Google Inc.

Fabian Roth

Jessica Lee

Harshit Kharbanda

Afroz Mohiuddin

Dounia Berrada

Samer Hassan Hassan

Ali Essam Ali Elqursh

Mikhail Khalman

Christopher Kelley

Nils Grimsmo

Belinda Zeng

Ian James Leader

Oana Gheorghita

Ali Ajdari Rad

Hans Van Wesenbeeck

Kristoffer Lidstroem

David Trotter Oleson

The present disclosure provides computer-implemented methods, systems, and devices for responding to requests associated with an image. A computing system obtains, wherein the image depicts a first set of textual content. The computing system determines one or more characteristics of the first set of textual content. The computing system determines a response type from a plurality of response types based on the one or more characteristics. The computing system generates a model input, wherein the model input comprises data descriptive of the first set of textual content and a prompt associated with the response type. The computing system provides providing the model input as an input to a machine-learned language model. The computing system receives a second set of text as an output of the machine-learned language model as a result of the machine-learned language model processing the model input. The computing system provides the second set of text for display to a user, wherein the second set of textual content is associated with the response type.

Systems and methods for analyzing text extracted from images and performing appropriate transformations on the extracted text

Systems and methods for augmented-reality tutoring can utilize optical character recognition, natural language processing, and/or augmented-reality rendering for providing real-time notifications for completing a determined task. The systems and methods can include utilizing one or more machine-learned models trained for quantitative reasoning and can include providing a plurality of different user interface elements at different times.

Dynamically adjusting instructions in an augmented-reality experience

A computing system may process previous inputs from a user into at least one electronic device, the previous inputs including at least a first input indicating that the user has woken up and a second input indicating that the user has left a sleeping location. The computing system may predict a bed-to-door time duration between the user waking up and the user leaving the sleeping location based on the first input indicating that the user has woken up and the second input indicating that the user has left the sleeping location. The computing system may determine a wakeup time for the user based on the predicted bed-to-door time duration and a time at which the user should leave the sleeping location to arrive at the appointment on time. The computing system may cause the at least one electronic device to output an alarm at the determined wakeup time.

Waking user up in time to arrive at appointment by calculating bed-to-door time

Growing community of inventors

Zurich, Switzerland

Fabian Roth