Microsoft Technology Licensing, LLC

Theo Lorrain-Hale

Patrick Michael Gan

Douglas Lane Milvaney

Benjamin Gustav Wilde

Ransom Lloyd Richardson

Sugandha SudeshKumar Kapoor

Brian Daniel Meersma

Paul Anthony Scudieri

Michael Adam Scarpati

Jenna Hong

Simoune Rebekah Morena Valerio Lucas

Orkhan Muradov

Courtney Sarah Cochrane

Cosmin Catrinescu

Vivek Mogalapalli

Nikhil Vilas Kulkarni

Feng Liu

Katie Nicole Rotella

William D Tierney

Manon Knoertzer

Yang Wang

Omar Basim Tuffaha

Alexey Romanov

Ryan Michael Lawrence

Christina Rose Long

Emili Koui-miclette

Kori Michelle Loomis

Andrew Boktor

Susanne Duswald

Moiz Shabbir Ghadiyali

Engagement signals may be generated and analyzed based on user interactions with documents, particularly in a collaboration environment. The user interactions may generate raw collaboration signals that may be received and processed into cleaned collaboration signals. For example, noise may be removed from the raw collaboration signals to generate the cleaned collaboration signals. The cleaned collaboration signals may be grouped into engagement signals, where each engagement signal represents an individual event or engagement event of the user with the document. The grouping may be based on boundary signals, time frames, and/or any other reasonable limiting element. Each of the engagement signals may be classified into one of several engagement types based on the cleaned collaboration signals in the engagement signal. The engagement signals may then be analyzed to make determinations, recommendations, or the like regarding one or more users of the document, the document content, or the like.

Engagement signal generation and analysis

A data processing system implements receiving a first textual prompt from a first user via a first user interface of a first client device, the first textual prompt includes a textual description of content to be generated by a generative model; providing the first textual prompt as a first input to the generative model to obtain as an output first collaborative content based on the first textual prompt; receiving an edited version of the first collaborative content from the first client device that includes edits to the first collaborative content provided by the first user; providing the edited version of the first collaborative content as a second input to the generative model to obtain as an output second collaborative content based on the edited version of the first collaborative content; and causing the first client device to present the second collaborative content on the first user interface.

Collaborative coauthoring with artificial intelligence

A method for managing annotation surfaces for a document includes receiving a request to add a note to a document, displaying a first user interface (UI) surface for the note, the first UI surface including an editable surface that is editable by a plurality of users and the first UI surface enabling visibility of content to the plurality of users in real-time, and attaching a second UI surface to the first UI surface, the second UI surface being a UI surface for a comment and the second surface UI surface requiring user action for posting the comment.

Method and system of managing and displaying document annotation surfaces

The present disclosure is directed to automated notification generation, where a generated notification comprises a live representation of a content update that is linked and synchronized with a distributed collaborative canvas (or other source content) comprising the content portion which is being updated. A non-limiting example of a content update is a message notification, such as an at-mention (@mention), that is included inline within a content portion. Other triggers for automated notification generation are also described. Generation of an exemplary notification comprises a contextual relevance analysis that not only selects, for a recipient of the message notification, a specific host application/service endpoint to present the notification in but also determines how/what specific content to present inline within the selected host application/service endpoint. The notification is automatically generated and provided to a selected host application/service endpoint for rendering of the notification inline with content of the host application/service endpoint.

Automated notification of content update providing live representation of content inline through host service endpoint(s)

A method and system for providing keyword suggestions to a user of a document during use of the document, the keyword suggestions being made to enable selection of the keywords as tags for the document. The method includes examining contents of a document, identifying a keyword related to the document based at least in part on the contents of the document, displaying the keyword on a user interface element relating to the document to enable a user to choose to add the keyword as a tag associated with the document, receiving an input indicating a user's approval of the keyword, and upon receiving the input, associating the keyword with the document as a tag.

Method and system for intelligently suggesting tags for documents

Growing community of inventors

Boston, MA, United States of America

Theo Lorrain-Hale