{"id":394790,"date":"2017-07-05T19:05:59","date_gmt":"2017-07-06T02:05:59","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=394790"},"modified":"2022-08-15T09:30:03","modified_gmt":"2022-08-15T16:30:03","slug":"contextually-intelligent-assistants","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/contextually-intelligent-assistants\/","title":{"rendered":"Contextually Intelligent Assistants"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background  has-background- card-background--full-bleed\">\n\t\t\t<img loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"788\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720.jpg\" class=\"attachment-full size-full\" alt=\"Graphic showing contextually intelligent assistants\" style=\"object-position: 69% 48%\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720.jpg 1920w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720-300x123.jpg 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720-1024x420.jpg 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720-768x315.jpg 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2020\/03\/CIA-graph_HCI_multi_03_2020_1920x720-1536x630.jpg 1536w\" sizes=\"(max-width: 1920px) 100vw, 1920px\" \/>\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 align-self-center\">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 id=\"contextually-intelligent-assistants\" class=\"h2\">Contextually Intelligent Assistants<\/h1>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p>A truly intelligent virtual assistant could make many new functions possible. As we envision this agent, it would have the capabilities to:<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Understand your world,<\/li><li>Leverage context to inform its actions,<\/li><li>Interact with you naturally and effectively.<\/li><\/ul>\n\n\n\n<p>The Contextually Intelligent Assistants project makes progress toward the type of contextual intelligence needed for next-generation assistants.&nbsp; It does this by improving the state-of-the-art in understanding task intent from task descriptions; modeling key contextual signals, such as location and time; enabling quick in-context capture of information; improving context-sensitive proactive and reactive retrieval; and managing notifications intelligently.<\/p>\n\n\n\n<p>Our aim is to make it easier for people to accomplish what they want, on any device, by making deep use of context when reactively responding to people\u2019s queries and by proactively presenting the right information to them at the right place, time, and context.<\/p>\n\n\n\n<p><strong>Microsoft Research Podcast<\/strong>: <a href=\"https:\/\/www.microsoft.com\/en-us\/research\/podcast\/building-contextually-intelligent-assistants-with-dr-paul-bennett\/\">Building Contextually Intelligent Assistants with Dr. Paul Bennett<\/a><\/p>\n\n\n\n<figure class=\"wp-block-image\"><a href=\"https:\/\/www.microsoft.com\/en-us\/research\/blog\/building-contextually-intelligent-assistants-with-dr-paul-bennett\/\"><img loading=\"lazy\" decoding=\"async\" width=\"300\" height=\"169\" src=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-300x169.png\" alt=\"Paul Bennett\" class=\"wp-image-560037\" srcset=\"https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-300x169.png 300w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-768x432.png 768w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-1024x576.png 1024w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-1066x600.png 1066w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-655x368.png 655w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788-343x193.png 343w, https:\/\/www.microsoft.com\/en-us\/research\/uploads\/prod\/2019\/01\/Paul-Bennett_Pod_Site_12_2018_1400x788.png 1400w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/a><\/figure>\n\n\n","protected":false},"excerpt":{"rendered":"<p>The Contextually Intelligent Assistants project makes progress toward the type of contextual intelligence needed for next-generation assistants.\u00a0 It does this by improving the state-of-the-art in understanding task intent from task descriptions.<\/p>\n","protected":false},"featured_media":642444,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-394790","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[559869,559887,488150,376904,417818,353645,243908,359789,329564,332468,630567],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Saleema Amershi","user_id":33505,"people_section":"Group name 1","alias":"samershi"},{"type":"user_nicename","display_name":"Susan Dumais","user_id":33565,"people_section":"Group name 1","alias":"sdumais"},{"type":"user_nicename","display_name":"Adam Fourney","user_id":30820,"people_section":"Group name 1","alias":"adamfo"},{"type":"user_nicename","display_name":"Eric Horvitz","user_id":32033,"people_section":"Group name 1","alias":"horvitz"},{"type":"user_nicename","display_name":"Ece Kamar","user_id":31710,"people_section":"Group name 1","alias":"eckamar"},{"type":"guest","display_name":"Robert Sim","user_id":395426,"people_section":"Group name 1","alias":""},{"type":"user_nicename","display_name":"Anne Loomis Thompson","user_id":31041,"people_section":"Group name 1","alias":"annelo"},{"type":"user_nicename","display_name":"Ryen W. White","user_id":33481,"people_section":"Group name 1","alias":"ryenw"},{"type":"user_nicename","display_name":"Dany Rouhana","user_id":31540,"people_section":"Group name 1","alias":"danyr"}],"msr_research_lab":[199565],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/394790"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":11,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/394790\/revisions"}],"predecessor-version":[{"id":869847,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/394790\/revisions\/869847"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/642444"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=394790"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=394790"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=394790"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=394790"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=394790"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}