Microsoft Technology Licensing, LLC

Poonam Ganesh Hattangady

Susan Marie Grimshaw

Caleb Whitmore

Michael Ivan Borysenko

Lloyd Alfred Moore

Clea H Allington

Joseph T Flint

Adam Sapek

Anh Phuong Tran

Cindy Kwan

Jeffrey Kevin Feiereisen

Kutlay Topatan

Eva Britta Karolina Burlin

Joan Li

Ian Dwyer Curry

Justin Son Pae

Andrew Winslow Brough

Albert Liu

Jaime J Hwacinski

Yung-Cheng Chen

Anna Aleksandrovna Pablo

Flora M Lee

Christopher Todd Guillory

Spencer K Nelson

John Mark Miller

Matthew D Wood

Hugh A Teegan

Michael Francis Palermiti, Ii

Keith C Bentley

Gary Jason Waliczek

Kuleen Haresh Mehta

Alan Mark Thomas

Tashfeen Ahmed

Ravi Teja Koganti

Anton Oguzhan A Andrews

Erich Jose Martino Pena

Kishore Kumar Prakash

Jane Van-nha Ly

Hugh Teegan

Anh P Tran

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 inferred context to improve the suggested draft reply message for the user. Various message data and additional context are obtained and included in a prompt provided to the AI model to improve suggested content. In some examples, the message data and additional context include a message thread history and previously sent messages, profile information of the sender and recipient(s) of the selected message, known relationship information between the sender and the user, etc. For instance, the user's preferred communication style and talking points can be inferred based on the profile data, relationship data, and the user's past communications with similar participants and used to tailor the suggested draft reply to the user.

Leveraging inferred context to improve suggested messages

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

A method performed by a computing system includes generating a to-do list user interface comprising a user actuatable list element corresponding to a particular entry on a to-do list associated with a user, and a user input mechanism actuatable to perform a to-do list management function comprising at least one of adding a new entry on the to-do list, deleting an existing entry on the to-do list, and modifying an existing entry on the to-do list. The method includes generating an agenda associated with the user, the agenda comprising an agenda item having an associated time period, and detecting a flick gesture on the user actuatable list element on the to-do list user interface, and adding, based on the detected flick gesture, an agenda item to the agenda associated with the user, the added agenda item corresponding to the particular entry on the to-do list.

User interface driven movement of data

Disclosed herein are systems, methods, and software for implementing enhanced menu presentation technology. In at least one implementation, a user interface to a personal information service is presented by a suitable computing system. The user interface includes a viewing pane and an information panel in which various personal information items may be organized. In response to a selection of any of the personal information items for viewing, content associated with the item is presented in the viewing pane. In addition, in response to an identification of an action group that includes multiple ones of the personal information items, an action menu is presented in at least a portion of a space in the user interface occupied by the viewing pane.

Presentating action menus in viewing panes

A to-do list management system surfaces a user interface with a user input mechanism that displays a user actuatable element for each item on a user's to-do list. It senses a flick gesture and automatically moves a to-do list item to the user's agenda. It can also sense a user input gesture and automatically remove an agenda item from the user's agenda, and place it on the user's to-do list.

Presenting action menus in viewing panes

Coalescing schedules that use a resource to extend battery life. Each of the schedules is defined to execute at a recurrent activation time within a defined tolerance. After receiving notification of an event, the schedules are accessed to identify the schedules that may be executed early based on their activation time and tolerance. The identified schedules are aggregated for execution.

Aggregating recurrent schedules to optimize resource consumption

Managing recurrent schedules based on events and conditions. Schedules from a plurality of applications are identified based on an activation time for the schedules and a determination of whether or not conditions defined for the schedules are met. The identified schedules are activated by performing actions associated with each of the identified schedules. In an embodiment, the schedules are grouped based on functionality and prioritized to avoid conflicts within each group.

Managing event-based conditional recurrent schedules

Growing community of inventors

Seattle, WA, United States of America

Poonam Ganesh Hattangady