公开(公告)号：US11875241B2

公开(公告)日：2024-01-16

申请号：US17462465

申请日：2021-08-31

Applicant: eBay Inc.

Inventor： Farah Abdallah ,  Robert Enyedi ,  Amit Srivastava ,  Elaine Lee ,  Braddock Craig Gaskill ,  Tomer Lancewicki ,  Xinyu Zhang ,  Jayanth Vasudevan ,  Dominique Jean Bouchon

IPC: G06N3/006 ,  G06F16/50 ,  G06Q30/0601 ,  G06Q30/0251 ,  G06F16/9032 ,  G06Q10/10 ,  G06F40/30 ,  G06N20/00 ,  G06F16/248

CPC classification number: G06N3/006 ,  G06F16/248 ,  G06F16/50 ,  G06F16/90332 ,  G06F40/30 ,  G06N20/00 ,  G06Q10/10 ,  G06Q30/0256 ,  G06Q30/0601 ,  G06Q30/0625

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

公开(公告)号：US20210390365A1

公开(公告)日：2021-12-16

申请号：US17462465

申请日：2021-08-31

Applicant: eBay Inc.

Inventor： Farah Abdallah ,  Robert Enyedi ,  Amit Srivastava ,  Elaine Lee ,  Braddock Craig Gaskill ,  Tomer Lancewicki ,  Xinyu Zhang ,  Jayanth Vasudevan ,  Dominique Jean Bouchon

IPC: G06N3/00 ,  G06F16/50 ,  G06Q30/06 ,  G06Q30/02 ,  G06F16/9032 ,  G06Q10/10 ,  G06F40/30 ,  G06N20/00 ,  G06F16/248

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

公开(公告)号：US20190156177A1

公开(公告)日：2019-05-23

申请号：US15859239

申请日：2017-12-29

Applicant: eBay Inc.

Inventor： Farah Abdallah ,  Robert Enyedi ,  Amit Srivastava ,  Elaine Lee ,  Braddock Craig Gaskill ,  Tomer Lancewicki ,  Xinyu Zhang ,  Jayanth Vasudevan ,  Dominique Jean Bouchon

IPC: G06N3/00 ,  G06N99/00 ,  G06F17/30 ,  G06F17/27

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

公开(公告)号：US20240095490A1

公开(公告)日：2024-03-21

申请号：US18523674

申请日：2023-11-29

Applicant: eBay Inc.

Inventor： Farah Abdallah ,  Robert Enyedi ,  Amit Srivastava ,  Elaine Lee ,  Braddock Craig Gaskill ,  Tomer Lancewicki ,  Xinyu Zhang ,  Jayanth Vasudevan ,  Dominique Jean Bouchon

IPC: G06N3/006 ,  G06F16/248 ,  G06F16/50 ,  G06F16/9032 ,  G06F40/30 ,  G06N20/00 ,  G06Q10/10 ,  G06Q30/0251 ,  G06Q30/0601

CPC classification number: G06N3/006 ,  G06F16/248 ,  G06F16/50 ,  G06F16/90332 ,  G06F40/30 ,  G06N20/00 ,  G06Q10/10 ,  G06Q30/0256 ,  G06Q30/0601 ,  G06Q30/0625

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data is then received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.

公开(公告)号：US11144811B2

公开(公告)日：2021-10-12

申请号：US15859239

申请日：2017-12-29

Applicant: eBay Inc.

Inventor： Farah Abdallah ,  Robert Enyedi ,  Amit Srivastava ,  Elaine Lee ,  Braddock Craig Gaskill ,  Tomer Lancewicki ,  Xinyu Zhang ,  Jayanth Vasudevan ,  Dominique Jean Bouchon

IPC: G06F3/048 ,  G06N3/00 ,  G06F16/50 ,  G06Q30/06 ,  G06Q30/02 ,  G06F16/9032 ,  G06Q10/10 ,  G06F40/30 ,  G06N20/00 ,  G06F16/248

Abstract: Aspect pre-selection techniques using machine learning are described. In one example, an artificial assistant system is configured to implement a chat bot. A user then engages in a first natural-language conversation. As part of this first natural-language conversation, a communication is generated by the chat bot to prompt the user to specify an aspect of a category that is a subject of a first natural-language conversation and user data is received in response. Data that describes this first natural-language conversation is used to train a model using machine learning. Data, is then be received by the chat bot as part of a second natural-language conversation. This data, from the second natural-language conversation, is processed using the model as part of machine learning to generate the second search query to include the aspect of the category automatically and without user intervention.