公开(公告)号：US20230215425A1

公开(公告)日：2023-07-06

申请号：US18076987

申请日：2022-12-07

Applicant: Amazon Technologies, Inc.

Inventor： Ruhi Sarikaya ,  Hung Tuan Pham ,  Savas Parastatidis ,  Dean Curtis ,  Pushpendre Rastogi ,  Nitin Ashok Jain ,  John Arland Nave ,  Abhinav Sethy ,  Arpit Gupta ,  Mayank Kumar ,  Nakul Dahiwade ,  Arshdeep Singh ,  Nikhil Reddy Kortha ,  Rohit Prasad

IPC: G10L15/16 ,  G06F16/9032 ,  G10L13/08

CPC classification number: G10L15/16 ,  G06F16/90332 ,  G10L13/08

Abstract: Techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. Upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. The system then uses a second machine learning model to determine a particular skill and intent to recommend. The system then prompts the user to accept the recommended skill and intent. If the user accepts, the system calls the recommended skill to execute. As part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. This enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.

公开(公告)号：US11270698B2

公开(公告)日：2022-03-08

申请号：US16550639

申请日：2019-08-26

Applicant: Amazon Technologies, Inc.

Inventor： Anjishnu Kumar ,  Xing Fan ,  Arpit Gupta ,  Ruhi Sarikaya

IPC: G10L15/22 ,  G10L13/00 ,  G10L15/14 ,  G10L15/18 ,  G06N5/02 ,  G06F40/30 ,  G10L17/00 ,  G06F40/295

Abstract: Techniques for determining a command or intent likely to be subsequently invoked by a user of a system are described. A user inputs a command (either via a spoken utterance or textual input) to a system. The system determines content responsive to the command. The system also determines a second command or corresponding intent likely to be invoked by the user subsequent to the previous command. Such determination may involve analyzing pairs of intents, with each pair being associated with a probability that one intent of the pair will be invoked by a user subsequent to a second intent of the pair. The system then outputs first content responsive to the first command and second content soliciting the user as to whether the system to execute the second command.