Microsoft Technology Licensing, LLC

Evan Lewis Jones

Kenneth Liam Kiemele

Donna Katherine Long

John Benjamin Hesketh

LaSean Tee Smith

Shawn Crispin Wright

Kathleen Patricia Mulcahy

Aaron Daniel Krauss

Dan Osborn

Andrew Jackson Klein

Darren Alexander Bennett

Bryant Daniel Hawthorne

Forest Woodcroft Gouin

Megan Saunders

Jamie R Cabaccang

Charla Marie Pereira

Daniel Lee Osborn

Enrico William Guld

Priya Ganadas

Joe Thompson

Helen Joan Hem Lam

David J W Seymour

Kin Hang Chu

Heather Joanne Alekson

William Axel Olsen

Bofan Hsu

Michael Edward Harnisch

Jason A Carter

Alberto Cerriteno

William Robert Schnurr

James Lewis Nance

Jennifer Jean Choi

Struan Andrew Robertson

Adam Roy Mitchell

Zachary D Wiesnoski

Anthony Robert Menard

James Michael Ratliff

Donna K Long

John B Hesketh

Lasean T Smith

Techniques for generating a machine learning model to detect event instances from physical sensor data, including applying a first machine learning model to first sensor data from a first physical sensor at a location to detect an event instance, determining that a performance metric for use of the first machine learning model is not within an expected parameter, obtaining second sensor data from a second physical sensor during a period of time at the same location as the first physical sensor, obtaining third sensor data from the first physical sensor during the period of time, generating location-specific training data by selecting portions of the third sensor data based on training event instances detected using the second sensor data, training a second ML model using the location-specific training data, and applying the second ML model instead of the first ML model for detecting event instances.

Automated localized machine learning training

A computer system is provided that includes a server configured to store a plurality of location accounts, each location account being associated with a physical space at a recorded geospatial location. The plurality of location accounts utilize shared data definitions of a physical space parameter. Each physical space is equipped with a corresponding on-premise sensor configured to detect measured values for the physical space parameter over time and send to the server a data stream indicating the measured values. The computer system further includes a network portal, via which an authorized user for a location account can selectively choose whether to share the measured values or a summary thereof with other location accounts via the network portal.

Sharing measured values of physical space parameters

A device for removal of personally identifiable data receives monitoring data acquired by a sensor. The monitoring data including personally identifiable data relating to one or more individuals being monitored. The system processes the acquired monitoring data to remove the personally identifiable data by at least one of abstraction or redaction while the monitoring data is located on the device. The processed monitoring data having the personally identifiable data removed can thereby be transmitted external to the device with reduced security risk.

Removing personally identifiable data before transmission from a device

Various methods and systems, for implementing three-dimensional resource integration, are provided. 3D resource integration includes integration of 3D resources into different types of functionality, such as, operating system, file explorer, application and augmented reality functionality. In operation, an indication to perform an operation with a 3D object is received. One or more 3D resource controls, associated with the operation, are accessed. The 3D resource control is a defined set of instructions on how to integrate 3D resources with 3D objects for generating 3D-based graphical interfaces associated with application features and operating system features. An input based on one or more control elements of the one or more 3D resource controls is received. The input includes the one or more control elements that operate to generate a 3D-based graphical interface for the operation. Based on receiving the input, the operation is executed with the 3D object and the 3D-based graphical interface.

Three-dimensional resource integration system

A computer device is provided that includes an input device, a sensor device, a display device, and a processor. The processor is configured to detect a physical object in a physical environment based on sensor data received via the sensor device, measure one or more physical parameters of the physical object based on the sensor data, determine a physical behavior of the physical object based on the measured one or more physical parameters, present a graphical representation of the physical behavior of the physical object via the display device, generate a simulation of the physical behavior of the physical object based on the measured one or more physical parameters, receive a user input to modify the one or more physical parameters for the simulation via the input device, and present the simulation with the modified one or more physical parameters via the display device.

Modifiable simulation of physical object behavior

A head-mounted display includes a visible-light camera configured to collect a visible-light image of a physical space, a surface sensor configured to measure one or more surface parameters of the physical space, a see-through display configured to visually present an augmentation image while light from the physical space passes through the see-through display to a user eye, and an augmented-reality engine. The augmented-reality engine may be configured to identify a surface of the physical space from the one or more measured surface parameters, compose a mixed-reality image that includes the augmentation image overlaid on the visible-light image, and visually present, via the see-through display, the mixed-reality image in alignment with the identified surface.

Mixed-reality image capture

Growing community of inventors

Kirkland, WA, United States of America

Evan Lewis Jones