Microsoft Technology Licensing, LLC

Caleb Whitmore

Poonam Ganesh Hattangady

Susan Marie Grimshaw

Matthew D Wood

Michael Francis Palermiti, Ii

Philip Zhian Loh

Michael Patrick Loughry

Michael Ivan Borysenko

Tashfeen Ahmed

Kuleen Haresh Mehta

Alan Mark Thomas

Ravi Teja Koganti

Stauffer Alexander Taylor

Anton Oguzhan A Andrews

Erich Jose Martino Pena

An electronic message computing system tracks new activity items that reflect activities that have not yet been seen by the user. A. generative artificial intelligence (AI) model generates a digest summary that is provided to the user the next time the user accesses the electronic message system. The digest summary summarizes new activity. The generative AI model also generates importance summaries that summarize the importance of a particular activity to the user, and content summaries that summarize the content of an activity item (such as an electronic mail message). The electronic messaging system also assigns a priority to each new activity item and provides the summaries, along with a priority, to a client computing system. The client computing system conducts a user experience, navigating the user through the new activity items, based upon the priority assigned by the electronic message computing system.

Electronic message system with artificial intelligence (AI)-generated personalized summarization

Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that use guardrails that prevent unnecessary AI model processing and accidental sending of an AI model-generated draft. In some examples, draft reply-generation is limited to a subset of messages (e.g., focused, non-confidential) and triggering of the draft reply generation is performed only after user interaction criteria are satisfied. In some examples, a confirmation message is presented when the draft reply is attempted to be sent with no changes or quickly after the draft is generated. For instance, the guardrails limit the number of times the AI model is invoked to generate suggested replies and further prevents users from accidentally sending drafts generated from the AI model.

Guardrails for efficient processing and error prevention in generating suggested messages

Systems and methods for using a generative artificial intelligence (AI) model using a multi-turn process to generate a suggested draft reply to a selected message. A first turn of the multi-turn process uses a shorter prompt including at least a portion of the body of the selected message and that requests multiple draft replies from the AI model. The resulting AI-generated draft replies are shortened, summarized, and/or otherwise converted into a plurality of shortened summaries that are presented as reply options to a user. Upon selecting a shortened summary, a more robust prompt is generated in a second turn with the AI model with the selected reply option to generate a more complex suggested draft reply to the selected message. Additionally, various customization options are provided, which when selected, reframe a query presented to the AI model to generate a more relevant and personalized response.

Efficient multi-turn generative AI model suggested message generation

Growing community of inventors

San Francisco, CA, United States of America

Caleb Whitmore