[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82394-en":3,"doc-seo-82394-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82394,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","From Raw IDs to Semantic Planning: How Recommender Systems Utilize Information at Scale","Recommender systems’ evolution is framed as a study of how they utilize information at scale. For decades, industrial systems largely relied on raw IDs—discrete, globally unique, and semantically opaque—for logging and exact lookup. Increasingly, systems incorporate richer item content, context, multimodal signals, and cross-domain structure, compressing this into semantic IDs. The paper argues this shift extends beyond generative recommendation and motivates semantic planning, predicting semantic targets before instantiating items or generated creatives, alongside changes to evaluation and multi-stakeholder coordination.","From Raw IDs to Semantic Planning: How Recommender Systems  \nUtilize Information at Scale  \narXiv :2607 .09540v 1 [ cs .IR] 10 Jul 2026  \nChanghong Jin  \nUniversity College Dublin Dublin, Ireland [changhong.jin@ucd.ie](changhong.jin@ucd.ie)  \nYingjie Niu  \nHuawei Ireland Research Centre Dublin, Ireland [yingjie.niu@huawei.com](yingjie.niu@huawei.com)  \nZheng Ju  \nUniversity College Dublin Dublin, Ireland [zheng.ju@ucd.ie](zheng.ju@ucd.ie)  \nShiqiu Yang University College Dublin  \nDublin, Ireland [shiqiu.yang@ucdconnect.ie](shiqiu.yang@ucdconnect.ie)  \nAghiles Salah Huawei Ireland Research Centre  \nDublin, Ireland [aghiles.salah@h-partners.com](aghiles.salah@h-partners.com)  \nXingsheng Guo  \nHuawei Ireland Research Centre Dublin, Ireland xingsheng.guo1@huawei[partners.com](partners.com)  \nRoger Zhe Li  \nHuawei Ireland Research Centre Dublin, Ireland [roger.zhe.li@huawei.com](roger.zhe.li@huawei.com)  \nMete Sertkan Huawei Ireland Research Centre  \nDublin, Ireland [mete.sertkan@h-partners.com](mete.sertkan@h-partners.com)  \nHuifeng Guo  \nHuawei Ireland Research Centre Dublin, Ireland [huifeng.guo@huawei.com](huifeng.guo@huawei.com)  \nRuihai Dong  \nUniversity College Dublin Dublin, Ireland [ruihai.dong@ucd.ie](ruihai.dong@ucd.ie)  \nBarry Smyth  \nUniversity College Dublin Dublin, Ireland [barry.smyth@ucd.ie](barry.smyth@ucd.ie)  \nAbstract  \nThe evolution of recommender systems can be explored by asking how they utilize information at scale. Throughout most of the historical period under consideration during the past two decades, industrial systems have relied on raw IDs, which are discrete, globally unique, and semantically opaque identifiers that enable exact lookup, logging, and item-specific memorization at scale. Overtime, however, recommender systems have sought to utilize richer sources of information, including item content, context, multimodal signals, and cross-domain structure. This development has led toa new stage in which part of such information is no longer used solely as auxiliary features around item identity, but is increasingly encapsulated in semantic IDs that provide a more structured, model-facing form of identity. We argue that this shift goes beyond the rise of generative recommendation over traditional methods. Indeed, it reflects a broader evolution in how recommender systems utilize information under industrial-scale constraints. This paper looks at the past, present, and future to examine three connected questions: why raw IDs dominated the early development of recommender systems, why semantic information is increasingly being encapsulated in IDs today, and what may come next once  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nrecommendations move beyond semantic retrieval. In particular, we introduce semantic planning as a possible future direction in which the system first predicts the semantic target of the next exposure, and only then instantiates that target as a specific item or generated creative. We further argue that such a shift may require changes not only in model design but also in evaluation and in the way recommender systems coordinate the objectives of users, platforms,","cbCaieTlDJhzRsGN","https://ap.wps.com/l/cbCaieTlDJhzRsGN","pdf",449961,1,6,"English","en",105,"# Abstract\n# Introduction\n## Multi-stakeholder recommender settings\n## Using information at scale","[{\"question\":\"为什么在早期工业级推荐系统中更偏好使用 Raw IDs？\",\"answer\":\"因为 Raw IDs 是离散且全局唯一、语义不透明的标识，能够在大规模场景下支持精确查找、日志记录以及基于条目身份的记忆。\"},{\"question\":\"语义信息如何逐步被封装进 Semantic IDs？\",\"answer\":\"推荐系统开始利用更丰富的信息来源，如条目内容、上下文、模态信号以及跨领域结构，并把其中一部分以更结构化、面向模型的方式封装进 Semantic IDs，而不只是把它们当作围绕条目身份的辅助特征。\"},{\"question\":\"文中提出的 Semantic Planning 指的是什么，以及会带来哪些影响？\",\"answer\":\"Semantic Planning 是一种未来方向：系统先预测下一次曝光要达到的语义目标，再把该目标具体化为特定条目或生成的创意。作者认为这一变化不仅要求模型设计调整，也需要在评估方式以及如何协调用户、平台与提供方目标方面做出改变。\"}]",1784180103,15,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"from-raw-ids-to-semantic-planning-how-recommender-systems-utilize-information-at-scale","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/from-raw-ids-to-semantic-planning-how-recommender-systems-utilize-information-at-scale/82394/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"为什么在早期工业级推荐系统中更偏好使用 Raw IDs？","Question",{"text":74,"@type":75},"因为 Raw IDs 是离散且全局唯一、语义不透明的标识，能够在大规模场景下支持精确查找、日志记录以及基于条目身份的记忆。","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"语义信息如何逐步被封装进 Semantic IDs？",{"text":79,"@type":75},"推荐系统开始利用更丰富的信息来源，如条目内容、上下文、模态信号以及跨领域结构，并把其中一部分以更结构化、面向模型的方式封装进 Semantic IDs，而不只是把它们当作围绕条目身份的辅助特征。",{"name":81,"@type":72,"acceptedAnswer":82},"文中提出的 Semantic Planning 指的是什么，以及会带来哪些影响？",{"text":83,"@type":75},"Semantic Planning 是一种未来方向：系统先预测下一次曝光要达到的语义目标，再把该目标具体化为特定条目或生成的创意。作者认为这一变化不仅要求模型设计调整，也需要在评估方式以及如何协调用户、平台与提供方目标方面做出改变。","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]