公开(公告)号：US11803847B2

公开(公告)日：2023-10-31

申请号：US16041658

申请日：2018-07-20

Applicant: eBay, Inc.

Inventor： David John Kamalsky ,  Vidit Aggarwal ,  Seyed-Mahdi Pedramrazi ,  Ethan Benjamin Rubinson ,  Sachin Tilloo ,  Sergio Pinzon Gonzales, Jr.

IPC: G06Q20/08 ,  G06Q20/38 ,  G06Q20/40 ,  H04L9/30 ,  G06F21/10 ,  G06F21/30 ,  G06F21/60 ,  G06F21/62 ,  G06Q20/42 ,  G06Q30/018 ,  G06Q40/08 ,  H04L65/612 ,  H04L67/53 ,  H04L67/63 ,  H04L9/06 ,  H04L9/32 ,  H04L9/40 ,  G06F16/18 ,  G06F16/27 ,  G06F21/64 ,  H04L67/52 ,  H04L9/00

CPC classification number: G06Q20/389 ,  G06F21/10 ,  G06F21/30 ,  G06F21/602 ,  G06F21/62 ,  G06F21/6218 ,  G06F21/6245 ,  G06Q20/0855 ,  G06Q20/3825 ,  G06Q20/3829 ,  G06Q20/401 ,  G06Q20/42 ,  G06Q30/018 ,  G06Q40/08 ,  H04L9/0637 ,  H04L9/0643 ,  H04L9/30 ,  H04L9/3236 ,  H04L9/3239 ,  H04L9/3247 ,  H04L9/3297 ,  H04L63/102 ,  H04L63/12 ,  H04L65/612 ,  H04L67/53 ,  H04L67/63 ,  G06F16/1805 ,  G06F16/27 ,  G06F21/645 ,  G06F2221/2107 ,  H04L9/50 ,  H04L67/52 ,  H04L2209/56

Abstract: Technologies are shown for controlling a transaction on a digitally stored blockchain by creating a contract data block for a transaction involving entities and by event code executed after receipt of digital signatures from the entities. A refund transaction may be digitally signed by entities and linked to the contract block within the blockchain. A payment transaction block may also be digitally signed by entities and linked to the contract block. Code authorized to execute by the blocks executes based on receipt of digital signature events.

公开(公告)号：US20180150448A1

公开(公告)日：2018-05-31

申请号：US15363283

申请日：2016-11-29

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/275 ,  G06F17/273 ,  G06F17/278 ,  G06F17/289 ,  G06K9/6842

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.

公开(公告)号：US11797765B2

公开(公告)日：2023-10-24

申请号：US17320538

申请日：2021-05-14

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F40/263 ,  G06F40/58 ,  G06F40/232 ,  G06F40/295 ,  G10L15/00 ,  G06V30/246 ,  G06F40/47 ,  G06F40/55

CPC classification number: G06F40/263 ,  G06F40/232 ,  G06F40/295 ,  G06F40/58 ,  G06F40/47 ,  G06F40/55 ,  G06V30/246 ,  G10L15/005

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.

公开(公告)号：US20190213248A1

公开(公告)日：2019-07-11

申请号：US16353796

申请日：2019-03-14

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F17/27 ,  G06F17/28

CPC classification number: G06F17/275 ,  G06F17/273 ,  G06F17/278 ,  G06F17/289 ,  G06K9/6842

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.

公开(公告)号：US20210271812A1

公开(公告)日：2021-09-02

申请号：US17320538

申请日：2021-05-14

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F40/263 ,  G06F40/58 ,  G06F40/232 ,  G06F40/295

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.

公开(公告)号：US11010549B2

公开(公告)日：2021-05-18

申请号：US16353796

申请日：2019-03-14

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F40/263 ,  G06F40/58 ,  G06F40/232 ,  G06F40/295 ,  G06K9/68 ,  G10L15/00

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.

公开(公告)号：US10282415B2

公开(公告)日：2019-05-07

申请号：US15363283

申请日：2016-11-29

Applicant: eBay Inc.

Inventor： Akshay Gupta ,  Hrishikesh Joshi ,  Saiyam Kohli ,  Vidit Aggarwal

IPC: G06F17/27 ,  G06F17/28 ,  G06K9/68

Abstract: Aspects of the present disclosure include a system comprising a machine-readable storage medium storing at least one program and computer-implemented methods for detecting a language of a text string. Consistent with some embodiments, the method may include applying multiple language identification models to a text string. Each language identification model provides a predicted language of the text string and a confidence score associated with the predicted language. The method may further include weighting each associated confidence score based on historical performance of the corresponding language identification model in predicting languages of other text strings. The method may further include selecting a predicted language of the text string from among the multiple predicted languages provided by the multiple language identification models based on a result of the weighting of the confidence score associated with the particular predicted language.