{"id":1732,"date":"2023-12-06T09:33:41","date_gmt":"2023-12-06T01:33:41","guid":{"rendered":"https:\/\/www.1ai.net\/?p=1732"},"modified":"2023-12-06T09:33:41","modified_gmt":"2023-12-06T01:33:41","slug":"%e5%be%ae%e8%bd%af-bing-%e6%8e%a8%e5%87%ba%e5%85%a8%e6%96%b0%e3%80%8c%e6%b7%b1%e5%ba%a6%e6%90%9c%e7%b4%a2%e3%80%8d%e5%8a%9f%e8%83%bd%ef%bc%9a%e5%80%9f%e5%8a%a9-openai-%e7%9a%84-gpt-4-%e6%8f%90","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/1732.html","title":{"rendered":"Microsoft Bing launches new &quot;deep search&quot; feature: using OpenAI&#039;s GPT-4 to provide more comprehensive search results"},"content":{"rendered":"<p><strong> <a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%be%ae%e8%bd%af\" title=\"[View articles tagged with [Microsoft]]\" target=\"_blank\" >Microsoft<\/a> <a href=\"https:\/\/www.1ai.net\/en\/tag\/bing\" title=\"_Other Organiser\" target=\"_blank\" >Bing<\/a> A new technology called Deep Search is being introduced.<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e6%b7%b1%e5%ba%a6%e6%90%9c%e7%b4%a2\" title=\"[See articles with [Deep Search] labels]\" target=\"_blank\" >Deep Search<\/a>)&quot; which is a new feature of <a href=\"https:\/\/www.1ai.net\/en\/tag\/openai\" title=\"[View articles tagged with [OpenAI]]\" target=\"_blank\" >OpenAI<\/a> GPT-4 Driver<\/strong>, designed to provide users with more relevant and comprehensive answers to complex search queries. Microsoft pointed out that Deep Search is not a replacement for Bing&#039;s existing web search, but an enhancement that allows users to explore the web more deeply.<\/p>\n<p class=\"article-content__img\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-1733\" title=\"202305050909339419_0\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2023\/12\/202305050909339419_0.jpg\" alt=\"202305050909339419_0\" width=\"1000\" height=\"464\" \/><\/p>\n<p>Microsoft explains,<strong>The new feature builds on Bing\u2019s current web indexing and ranking systems and is enhanced with GPT-4, which transforms search queries into more comprehensive descriptions of results.<\/strong>.<\/p>\n<p>For example, if a user wants to learn about loyalty programs in different countries and enters the query: \u201cHow does the points system work in Japan?\u201d Deep Search expands this query to the following:<\/p>\n<blockquote><p>Provides an explanation of how the various loyalty card programs in Japan work, including the benefits, requirements, and restrictions of each program. Includes examples of popular loyalty cards from different categories (such as convenience stores, supermarkets, and restaurants). Shows the pros and cons of using loyalty cards in Japan compared to other payment methods, including current rewards and benefits. Highlights<span class=\"spamTxt\">Most Popular<\/span>services and participating merchants.<\/p><\/blockquote>\n<p>With this expanded description, you are able to explain your intentions better than with just a few words.<\/p>\n<p><strong>In cases where the search query is more vague, Deep Search finds all possible intents and creates a comprehensive description for each one. Deep Search then displays these intents to you, allowing you to choose the right one.<\/strong>.<\/p>\n<p>Once an expanded description is created, Bing will pull up relevant results that don&#039;t usually appear in typical search results, Microsoft said. Deep search finds pages that might match the expanded query, rewrites the query, and then searches for those variations.<\/p>\n<p>Continuing with the loyalty points example above, a deeper search might also look for things like \u201cJapanese loyalty card program,\u201d \u201cJapanese travelers<span class=\"spamTxt\">optimal<\/span>Loyalty Cards in Japan,\u201d \u201cCompare Japanese Loyalty Programs by Category,\u201d \u201cRedeem Loyalty Cards in Japan,\u201d and \u201cManage Loyalty Points with a Mobile App.\u201d<\/p>\n<p>&quot;By doing this,<strong>Deep search finds results that cover different aspects of my query, even if they don\u2019t include the original keyword<\/strong>&quot;Regular Bing searches already consider millions of web pages for every search, and<strong>Deep search does ten times the work to find more informative and specific results than normal search rankings.<\/strong>.<\/p>\n<p>Once Deep Search has gathered the web pages, it ranks them based on how well they match the expanded description. When ranking, Deep Search considers how well the topic matches the query, whether it has an appropriate level of detail, the credibility of the page, and its recency and popularity.<\/p>\n<p>Microsoft noted,<strong>Deep search is optional and may take up to 30 seconds to complete<\/strong>, which is why it\u2019s not suitable for every query or user. For users who don\u2019t want a more comprehensive answer, they can get regular Bing search results instantly.<\/p>","protected":false},"excerpt":{"rendered":"<p>Microsoft Bing is introducing a new feature called Deep Search, powered by OpenAI's GPT-4, designed to provide users with more relevant and comprehensive answers to complex search queries. Microsoft noted that Deep Search is not a replacement for Bing's existing web search, but rather an enhancement that allows users to explore the web in greater depth. Microsoft explains that the new feature builds on Bing's current Web indexing and ranking system and enhances it with GPT-4, which transforms search queries into more comprehensive descriptions of results. For example, if a user wants to learn about loyalty programs in different countries\/regions and enters the query, \"How does the points system work in Japan.\" Deep<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[557,190,280,558],"collection":[],"class_list":["post-1732","post","type-post","status-publish","format-standard","hentry","category-news","tag-bing","tag-openai","tag-280","tag-558"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/1732","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/comments?post=1732"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/1732\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=1732"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=1732"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=1732"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=1732"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}