Patents by Inventor Michelle Gregory
Michelle Gregory 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).
-
Patent number: 11550835Abstract: A method of automatically generating content summaries for topics includes receiving a taxonomy for a concept and a text corpus. The method further includes generating an annotated dataset having term annotations corresponding to the concept from the text corpus based on the taxonomy, parsing the annotated dataset into a custom generated document object having a structured layout, determining features for the term annotations, and extracting snippets from the custom generated document object, where each of the snippets corresponds to a section of the custom generated document object. The method further includes scoring the snippets based on the features such that each of the snippets corresponds to a score, filtering one or more snippets from the snippets when one or more snippet filtering conditions is met, ranking the snippets into an ordered list for the concept based on the score, and providing, to a user computing device, the ordered list.Type: GrantFiled: June 15, 2018Date of Patent: January 10, 2023Assignee: ELSEVIER, INC.Inventors: Marius Doornenbal, Srinivasa Satya Sameer Kumar Chivukula, Judson Dunham, Rick Misra, Michelle Gregory
-
Publication number: 20210069362Abstract: A sanitization device may include a sanitization compartment including an ozone outlet, a connector defining a fluid pathway that is fluidly coupled to the sanitization compartment, an ozone operating system having an ozone generator configured to generate ozone and a distribution fan configured to urge ozone generated by the ozone generator through the fluid pathway of the connector and into the sanitization compartment, a filter access door transitionable between an open position and a closed position, the filter access door including a filter holder configured to receive a filter such that the filter fluidly couples to the ozone outlet when the filter access door is in the closed position, the filter is configured to reduce ozone passing therethrough to oxygen and the filter is downstream of the connector, and an exhaust fan fluidly coupled to the ozone outlet and configured to urge ozone through the filter.Type: ApplicationFiled: September 4, 2020Publication date: March 11, 2021Applicant: SOCLEAN, INC.Inventors: Michelle Gregory, Matthew McCambridge, Julianna Miller, Mike Le, Kurt MAW, Ashley James Nye LEGG, Robert WILKINS, Robert A. CHARLES, Alex CHAVES, Gregory Randall LANIER, JR.
-
Patent number: 10740560Abstract: Systems and methods of extracting funding information from text are disclosed herein. The method includes receiving a text document, extracting paragraphs from the text document using a natural language processing model or a machine learning model, and classifying, using a machine learning classifier, the paragraphs as having funding information or not having funding information. The method further includes labeling, using a first annotator, potential entities within the paragraphs classified as having funding information, and labeling, using a second annotator, potential entities within the paragraphs classified as having funding information, where the first annotator implements a first named-entity recognition model and the second annotator implements a second named-entity recognition model that is different from the first named-entity recognition model.Type: GrantFiled: June 27, 2018Date of Patent: August 11, 2020Assignee: Elsevier, Inc.Inventors: Michelle Gregory, Subhradeep Kayal, Georgios Tsatsaronis, Zubair Afzal
-
Publication number: 20190005020Abstract: Systems and methods of extracting funding information from text are disclosed herein. The method includes receiving a text document, extracting paragraphs from the text document using a natural language processing model or a machine learning model, and classifying, using a machine learning classifier, the paragraphs as having funding information or not having funding information. The method further includes labeling, using a first annotator, potential entities within the paragraphs classified as having funding information, and labeling, using a second annotator, potential entities within the paragraphs classified as having funding information, where the first annotator implements a first named-entity recognition model and the second annotator implements a second named-entity recognition model that is different from the first named-entity recognition model.Type: ApplicationFiled: June 27, 2018Publication date: January 3, 2019Applicant: Elsevier, Inc.Inventors: Michelle Gregory, Subhradeep Kayal, Georgios Tsatsaronis, Zubair Afzal
-
