Patents by Inventor Jacques-Olivier Goussard
Jacques-Olivier Goussard 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: 20240133712Abstract: A method includes storing, in computer memory, a tessellation comprising a plurality of tiles corresponding to a plurality of geographical regions. The plurality of tiles are stored with travel times in a plurality of transportation modalities across a plurality of edges of the plurality of tiles. The method also includes storing, in the computer memory, associations between a plurality of points of interest and corresponding tiles of the plurality of tiles based on locations of the plurality of points of interests relative to the plurality of geographic regions, determining, by one or more processors, a first set of the plurality of tiles reachable from a first tile of the plurality of tiles in up to a first total travel time based on the travel times across the plurality of edges, and identifying, by the one or more processors, a first set of the plurality of points of interest associated with the first set of the plurality of tiles.Type: ApplicationFiled: October 23, 2022Publication date: April 25, 2024Applicant: Expedia, Inc.Inventors: Jacques-Olivier Goussard, Mahamane Kanoute, Herve Hacot, Jean-Louis Miglietti, Guillaume Fouquereau
-
Patent number: 10388278Abstract: In accordance with aspects of the disclosure, a computing device may identify a prompt associated with an automated dialog application. An application expectation of the automated dialog application may be identified. The application expectation may comprise a structured natural language representation for a natural language response to the prompt. The computing device may receive natural language input responsive to the prompt, populate one or more data fields of the structured natural language representation with at least a portion of the natural language input, and may respond to the application expectation using the one or more data fields of the structured natural language representation.Type: GrantFiled: February 13, 2017Date of Patent: August 20, 2019Assignee: Nuance Communications, Inc.Inventors: Jacques-Olivier Goussard, Richard Beaufort
-
Patent number: 9767794Abstract: Methods and systems for managing multiple tasks using a dialog are presented. In some embodiments, a processor may parse a first natural language user input received at a user device to extract task related information from the first natural language user input. In response to identifying that the first natural language user input comprises a request to perform a first task, the processor may initiate execution of the first task. The user device may receive a second natural language user input after execution of the first task has been initiated which requests execution of a second task. The processor may initiate execution of the second task before execution of the first task is complete.Type: GrantFiled: August 11, 2014Date of Patent: September 19, 2017Assignee: Nuance Communications, Inc.Inventors: Mitchell Vibbert, Jacques-Olivier Goussard, Richard J. Beaufort, Benjamin P. Monnahan
-
Publication number: 20170154621Abstract: In accordance with aspects of the disclosure, a computing device may identify a prompt associated with an automated dialog application. An application expectation of the automated dialog application may be identified. The application expectation may comprise a structured natural language representation for a natural language response to the prompt. The computing device may receive natural language input responsive to the prompt, populate one or more data fields of the structured natural language representation with at least a portion of the natural language input, and may respond to the application expectation using the one or more data fields of the structured natural language representation.Type: ApplicationFiled: February 13, 2017Publication date: June 1, 2017Inventors: Jacques-Olivier Goussard, Richard Beaufort
-
Patent number: 9666185Abstract: Methods and systems for providing help prompts to a user of an automated dialog system are presented. In some embodiments, a computing device may receive a help request from the user of an automated dialog system. The help request may comprise a user request for information about one or more capabilities of the automated dialog system. The computing device may identify information expected to be input by the user to request that the automated dialog system perform its one or more capabilities. A natural language help prompt may be generated to provide guidance to the user to provide the identified information expected to be input.Type: GrantFiled: October 6, 2014Date of Patent: May 30, 2017Assignee: Nuance Communications, Inc.Inventors: Jacques-Olivier Goussard, Richard J. Beaufort
-
Patent number: 9607102Abstract: Disclosed methods and systems are directed to task switching in dialog processing. The methods and systems may include activating a primary task, receiving, one or more ambiguous natural language commands, and identifying a first candidate task for each of the one or more ambiguous natural language commands. The methods and system may also include identifying, for each of the one or more ambiguous natural language commands and based on one or more rules, a second candidate task of the plurality of tasks corresponding to the ambiguous natural language command, determining whether to modify at least one of the one or more rules-based task switching rules based on whether a quality metric satisfies a threshold quantity, and when the second quality metric satisfies the threshold quantity, changing the task switching rule for the corresponding candidate task from a rules-based model to the optimized statistical based task switching model.Type: GrantFiled: September 5, 2014Date of Patent: March 28, 2017Assignee: Nuance Communications, Inc.Inventors: Jean-Francois Lavallee, Jacques-Olivier Goussard, Richard Beaufort
-
Patent number: 9606985Abstract: In accordance with aspects of the disclosure, a computing device may identify a prompt associated with an automated dialog application. An application expectation of the automated dialog application may be identified. The application expectation may comprise a structured natural language representation for a natural language response to the prompt. The computing device may receive natural language input responsive to the prompt, populate one or more data fields of the structured natural language representation with at least a portion of the natural language input, and may respond to the application expectation using the one or more data fields of the structured natural language representation.Type: GrantFiled: June 13, 2014Date of Patent: March 28, 2017Assignee: Nuance Communications, Inc.Inventors: Jacques-Olivier Goussard, Richard J. Beaufort
