Patents by Inventor Mugurel Ionut Andreica
Mugurel Ionut Andreica 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: 20240185857Abstract: Implementations set forth herein relate to a system that employs an automated assistant to further interactions between a user and another application, which can provide the automated assistant with permission to initialize relevant application actions simultaneous to the user interacting with the other application. Furthermore, the system can allow the automated assistant to initialize actions of different applications, despite being actively operating a particular application. Available actions can be gleaned by the automated assistant using various application-specific schemas, which can be compared with incoming requests from a user to the automated assistant. Additional data, such as context and historical interactions, can also be used to rank and identify a suitable application action to be initialized via the automated assistant.Type: ApplicationFiled: February 12, 2024Publication date: June 6, 2024Inventors: Denis Burakov, Behshad Behzadi, Mario Bertschlewr, Bohdan Vlasyuk, Daniel Cotting, Michael Golikov, Lucas Mirelmann, Steve Cheng, Sergey Nazarov, Zaheed Sabur, Marcin Nowak-Przygodzki, Mugurel Ionut Andreica, Radu Voroneanu
-
Patent number: 11971936Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to extract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website.Type: GrantFiled: October 26, 2022Date of Patent: April 30, 2024Assignee: GOOGLE LLCInventors: Gökhan Bakir, Andre Elisseeff, Torsten Marek, João Paulo Pagaime da Silva, Mathias Carlen, Dana Ritter, Lukasz Suder, Ernest Galbrun, Matthew Stokes, Marcin Nowak-Przygodzki, Mugurel-Ionut Andreica, Marius Dumitran
-
Publication number: 20240070217Abstract: A computer-implemented method is described. The method includes a computing system receiving a first voice input from a user for generating a bookmark. Responsive to receiving the voice input, the computing system obtains a resource identifier associated with a resource page. The method includes the computing system storing the resource identifier as a bookmark in a bookmark index that is accessible in response to a request from a user device. The method further includes the computing system using the resource identifier, stored as the bookmark, to access the resource page. The computing system uses the resource identifier to access the resource page based on the request from the user device. The request is generated by the user device in response to the user device receiving a second voice input from the user.Type: ApplicationFiled: November 7, 2023Publication date: February 29, 2024Inventors: Mugurel Ionut Andreica, Gokhan H. Bakir, Tak Keung Cheng, Marcin M. Nowak-Przygodzki
-
Patent number: 11900944Abstract: Implementations set forth herein relate to a system that employs an automated assistant to further interactions between a user and another application, which can provide the automated assistant with permission to initialize relevant application actions simultaneous to the user interacting with the other application. Furthermore, the system can allow the automated assistant to initialize actions of different applications, despite being actively operating a particular application. Available actions can be gleaned by the automated assistant using various application-specific schemas, which can be compared with incoming requests from a user to the automated assistant. Additional data, such as context and historical interactions, can also be used to rank and identify a suitable application action to be initialized via the automated assistant.Type: GrantFiled: January 31, 2022Date of Patent: February 13, 2024Assignee: GOOGLE LLCInventors: Denis Burakov, Behshad Behzadi, Mario Bertschler, Bohdan Vlasyuk, Daniel Cotting, Michael Golikov, Lucas Mirelmann, Steve Cheng, Sergey Nazarov, Zaheed Sabur, Marcin Nowak-Przygodzki, Mugurel Ionut Andreica, Radu Voroneanu
-
Patent number: 11829433Abstract: A computer-implemented method is described. The method includes a computing system receiving a first voice input from a user for generating a bookmark. Responsive to receiving the voice input, the computing system obtains a resource identifier associated with a resource page. The method includes the computing system storing the resource identifier as a bookmark in a bookmark index that is accessible in response to a request from a user device. The method further includes the computing system using the resource identifier, stored as the bookmark, to access the resource page. The computing system uses the resource identifier to access the resource page based on the request from the user device. The request is generated by the user device in response to the user device receiving a second voice input from the user.Type: GrantFiled: August 19, 2022Date of Patent: November 28, 2023Assignee: GOOGLE LLCInventors: Mugurel Ionut Andreica, Gokhan H. Bakir, Tak Keung Cheng, Marcin M. Nowak-Przygodzki
