效果、性能双突破！快手OneSug端到端生成式框架入选AAAI 2026

财闻01-31

当你在电商平台搜索“苹果”，系统会推荐“水果”还是“手机”？或者直接跳到某个品牌旗舰店？短短一个词，背后承载了完全不同的购买意图。而推荐是否精准，直接影响用户的搜索体验，也影响平台的转化效率。基于上述问题，快手在业界首次提出端到端的生成式统一查询推荐框架——OneSug，成功将召回、粗排、精排等多个阶段统一在一个生成模型中，显著提升了推荐效果与系统效率，在快手电商场景中实现了业务指标与用户体验的...

网页链接

免责声明：本文观点仅代表作者个人观点，不构成本平台的投资建议，本平台不对文章信息准确性、完整性和及时性做出任何保证，亦不对因使用或信赖文章信息引发的任何损失承担责任。

精彩评论

我们需要你的真知灼见来填补这片空白

发表看法

{"i18n":{"language":"zh_CN"},"isChannel":false,"data":{"share":"https://www.laohu8.com/m/news/2607910075?lang=zh_CN&edition=full","thumbnail":"","is_english":false,"pubTime":"2026-01-31 12:28","share_image_url":"https://static.laohu8.com/9a95c1376e76363c1401fee7d3717173","id":"2607910075","market":"hk","top_or_hot":-1,"title":"效果、性能双突破！快手OneSug端到端生成式框架入选AAAI 2026","media":"财闻","content":"<div>\n<p>当你在电商平台搜索“苹果”，系统会推荐“水果”还是“手机”？或者直接跳到某个品牌旗舰店？短短一个词，背后承载了完全不同的购买意图。而推荐是否精准，直接影响用户的搜索体验，也影响平台的转化效率。基于上述问题，快手在业界首次提出端到端的生成式统一查询推荐框架——OneSug，成功将召回、粗排、精排等多个阶段统一在一个生成模型中，显著提升了推荐效果与系统效率，在快手电商场景中实现了业务指标与用户体验的...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260131122849a46b89a6&s=b\">网页链接</a>\n\n</div>\n","source":"tencent","html":"<!DOCTYPE html>\n<html>\n<head>\n<meta http-equiv=\"Content-Type\" content=\"text/html; charset=utf-8\" />\n<meta name=\"viewport\" content=\"width=device-width,initial-scale=1.0,minimum-scale=1.0,maximum-scale=1.0,user-scalable=no\"/>\n<meta name=\"format-detection\" content=\"telephone=no,email=no,address=no\" />\n<title>效果、性能双突破！快手OneSug端到端生成式框架入选AAAI 2026</title>\n<style type=\"text/css\">\na,abbr,acronym,address,applet,article,aside,audio,b,big,blockquote,body,canvas,caption,center,cite,code,dd,del,details,dfn,div,dl,dt,\nem,embed,fieldset,figcaption,figure,footer,form,h1,h2,h3,h4,h5,h6,header,hgroup,html,i,iframe,img,ins,kbd,label,legend,li,mark,menu,nav,\nobject,ol,output,p,pre,q,ruby,s,samp,section,small,span,strike,strong,sub,summary,sup,table,tbody,td,tfoot,th,thead,time,tr,tt,u,ul,var,video{ font:inherit;margin:0;padding:0;vertical-align:baseline;border:0 }\nbody{ font-size:16px; line-height:1.5; color:#999; background:transparent; }\n.wrapper{ overflow:hidden;word-break:break-all;padding:10px; }\nh1,h2{ font-weight:normal; line-height:1.35; margin-bottom:.6em; }\nh3,h4,h5,h6{ line-height:1.35; margin-bottom:1em; }\nh1{ font-size:24px; }\nh2{ font-size:20px; }\nh3{ font-size:18px; }\nh4{ font-size:16px; }\nh5{ font-size:14px; }\nh6{ font-size:12px; }\np,ul,ol,blockquote,dl,table{ margin:1.2em 0; }\nul,ol{ margin-left:2em; }\nul{ list-style:disc; }\nol{ list-style:decimal; }\nli,li p{ margin:10px 0;}\nimg{ max-width:100%;display:block;margin:0 auto 1em; }\nblockquote{ color:#B5B2B1; border-left:3px solid #aaa; padding:1em; }\nstrong,b{font-weight:bold;}\nem,i{font-style:italic;}\ntable{ width:100%;border-collapse:collapse;border-spacing:1px;margin:1em 0;font-size:.9em; }\nth,td{ padding:5px;text-align:left;border:1px solid #aaa; }\nth{ font-weight:bold;background:#5d5d5d; }\n.symbol-link{font-weight:bold;}\n/* header{ border-bottom:1px solid #494756; } */\n.title{ margin:0 0 8px;line-height:1.3;color:#ddd; }\n.meta {color:#5e5c6d;font-size:13px;margin:0 0 .5em; }\na{text-decoration:none; color:#2a4b87;}\n.meta .head { display: inline-block; overflow: hidden}\n.head .h-thumb { width: 30px; height: 30px; margin: 0; padding: 0; border-radius: 50%; float: left;}\n.head .h-content { margin: 0; padding: 0 0 0 9px; float: left;}\n.head .h-name {font-size: 13px; color: #eee; margin: 0;}\n.head .h-time {font-size: 11px; color: #7E829C; margin: 0;line-height: 11px;}\n.small {font-size: 12.5px; display: inline-block; transform: scale(0.9); -webkit-transform: scale(0.9); transform-origin: left; -webkit-transform-origin: left;}\n.smaller {font-size: 12.5px; display: inline-block; transform: scale(0.8); -webkit-transform: scale(0.8); transform-origin: left; -webkit-transform-origin: left;}\n.bt-text {font-size: 12px;margin: 1.5em 0 0 0}\n.bt-text p {margin: 0}\n</style>\n</head>\n<body>\n<div class=\"wrapper\">\n<header>\n<h2 class=\"title\">\n效果、性能双突破！快手OneSug端到端生成式框架入选AAAI 2026\n</h2>\n\n<h4 class=\"meta\">\n\n\n2026-01-31 12:28 北京时间&nbsp;&nbsp;&nbsp;<a href=http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260131122849a46b89a6&s=b><strong>财闻</strong></a>\n\n\n</h4>\n\n</header>\n<article>\n<div>\n<p>当你在电商平台搜索“苹果”，系统会推荐“水果”还是“手机”？或者直接跳到某个品牌旗舰店？短短一个词，背后承载了完全不同的购买意图。而推荐是否精准，直接影响用户的搜索体验，也影响平台的转化效率。基于上述问题，快手在业界首次提出端到端的生成式统一查询推荐框架——OneSug，成功将召回、粗排、精排等多个阶段统一在一个生成模型中，显著提升了推荐效果与系统效率，在快手电商场景中实现了业务指标与用户体验的...</p>\n\n<a href=\"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260131122849a46b89a6&s=b\">网页链接</a>\n\n</div>\n\n\n</article>\n</div>\n</body>\n</html>\n","isBrief":false,"type":0,"news_type":1,"symbol":"LU0244354667.USD","symbol_name":"SCHRODER ISF CHINA OPPORTUNITIES \"A\" ACC","start_time":0,"source_url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260131122849a46b89a6&s=b","article_id":"2607910075","we_media_id":null,"thumbnails":[],"rights":{"source":"tencent","url":"http://gu.qq.com/resources/shy/news/detail-v2/index.html#/?id=nesSN20260131122849a46b89a6&s=b","rn_cache_url":null,"customStyle":"body{padding-top:10px;}#news_title{font-weight:bold;#titleStyle#;}#news_description