Amazon Technologies, Inc.

Thomas Irvine Nelson

Jae Pum Park

Timothy Thomas Gray

Dilek Zeynep Hakkani-Tur

Yang Liu

Saurabh Gupta

Richard Leigh Mains

Anna Chen Santos

Yelin Kim

Shilpan Bhagat

Joshua Seth Levy

Described herein is a system for improving sentiment detection and/or recognition using multiple inputs. For example, an autonomously motile device is configured to generate audio data and/or image data and perform sentiment detection processing. The device may process the audio data and the image data using a multimodal temporal attention model to generate sentiment data that estimates a sentiment score and/or a sentiment category. In some examples, the device may also process language data (e.g., lexical information) using the multimodal temporal attention model. The device can adjust its operations based on the sentiment data. For example, the device may improve an interaction with the user by estimating the user's current emotional state, or can change a position of the device and/or sensor(s) of the device relative to the user to improve an accuracy of the sentiment data.

Multimodal sentiment detection

Systems and methods for presenting a user interface in a first mode and a second mode based on detection of a touch gesture is described herein. In some embodiments, a first user interface may be presented on an electronic device's display. The first user interface may include a list of items, which may be formatted such that they are optimally viewable from a first distance away from the display. In response to detecting a touch gesture, such as a scrolling gesture, a second user interface may be presented including the list of items, which may be formatted such that they are optimally viewed from a second distance. For example, the first user interface may be optimally viewable from a distance of approximately seven to ten feet from the display. As another example, the second user interface may optimally viewable from a distance of approximately one to three feet.

Methods and devices for providing optimal viewing displays

A system that generates a personalized content grouped by type and ordered by relevancy. The system determines relevant data for individual feature groups, determines first feature groups that have relevant data to display and displays a page of content for each of the first feature groups. For example, a first page of content may indicate a clock, temperature, weather forecast or timer, a second page of content may correspond to communications and indicate a recent message, a third page of content may correspond to a calendar and may indicate an upcoming event, a fourth page of content may correspond to shipping notifications and may indicate an upcoming shipment, a fifth page of content may correspond to contacts and may indicate an available favorite contact and a sixth page of content may correspond to trending news. The device may generate synthesized speech corresponding to the display of content.

Organization of personalized content

Growing community of inventors

Seattle, WA, United States of America

Thomas Irvine Nelson