-
Publication number: 20230377572Abstract: Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.Type: ApplicationFiled: August 7, 2023Publication date: November 23, 2023Inventors: Mugurel-Ionut Andreica, Vladimir Vuskovic, Joseph Lange, Sharon Stovezky, Marcin Nowak-Przygodzki
-
Patent number: 11769502Abstract: Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.Type: GrantFiled: June 4, 2021Date of Patent: September 26, 2023Assignee: GOOGLE LLCInventors: Mugurel Ionut Andreica, Vladimir Vuskovic, Joseph Lange, Sharon Stovezky, Marcin Nowak-Przygodzki
-
Publication number: 20230274737Abstract: The present disclosure is directed to automating user interactions in an application. In particular, the computing device can determine, based on the input data, an intent associated with performing an action on the computing device. Additionally, the computing device can invoke, using an application-level assistant component configured to provide an application-level interface on the computing device, execution of an application. Moreover, the computing device can transmit, to a system-level assistant component configured to provide a system-level interface with the computing device, instructions to interface with an actionable component of the application. The instructions can be transmitted using a trusted intermediary component configured to facilitate an interface between the system-level assistant component and the application-level assistant component.Type: ApplicationFiled: May 31, 2022Publication date: August 31, 2023Inventors: Keun Soo Yim, Ilya Firman, Adam Miller Coimbra, Robert James Berry, Mugurel Ionut Andreica, Mikhail Reutov, Gabriel Oak Taubman, Cliff Shan Kuang, Michael Oh, Svetoslav Radoslavov Ganov, Kalyana Ram Desineni
-
Publication number: 20230169102Abstract: Implementations are directed to determining, based on a submitted query that is a compound query, that a set of multiple sub-queries are collectively an appropriate interpretation of the compound query. Those implementations are further directed to providing, in response to such a determination, a corresponding command for each of the sub-queries of the determined set. Each of the commands is to a corresponding agent (of one or more agents), and causes the agent to generate and provide corresponding responsive content. Those implementations are further directed to causing content to be rendered in response to the submitted query, where the content is based on the corresponding responsive content received in response to the commands.Type: ApplicationFiled: January 30, 2023Publication date: June 1, 2023Inventors: Joseph Lange, Mugurel Ionut Andreica, Marcin Nowak-Przygodzki
-
Publication number: 20230169134Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a first input associated with a bookmark and, in response to receiving the first input, obtaining context data for deriving annotations for the bookmark. An annotation engine of a system obtains multiple annotations that are derived using information included in the context data and a transcription of the first input associated with the bookmark. The annotation engine generates an importance value for each annotation. The importance value characterizes a relationship between each annotation and at least one of: the information included in the context data; or the transcription of the first input. The annotation engine generates a set of annotations for retrieving the bookmark. Each annotation in the set of annotations is generated from the obtained multiple annotations and each annotation has an importance value that exceeds a threshold value.Type: ApplicationFiled: January 26, 2023Publication date: June 1, 2023Inventors: Mugurel-Ionut Andreica, Jonathan Small, Marcin M. Nowak-Przygodzki
-
Publication number: 20230050054Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website.Type: ApplicationFiled: October 26, 2022Publication date: February 16, 2023Inventors: Gökhan Bakir, Andre Elisseeff, Torsten Marek, João Paulo Pagaime da Silva, Mathias Carlen, Dana Ritter, Lukasz Suder, Ernest Galbrun, Matthew Stokes, Marcin Nowak-Przygodzki, Mugurel-Ionut Andreica, Marius Dumitran
-
