-
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
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.
-
2.
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。
-
公开(公告)号:US11120341B1
公开(公告)日:2021-09-14
申请号:US14974634
申请日:2015-12-18
Applicant: Amazon Technologies, Inc.
Inventor: David Spike Palfrey , Sina Samangooei , Mihai Valentin Tablan , Maxime Peyrard
Abstract: Techniques are described for determining the value of individual facts in a knowledge base, and various applications of such fact values. In one example, the knowledge base is part of a question answering system. A ranking of knowledge base facts based on the number of times each of the knowledge base facts is used in answering user questions (e.g., as determined from question answering logs) is used to derive a fact value function that may then be used to determine the value of other facts included in or subsequently added to the knowledge base.
-
公开(公告)号:US09659052B1
公开(公告)日:2017-05-23
申请号:US14038098
申请日:2013-09-26
Applicant: Amazon Technologies, Inc.
Inventor: Barry Dean Glennon , David Spike Palfrey , William Tunstall-Pedoe , Duncan Joseph Reynolds , Petra Elisabeth Holmes , Gregory Christopher Doran
IPC: G06F17/30
CPC classification number: G06F17/30607 , G06F17/30303 , G06F17/30598
Abstract: A system and method to recognize and resolve when a source data object is the same or similar to an existing data object in a database using structured information and facts about each object. The system and method compare relations of the source data object and relations of the existing data object in the database and determine how similar the source data object is to the data object in the database based on scores of the comparisons. The system and method may provide outputs, such as whether the data objects match, the data objects are distinct, the source data object is a strong match to multiple data objects in the database, and the data objects conflict one another. The system and method may then resolve the database entries based on the potential matching outputs.
-
公开(公告)号:US09646260B1
公开(公告)日:2017-05-09
申请号:US13925627
申请日:2013-06-24
Applicant: Amazon Technologies, Inc.
Inventor: William Tunstall-Pedoe , Jianhan Zhu , Gregory Christopher Doran , Petra Elisabeth Holmes , David Spike Palfrey
Abstract: Techniques are described for adding knowledge to a knowledge base in which alternative information retrieval techniques are used to obtain missing information from an available corpus of documents (e.g., the World Wide Web). Existing relationships in a knowledge base are used to identify entities for which the relationships are not expressed in the knowledge base. The alternative information retrieval techniques are then used to find this information.
-
公开(公告)号:US11055355B1
公开(公告)日:2021-07-06
申请号:US16017032
申请日:2018-06-25
Applicant: Amazon Technologies, Inc.
Inventor: Emilio Fabio Monti , Anjishnu Kumar , David Spike Palfrey , Sainyam Kapoor , Janez Starc , Samuel Tucker
IPC: G06F16/9032 , G10L15/183 , G10L15/22
Abstract: A method comprising sending query data representative of a query to a first and second query-answering subsystem of a query-answering system. It is determined that the query-answering system lacks a satisfactory answer to the query. Paraphrase data representative of a rephrased version of the query is received. The paraphrase data is sent to the first and second query-answering subsystems. Answer data representative of an answer to the rephrased version of the query is received from the first query-answering subsystem.
-
公开(公告)号:US10963497B1
公开(公告)日:2021-03-30
申请号:US15083790
申请日:2016-03-29
Applicant: Amazon Technologies, Inc.
Inventor: Mihai Valentin Tablan , Sina Samangooei , Arpit Mittal , David Spike Palfrey , Emilio Monti , Pedro Ribeiro , Benjamin David Scott , Petra Elisabeth Holmes , Dianhuan Lin
IPC: G06F16/33
Abstract: A query parsing system uses a multi-stage process to parse the text of incoming queries before attempting to answer the queries. The multi-stage configuration involves a first trained classifier to determine the query type, or intent, of the text and a plurality of second trained classifiers, where each of the second trained classifiers is configured particularly for one specific respective query type. During query processing, the first trained classifier is used on the text to identify the query type. A second trained classifier for that specific identified query type is then found and used on the text to identify what strings in the text correspond to specific entities needed to resolve the query. The identified text strings and query type are then placed into a form understandable by a knowledge base and sent to the knowledge base for resolution. The classifiers may be trained using queries and answers previously processed by the knowledge base using a rules/template resolution process.
-
公开(公告)号:US10049375B1
公开(公告)日:2018-08-14
申请号:US14666023
申请日:2015-03-23
Applicant: Amazon Technologies, Inc.
Inventor: Giovanni Zappella , Marcel Ackermann , Rodolphe Jenatton , David Spike Palfrey , Samuel Theodore Sandler
Abstract: A system is disclosed that identifies early adopter users by creating a directed graph of item access information for an item category and performing a page rank type process on the item access information. This directed graph may be created in a reverse temporal order. The early adopter users can be identified as the users with nodes in the directed graph that have a threshold number or rate of incoming links directly or indirectly pointing towards the nodes. Using the early adopter users as a sample, systems herein can determine whether to recommend an item based on the popularity of the item with respect to the early adopter users. Further, systems herein can determine an inventory level to maintain for an item based on the popularity of the item with respect to the early adopter users.
-
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
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
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。
-
-
-
-
-
-
-
-
-