{"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\/hu\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","title":{"rendered":"A Microsoft felfedte a Bingben haszn\u00e1lt vektor keres\u00e9si k\u00f6nyvt\u00e1r k\u00f3dj\u00e1t.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Microsoft v\u00e1llalat kiadta<\/a><\/noindex> a g\u00e9pi tanul\u00e1s k\u00f6nyvt\u00e1r\u00e1nak eredeti sz\u00f6vegei SPTAG<\/a><\/noindex> (T\u00e9rbeli Part\u00edci\u00f3s Fa \u00e9s Grafikon) az approximat\u00edv algoritmus megval\u00f3s\u00edt\u00e1s\u00e1val a legk\u00f6zelebbi szomsz\u00e9d keres\u00e9s\u00e9re<\/a><\/noindex>. A k\u00f6nyvt\u00e1r kifejlesztve<\/a><\/noindex> a Microsoft Research kutat\u00f3egys\u00e9g\u00e9ben \u00e9s a Microsoft Search Technology Center fejleszt\u0151 k\u00f6zpontj\u00e1ban k\u00e9sz\u00fclt. A SPTAG a gyakorlatban a Bing keres\u0151motorban alkalmaz\u00e1sra ker\u00fcl a legrelev\u00e1nsabb tal\u00e1latok meghat\u00e1roz\u00e1s\u00e1ra a keres\u00e9si kifejez\u00e9sek kontextus\u00e1nak figyelembev\u00e9tel\u00e9vel. A k\u00f3d C++ nyelven \u00edr\u00f3dott, \u00e9s terjeszt\u00e9sre ker\u00fcl<\/a><\/noindex> MIT licenc alatt \u00e1ll. T\u00e1mogatott a Linux \u00e9s Windows verzi\u00f3ja. Van egy k\u00f6tege a Python nyelvhez.<\/p>\n

B\u00e1r a vektort\u00e1rol\u00f3k keres\u0151motorokban val\u00f3 haszn\u00e1lat\u00e1nak \u00f6tlete m\u00e1r r\u00e9g\u00f3ta l\u00e9tezik, a gyakorlatban a vektorokkal v\u00e9gzett m\u0171veletek magas er\u0151forr\u00e1s-ig\u00e9nye \u00e9s a sk\u00e1l\u00e1zhat\u00f3s\u00e1gi korl\u00e1tok megnehez\u00edtik a bevezet\u00e9st. A m\u00e9ly g\u00e9pi tanul\u00e1s m\u00f3dszereinek kombin\u00e1l\u00e1sa az approximat\u00edv legk\u00f6zelebbi szomsz\u00e9d keres\u00e9si algoritmusokkal lehet\u0151v\u00e9 tette a vektorrendszerek teljes\u00edtm\u00e9ny\u00e9nek \u00e9s sk\u00e1l\u00e1zhat\u00f3s\u00e1g\u00e1nak emel\u00e9s\u00e9t olyan szintre, amely elfogadhat\u00f3 a nagyobb keres\u0151motorok sz\u00e1m\u00e1ra. P\u00e9ld\u00e1ul a Bing eset\u00e9ben t\u00f6bb mint 150 milli\u00e1rd vektor m\u00e9ret\u0171 vektoriindex eset\u00e9n a legrelev\u00e1nsabb tal\u00e1latok kiv\u00e1laszt\u00e1s\u00e1nak ideje 8 ms-on bel\u00fcl van.<\/p>\n

A k\u00f6nyvt\u00e1r tartalmazza az index\u00e9p\u00edt\u0151 \u00e9s a vektorok keres\u00e9s\u00e9nek megszervez\u00e9s\u00e9re szolg\u00e1l\u00f3 eszk\u00f6z\u00f6ket, valamint egy eszk\u00f6zk\u00e9szletet az online keres\u00e9si rendszer elosztott t\u00e1mogat\u00e1s\u00e1ra, amely rendk\u00edv\u00fcl nagy vektorkollekci\u00f3kat \u00f6lel fel. A k\u00f6vetkez\u0151 modulokat k\u00edn\u00e1lja<\/a><\/noindex> : indexel\u0151 az indexel\u00e9shez, keres\u0151 az index haszn\u00e1lat\u00e1val t\u00f6rt\u00e9n\u0151 keres\u00e9shez, elosztott szerverekb\u0151l \u00e1ll\u00f3 klaszterben, szerver az \u00fcgyint\u00e9z\u0151k futtat\u00e1s\u00e1hoz a csom\u00f3pontokon, Aggreg\u00e1tor a t\u00f6bb szerver egyes\u00edt\u00e9s\u00e9re \u00e9s kliens a lek\u00e9rdez\u00e9sek k\u00fcld\u00e9s\u00e9re. T\u00e1mogatott az \u00faj vektorok indexbe val\u00f3 felv\u00e9tele \u00e9s vektorok val\u00f3s id\u0151ben t\u00f6rt\u00e9n\u0151 elt\u00e1vol\u00edt\u00e1sa.<\/p>\n

