Patents by Inventor Robert Enyedi
Robert Enyedi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240095490Abstract: 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.Type: ApplicationFiled: November 29, 2023Publication date: March 21, 2024Applicant: eBay Inc.Inventors: Farah Abdallah, Robert Enyedi, Amit Srivastava, Elaine Lee, Braddock Craig Gaskill, Tomer Lancewicki, Xinyu Zhang, Jayanth Vasudevan, Dominique Jean Bouchon
-
Patent number: 11875241Abstract: 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.Type: GrantFiled: August 31, 2021Date of Patent: January 16, 2024Assignee: eBay Inc.Inventors: Farah Abdallah, Robert Enyedi, Amit Srivastava, Elaine Lee, Braddock Craig Gaskill, Tomer Lancewicki, Xinyu Zhang, Jayanth Vasudevan, Dominique Jean Bouchon
-
Patent number: 11545134Abstract: Techniques for the generation of dubbed audio for an audio/video are described.Type: GrantFiled: December 10, 2019Date of Patent: January 3, 2023Assignee: Amazon Technologies, Inc.Inventors: Marcello Federico, Robert Enyedi, Yaser Al-Onaizan, Roberto Barra-Chicote, Andrew Paul Breen, Ritwik Giri, Mehmet Umut Isik, Arvindh Krishnaswamy, Hassan Sawaf
-
Publication number: 20210390365Abstract: 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.Type: ApplicationFiled: August 31, 2021Publication date: December 16, 2021Applicant: eBay Inc.Inventors: Farah Abdallah, Robert Enyedi, Amit Srivastava, Elaine Lee, Braddock Craig Gaskill, Tomer Lancewicki, Xinyu Zhang, Jayanth Vasudevan, Dominique Jean Bouchon
-
Patent number: 11144811Abstract: 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.Type: GrantFiled: December 29, 2017Date of Patent: October 12, 2021Assignee: eBay Inc.Inventors: Farah Abdallah, Robert Enyedi, Amit Srivastava, Elaine Lee, Braddock Craig Gaskill, Tomer Lancewicki, Xinyu Zhang, Jayanth Vasudevan, Dominique Jean Bouchon
-
Publication number: 20190156177Abstract: 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.Type: ApplicationFiled: December 29, 2017Publication date: May 23, 2019Applicant: eBay Inc.Inventors: Farah Abdallah, Robert Enyedi, Amit Srivastava, Elaine Lee, Braddock Craig Gaskill, Tomer Lancewicki, Xinyu Zhang, Jayanth Vasudevan, Dominique Jean Bouchon
-
Publication number: 20120221404Abstract: An approach is provided for providing an advertising platform. The advertising platform determines an initiation of a location-based search at a device, and one or more results of the location-based search. The one or more results include at least one listing for at least one merchant. The advertising platform then processes and/or facilitates a processing of the one or more results to determine one or more advertisements associated with the at least one merchant for presentation at the device. The advertising platform then causes, at least in part, tracking of user interaction information in response to the presentation of the one or more advertisements.Type: ApplicationFiled: March 28, 2011Publication date: August 30, 2012Applicant: Nokia CorporationInventors: Zahid N. Ahmed, Catalin Horatiu Roman, Mihai-Robert Enyedi, Laurent Chollat