span{font-size:12px;#descriptionStyle#;}.footer-note{#statement#}","selectors":".mod-LoadTzbdNews, body","filters":".relate-stock, .hot-list, .recom-box, .wx-sou","directOrigin":true},"url":"https://stock-news.laohu8.com/highlight/detail?id=2607910075","pubTimestamp":1769833713,"columns":[],"sourceInfo":{"source_id":"tencent","name":"腾讯"},"weMediaInfo":null,"summary":"本工作相关成果《OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion》已被人工智能顶级会议 AAAI 2026 接收。针对上述问题，快手提出的 OneSug 模型主要包括3个部分：首先是 Prefix-Query表征增强模块。其次是统一的Enc-Dec生成架构。OneSug 的生成架构基于Enc-Dec结构，并直接通过自回归方式生成用户最有可能点击的Query。总体而言，OneSug 是业界首个在电商场景中实现全流量部署的端到端生成式Query推荐系统，其统一建模方式显著提升了语义理解与个性化推荐的能力，为生成式模型在搜广推的落地提供了新范式。","collect":0,"end_time":0,"defaultTopTitle":"qq.com","property":[],"viewcount":null,"language":"zh","relate_stocks":{"81024":"快手-WR","LU0244354667.USD":"SCHRODER ISF CHINA OPPORTUNITIES \"A\" ACC","LU0359201612.USD":"贝莱德中国基金A2","LU0359202008.SGD":"Blackrock China Fund A2 SGD-H","LU1251922891.USD":"NINETY ONE GSF ALL CHINA EQUITY \"A\" (USD) ACC","LU0051755006.USD":"摩根大通中国A (dist)","LU1023057109.AUD":"BGF CHINA \"A2\" (AUDHDG) ACC","LU1720050803.USD":"安联全方位中国股票基金","BK1095":"互动媒体与服务","LU0210526637.USD":"JPM CHINA \"A\" (USD) ACC","LU0572944931.SGD":"Janus Henderson Horizon China Opportunities A2 SGD","LU0326950275.SGD":"Schroder ISF China Opportunities A Acc SGD-H","BK1591":"就地过年概念","LU0456827905.SGD":"JPMorgan Funds - China A (acc) SGD","LU1303224171.USD":"NINETY ONE GSF ALL CHINA EQUITY \"A\" (USD) INC","LU1719994722.HKD":"NINETY ONE GSF ALL CHINA EQUITY \"A\" (HKD) ACC","BK1590":"短视频概念股","LU2097828557.USD":"AZ EQUITY CHINA \"A\" (USD) ACC","LU2097828631.EUR":"AZ EQUITY CHINA \"A\" (EUR) ACC","LU1794554557.SGD":"Allianz All China Equity AT Acc H2-SGD","LU1770034418.SGD":"ALL CHINA EQUITY \"A\" (SGDHDG) ACC","01024":"快手-W","LU2097828714.EUR":"AZ EQUITY CHINA \"BAZ\" (EUR) ACC","LU0463099449.HKD":"SCHRODER ISF CHINA OPPORTUNITIES \"A\" (HKD) ACC","LU2097828805.USD":"AZ EQUITY CHINA \"A-AZ\" (USD) ACC","LU0327786744.USD":"Janus Henderson Horizon China Opportunities A2 USD","LU0359201885.HKD":"BGF CHINA \"A2\" (HKD) ACC","LU0348766576.USD":"ALLIANZ LITTLE DRAGONS \"A\" (USD) INC","LU0211977185.USD":"EASTSPRING INVESTMENTS GREATER CHINA EQUITY \"A\" ACC","LU0348767384.USD":"ALLIANZLITTLE DRAGONS \"A\" (USD) ACC","LU0140636845.USD":"施罗德大中华区股票A Acc","LU0307460666.USD":"EASTSPRING INVESTMENTS CHINA EQUITY \"A\" ACC","LU2097828474.EUR":"AZ EQUITY CHINA \"A\" (EUR) ACC A","LU0593848301.USD":"未来资产亚洲卓越消费股票基金A","BK1610":"ETF&股票定投概念","LU0588546209.SGD":"Eastspring Investments - China Equity Fund AS SGD","BK1575":"同股不同权","LU1188198961.HKD":"SCHRODER ISF CHINA OPPORTUNITIES \"A\" (HKD) INC QV","BK1608":"元宇宙概念","BK1615":"港股-互联网"},"translate_title":"Double breakthroughs in effect and performance! Kuaishou OneSug end-to-end generative framework selected for AAAI 2026","themeId":null,"isJumpTheme":false,"ttsUrl":null,"symbols_score_info":{"81024":0.6,"01024":1.96,"KSTmain":0.6},"content_text":"当你在电商平台搜索“苹果”，系统会推荐“水果”还是“手机”？