Amazon Technologies, Inc.

Alexander Jonathan Pinkus

David Earl Heckerman

Samuel Scott Gigliotti

Chao Wang

David Robert Cole

Viktor Rozgic

Narendra Gyanchandani

Bilyana Slavova

Sohel R Ahuja

Julian Embry Herwitz

Hanhan Wang

Jessica Nicole Jenks

Stephen David Avalone

Samuel Elbert McGowan

Adrien Charles Guerard

Siddharth Natarajan

Mohammad Taha Bahadori

Matthew Ryan Fielden

Alexander Roy Wishkoski

Described is a system and method that determines character sequences from speech, without determining the words of the speech, and processes the character sequences to determine sentiment data indicative of emotional state of a user that output the speech. The emotional state may then be presented or provided as an output to the user.

Character-level emotion detection

A microphone acquires audio data of a user's speech. The audio data is processed to determine sentiment data indicative of perceived emotional content of the speech. For example, the sentiment data may include values for one or more of valence that is based on a particular change in pitch over time or activation that is based on speech pace. A simplified user interface provides the user with a graphical representation based on the sentiment data and associated descriptors. For example, a visual indicator such as a dot may be shown at particular coordinates onscreen that correspond to the sentiment data. Text descriptors may also be presented near the dot. As the user continues speaking, and new audio data is processed, the interface is dynamically updated. The user may use this information to assess their state of mind, facilitate interactions with others, and so forth.

System for presentation of sentiment data

Embodiments are described for implementing a contextual browsing assistant service. In accordance with at least one embodiment, event data comprising content being presented via an interface of a system may be obtained. First information about the content may be extracted from the event data. In embodiments, the first information about the content may be extracted utilizing a content extractor. An item included in the first information may be identified based on a comparison of the first information and second information that identifies a plurality of items offered by an electronic marketplace. In an embodiment, third information about the identified item may be presented via the interface.

Contextual and personalized browsing assistant

Growing community of inventors

Seattle, WA, United States of America

Alexander Jonathan Pinkus