公开(公告)号：US12007988B2

公开(公告)日：2024-06-11

申请号：US18182303

申请日：2023-03-10

Applicant: Amazon Technologies, Inc.

Inventor： Ramesh M Nallapati ,  Zhiguo Wang ,  Bing Xiang ,  Patrick Ng ,  Yung Haw Wang ,  Mukul Karnik ,  Nanyan Li ,  Sharanabasappa Parashuram Revadigar ,  Timothy Jones ,  Stephen Michael Ash ,  Sudipta Sengupta ,  Gregory David Adams ,  Deepak Shantha Murthy ,  Douglas Scott Cerny ,  Stephanie Weeks ,  Hanbo Li

IPC: G06F16/2452 ,  G06F16/242 ,  G06F40/295 ,  G06N20/00

CPC classification number: G06F16/24522 ,  G06F16/2423 ,  G06F16/243 ,  G06F40/295 ,  G06N20/00

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

公开(公告)号：US11941016B2

公开(公告)日：2024-03-26

申请号：US17687492

申请日：2022-03-04

Applicant: Amazon Technologies, Inc.

Inventor： Timothy Jones ,  Andrew Borthwick ,  Sergei Dobroshinsky ,  Shehzad Qureshi ,  Stephen Michael Ash ,  Pedrito Uriah Maynard-Zhang ,  Chethan Kommaranahalli Rudramuni ,  Abhishek Sharma ,  Juliana Saussy ,  Adam Lawrence Joseph Heinermann ,  Alaykumar Navinchandra Desai ,  Mehul A. Shah ,  Mehul Y. Shah ,  Anurag Windlass Gupta ,  Prajakta Datta Damle

IPC: G06F16/25 ,  G06F9/54 ,  G06N20/00

CPC classification number: G06F16/254 ,  G06F9/543 ,  G06N20/00

Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

公开(公告)号：US11500865B1

公开(公告)日：2022-11-15

申请号：US17219706

申请日：2021-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Jun Wang ,  Zhiguo Wang ,  Sharanabasappa Parashuram Revadigar ,  Ramesh M Nallapati ,  Bing Xiang ,  Stephen Michael Ash ,  Timothy Jones ,  Sudipta Sengupta ,  Rishav Chakravarti ,  Patrick Ng ,  Jiarong Jiang ,  Hanbo Li ,  Donald Harold Rivers Weidner

IPC: G06F7/00 ,  G06F16/2452 ,  G06F40/295 ,  G06N20/00 ,  G06F16/242

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

公开(公告)号：US20230325384A1

公开(公告)日：2023-10-12

申请号：US18182303

申请日：2023-03-10

Applicant: Amazon Technologies, Inc.

Inventor： Ramesh M Nallapati ,  Zhiguo Wang ,  Bing Xiang ,  Patrick Ng ,  Yung Haw Wang ,  Mukul Karnik ,  Nanyan Li ,  Sharanabasappa Parashuram Revadigar ,  Timothy Jones ,  Stephen Michael Ash ,  Sudipta Sengupta ,  Gregory David Adams ,  Deepak Shantha Murthy ,  Douglas Scott Cerny ,  Stephanie Weeks ,  Hanbo Li

IPC: G06F16/2452 ,  G06F16/242 ,  G06F40/295 ,  G06N20/00

CPC classification number: G06F16/24522 ,  G06F16/243 ,  G06F16/2423 ,  G06F40/295 ,  G06N20/00

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

公开(公告)号：US20220261413A1

公开(公告)日：2022-08-18

申请号：US17687492

申请日：2022-03-04

Applicant: Amazon Technologies, Inc.

Inventor： Timothy Jones ,  Andrew Borthwick ,  Sergei Dobroshinsky ,  Shehzad Qureshi ,  Stephen Michael Ash ,  Pedrito Uriah Maynard-Zhang ,  Chethan Kommaranahalli Rudramuni ,  Abhishek Sharma ,  Juliana Saussy ,  Adam Lawrence Joseph Heinermann ,  Alaykumar Navinchandra Desai ,  Mehul A. Shah ,  Mehul Y. Shah ,  Anurag Windlass Gupta ,  Prajakta Datta Damle

IPC: G06F16/25 ,  G06F9/54 ,  G06N20/00

Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

公开(公告)号：US11726997B2

公开(公告)日：2023-08-15

申请号：US18055384

申请日：2022-11-14

Applicant: Amazon Technologies, Inc.

