Amazon Technologies, Inc.

Meta Platforms, Inc.

Sheng Bi

Ariel Grob Dos Santos

Chun-Che Wang

Tarun Agarwal

Vikas Seshagiri Rao Bhardwaj

Gunashekar Jayaraman

Jared Kramer

Michael Greenberg

Polly Po Yee Lee

Hung Chiu Phillip Keung

Kapil Chahal

Royden Mark Jacob Lewis

Dhvani Yogesh Shah

Paul Grunchich

Jason Sun

Benjamin King

Hunlan Lin

Anirban Chakraborty

Brock Christopher Stoops

Chenzhi Shao

Angela Alarcon

Jay Reynolds

Naiem Khodabandehloo Yeganeh

In one embodiment, a method includes receiving a user input associated with a task from a client system associated with a first user, calculating an idle time associated with the task based on the user input and the task, determining a level of interactivity of content items to display for the first user during the idle time based on a length of the idle time and a type of the task, retrieving personalized content items based on the level of interactivity and contextual information associated with the task, and sending instructions to the client system for presenting the personalized content items during the idle time, wherein the personalized content items have the determined level of interactivity.

Presenting personalized content during idle time for assistant systems

A speech interface device is configured to display an Augmented Reality (AR) user interface that displays information specific to a vehicle or other object. For example, the device may capture images of the vehicle and may displaying the AR user interface with labels, graphical elements, visual effects, and/or additional information superimposed above corresponding portions of the vehicle represented in the images. Using a remote system to perform speech processing, the device may respond to a voice command, enabling the AR user interface to display specific information about the vehicle and/or features of the vehicle in response to the voice command. The device may also send position data indicating information about what is displayed on the AR user interface, enabling the remote system to provide information about specific features or components based on where the device is pointed.

Speech-enabled augmented reality user interface

Systems and methods are provided for retraining a machine learning model to learn a retrained machine learning model. After a computing system receives an execution log of a prediction service and an observed user action, it may create retraining data. From the retraining data, the computing system may learn a retrained machine learning model. The retrained machine learning model can be used to compute future predictions of user actions if it has an improved performance over the original machine learning model.

Automatic re-training of offline machine learning models

Disclosed are various embodiments for an automated service agent. Natural language inputs are obtained from a client. The natural language inputs and other data are input to machine learning models to identify intents reflected in the natural language inputs. A state in a workflow is updated to reflect the identified intents. Responses may be communicated to the client to further progress in the workflow.

Language based solution agent

Growing community of inventors

Bellevue, WA, United States of America

Sheng Bi