Publication number: 20180365323Abstract: A method of automatically generating content summaries for topics includes receiving a taxonomy for a concept and a text corpus. The method further includes generating an annotated dataset having term annotations corresponding to the concept from the text corpus based on the taxonomy, parsing the annotated dataset into a custom generated document object having a structured layout, determining features for the term annotations, and extracting snippets from the custom generated document object, where each of the snippets corresponds to a section of the custom generated document object. The method further includes scoring the snippets based on the features such that each of the snippets corresponds to a score, filtering one or more snippets from the snippets when one or more snippet filtering conditions is met, ranking the snippets into an ordered list for the concept based on the score, and providing, to a user computing device, the ordered list.Type: ApplicationFiled: June 15, 2018Publication date: December 20, 2018Applicant: Elsevier, Inc.Inventors: Marius Doornenbal, Srinivasa Satya Sameer Kumar Chivukula, Judson Dunham, Rick Misra, Michelle Gregory
-
Patent number: 7403901Abstract: A system, method and computer program are provided for generating error and summary reports for a data load. A plurality of records to be loaded in a database are received. The records may include medical records. A data management template corresponding to the records is chosen. It is verified that all records to be loaded match the data management template. The records are sent to a database for loading in the database upon validation that the records match the data management template. A report of records that match the data management template and records that do not match the data management template is compiled.Type: GrantFiled: April 13, 2000Date of Patent: July 22, 2008Assignee: Accenture LLPInventors: Kevin W. Carley, Lisa Marie Harrington, Jennifer Scot Dikeman, Megan Davies Moody, Mary Michelle Gregory
-
Publication number: 20070255666Abstract: Hypothesis analysis methods, hypothesis analysis devices, and articles of manufacture are described according to some aspects. In one aspect, a hypothesis analysis method includes providing a hypothesis, providing an indicator which at least one of supports and refutes the hypothesis, using the indicator, associating evidence with the hypothesis, weighting the association of the evidence with the hypothesis, and using the weighting, providing information regarding the accuracy of the hypothesis.Type: ApplicationFiled: April 28, 2006Publication date: November 1, 2007Inventors: Antonio Sanfilippo, Andrew Cowell, Michelle Gregory, Robert Baddeley, Patrick Paulson, Stephen Tratz, Ryan Hohimer
-
Publication number: 20070106493Abstract: Methods of defining ontologies, word disambiguation methods, computer systems, and articles of manufacture are described according to some aspects. In one aspect, a word disambiguation method includes accessing textual content to be disambiguated, wherein the textual content comprises a plurality of words individually comprising a plurality of word senses, for an individual word of the textual content, identifying one of the word senses of the word as indicative of the meaning of the word in the textual content, for the individual word, selecting one of a plurality of event classes of a lexical database ontology using the identified word sense of the individual word, and for the individual word, associating the selected one of the event classes with the textual content to provide disambiguation of a meaning of the individual word in the textual content.Type: ApplicationFiled: November 4, 2005Publication date: May 10, 2007Inventors: Antonio Sanfilippo, Stephen Tratz, Michelle Gregory, Alan Chappell, Paul Whitney, Christian Posse, Robert Baddeley, Ryan Hohimer
-
Patent number: 6701345Abstract: A notification when multiple users attempt to alter the same data may first begin when connections to a plurality of user stations are monitored. An instruction for initiating a load process is received from a user station. Data is downloaded from the one of the user stations to the server. It is determined whether another load process is being concurrently executed by another user station. If it is determined that a load process is being concurrently executed, a notification is sent to the user station. A notification is also sent to the user station that initiated the concurrently executing load process. At least one of the load processes is suspended upon detecting the concurrently executed load process. At least one of the load processes may be allowed to continue upon receiving a command to continue from the user station associated with the suspended load process.Type: GrantFiled: April 13, 2000Date of Patent: March 2, 2004Assignee: Accenture LLPInventors: Kevin W. Carley, Lisa Marie Harrington, Jennifer Scot Dikeman, Megan Davies Moody, Mary Michelle Gregory