公开(公告)号：US11615239B2

公开(公告)日：2023-03-28

申请号：US16836462

申请日：2020-03-31

Applicant: Adobe Inc.

Inventor： Oliver Brdiczka ,  Ajinkya Kale ,  Piyush Chandra ,  Tracy King ,  Abhishek Gupta ,  Sourabh Goel ,  Nitin Garg ,  Deepika Naryani ,  Feroz Ahmad ,  Vikas Sagar

IPC: G06F15/16 ,  G06F9/54 ,  H04L29/06 ,  G06F40/20 ,  G06F40/40 ,  G06F40/35 ,  H04L51/00

Abstract: The present disclosure relates to systems for identifying instances of natural language input, determining intent classifications associated with instances of natural language input, and generating responses based on the determined intent classifications. In particular, the disclosed systems intelligently identify and group instances of natural language input based on characteristics of the user input. Additionally, the disclosed systems determine intent classifications for the instances of natural language input based message queuing in order to delay responses to the user input in ways that increase accuracy of the responses, while retaining a conversational aspect of the ongoing chat. Moreover, in one or more embodiments, the disclosed systems generate responses utilizing natural language.

公开(公告)号：US20210303784A1

公开(公告)日：2021-09-30

申请号：US16836462

申请日：2020-03-31

Applicant: Adobe Inc.

Inventor： Oliver Brdiczka ,  Ajinkya Kale ,  Piyush Chandra ,  Tracy King ,  Abhishek Gupta ,  Sourabh Goel ,  Nitin Garg ,  Deepika Naryani ,  Feroz Ahmad ,  Vikas Sagar

IPC: G06F40/20 ,  G06F40/40

Abstract: The present disclosure relates to systems for identifying instances of natural language input, determining intent classifications associated with instances of natural language input, and generating responses based on the determined intent classifications. In particular, the disclosed systems intelligently identify and group instances of natural language input based on characteristics of the user input. Additionally, the disclosed systems determine intent classifications for the instances of natural language input based message queuing in order to delay responses to the user input in ways that increase accuracy of the responses, while retaining a conversational aspect of the ongoing chat. Moreover, in one or more embodiments, the disclosed systems generate responses utilizing natural language.