或者直接跳到某个品牌旗舰店？短短一个词，背后承载了完全不同的购买意图。而推荐是否精准，直接影响用户的搜索体验，也影响平台的转化效率。基于上述问题，快手在业界首次提出端到端的生成式统一查询推荐框架——OneSug，成功将召回、粗排、精排等多个阶段统一在一个生成模型中，显著提升了推荐效果与系统效率，在快手电商场景中实现了业务指标与用户体验的双重提升。本工作相关成果《OneSug: The Unified End-to-End Generative Framework for E-commerce Query Suggestion》已被人工智能顶级会议 AAAI 2026 接收。查询推荐（Query Suggestion）是现代电商搜索系统中的关键功能，通过在用户输入过程中实时推荐相关查询，帮助用户快速明确意图，提升搜索体验与转化效率。传统方法通常采用多阶段级联架构（MCA），虽然在效率与效果之间取得了一定平衡，但由于各阶段目标不一致、长尾查询召回困难等问题，限制了系统性能的进一步突破。而近年来，生成式检索（Generative Retrieval）因其强大的语义理解与生成能力，在推荐与搜索领域展现出巨大潜力。然而，现有方法多聚焦于视频推荐，其本质上是一个开集到开集的任务，难以直接应用于输入输出都是开放词表的的查询推荐场景。针对上述问题，快手提出的 OneSug 模型主要包括3个部分：首先是 Prefix-Query表征增强模块。Sug场景下，用户输入的前缀往往较短且意图模糊（如“苹果”可指水果或品牌）。为此，快手提出的解决方式分为语义与业务空间对齐、层次化语义ID生成2个部分。其次是统一的Enc-Dec生成架构。OneSug 的生成架构基于Enc-Dec结构，并直接通过自回归（Autoregressive）方式生成用户最有可能点击的Query。此外，借助用户行为偏好对齐（RWR）的方式，通过用户偏好量化、混合排序框架奖励加权偏好优化、混合排序框架的方法，分别对用户在搜索场景下的真实行为进行了精细化分级。RWR 的核心思想是根据正负样本之间的奖励差距，让模型学习到用户对不同query的个性化偏好。总体而言，OneSug 是业界首个在电商场景中实现全流量部署的端到端生成式Query推荐系统，其统一建模方式显著提升了语义理解与个性化推荐的能力，为生成式模型在搜广推的落地提供了新范式。未来，我们将进一步探索大语言模型在排序阶段的强化学习优化、实时更新等方向，持续推动端到端生成式系统在推荐、广告等多业务场景中的广泛应用。","kind":"news","is_publish_news":true,"is_publish_highlight":false,"is_publish_live":false,"is_publish_wemedia":null,"editions":null,"column":"","sentiment":"0","news_tag":"","news_rank":0,"isVideo":false,"video":null,"symbols":[],"gpt_button":0,"need_auth":false,"need_login_tip":false,"code":"91000000","status":"200"},"commentList":[],"isCommentEnd":true,"newsSizeData":{"likeSize":0,"commentSize":0,"repostSize":0,"favoriteSize":0,"likeStatus":false,"favoriteStatus":false},"APP":{"userAgent":"Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; ClaudeBot/1.0; +claudebot@anthropic.com)","isDev":false,"isTTM":false,"tenantId":"TBCN","deviceId":"web-server-community-laohu8-v3","version":"4.42.0","shortVersion":"4.42.0","platform":"web","vendor":"web","appName":"laohu8","isIOS":false,"isAndroid":false,"isTiger":false,"isTHS":false,"isWeiXin":false,"isWeiXinMini":false,"isWeiBo":false,"isQQ":false,"isBaiduSwan":false,"isBaiduBox":false,"isDingTalk":false,"isToutiao":false,"isOnePlus":false,"isHuaWei":false,"isXiaomi":false,"isXiaomiWebView":false,"isOppo":false,"isVivo":false,"isSamsung":false,"isMobile":false},"href":"/m/news/2607910075","isCrawlerRequest":true}