-
Patent number: 9373322Abstract: A method for training a system is provided. The method may include storing one or more backend communication logs, each of the one or more backend communication logs including a user query and a corresponding backend query. The method may further include parsing the one or more backend communication logs to extract statistical information and generating a mapping between each user query and a corresponding set of language tags. The method may also include sorting the one or more backend communication logs based upon, at least in part, the extracted statistical information.Type: GrantFiled: April 10, 2013Date of Patent: June 21, 2016Assignee: Nuance Communications, Inc.Inventor: Jacques-Olivier Goussard
-
Publication number: 20160098988Abstract: Methods and systems for providing help prompts to a user of an automated dialog system are presented. In some embodiments, a computing device may receive a help request from the user of an automated dialog system. The help request may comprise a user request for information about one or more capabilities of the automated dialog system. The computing device may identify information expected to be input by the user to request that the automated dialog system perform its one or more capabilities. A natural language help prompt may be generated to provide guidance to the user to provide the identified information expected to be input.Type: ApplicationFiled: October 6, 2014Publication date: April 7, 2016Inventors: Jacques-Olivier Goussard, Richard J. Beaufort
-
Publication number: 20160070696Abstract: Disclosed methods and systems are directed to task switching in dialogue processing. The methods and systems may include activating a primary task, receiving, one or more ambiguous natural language commands, and identifying a first candidate task for each of the one or more ambiguous natural language commands. The methods and system may also include identifying, for each of the one or more ambiguous natural language commands and based on one or more rules, a second candidate task of the plurality of tasks corresponding to the ambiguous natural language command, determining whether to modify at least one of the one or more rules-based task switching rules based on whether a quality metric satisfies a threshold quantity, and when the second quality metric satisfies the threshold quantity, changing the task switching rule for the corresponding candidate task from a rules-based model to the optimized statistical based task switching model.Type: ApplicationFiled: September 5, 2014Publication date: March 10, 2016Inventors: Jean-Francois Lavallee, Jacques-Olivier Goussard, Richard Beaufort
-
Publication number: 20160042735Abstract: Methods and systems for managing multiple tasks using a dialog are presented. In some embodiments, a processor may parse a first natural language user input received at a user device to extract task related information from the first natural language user input. In response to identifying that the first natural language user input comprises a request to perform a first task, the processor may initiate execution of the first task. The user device may receive a second natural language user input after execution of the first task has been initiated which requests execution of a second task. The processor may initiate execution of the second task before execution of the first task is complete.Type: ApplicationFiled: August 11, 2014Publication date: February 11, 2016Inventors: Mitchell Vibbert, Jacques-Olivier Goussard, Richard J. Beaufort, Benjamin P. Monnahan
-
Publication number: 20160026608Abstract: Designing a dialog application is a difficult task that typically requires a complete understanding of the dialog framework and a high level of expertise to map system requirements to the actual implementations. In contrast, determining the logic of the dialog application via sample interaction is typically very simple and efficient. A developer can describe via speech or text what the operations of the application are, effectively writing dialog samples. Methods described herein reverse the way dialog applications are designed by obtaining annotated dialog samples and defined concepts related to a requested dialog application; analyzing the annotated dialog samples, defined concepts, and one or more relationships between or among the defined concepts; and generating an executable dialog application based on the analysis of the annotated dialog samples and the defined concepts.Type: ApplicationFiled: July 22, 2014Publication date: January 28, 2016Inventors: Jan Curin, Jacques-Olivier Goussard, Real Tremblay, Richard J. Beaufort, Jan Kleindienst, Jiri Havelka, Raimo Bakis
-
Publication number: 20150364132Abstract: In accordance with aspects of the disclosure, a computing device may identify a prompt associated with an automated dialog application. An application expectation of the automated dialog application may be identified. The application expectation may comprise a structured natural language representation for a natural language response to the prompt. The computing device may receive natural language input responsive to the prompt, populate one or more data fields of the structured natural language representation with at least a portion of the natural language input, and may respond to the application expectation using the one or more data fields of the structured natural language representation.Type: ApplicationFiled: June 13, 2014Publication date: December 17, 2015Inventors: Jacques-Olivier Goussard, Richard J. Beaufort
-
Publication number: 20140309993Abstract: A method for training a system is provided. The method may include storing one or more backend communication logs, each of the one or more backend communication logs including a user query and a corresponding backend query. The method may further include parsing the one or more backend communication logs to extract statistical information and generating a mapping between each user query and a corresponding set of language tags. The method may also include sorting the one or more backend communication logs based upon, at least in part, the extracted statistical information.Type: ApplicationFiled: April 10, 2013Publication date: October 16, 2014Applicant: Nuance Communications, Inc.Inventor: Jacques-Olivier Goussard