u00edch sousedstv\u00ed<\/a><\/noindex>) a SPTAG-BKT (strom k-pr\u016fm\u011br\u016f (k-means tree<\/a><\/noindex> a graf relativn\u00edch okolnost\u00ed). Prvn\u00ed metoda vy\u017eaduje m\u00e9n\u011b zdroj\u016f p\u0159i pr\u00e1ci s indexem, zat\u00edmco druh\u00e1 demonstruje vy\u0161\u0161\u00ed p\u0159esnost v\u00fdsledk\u016f vyhled\u00e1v\u00e1n\u00ed ve velmi velk\u00fdch kolekc\u00edch vektor\u016f.<\/p>\n

Vektorov\u00e9 vyhled\u00e1v\u00e1n\u00ed v\u0161ak nen\u00ed omezeno pouze na text a m\u016f\u017ee se aplikovat na multimedi\u00e1ln\u00ed informace a obr\u00e1zky, stejn\u011b jako v syst\u00e9mech automatick\u00e9ho doporu\u010dov\u00e1n\u00ed. Nap\u0159\u00edklad v jednom z prototyp\u016f na b\u00e1zi r\u00e1mce PyTorch byla realizov\u00e1na vektorov\u00e1 syst\u00e9m pro vyhled\u00e1v\u00e1n\u00ed zalo\u017een\u00e9 na podobnosti objekt\u016f na obr\u00e1zc\u00edch, stav\u011bn\u00e9 s vyu\u017eit\u00edm dat z n\u011bkolika referen\u010dn\u00edch sb\u00edrek s obr\u00e1zky zv\u00ed\u0159at, ko\u010dek a ps\u016f, kter\u00e9 byly p\u0159evedeny na sady vektor\u016f. Kdy\u017e je p\u0159ijato vstupn\u00ed obr\u00e1zek k vyhled\u00e1v\u00e1n\u00ed, je p\u0159eveden pomoc\u00ed modelu strojov\u00e9ho u\u010den\u00ed na vektor, na z\u00e1klad\u011b kter\u00e9ho je pomoc\u00ed algoritmu SPTAG z indexu vybr\u00e1no nejpodobn\u011bj\u0161\u00ed vektory a jako v\u00fdsledek se vrac\u00ed k nim p\u0159i\u0159azen\u00e9 obr\u00e1zky.<\/p>\n

<\/a><\/noindex><\/p>\n

Zdroj: opennet.ru<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Microsoft \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f SPTAG (Space Partition Tree And Graph) \u0441 \u0440\u0435\u0430\u043b\u0438\u0437\u0430\u0446\u0438\u0435\u0439 \u0430\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0430 \u043f\u0440\u0438\u0431\u043b\u0438\u0437\u0438\u0442\u0435\u043b\u044c\u043d\u043e\u0433\u043e \u043f\u043e\u0438\u0441\u043a\u0430 \u0431\u043b\u0438\u0436\u0430\u0439\u0448\u0435\u0433\u043e \u0441\u043e\u0441\u0435\u0434\u0430. \u0411\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0430 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u0430\u043d\u0430 \u0432 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044c\u0441\u043a\u043e\u043c \u043f\u043e\u0434\u0440\u0430\u0437\u0434\u0435\u043b\u0435\u043d\u0438\u0438 Microsoft Research \u0438 \u0446\u0435\u043d\u0442\u0440\u0435 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u044b\u0445 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0438\u0439 (Microsoft Search Technology Center). \u041d\u0430 \u043f\u0440\u0430\u043a\u0442\u0438\u043a\u0435 SPTAG \u043f\u0440\u0438\u043c\u0435\u043d\u044f\u0435\u0442\u0441\u044f \u0432 \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u043e\u0439 \u0441\u0438\u0441\u0442\u0435\u043c\u0435 Bing \u0434\u043b\u044f \u043e\u043f\u0440\u0435\u0434\u0435\u043b\u0435\u043d\u0438\u044f \u043d\u0430\u0438\u0431\u043e\u043b\u0435\u0435 \u0440\u0435\u043b\u0435\u0432\u0430\u043d\u0442\u043d\u044b\u0445 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u043e\u0432 \u0441 \u0443\u0447\u0451\u0442\u043e\u043c \u043a\u043e\u043d\u0442\u0435\u043a\u0441\u0442\u0430 \u043f\u043e\u0438\u0441\u043a\u043e\u0432\u044b\u0445 \u0437\u0430\u043f\u0440\u043e\u0441\u043e\u0432. […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-33865","post","type-post","status-publish","format-standard","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47Microsoft otev\u0159el k\u00f3d knihovny vektorov\u00e9ho vyhled\u00e1v\u00e1n\u00ed, pou\u017e\u00edvan\u00e9 v Bingu | ProHoster","description":"Spole\u010dnost Microsoft zve\u0159ejnila zdrojov\u00e9 k\u00f3dy knihovny strojov\u00e9ho u\u010den\u00ed.","canonical_url":"https:\/\/prohoster.info\/cs\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"cs_CZ","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47Microsoft \u043e\u0442\u043a\u0440\u044b\u043b \u043a\u043e\u0434 \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 \u0432\u0435\u043a\u0442\u043e\u0440\u043d\u043e\u0433\u043e \u043f\u043e\u0438\u0441\u043a\u0430, \u0438\u0441\u043f\u043e\u043b\u044c\u0437\u0443\u0435\u043c\u043e\u0439 \u0432 Bing | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Microsoft \u043e\u043f\u0443\u0431\u043b\u0438\u043a\u043e\u0432\u0430\u043b\u0430 \u0438\u0441\u0445\u043e\u0434\u043d\u044b\u0435 \u0442\u0435\u043a\u0441\u0442\u044b \u0431\u0438\u0431\u043b\u0438\u043e\u0442\u0435\u043a\u0438 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f","og:url":"https:\/\/prohoster.info\/cs\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2019-10-31T18:55:06+00:00","article:modified_time":"2019-10-31T18:55:06+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"33865","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":null,"schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":"2026-01-21 17:01:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 02:32:26","updated":"2026-01-21 17:01:19","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/33865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/comments?post=33865"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/posts\/33865\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/media?parent=33865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/categories?post=33865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/cs\/wp-json\/wp\/v2\/tags?post=33865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}