Microsoft Technology Licensing, LLC

Nicholas David Burton

Andrew Wilson

Kathryn Stone Perez

Alex A Kipman

Christian F Huitema

Yancey Christopher Smith

David James Quinn

Royal D Winchester

Iain A McFadzen

Peter Alan Ridgway

Carol Clark

David T Hill

Andrew John Bastable

Arash Ghanaie-Sichanie

Jian Wu

Senthil Kumar Velayutham

Sebastian Sylvan

Qi Liu

Diego Fernandes Nehab

William Bryan

James Thomas

Mark Stevenson

A system and method for selecting a target device out of a larger group of candidate devices for rendering a response from a virtual assistant to an end-user is disclosed. The system determines that a same trigger phrase included in an utterance has been received by multiple devices that are in proximity to one another at around the same time. These candidate devices can collect attention data, such as user gaze toward a device, to select the device that was most likely the intended recipient of the utterance. The system is configured to control the virtual assistant to render a response solely via the selected device.

Selective response rendering for virtual assistants

Technology is disclosed for automatically generating a facial avatar resembling a user in a defined art style. One or more processors generate a user 3D head model for the user based on captured 3D image data from a communicatively coupled 3D image capture device. A set of user transferable head features from the user 3D head model are automatically represented by the one or more processors in the facial avatar in accordance with rules governing transferable user 3D head features. In some embodiments, a base or reference head model of the avatar is remapped to include the set of user head features. In other embodiments, an avatar head shape model is selected based on the user 3D head model, and the transferable user 3D head features are represented in the avatar head shape model.

Generating an avatar from real time image data

Using facial recognition and gesture/body posture recognition techniques, a system can naturally convey the emotions and attitudes of a user via the user's visual representation. Techniques may comprise customizing a visual representation of a user based on detectable characteristics, deducting a user's temperament from the detectable characteristics, and applying attributes indicative of the temperament to the visual representation in real time. Techniques may also comprise processing changes to the user's characteristics in the physical space and updating the visual representation in real time. For example, the system may track a user's facial expressions and body movements to identify a temperament and then apply attributes indicative of that temperament to the visual representation. Thus, a visual representation of a user, which may be, for example, an avatar or fanciful character, can reflect the user's expressions and moods in real time.

Visual representation expression based on player expression

A system is disclosed for rendering low latency resource objects by providing the latest position data from a central processing unit for the low latency resource object right before a graphic processing unit is to render the low latency resource object.

Low latency rendering of objects

A system and method is disclosed determining caloric burn via an HCI system. Using a capture device which is able to detect the thickness of a user's arms, legs, torso, etc., the system determines a mass for each of a user's body parts. Thereafter, in one example, the system measures caloric burn for a given body part as a function of how far the body part was displaced, a mass of the body part displaced and gravity.

Caloric burn determination from body movement

Data captured with respect to a human may be analyzed and applied to a visual representation of a user such that the visual representation begins to reflect the behavioral characteristics of the user. For example, a system may have a capture device that captures data about the user in the physical space. The system may identify the user's characteristics, tendencies, voice patterns, behaviors, gestures, etc. Over time, the system may learn a user's tendencies and intelligently apply animations to the user's avatar such that the avatar behaves and responds in accordance with the identified behaviors of the user. The animations applied to the avatar may be animations selected from a library of pre-packaged animations, or the animations may be entered and recorded by the user into the avatar's avatar library.

Bringing a visual representation to life via learned input from the user

Techniques may comprise identifying surfaces, textures, and object dimensions from unorganized point clouds derived from a capture device, such as a depth sensing device. Employing target digitization may comprise surface extraction, identifying points in a point cloud, labeling surfaces, computing object properties, tracking changes in object properties over time, and increasing confidence in the object boundaries and identity as additional frames are captured. If the point cloud data includes an object, a model of the object may be generated. Feedback of the model associated with a particular object may be generated and provided real time to the user. Further, the model of the object may be tracked in response to any movement of the object in the physical space such that the model may be adjusted to mimic changes or movement of the object, or increase the fidelity of the target's characteristics.

Target digitization, extraction, and tracking

Using facial recognition and gesture/body posture recognition techniques, a system can naturally convey the emotions and attitudes of a user via the user's visual representation. Techniques may comprise customizing a visual representation of a user based on detectable characteristics, deducting a user's temperament from the detectable characteristics, and applying attributes indicative of the temperament to the visual representation in real time. Techniques may also comprise processing changes to the user's characteristics in the physical space and updating the visual representation in real time. For example, the system may track a user's facial expressions and body movements to identify a temperament and then apply attributes indicative of that temperament to the visual representation. Thus, a visual representation of a user, such as an avatar or fanciful character, can reflect the user's expressions and moods in real time.

Growing community of inventors

Derbyshire, United Kingdom

Nicholas David Burton