A k\u00f6nyvt\u00e1r azt felt\u00e9telezi, hogy a feldolgozott \u00e9s a gy\u0171jtem\u00e9nyben bemutatott adatok \u00f6sszekapcsolt vektorok form\u00e1j\u00e1ban vannak, amelyeket az euclideai<\/a><\/noindex> (L2) vagy koszinusz<\/a><\/noindex> t\u00e1vols\u00e1gok alapj\u00e1n lehet \u00f6sszehasonl\u00edtani. A keres\u00e9si lek\u00e9rdez\u00e9s eredm\u00e9nyek\u00e9nt azok a vektorok t\u00e9rnek vissza, amelyek t\u00e1vols\u00e1ga a kimeneti vektort\u00f3l a legkisebb. Az SPTAG k\u00e9t m\u00f3dszert k\u00edn\u00e1l a vektort\u00e9r megszervez\u00e9s\u00e9re: SPTAG-KDT (K-dimenzion\u00e1lis fa (kd-tree<\/a><\/noindex>, ennek eredm\u00e9nyek\u00e9nt a lek\u00e9rdez\u00e9sek olyan form\u00e1t \u00f6ltenek, mint a fent eml\u00edtett. relat\u00edv szomsz\u00e9ds\u00e1gok grafikonja<\/a><\/noindex>) \u00e9s SPTAG-BKT (k-k\u00f6z\u00e9p fa (k-means tree<\/a><\/noindex> a relat\u00edv k\u00f6rnyezetek grafikonja). Az els\u0151 m\u00f3dszer kevesebb er\u0151forr\u00e1st ig\u00e9nyel az index m\u0171k\u00f6dtet\u00e9sekor, m\u00edg a m\u00e1sodik m\u00f3dszer a keres\u00e9si eredm\u00e9nyek magasabb pontoss\u00e1g\u00e1t mutatja meg nagyon nagy vektorkollekci\u00f3k eset\u00e9n.<\/p>\n

Ezenk\u00edv\u00fcl a vektoros keres\u00e9s nem korl\u00e1toz\u00f3dik a sz\u00f6vegre, alkalmazhat\u00f3 multim\u00e9di\u00e1s inform\u00e1ci\u00f3kra \u00e9s k\u00e9pekre is, valamint automatiz\u00e1lt aj\u00e1nl\u00e1si rendszerekben. P\u00e9ld\u00e1ul az egyik protot\u00edpusban a PyTorch keretrendszerre \u00e9p\u00edtve egy vektoralap\u00fa keres\u0151 rendszert val\u00f3s\u00edtottak meg, amely figyelembe vette az objektumok hasonl\u00f3s\u00e1g\u00e1t a k\u00e9peken. Ez a rendszer t\u00f6bb referencia kollekci\u00f3 adatait haszn\u00e1lva k\u00e9sz\u00fclt, amelyek \u00e1llatok - macsk\u00e1k \u00e9s kuty\u00e1k k\u00e9peit tartalmazt\u00e1k, ezeket vektork\u00e9szletekk\u00e9 alak\u00edtott\u00e1k. Amikor egy bemeneti k\u00e9p \u00e9rkezik, azt g\u00e9pi tanul\u00e1si modellel vektorr\u00e1 alak\u00edtj\u00e1k, \u00e9s az SPTAG algoritmus seg\u00edts\u00e9g\u00e9vel a legjobban hasonl\u00edt\u00f3 vektorokat v\u00e1lasztj\u00e1k ki az indexb\u0151l, \u00edgy a hozz\u00e1juk kapcsol\u00f3d\u00f3 k\u00e9peket adj\u00e1k vissza eredm\u00e9nyk\u00e9nt.<\/p>\n

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

Forr\u00e1s: 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\udd47A Microsoft nyilv\u00e1noss\u00e1gra hozta a Bingben haszn\u00e1lt vektorkeres\u0151 k\u00f6nyvt\u00e1r k\u00f3dj\u00e1t | ProHoster","description":"A Microsoft k\u00f6zz\u00e9tette a g\u00e9pi tanul\u00e1si k\u00f6nyvt\u00e1r forr\u00e1sk\u00f3dj\u00e1t.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/microsoft-otkryl-kod-biblioteki-vektornogo-poiska-ispolzuemoj-v-bing","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","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\/hu\/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\/hu\/wp-json\/wp\/v2\/posts\/33865","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=33865"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/33865\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=33865"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=33865"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=33865"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}