Google Inc.

Verily Life Sciences LLC

Verily Ufe Sciences LLC

Nathan Dickerson Beach

Joshua Burkart

Daniel George Koulomzin

Brett Rolston Lider

Jeffrey Hoefs

William Jacob Benhardt Biesinger

Shih-Yo Cheng

Alok Chandel

Tomer Amarilio

Thomas Matthew Rudick

Matias Gonzalo Duarte

Sujith Ravi

Morten Just Petersen

Matthew K Gray

Joao Paulo Gil De Paiva

John Patrick McGregor, Jr

Russell J Ryan

Ray Su

Namrata U Godbole

Thomas W Colthurst

Mirko Ranieri

Alexander Hills

Marius G Andrei

Introduced here are diabetes management platforms able to impute blood glucose level values for a subject whose glycemic health state is being monitored. These imputed values can be used to estimate the glycemic health state of the subject at a given point in time, identify appropriate recommendations for improving the glycemic health state, etc. More specifically, a diabetes management platform can initially acquire one or more explicit data values generated by a glucose monitoring device. The diabetes management platform can then design a statistical model for imputing data values based on the one or more explicit data values. The diabetes management platform may employ several different computational techniques for performing imputation.

Imputation of blood glucose monitoring data

To better understand the impact of glycemic events, some entities have begun examining the relationship between the blood glucose level and another physiological parameter. However, this relationship can be difficult to understand. Introduced here are computer programs and associated computer-implemented techniques for discovering glycemic events in a series of data values representative of blood glucose measurements and then altering the measurement schedule of a sensor capable of generating measurements in a dimension other than blood glucose based on the glycemic events. By altering the measurement schedule of the sensor, a diabetes management platform can better understand how, if at all, dimensions other than blood glucose are related to the glycemic health state of a subject whose blood glucose level is being monitored.

Investigation of glycemic events in blood glucose data

Investigation of glycemic events in blood glucose

A computing device is described that receives, at a first particular time, first notification data. Responsive to receiving the first notification data, the computing device outputs, at a first intensity level, a first alert associated with the first notification data. The computing device receives, at a second particular time after the first particular time, second notification data. Responsive to the computing device receiving an indication of user interaction with the computing device between the first particular time and the second particular time, the computing device outputs, at the first intensity level, a second alert associated with the second notification data. Conversely, responsive to the computing device not receiving the indication of user interaction with the computing device, the computing device either outputs, at a second intensity level that is less than the first intensity level, the second alert, or refrains from outputting the second alert entirely.

Limiting alerts on a computing device

A computing device may receive a communication sent from an external computing device. At least one processor of the computing device may determine, using an on-device machine-trained model and based at least in part on the communication, one or more candidate responses to the communication. The at least one processor may receive an indication of a user input that selects a candidate response from the one or more candidate responses. Responsive to receiving the indication of the user input that selects the candidate response, the at least one processor may send the candidate response to the external computing device.

Smart replies using an on-device model

A computing device is described that receives notification data, and selects, based on the notification data, a template graphical user interface (GUI) view from a plurality of template GUI views. The computing device automatically generates, from a portion of the notification data, an application GUI view that includes the portion of the notification data included within one or more fields of the template GUI view. The computing device outputs, for display, the application GUI view.

Automatic graphical user interface generation from notification data

A computing system includes a communication unit configured to receive a plurality of message histories, at least one processor, and at least one module. The at least one module is operable by the at least one processor to: determine, based on the plurality of message histories, a plurality of message and response pairs, determine a number of instances of each response for each message from the plurality of message and response pairs, classify each response from the plurality of message and response pairs as having an information type, and store an indication of each unique message from the plurality of message and response pairs, an indication of the information type associated with the respective response associated with the unique message, and a number of responses from the plurality of message and response pairs having the information type.

Predictive responses to incoming communications

Display screen with animated graphical user interface

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying an image for an entity. In one aspect, a method includes identifying a set of resources. Each resource can include at least one image and reference at least one entity. Each image is assigned to a particular entity based on an overall entity scores for the image relative to the entities. The overall entity score for an image and an entity can specify a measure of topical relatedness between the image and the entity. For each individual entity referenced by at least one of the resources, a group of images that have been assigned to the individual entity is identified. An image evocative of each individual entity is selected from the group based on image rank scores. The image rank score for an image can be determined based on visual characteristics of the image.

Identifying an image for an entity

Growing community of inventors

Somerville, MA, United States of America

Nathan Dickerson Beach