公开(公告)号：US10997223B1

公开(公告)日：2021-05-04

申请号：US15635860

申请日：2017-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Christos Christodoulopoulos ,  Arpit Mittal ,  Andrew Christopher Graham Hopkinson

IPC: G06F16/33 ,  G06F16/338 ,  G06F16/951 ,  G06F40/30 ,  G06F40/169 ,  G06F40/295

Abstract: A method comprising receiving subject data indicative of a subject entity and selecting, from a plurality of data sets, and based on the subject data, a subject entity data set which corresponds to the subject entity. The subject entity data set comprises first related entity data representative of a first related entity related to the subject entity and first text data representative of first text associated with the first related entity. Unstructured text data representative of unstructured text is received and processed, using the first text data, to identify a portion of the unstructured text data corresponding to the first text data. The first text data is used to identify, from the subject entity data set, the first related entity data and the portion of the unstructured text data is identified as corresponding to the first related entity data.

公开(公告)号：US10896222B1

公开(公告)日：2021-01-19

申请号：US15635873

申请日：2017-06-28

Applicant: Amazon Technologies, Inc.

Inventor： Christos Christodoulopoulos ,  Arpit Mittal ,  Andrew Christopher Graham Hopkinson

IPC: G06F16/901 ,  G06N5/02 ,  G06F16/22 ,  G06F40/295

Abstract: A method comprising receiving subject data indicative of a subject entity. First entity data is obtained from a knowledge database using the subject data, the first entity data representative of a first related entity related to the subject entity. First text data is obtained from the knowledge database using the first entity data, the first text data representative of first text associated with the first related entity. A subject entity data set is generated. The subject entity data set comprises first related entity data based on the first entity data, and the first text data.

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.