[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-201808-105":59,"doc-detail-201808-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","accurate-action-recommendation-for-smart-home-via-two-level-encoders-and-commonsense-knowledge","Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge","","SmartSense addresses the challenge of recommending next actions for users controlling home devices. Action recommendation is difficult due to context correlations, where both queried contexts and users’ historical actions jointly shape future behavior, and due to capricious intentions embedded in action sequences. SmartSense summarizes individual actions with device control and temporal contexts using self-attention, then models sequences with query-attentive summarization to extract query-related patterns. It further transfers commonsense knowledge from routine data to better handle intentions in sequences, achieving state-of-the-art results with up to 9.8% higher mAP@1.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/accurate-action-recommendation-for-smart-home-via-two-level-encoders-and-commonsense-knowledge/201808/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/accurate-action-recommendation-for-smart-home-via-two-level-encoders-and-commonsense-knowledge/201808.png","ImageObject",300,407,{"name":92,"@type":93},"Sophia Brooks","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-08","2026-09-04",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does SmartSense solve in smart homes?","Question",{"text":112,"@type":113},"SmartSense recommends next actions for users to control home devices, predicting future device controls from context and past behavior.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why is action recommendation for smart homes challenging?",{"text":117,"@type":113},"It must model correlations across multiple contexts (like day and hour), incorporate both sequential action patterns and queried contextual information, and handle irregular or “capricious” intentions found in user histories.",{"name":119,"@type":110,"acceptedAnswer":120},"How does SmartSense model individual actions and temporal context?",{"text":121,"@type":113},"It summarizes each action’s device control together with temporal contexts using self-attention to capture their correlation and determine action importance.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},201808,1788538926,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143},962084925636,"https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d","Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge  \nHyunsik Jeon  \nSeoul National University Seoul, South Korea [jeon185@snu.ac.kr](jeon185@snu.ac.kr)  \nJongjin Kim  \nSeoul National University Seoul, South Korea [j2kim99@snu.ac.kr](j2kim99@snu.ac.kr)  \nHoyoung Yoon  \nSeoul National University Seoul, South Korea [crazy8597@snu.ac.kr](crazy8597@snu.ac.kr)  \nJaeri Lee  \nSeoul National University Seoul, South Korea [jlunits2@snu.ac.kr](jlunits2@snu.ac.kr)  \nABSTRACT  \nHow can we accurately recommend actions for users to control their devices at home? Action recommendation for smart home has attracted increasing attention due to its potential impact on the markets of Internet of Things (IoT) . However, designing an effective action recommender system is challenging because it requires handling context correlations, considering both queried contexts and previous histories of users, and dealing with capricious intentionsin history. In this work, we propose SmartSense, an accurate action recommendation method for smart home. For individual action, SmartSense summarizes its device control and temporal contextsin a self-attentive manner, to reflect the importance of the correlation between them. SmartSense then summarizes sequences considering queried contexts in a query-attentive manner to extract the query-related patterns from the sequential actions. SmartSense also transfers the commonsense knowledge from routine data to better handle intentions in action sequences. As a result, SmartSense addresses all three main challenges of action recommendation for smart home, and achieves the state-of-the-art performance giving up to 9. 8% higher mAP@1 than the best competitor.  \nCCS CONCEPTS  \n• Information systems → Recommender systems.  \nKEYWORDS  \naction recommendation, transformer, commonsense knowledge  \nACM Reference Format:  \nHyunsik Jeon, Jongjin Kim, Hoyoung Yoon, Jaeri Lee, and U Kang. 2022. Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge. In Proceedings of the 31stACM International Conference on Information and Knowledge Management (CIKM’22), October 17–21, 2022, Atlanta, GA, USA. ACM, New York, NY, USA, 10 pages. [https:](https:)//[doi.org/10.1145/3511808.3557226](doi.org/10.1145/3511808.3557226)  \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 ACM 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](from permissions@acm.org).  \nCIKM’22, October 17–21, 2022, Atlanta, GA, USA © 2022 Association for Computing Machinery.  \nACM ISBN 978-1-4503-9236-5/22/10. . . $15.00 [https://doi.org/10.1145/3511808.3557226](https://doi.org/10.1145/3511808.3557226)  \nU Kang  \nSeoul National University Seoul, South Korea [ukang@snu.ac.kr](ukang@snu.ac.kr)  \nPrevious device control Next device control  \n1. A/C: on Time  \n4. TV: off  \n4. TV: off  \n(a) Historical dependency of device controls.  \nDawn (00:00-06:00)  \nContext  \nDevice controls  \n(b) Contextual dependency of device controls.  \nFigure 1: Historical and contextual dependency patterns of SmartThings users. (a) Frequent previous device control rankings of two different device controls. The next device controls are affected by previous ones. (b) Frequent device control rankings according to two different given hours. Temporal contexts affect users’ device controls.  \nWasher:  \nrun (16:41)  \nWater purifier: act (19:22)  \n : Laundry-related  \nactions  \n: Other actions  \nFigure 2: An example of sequential device controls performed by a SmartThi","cbCaihIeK2METNIQ","https://ap.wps.com/l/cbCaihIeK2METNIQ","pdf",2118462,"English","# Abstract\n# Introduction\n## Action Recommendation in Smart Home\n## Challenges SmartSense Targets","[{\"question\":\"What problem does SmartSense solve in smart homes?\",\"answer\":\"SmartSense recommends next actions for users to control home devices, predicting future device controls from context and past behavior.\"},{\"question\":\"Why is action recommendation for smart homes challenging?\",\"answer\":\"It must model correlations across multiple contexts (like day and hour), incorporate both sequential action patterns and queried contextual information, and handle irregular or “capricious” intentions found in user histories.\"},{\"question\":\"How does SmartSense model individual actions and temporal context?\",\"answer\":\"It summarizes each action’s device control together with temporal contexts using self-attention to capture their correlation and determine action importance.\"}]","Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledge | PDF",25]