{"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\/sk\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","title":{"rendered":"Microsoft otvoril k\u00f3d kni\u017enice vektorov\u00e9ho vyh\u013ead\u00e1vania, ktor\u00e1 sa pou\u017e\u00edva v Bingu","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Spolo\u010dnos\u0165 Microsoft publikovala<\/a><\/noindex> p\u00f4vodn\u00e9 texty kni\u017enice strojov\u00e9ho u\u010denia SPTAG<\/a><\/noindex> (Space Partition Tree And Graph) s implement\u00e1ciou algoritmu pribl\u00ed\u017eenej h\u013eadania najbli\u017e\u0161ieho suseda<\/a><\/noindex>. Kni\u017enica bola vyvinut\u00e1<\/a><\/noindex> v v\u00fdskumnom oddelen\u00ed Microsoft Research a v centre v\u00fdvoja vyh\u013ead\u00e1vac\u00edch technol\u00f3gi\u00ed (Microsoft Search Technology Center). V praxi sa SPTAG vyu\u017e\u00edva vo vyh\u013ead\u00e1vacom syst\u00e9me Bing na ur\u010denie najrelevantnej\u0161\u00edch v\u00fdsledkov s oh\u013eadom na kontext vyh\u013ead\u00e1vac\u00edch dopytov. K\u00f3d je nap\u00edsan\u00fd v jazyku C++ a distribuovan\u00fd<\/a><\/noindex> je pod licenciou MIT. Podporuje sa zostavenie pre Linux a Windows. Existuje obal pre jazyk Python.<\/p>\n

Napriek tomu, \u017ee my\u0161lienky vyu\u017eitia vektorov\u00fdch \u00falo\u017e\u00edsk vo vyh\u013ead\u00e1vac\u00edch syst\u00e9moch s\u00fa tu u\u017e dlh\u0161\u00ed \u010das, ich implement\u00e1cii br\u00e1ni vysok\u00e1 n\u00e1ro\u010dnos\u0165 oper\u00e1ci\u00ed s vektormi a obmedzenia v \u0161k\u00e1lovate\u013enosti. Kombin\u00e1cia met\u00f3d hlbok\u00e9ho strojov\u00e9ho u\u010denia s algoritmami pribl\u00ed\u017eenej h\u013eadania najbli\u017e\u0161ieho suseda umo\u017enila dosiahnu\u0165 v\u00fdkonnos\u0165 a \u0161k\u00e1lovate\u013enos\u0165 vektorov\u00fdch syst\u00e9mov na \u00farove\u0148, ktor\u00e1 je prijate\u013en\u00e1 pre ve\u013ek\u00e9 vyh\u013ead\u00e1vacie syst\u00e9my. Napr\u00edklad vo vyh\u013ead\u00e1va\u010di Bing pre vektorov\u00fd index s viac ako 150 miliardami vektorov sa \u010das na vyh\u013eadanie najrelevantnej\u0161\u00edch v\u00fdsledkov zmest\u00ed do 8 ms.<\/p>\n

Kni\u017enica obsahuje prostriedky na vytv\u00e1ranie indexu a organiz\u00e1ciu h\u013eadania vektorov, ako aj s\u00fabor n\u00e1strojov na spr\u00e1vu distribuovanej online vyh\u013ead\u00e1vacej s\u00fastavy, ktor\u00e1 pokr\u00fdva ve\u013emi ve\u013ek\u00e9 zbierky vektorov. S\u00fa pon\u00fakan\u00e9<\/a><\/noindex> nasleduj\u00face moduly: index builder na indexovanie, searcher na h\u013eadanie s vyu\u017eit\u00edm indexu, distribuovan\u00e9ho v klastri z viacer\u00fdch uzlov, server na spustenie spracovate\u013eov na uzloch, Aggregator na zl\u00fa\u010denie nieko\u013ek\u00fdch serverov do jedn\u00e9ho celku a klient pre odosielanie dopytov. Podporuje sa prid\u00e1vanie nov\u00fdch vektorov do indexu a odstra\u0148ovanie vektorov za behu.<\/p>\n