Patent number: 11574028Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a first input associated with a bookmark and, in response to receiving the first input, obtaining context data for deriving annotations for the bookmark. An annotation engine of a system obtains multiple annotations that are derived using information included in the context data and a transcription of the first input associated with the bookmark. The annotation engine generates an importance value for each annotation. The importance value characterizes a relationship between each annotation and at least one of: the information included in the context data; or the transcription of the first input. The annotation engine generates a set of annotations for retrieving the bookmark. Each annotation in the set of annotations is generated from the obtained multiple annotations and each annotation has an importance value that exceeds a threshold value.Type: GrantFiled: April 16, 2019Date of Patent: February 7, 2023Assignee: GOOGLE LLCInventors: Mugurel Ionut Andreica, Jonathan Small, Marcin M. Nowak-Przygodzki
-
Patent number: 11567980Abstract: Implementations are directed to determining, based on a submitted query that is a compound query, that a set of multiple sub-queries are collectively an appropriate interpretation of the compound query. Those implementations are further directed to providing, in response to such a determination, a corresponding command for each of the sub-queries of the determined set. Each of the commands is to a corresponding agent (of one or more agents), and causes the agent to generate and provide corresponding responsive content. Those implementations are further directed to causing content to be rendered in response to the submitted query, where the content is based on the corresponding responsive content received in response to the commands.Type: GrantFiled: May 7, 2018Date of Patent: January 31, 2023Assignee: GOOGLE LLCInventors: Joseph Lange, Mugurel Ionut Andreica, Marcin Nowak-Przygodzki
-
Publication number: 20220391466Abstract: A computer-implemented method is described. The method includes a computing system receiving a first voice input from a user for generating a bookmark. Responsive to receiving the voice input, the computing system obtains a resource identifier associated with a resource page. The method includes the computing system storing the resource identifier as a bookmark in a bookmark index that is accessible in response to a request from a user device. The method further includes the computing system using the resource identifier, stored as the bookmark, to access the resource page. The computing system uses the resource identifier to access the resource page based on the request from the user device. The request is generated by the user device in response to the user device receiving a second voice input from the user.Type: ApplicationFiled: August 19, 2022Publication date: December 8, 2022Inventors: Mugurel Ionut Andreica, Gokhan H. Bakir, Tak Keung Cheng, Marcin M. Nowak-Przygodzki
-
Patent number: 11487832Abstract: Implementations are described herein for analyzing existing interactive web sites to facilitate automatic engagement with those web sites, e.g., by automated assistants or via other user interfaces, with minimal effort from the hosts of those websites. For example, in various implementations, techniques described herein may be used to abstract, validate, maintain, generalize, extend and/or distribute individual actions and “traces” of actions that are useable to navigate through various interactive websites. Additionally, techniques are described herein for leveraging these actions and/or traces to automate aspects of interaction with a third party website.Type: GrantFiled: May 9, 2019Date of Patent: November 1, 2022Assignee: GOOGLE LLCInventors: Gökhan Bakir, Andre Elisseeff, Torsten Marek, João Paulo Pagaime da Silva, Mathias Carlen, Dana Ritter, Lukasz Suder, Ernest Galbrun, Matthew Stokes, Marcin Nowak-Przygodzki, Mugurel-Ionut Andreica, Marius Dumitran
-
Patent number: 11423113Abstract: A computer-implemented method is described. The method includes a computing system receiving a first voice input from a user for generating a bookmark. Responsive to receiving the voice input, the computing system obtains a resource identifier associated with a resource page. The method includes the computing system storing the resource identifier as a bookmark in a bookmark index that is accessible in response to a request from a user device. The method further includes the computing system using the resource identifier, stored as the bookmark, to access the resource page. The computing system uses the resource identifier to access the resource page based on the request from the user device. The request is generated by the user device in response to the user device receiving a second voice input from the user.Type: GrantFiled: October 19, 2020Date of Patent: August 23, 2022Assignee: GOOGLE LLCInventors: Mugurel Ionut Andreica, Gokhan H. Bakir, Tak Keung Cheng, Marcin M. Nowak-Przygodzki
