Microsoft Technology Licensing, LLC

Zach Johnson

Mike Hayton

Shipeng Li

Fei Wang

Christian Klein

Xian-Sheng Hua

Mark D Schwesinger

Andrew L Silverman

Sean E Kollenkark

Gregg Robert Wygonik

Joseph Lloyd McClanahan

Waiman Lam

Aaron DeYonker

Mark G Young

Zhike Kong

Bruno Kraychete Da Costa

Rodrigo Maialle Bomfim

Jeffrey Christopher Abraham

Shane McRoberts

Matthew Fleming

Robert N Pulliam

Embodiments are disclosed that relate to providing digital content recommendations based upon environmental sensor data. For example, one embodiment provides a computing device configured to receive sensor data from a sensor system, to detect a user present in the use environment via the sensor data, identify the user, recognize a current state of each of one or more use environment state features associated with the user via the sensor data, and store the current state of each of the one or more use environment state features. The computing device is further configured to detect a triggering condition for a selected use environment state feature, and in response provide information related to the selected use environment state feature based upon one or more of the current state of the use selected use environment state feature and a previously-stored state of the selected use environment state feature.

Providing recommendations based upon environmental sensing

A contextual state of a graphical user interface presented via a display of the computing system is identified. A voice command is selected from a set of voice commands based on the contextual state of the graphical user interface. A context-specific voice-command suggestion corresponding to the selected voice command is identified. A graphical user interface including the context-specific voice-command suggestion is presented via a display.

Voice-command suggestions based on computer context

Various embodiments related to the ability to find content for consumption across all endpoint computing devices in a computing system are disclosed. For example, one disclosed embodiment provides a method for presenting content including aggregating endpoint metadata for each endpoint computing device in a computing system and content metadata of content stored on each of a plurality of endpoint computing devices, receiving a request for a content item on a selected endpoint computing device, querying aggregated endpoint metadata and content metadata to find instances of the content item and corresponding endpoint computing device locations, generating a ranked list of instances of the content item based on selection criteria, and selecting an instance of the content item from the ranked list for playback by the selected endpoint computing device.

Media content location awareness and decision making

Described herein is technology for, among other things, selecting a representative thumbnail from a video clip. The technology involves analyzing frames of the video clip to determine which frames are stable, the result of the analysis being a number of segments of stable frames. From the stable segments, a number of candidate segments are selected, where candidate segments are those segments determined to a degree of certainty to be program content. The representative thumbnail is then selected from among the frames of the candidate segments.

Smart video thumbnail

Growing community of inventors

Woodinville, WA, United States of America

Zach Johnson