公开(公告)号：US09965726B1

公开(公告)日：2018-05-08

申请号：US14696214

申请日：2015-04-24

Applicant: Amazon Technologies, Inc.

Inventor： Mihai Valentin Tablan ,  Andrew Graham Fenn ,  David Spike Palfrey ,  Petra Elisabeth Holmes ,  Sina Samangooei

IPC: G06F15/18 ,  G06N3/00 ,  G06N3/12 ,  G06N99/00 ,  G06F17/30

CPC classification number: G06N99/005 ,  G06F17/30657 ,  G06F17/30867 ,  G06N3/126

Abstract: Techniques are described for adding knowledge to a knowledge base.

公开(公告)号：US09582757B1

公开(公告)日：2017-02-28

申请号：US14341595

申请日：2014-07-25

Applicant: Amazon Technologies, Inc.

Inventor： Petra Elisabeth Holmes ,  Andrew Graham Fenn ,  Andrew Hopkinson ,  David Spike Palfrey ,  William Tunstall-Pedoe ,  Neil Copland

IPC: G06F17/00 ,  G06F17/20 ,  G06N5/02

CPC classification number: G06N3/006 ,  G06F17/3043 ,  G06N5/02 ,  G06N5/04 ,  G06N7/005

Abstract: A system and method is disclosed for improving automated question-answering using real-world knowledge from a knowledge base. The system can be used to answer questions from various users. The system can generate answers to these questions using data stored in a knowledge base. In some embodiments, the system is provided with a list of questions separate from any user questions. The system can be trained using these questions in advance of a user question. The system can process the presented questions to determine that it can generate high-quality correct answers. The system can take various steps to determine a high-quality answer to a question. The system can utilize human intelligence providers to improve this process, such as through a human interactive task system. Human intelligence can be used to determine that a question is understood, that a question is answered, and that the answer is of high quality.

Abstract translation: 公开了一种用于使用来自知识库的真实世界知识来改进自动化问答的系统和方法。 该系统可用于回答各种用户的问题。 系统可以使用存储在知识库中的数据来生成对这些问题的答案。 在一些实施例中，向系统提供与任何用户问题分离的问题列表。 系统可以在用户问题之前使用这些问题进行培训。 系统可以处理提出的问题，以确定它可以生成高质量的正确答案。 系统可以采取各种步骤来确定问题的高质量答案。 该系统可以利用人类智能提供者改善这一过程，例如通过人类交互任务系统。 可以使用人类智力来确定一个问题被理解，一个问题得到回答，答案是高质量的。

公开(公告)号：US20180157960A1

公开(公告)日：2018-06-07

申请号：US15443221

申请日：2017-02-27

Applicant: Amazon Technologies, Inc.

Inventor： Petra Elisabeth Holmes ,  Andrew Graham Fenn ,  Andrew Hopkinson ,  David Spike Palfrey ,  William Tunstall-Pedoe ,  Neil Copland

IPC: G06N3/00 ,  G06N5/02 ,  G06N7/00 ,  G06F17/30

CPC classification number: G06N3/006 ,  G06F16/24522 ,  G06N5/02 ,  G06N5/04 ,  G06N7/005

Abstract: A system and method is disclosed for improving automated question-answering using real-world knowledge from a knowledge base. The system can be used to answer questions from various users. The system can generate answers to these questions using data stored in a knowledge base. In some embodiments, the system is provided with a list of questions separate from any user questions. The system can be trained using these questions in advance of a user question. The system can process the presented questions to determine that it can generate high-quality correct answers. The system can take various steps to determine a high-quality answer to a question. The system can utilize human intelligence providers to improve this process, such as through a human interactive task system. Human intelligence can be used to determine that a question is understood, that a question is answered, and that the answer is of high quality.

公开(公告)号：US09466294B1

公开(公告)日：2016-10-11

申请号：US13899171

申请日：2013-05-21

Applicant: Amazon Technologies, Inc.

Inventor： William Tunstall-Pedoe ,  Andrew Graham Fenn ,  Robert Peter Stacey ,  Adam John Philip Wood

IPC: G06F17/30 ,  G10L15/22

CPC classification number: G10L15/22 ,  G06F17/30654 ,  G10L2015/228

Abstract: Techniques for facilitating transactions are described in which the system facilitating the transaction engages in natural language dialog with the user to achieve the desired result. Instead of treating successive input independently, the system maintains a dialog context in which information generated in response to recent input may be used to inform responses to further input.

Abstract translation: 描述了促进交易的技术，其中促进交易的系统与用户进行自然语言对话以实现期望的结果。 不是独立地处理连续输入，而是保持对话上下文，其中可以使用响应于最近的输入生成的信息来通知对进一步输入的响应。

公开(公告)号：US09286910B1

公开(公告)日：2016-03-15

申请号：US14208700

申请日：2014-03-13

Applicant: Amazon Technologies, Inc.

Inventor： Meng Li ,  Duncan Joseph Reynolds ,  William Tunstall-Pedoe ,  Petra Elisabeth Holmes ,  Robert Peter Stacey ,  David Spike Palfrey ,  Andrew Graham Fenn ,  Mark Rafn ,  Graham John French

IPC: G10L25/48

CPC classification number: G10L25/48 ,  G06F17/30654 ,  G06F17/30699 ,  G10L15/26

Abstract: A system for resolving a user's question regarding media at the user's location where the question includes ambiguity as to the context of the question. Context information is acquired from a device or devices at the user's location, and if multiple possible contexts are identified, the system may attempt to resolve the question for more than one of the possible contexts. The system for answering questions and the source of the media may be different and independent.

Abstract translation: 用于在用户位置处解决用户关于媒体的问题的系统，其中问题包括关于问题的上下文的模糊性。 从用户位置的设备或设备获取上下文信息，并且如果识别出多个可能的上下文，则系统可以尝试解决多个可能上下文中的问题。 回答问题的系统和媒体的来源可能是不同的和独立的。