Inventor： Jun Wang ,  Zhiguo Wang ,  Sharanabasappa Parashuram Revadigar ,  Ramesh M Nallapati ,  Bing Xiang ,  Stephen Michael Ash ,  Timothy Jones ,  Sudipta Sengupta ,  Rishav Chakravarti ,  Patrick Ng ,  Jiarong Jiang ,  Hanbo Li ,  Donald Harold Rivers Weidner

IPC: G06F7/00 ,  G06F16/2452 ,  G06F40/295 ,  G06N20/00 ,  G06F16/242

CPC classification number: G06F16/24522 ,  G06F16/243 ,  G06F40/295 ,  G06N20/00

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

公开(公告)号：US20230078177A1

公开(公告)日：2023-03-16

申请号：US18055384

申请日：2022-11-14

Applicant: Amazon Technologies, Inc.

Inventor： Jun Wang ,  Zhiguo Wang ,  Sharanabasappa Parashuram Revadigar ,  Ramesh M Nallapati ,  Bing Xiang ,  Stephen Michael Ash ,  Timothy Jones ,  Sudipta Sengupta ,  Rishav Chakravarti ,  Patrick Ng ,  Jiarong Jiang ,  Hanbo Li ,  Donald Harold Rivers Weidner

IPC: G06F16/2452 ,  G06F40/295 ,  G06N20/00 ,  G06F16/242

Abstract: Multiple stage filtering may be implemented for natural language query processing pipelines. Natural language queries may be received at a natural language query processing system and processed through a query language processing pipeline. The query language processing pipeline may filter candidate linkages for a natural language query before performing further filtering of the candidate linkages in the natural language query processing pipeline as part of generating an intermediate representation used to execute the natural language query.

公开(公告)号：US11604794B1

公开(公告)日：2023-03-14

申请号：US17219689

申请日：2021-03-31

Applicant: Amazon Technologies, Inc.

Inventor： Ramesh M Nallapati ,  Zhiguo Wang ,  Bing Xiang ,  Patrick Ng ,  Yung Haw Wang ,  Mukul Karnik ,  Nanyan Li ,  Sharanabasappa Parashuram Revadigar ,  Timothy Jones ,  Stephen Michael Ash ,  Sudipta Sengupta ,  Gregory David Adams ,  Deepak Shantha Murthy ,  Douglas Scott Cerny ,  Stephanie Weeks ,  Hanbo Li

IPC: G06F16/245 ,  G06F16/2452 ,  G06F16/242 ,  G06F40/295 ,  G06N20/00

Abstract: Interactive assistances for executing natural language queries to data sets may be performed. A natural language query may be received. Candidate entity linkages may be determined between an entity recognized in the natural language query and columns in data sets. The candidate linkages may be ranked according to confidence scores which may be evaluated to detect ambiguity for an entity linkage. Candidate entity linkages may be provided to a user via an interface to select an entity linkage to use as part of completing the natural language query.

公开(公告)号：US11269911B1

公开(公告)日：2022-03-08

申请号：US16199115

申请日：2018-11-23

Applicant: Amazon Technologies, Inc.

Inventor： Timothy Jones ,  Andrew Borthwick ,  Sergei Dobroshinsky ,  Shehzad Qureshi ,  Stephen Michael Ash ,  Pedrito Uriah Maynard-Zhang ,  Chethan Kommaranahalli Rudramuni ,  Abhishek Sharma ,  Juliana Saussy ,  Adam Lawrence Joseph Heinermann ,  Alaykumar Navinchandra Desai ,  Mehul A. Shah ,  Mehul Y. Shah ,  Anurag Windlass Gupta ,  Prajakta Datta Damle

IPC: G06F16/25 ,  G06F9/54 ,  G06N20/00

Abstract: Specified performance attributes may be used to configure machine learning transformations for ETL jobs. Performance attributes for a machine learning pipeline that applies a model to as part of a transformation for an ETL job may be used to configure a parameter in a stage of the machine learning pipeline. The configured stage may then be used when training the model. The trained machine learning pipeline may then be applied as part of a transformation operation included in an ETL job performed by the ETL system.

公开(公告)号：US10599614B1

公开(公告)日：2020-03-24

申请号：US15860393

申请日：2018-01-02

Applicant: Amazon Technologies, Inc.

Inventor： Andrew Borthwick ,  Tianyi Lu ,  Shehzad Qureshi ,  Timothy Jones

IPC: G06F17/30 ,  G06F16/13 ,  G06N20/00 ,  G06F16/174

Abstract: Block size reduction iterations are performed on a plurality of blocks of records until a block size criterion is met. An iteration comprises identifying, from a first collection of blocks, using one or more pivot operations, a set of combinations of oversized blocks such that at least one record belongs to all blocks of a combination. A new block comprising records that are members of each block of a first combination of the set is included in a second collection of blocks to be examined in a subsequent iteration. On at least one block created in an iteration, analysis operations are performed.