-
Publication number: 20220157317Abstract: Implementations set forth herein relate to a system that employs an automated assistant to further interactions between a user and another application, which can provide the automated assistant with permission to initialize relevant application actions simultaneous to the user interacting with the other application. Furthermore, the system can allow the automated assistant to initialize actions of different applications, despite being actively operating a particular application. Available actions can be gleaned by the automated assistant using various application-specific schemas, which can be compared with incoming requests from a user to the automated assistant. Additional data, such as context and historical interactions, can also be used to rank and identify a suitable application action to be initialized via the automated assistant.Type: ApplicationFiled: January 31, 2022Publication date: May 19, 2022Inventors: Denis Burakov, Behshad Behzadi, Mario Bertschler, Bohdan Vlasyuk, Daniel Cotting, Michael Golikov, Lucas Mirelmann, Steve Cheng, Sergey NAZAROV, Zaheed Sabur, Marcin Nowak-Przygodzki, Mugurel Ionut Andreica, Radu Voroneanu
-
Patent number: 11238868Abstract: Implementations set forth herein relate to a system that employs an automated assistant to further interactions between a user and another application, which can provide the automated assistant with permission to initialize relevant application actions simultaneous to the user interacting with the other application. Furthermore, the system can allow the automated assistant to initialize actions of different applications, despite being actively operating a particular application. Available actions can be gleaned by the automated assistant using various application-specific schemas, which can be compared with incoming requests from a user to the automated assistant. Additional data, such as context and historical interactions, can also be used to rank and identify a suitable application action to be initialized via the automated assistant.Type: GrantFiled: June 13, 2019Date of Patent: February 1, 2022Assignee: Google LLCInventors: Denis Burakov, Behshad Behzadi, Mario Bertschler, Bohdan Vlasyuk, Daniel Cotting, Michael Golikov, Lucas Mirelmann, Steve Cheng, Sergey Nazarov, Zaheed Sabur, Marcin Nowak-Przygodzki, Mugurel Ionut Andreica, Radu Voroneanu
-
Publication number: 20210295841Abstract: Implementations are set forth herein for creating an order of execution for actions that were requested by a user, via a spoken utterance to an automated assistant. The order of execution for the requested actions can be based on how each requested action can, or is predicted to, affect other requested actions. In some implementations, an order of execution for a series of actions can be determined based on an output of a machine learning model, such as a model that has been trained according to supervised learning. A particular order of execution can be selected to mitigate waste of processing, memory, and network resources—at least relative to other possible orders of execution. Using interaction data that characterizes past performances of automated assistants, certain orders of execution can be adapted over time, thereby allowing the automated assistant to learn from past interactions with one or more users.Type: ApplicationFiled: June 4, 2021Publication date: September 23, 2021Inventors: Mugurel Ionut Andreica, Vladimir Vuskovic, Joseph Lange, Sharon Stovezky, Marcin Nowak-Przygodzki
-
Publication number: 20210240793Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a first input associated with a bookmark and, in response to receiving the first input, obtaining context data for deriving annotations for the bookmark. An annotation engine of a system obtains multiple annotations that are derived using information included in the context data and a transcription of the first input associated with the bookmark The annotation engine generates an importance value for each annotation. The importance value characterizes a relationship between each annotation and at least one of: the information included in the context data; or the transcription of the first input. The annotation engine generates a set of annotations for retrieving the bookmark. Each annotation in the set of annotations is generated from the obtained multiple annotations and each annotation has an importance value that exceeds a threshold value.Type: ApplicationFiled: April 16, 2019Publication date: August 5, 2021Inventors: Mugurel Ionut Andreica, Jonathan Small, Marcin M. Nowak-Przygodzki