Amazon Technologies, Inc.

Nicholas Sun

Wei Niu

Murtuza S Naguthanawala

Tak Chung Lung

Phillip H Keung

Yaxin Huang

Fan Luo

Sharifa Monawer

Yunlong Liu

Srikanth Veerapaneni

Daniel Stephen Edmiston

Damian Finol Correa

Yi-Hsin Chen

Techniques for document recommendation based on conversational log for real time assistance are described. A first machine learning module identifies key phrases of a conversational log in real time. The first machine learning module executes multiple machine learning models trained to determine a probability that a portion of a conversation includes a key phrase. A second machine learning module identifies assistance pertaining to the identified key phrases of the conversational log. The second machine learning module executes a machine learning model trained to identify semantic similarity and word matching features of embedding representations of the key phrases and a knowledge base of assistance. The assistance is provided to a user during a conversation in real time.

Document recommendation based on conversational log for real time assistance

Techniques for action recommendation based on conversational log for real time assistance are described. Pre-generated intent clusters can be used to identify a relevant intent of a user in a given conversation between the user and a contact center agent. Based on the identified intent, certain recommended actions can be performed on the computing device of the contact center agent to facilitate the conversation between the user and the contact center agent. Feedback relating to the conversation and/or the recommended actions can be recorded and used to update the pre-generated intent clusters to improve the quality and relevance of the actions recommended for future conversations.

Computing action recommendation system for facilitating real time communication

A blockchain is used to track chain of custody associated with devices and user entities associated with those devices. In an embodiment, an identity engine traverses a blockchain to determine one or more transactions associated with a device and, in some cases, one or more users of that device. Based at least in part on the content of an authentication or provisioning request and that of the chain of custody, the identity engine provisions the device for a given user.

Blockchain-backed device and user provisioning

Systems and methods are described for authenticating parties who communicate via unauthenticated channels. A user authentication verification service receives a request to confirm the identity of a party who communicates via an unauthenticated channel. The user authentication verification service may identify a computing device associated with the claimed user identity, and may determine that the computing device (or an application installed on the computing device) can be used to authenticate the user. The user authentication verification service may thus transmit a push notification or other request to the computing device to request authentication from the user that the party claims to be or represent. The user authentication verification service may then receive information from the computing device, confirm that the information authenticates that the party is the user (or is acting on behalf of the user), and authorize communication via the unauthenticated channel.

User authentication verification service

Growing community of inventors

Mercer Island, WA, United States of America

Nicholas Sun