Amazon Technologies, Inc.

Xu Zhang

Prashant J Thakare

Shiladitya Roy

Rohit Bhattacharjee

Nikhil Gupta

Shih-Fu Chang

Pradeep Natarajan

Yue Wu

Clare Elizabeth Veladanda

Andres Felipe Borja Jaramillo

Nicholas Adam Cummings

Alberto Milan Gutierrez

Rashmi Tonge

Monty Eich

Troy Dean Schuring

Rohin Dabas

Nnenna Eleanya Okwara

Veer Yuganter Singh

Sabrina Chandrasekaran

Varsha Hedau

Alekya Jonnala

Sol Jee Cho

David Z Chen

Pranav Kumar Singh

Maksym Kolodeznyi

Techniques for resuming a skill session are described. A system receives a user input, determines a skill to execute with respect to the user input, opens a skill session, and causes the skill to execute. After the skill executes, the skill indicates the skill session is to be placed in a background state, resulting in the user being able to conduct one or more skill sessions while the skill processes in the background state. Sometime after placing the skill session in the background state, the skill requests the system to resume the skill session. If the system determines the skill session is to be resumed, the system sends data to the skill indicating that the skill session will be resumed. Once the skill session is to be resumed, the system places the skill session in an active state, and calls the skill to resume processing of the skill session.

Skill session backgrounding and resumption

An image processing system may receive image data from a camera of a user device and perform gaze prediction processing of the image data to predict one or more gaze patterns. The gaze prediction processing may include processing the image data using a neural network to detect faces and/or objects and generate an image feature map. The gaze prediction processing may include performing gaze direction prediction operations using the feature map and detected faces and/or objects to determine gaze direction probability data. The gaze prediction processing may include predicting a gaze pattern based on the gaze direction probability data and the image feature map. The gaze pattern may be short-term (e.g., atomic-level) or long-term (e.g., event-level).

Gaze prediction

A speech-processing system may provide access to one or more skills via spoken commands and/or responses in the form of synthesized speech. The system may be capable of keeping one or more skills active in the background while a user interacts (e.g., provides inputs to and/or receives outputs from) with a skill running in the foreground. A background skill may receive some trigger data, and determine to request the system to return the background skill to the foreground to, for example, request a user input regarding an action previously requested by the user. In some cases, the user may invoke a background skill to continue a previous interaction. The system may return the background skill to the foreground. The resumed skill may continue a previous interaction to, for example, to query the user for instructions, provide an update or alert, or continue a previous output.

Task resumption in a natural understanding system

Techniques for transferring control of a system-user dialog session are described. A first speechlet component may interact with a user until the first speechlet component receives user input that the first speechlet component cannot handle. The first speechlet component may output an action representing the user input. A system may determine a second speechlet component configured to execute the action. The system may send the second speechlet component a navigator object that results in the second speechlet component handling the user interaction that the first speechlet component could not handle. Once the second speechlet component is finished processing, the second speechlet component may output an updated navigator object, which causes the first speechlet component to either further interact with a user or cause a current dialog session to be closed. The system may additionally maintain a data structure representing calling speechlet components and called speechlet components associated with the session.

Multi-speechlet response

Growing community of inventors

Bothell, WA, United States of America

Xu Zhang