Kni\u017enica predpoklad\u00e1, \u017ee spracov\u00e1van\u00e9 a prezentovan\u00e9 v zbierke \u00fadaje s\u00fa usporiadan\u00e9 vo forme prepojen\u00fdch vektorov, ktor\u00e9 je mo\u017en\u00e9 porovn\u00e1va\u0165 na z\u00e1klade euklidovsk\u00fdch<\/a><\/noindex> (L2) alebo kos\u00ednusov\u00fdch<\/a><\/noindex> vzdialenost\u00ed. Pri vyh\u013ead\u00e1vacom dopyte sa vr\u00e1tia vektory, ktor\u00fdch vzdialenos\u0165 od po\u010diato\u010dn\u00e9ho vektora je minim\u00e1lna. V SPTAG sa poskytuj\u00fa dva met\u00f3dy organiz\u00e1cie vektorov\u00e9ho priestoru: SPTAG-KDT (K-rozmern\u00e9 strom (kd-tree<\/a><\/noindex>) a graf relat\u00edvnych susedstiev<\/a><\/noindex>) a SPTAG-BKT (strom k-stredn\u00fdch (k-means tree<\/a><\/noindex> a graf relat\u00edvnych okolitost\u00ed). Prv\u00e1 met\u00f3da vy\u017eaduje menej zdrojov pri pr\u00e1ci s indexom, zatia\u013e \u010do druh\u00e1 vykazuje vy\u0161\u0161iu presnos\u0165 v\u00fdsledkov vyh\u013ead\u00e1vania pri ve\u013emi ve\u013ek\u00fdch kolekci\u00e1ch vektorov.<\/p>\n

Vektorov\u00e9 vyh\u013ead\u00e1vanie nie je obmedzen\u00e9 iba na text, ale m\u00f4\u017ee sa aplikova\u0165 aj na multimedi\u00e1lne inform\u00e1cie a obr\u00e1zky, ako aj v syst\u00e9moch na automatick\u00e9 generovanie odpor\u00fa\u010dan\u00ed. Napr\u00edklad v jednom z prototypov na b\u00e1ze r\u00e1mca PyTorch bola implementovan\u00e1 vektorov\u00e1 syst\u00e9m na vyh\u013ead\u00e1vanie so zoh\u013eadnen\u00edm podobnosti objektov na obr\u00e1zkoch, ktor\u00fd bol vytvoren\u00fd s pou\u017eit\u00edm \u00fadajov z viacer\u00fdch referen\u010dn\u00fdch kolekci\u00ed s obr\u00e1zkami zvierat, ma\u010diek a psov, ktor\u00e9 boli preveden\u00e9 na s\u00fapravy vektorov. Pri prich\u00e1dzaj\u00facom obr\u00e1zku na vyh\u013ead\u00e1vanie je preveden\u00fd pomocou modelu strojov\u00e9ho u\u010denia na vektor, na z\u00e1klade ktor\u00e9ho sa pomocou algoritmu SPTAG vyberaj\u00fa z indexu najpodobnej\u0161ie vektory a ako v\u00fdsledok sa vracaj\u00fa s nimi spojen\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 otvoril k\u00f3d kni\u017enice vektorov\u00e9ho vyh\u013ead\u00e1vania, pou\u017e\u00edvan\u00e9ho v Bingu | ProHoster","description":"Spolo\u010dnos\u0165 Microsoft publikovala zdrojov\u00e9 k\u00f3dy kni\u017enice strojov\u00e9ho u\u010denia.","canonical_url":"https:\/\/prohoster.info\/sk\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"sk_SK","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\/sk\/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\/sk\/wp-json\/wp\/v2\/posts\/33865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/comments?post=33865"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/posts\/33865\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/media?parent=33865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/categories?post=33865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/sk\/wp-json\/wp\/v2\/tags?post=33865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}