{"id":15543,"date":"2024-07-14T09:47:43","date_gmt":"2024-07-14T01:47:43","guid":{"rendered":"https:\/\/www.1ai.net\/?p=15543"},"modified":"2024-07-14T09:47:43","modified_gmt":"2024-07-14T01:47:43","slug":"%e5%bf%ab%e7%9c%8b%ef%bc%9a%e6%ad%a3%e5%9c%a8%e7%a0%94%e5%8f%91%e4%ba%8c%e6%ac%a1%e5%85%83%e5%9e%82%e7%b1%bb%e5%a4%a7%e6%a8%a1%e5%9e%8b%ef%bc%8c%e6%99%ba%e8%83%bd%e9%97%ae%e7%ad%94%e5%8f%8a-ip","status":"publish","type":"post","link":"https:\/\/www.1ai.net\/en\/15543.html","title":{"rendered":"Quick Look: A large vertical model of the second dimension is being developed, and the intelligent question-answering and IP character interaction applications have started internal testing"},"content":{"rendered":"<p data-vmark=\"faed\"><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%bf%ab%e7%9c%8b\" title=\"[Sees articles with tags]\" target=\"_blank\" >Look<\/a>Tian Guicheng, a senior algorithm engineer in the search R&amp;D team, revealed at the Zilliz &quot;User Tech&quot; event on July 11 that Kuaikan Comics is currently trying to build a<a href=\"https:\/\/www.1ai.net\/en\/tag\/%e5%a4%a7%e6%a8%a1%e5%9e%8b\" title=\"[View articles tagged with [large models]]\" target=\"_blank\" >Large Model<\/a>Fine-tune and train quickly.<strong><a href=\"https:\/\/www.1ai.net\/en\/tag\/%e4%ba%8c%e6%ac%a1%e5%85%83\" title=\"_Other Organiser\" target=\"_blank\" >Second Dimension<\/a>Vertical large model of the field<\/strong>.<\/p>\n<p data-vmark=\"5a7e\">According to Kuaikan, it claims that it has a very rich RAG (Retrieval-Augmented Generation) application scenario.<strong>\u00a0AI intelligent question and answer and IP character interaction<\/strong>Substantial progress has been made in the two scenarios, and related AI products have also<strong>Under internal testing<\/strong>, users will soon be able to experience the features of new products in the future.<\/p>\n<p data-vmark=\"e8c3\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-15544\" title=\"c2bd32a7-2e81-4d5d-95c3-05da68cf6a8f\" src=\"https:\/\/www.1ai.net\/wp-content\/uploads\/2024\/07\/c2bd32a7-2e81-4d5d-95c3-05da68cf6a8f.jpg\" alt=\"c2bd32a7-2e81-4d5d-95c3-05da68cf6a8f\" width=\"600\" height=\"221\" \/><\/p>\n<p data-vmark=\"98cc\">According to reports, the implementation scheme behind IP character interaction is a large role-playing model + knowledge base RAG, which is divided into<strong>Original plot knowledge base<\/strong>and<strong>User personalized memory knowledge base<\/strong>The official also said, &quot;We hope to derive IP character interactive applications through these IPs, where users can interact with the characters in the IP.<strong>Immersive Chat<\/strong>,<strong>Rather than a purely virtual character<\/strong>This is what makes the Kuaikan IP character interaction different from the common virtual role-playing applications on the market.\u201d<\/p>","protected":false},"excerpt":{"rendered":"<p>Tian Guicheng, a senior algorithm engineer in the R&amp;D team of Qiuwang Search, revealed at Zilliz's \"User Tech\" event on July 11 that Qiuwang Comics is now trying to fine-tune its vertical model in the secondary yuan field based on the open source model. From the side of Quick Look, it was learned that Quick Look claims to have very rich RAG (Retrieval-Augmented Generation) application scenarios internally, and has made substantial progress in two scenarios of AI intelligent Q&amp;A and IP character interaction, and the related AI products are under internal testing, so that users will soon be able to experience the functions of the new products in the future. According to the introduction, the realization program behind the IP character interaction is a role-playing model + knowledge.<\/p>","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[146],"tags":[1456,216,3485],"collection":[],"class_list":["post-15543","post","type-post","status-publish","format-standard","hentry","category-news","tag-1456","tag-216","tag-3485"],"acf":[],"_links":{"self":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15543","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=15543"}],"version-history":[{"count":0,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/posts\/15543\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/media?parent=15543"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/categories?post=15543"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/tags?post=15543"},{"taxonomy":"collection","embeddable":true,"href":"https:\/\/www.1ai.net\/en\/wp-json\/wp\/v2\/collection?post=15543"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}