Patents by Inventor Carlos Fernández Musoles
Carlos Fernández Musoles 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: 20240079000Abstract: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.Type: ApplicationFiled: September 12, 2023Publication date: March 7, 2024Inventors: Carlos Fernández Musoles, Unai Garay Maestre, Walter Bender
-
Publication number: 20240005910Abstract: Provided is a process including obtaining a set of natural-language text documents that discuss a topic, the set of documents containing different states of knowledge about the topic at different times. The process includes selecting an ontology from among a plurality of ontologies that correspond to different domains of knowledge, the selection being based on the ontology corresponding to a domain of knowledge including the topic. The process includes identifying concepts discussed in the documents using the ontology and detecting changes in at least some of the concepts over time based on differences between discussion of the concepts in documents authored at different times. The process includes updating natural language instructions on the topic based on the detected changes in the concepts and storing the updated natural language instructions in memory.Type: ApplicationFiled: April 19, 2023Publication date: January 4, 2024Inventors: Adam Tomkins, Walter Bender, Carlos Fernández Musoles
-
Patent number: 11790889Abstract: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.Type: GrantFiled: March 23, 2021Date of Patent: October 17, 2023Assignee: Sorcero, Inc.Inventors: Carlos Fernández Musoles, Unai Garay Maestre, Walter Bender
-
Patent number: 11699432Abstract: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.Type: GrantFiled: September 15, 2021Date of Patent: July 11, 2023Assignee: Sorcero, Inc.Inventors: Walter Bender, Unai Garay Maestre, Carlos Fernandez Musoles, Adam Tomkins
-
Patent number: 11636847Abstract: A process including obtaining a set of natural-language text documents that discuss a topic, the set of documents containing different states of knowledge about the topic at different times. The process includes selecting an ontology from among a plurality of ontologies that correspond to different domains of knowledge, the selection being based on the ontology corresponding to a domain of knowledge including the topic. The process includes identifying concepts discussed in the documents using the ontology and detecting changes in at least some of the concepts over time based on differences between discussion of the concepts in documents authored at different times. The process includes updating natural language instructions on the topic based on the detected changes in the concepts and storing the updated natural language instructions in memory.Type: GrantFiled: March 23, 2021Date of Patent: April 25, 2023Assignee: Sorcero, Inc.Inventors: Adam Tomkins, Walter Bender, Carlos Fernández Musoles
-
Patent number: 11557276Abstract: A method includes obtaining parameters and a document, determining a domain based on the parameters, where the domain maps to a first ontology, and where ontologies map n-grams onto a set of concepts. The method includes scoring a first set of n-grams of the document using a scoring model based on relations between members of the first set of n-grams, selecting sections of the text based on n-gram scores provided by the scoring model, and determining an initial n-gram set, where each respective n-gram of the initial n-gram set maps to a respective concept of the set of concepts, and where each respective n-gram is identified by an ontology other than the first ontology. The method includes determining related n-grams mapped to the set of concepts associated with the domain and generating a text summary for the document based on the sections and the related n-grams.Type: GrantFiled: March 23, 2021Date of Patent: January 17, 2023Assignee: Sorcero, Inc.Inventors: Walter Bender, Unai Garay Maestre, Carlos Fernández Musoles, Adam Tomkins
-
Publication number: 20220005463Abstract: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.Type: ApplicationFiled: September 15, 2021Publication date: January 6, 2022Inventors: Walter Bender, Unai Garay Maestre, Carlos Fernandez Musoles, Adam Tomkins
-
Patent number: 11151982Abstract: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.Type: GrantFiled: March 23, 2021Date of Patent: October 19, 2021Assignee: Sorcero, Inc.Inventors: Adam Tomkins, Walter Bender, Carlos Fernández Musoles, Richard Graves, Dipanwita Das
-
Publication number: 20210294781Abstract: Provided is a computer-implemented process including obtaining a corpus of natural-language text documents, automatically generating questions about information in corresponding portions of the documents, and associating the questions with the corresponding portions of the documents. The process further includes storing the questions and the associations with the corresponding portions of the documents in memory to form an index of automatically-generated questions to corresponding portions of documents that answer the questions.Type: ApplicationFiled: March 23, 2021Publication date: September 23, 2021Inventors: Carlos Fernández Musoles, Unai Garay Maestre, Walter Bender
-
Publication number: 20210295822Abstract: Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.Type: ApplicationFiled: March 23, 2021Publication date: September 23, 2021Inventors: Adam Tomkins, Walter Bender, Carlos Fernández Musoles, Richard Graves, Dipanwita Das
-
Publication number: 20210294829Abstract: Provided is a method including obtaining parameters and a document, determining a domain based on the parameters, where the domain maps to a first ontology, and where ontologies map n-grams onto a set of concepts. The method includes scoring a first set of n-grams of the document using a scoring model based on relations between members of the first set of n-grams, selecting sections of the text based on n-gram scores provided by the scoring model, and determining an initial n-gram set, where each respective n-gram of the initial n-gram set maps to a respective concept of the set of concepts, and where each respective n-gram is identified by an ontology other than the first ontology. The method includes determining related n-grams mapped to the set of concepts associated with the domain and generating a text summary for the document based on the sections and the related n-grams.Type: ApplicationFiled: March 23, 2021Publication date: September 23, 2021Inventors: Walter Bender, Unai Garay Maestre, Carlos Fernández Musoles, Adam Tomkins
-
Publication number: 20210294828Abstract: Provided is a process including obtaining a set of natural-language text documents that discuss a topic, the set of documents containing different states of knowledge about the topic at different times. The process includes selecting an ontology from among a plurality of ontologies that correspond to different domains of knowledge, the selection being based on the ontology corresponding to a domain of knowledge including the topic. The process includes identifying concepts discussed in the documents using the ontology and detecting changes in at least some of the concepts over time based on differences between discussion of the concepts in documents authored at different times. The process includes updating natural language instructions on the topic based on the detected changes in the concepts and storing the updated natural language instructions in memory.Type: ApplicationFiled: March 23, 2021Publication date: September 23, 2021Inventors: Adam Tomkins, Walter Bender, Carlos Fernández Musoles