Microsoft Technology Licensing, LLC

Xiaoyu Chai

Connie Qin Yang

Steve K Lim

Logan Ringer

Nithin Adapa

Matthew Scott Rosoff

Igor B Peev

Stephen C Rowe

Brandon H Paddock

Paul Luo Li

Steven Marcel Elza Wilssens

James H Dooley, Iv

Choo Yei Chong

Minsuk Kang

Frederick Douglass Campbell

Alexander S Weil

Ho Jeannie Chung

Dale R Johnson

Irina Ioana Niculescu

Xinyi Zhang

Jilong Liao

Xiao Cai

Neeraja Abburu

Tomas Aleksas Mereckis

Eamon Guthrie Cosgrove Millman

Soheil Sadeghi

Ioana Laura Marginas

Omari Carter-thorpe

Eleanor Ann Robinson

Disclosed herein is a system for leveraging telemetry data representing usage of a component installed on a group of sampled computing devices to confidently infer the quality of a user experience and/or the behavior of the component (e.g., an operating system) on a larger group of unsampled computing devices. The system is configured to use a propensity score matching approach to identify a sampled computing device that best represents an unsampled computing device using configuration data that is collected from both the sampled and unsampled computing devices. The quality of the user experience and/or the behavior of the component may be captured by a metric of interest (e.g., a QoS value). Accordingly, the system is configured to use the known metric of interest, determined from the telemetry data collected for the sampled computing device, to determine or predict the metric of interest for the unsampled computing device.

Using propensity score matching to determine metric of interest for unsampled computing devices

Systems and methods directed to generating a predicted quality metric are provided. Telemetry data may be received from a from a first group of devices executing first software. A quality metric for the first software may be generated based on the first telemetry data. Telemetry data from a second group of devices may be received, where the second group of devices is different from the first group of devices. Covariates impacting the quality metric based on features included in the first telemetry data and the second telemetry data may be identified, and a coarsened exact matching process may be performed utilizing the identified covariates to generate a predicted quality metric for the first software based on the second group of devices.

Feature deployment readiness prediction

A server computing device generates training data based upon an identifier for a device, a timestamp, and a label received from a developer computing device. The server computing device trains a computer-implemented machine learning (ML) model based upon the training data. The server computing device also generates client configuration data for the ML model that specifies transformations that are to be applied to values in order to generate input values for the ML model. The server computing device deploys ML assets to client computing devices, the ML assets comprising the ML model and the client configuration data. The client computing devices execute the ML model using input values derived via transformations of (local) values produced by the client computing devices and transmit telemetry data to the server computing device. The server computing device updates the ML assets based upon the telemetry data.

Computing system for training, deploying, executing, and updating machine learning models

Technologies are described for utilizing machine learning ('ML') to adjust operational characteristics of a computing system based upon detected HID activity. Labeled training data is collected with user consent that includes data describing HID activity and data that identifies user activity taking place on a computing device when the data HID activity took place. A ML model is trained using the labeled training data that can receive data describing current HID activity and identify user activity currently taking place on another computing device based upon the current HID activity. The ML model can then select features of the other computing device that are beneficial to the identified user activity. The ML model can then cause one or more operational characteristics of the other computing device to be adjusted based upon the identified user activity, thereby saving valuable computing resources. A UI can also be presented that describes the identified features.

Machine learning system for adjusting operational characteristics of a computing system based upon HID activity

Growing community of inventors

Bellevue, WA, United States of America

Xiaoyu Chai