Microsoft Technology Licensing, LLC

Anav Silverman

Shikha Devesh Desai

Susan Michele Hendrich

Yu Been Lee

Alyssa Rachel Mayo

Patricia Hendricks Balik

Gwenyth Alanna Vabalis Hardiman

Penelope Ann Collisson

Erez Kikin-Gil

David Benjamin Lee

Suzan Marashi

Christopher Andrews Jung

Stephanie Sharp

David Lee

The present disclosure relates to processing operations configured to tailor notifications of productivity feature suggestions based on predictive relevance to a context associate with user access to an electronic document. Machine learning modeling executes a contextual evaluation of user access to predictively determine relevance of a suggestion that relates to: 1) a confidence in the quality of the suggestion; and 2) a timing prediction as to the urgency for surfacing the suggestion to the user so that the suggestion is most applicable. Example notifications are proactive interruptions that aim to aid processing efficiency in task execution as well as an improve user interface experience when users work with an application/service and/or an application platform that comprises a suite of applications/services. A manner in which the notification is presented may vary based on the confidence in the relevance of the suggestion and timing relevance for interrupting a user's workflow.

Proactive notification of relevant feature suggestions based on contextual analysis

The present disclosure relates to processing operations configured to identify and present productivity features that are contextually relevant for user access to an electronic document. In doing so, signal data is evaluated to determine a context associated with user access to an electronic document and insights, from the determined context, are utilized to rank productivity features for relevance to a user workflow. As an example, an intelligent learning model is trained and implemented to identify what productivity features are most relevant to a current task of a user. Productivity features are identified and ranked for contextual relevance. A notification comprising one or more ranked productivity features is presented to a user. In one example, the notification is presented through a user interface of an application/service. For instance, a user interface pane is surfaced to present suggestions. However, in alternative examples, notification of ranked productivity features is presented through different modalities.

Relevance ranking of productivity features for determined context

Non-limiting examples of the present disclosure describe automatic creation of a composite data object from a received drag and drop action. A drag and drop action is received through a user interface of a productivity service. The drag and drop action is analyzed, where an analysis comprises: evaluation of attributes of data objects of the drag and drop action, evaluation of a relationship between the data objects and a determination of user intent for the drag and drop action based on a placement of the first data object onto a position of the second data object. A group type is created that comprises an arrangement of the first data object and the second data object based on the analysis of the drag and drop action. A representation of a composite data object is surfaced, through the user interface, based on the created group type.

Drag and drop of objects to create new composites

Growing community of inventors

Sammamish, WA, United States of America

Anav Silverman