Patents by Inventor George L. Williams
George L. Williams 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: 12008584Abstract: There is a need for more effective and efficient anomaly detection. This need can be addressed by, for example, solutions for performing/executing graph convolutional anomaly detection. In one example, a method includes identifying related graph database input data associated with a predictive entity; generating related graph feature data for the predictive entity; generating, based on the related graph feature data and using a graph convolutional neural network model, an anomaly detection score for the predictive entity, wherein at least a portion of the graph convolutional neural network model is trained using confirmation feedback data; performing an anomaly confirmation to generate the confirmation feedback data object for the predictive entity, and integrating the confirmation feedback data object for the predictive entity into the confirmation feedback data associated with the graph convolutional anomaly detection.Type: GrantFiled: October 3, 2022Date of Patent: June 11, 2024Assignee: OPTUM, INC.Inventors: Parker J. Erickson, Gerald Liu, Rex Shen, Devin Uner, George L Williams, Zachary Babcock, Lydia M. Narum
-
Patent number: 11969300Abstract: An implantable medical lead may include an electrode at a distal portion of the lead that is configured to monitor or provide therapy to a target site. The lead may include a visible indicator that is visible to the naked eye of a clinician at a medial portion of the lead that is configured to indicate when the electrodes of the lead are longitudinally and radially aligned properly to monitor or treat the target site. A clinician may insert the lead into the patient using an introducer sheath inserted to a predetermined depth into the patient and subsequently aligning the distal portion of the lead by orienting the indicator at an entry port of the introducer sheath.Type: GrantFiled: August 12, 2021Date of Patent: April 30, 2024Assignee: Medtronic, Inc.Inventors: George W. McFall, Thomas D. Brostrom, Mark T. Marshall, Dina L. Williams, Megan Harris, Keith D. Anderson, Maggie J. Pistella
-
Publication number: 20240106700Abstract: The present disclosure generally relates to methods for sending event notifications. In some examples, a controller periodically sends messages concerning a status of an event corresponding to the controller. In some examples, at a first time while periodically sending the messages and in accordance with a determination that the status of the event has changed, the controller sends a message concerning data other than the status of the event. In some examples, at the first time while periodically sending the messages and in accordance with a determination that the status of the event has not changed, the controller continues to periodically send the messages without sending the message concerning data other than the status of the event.Type: ApplicationFiled: June 23, 2023Publication date: March 28, 2024Inventors: Ramy R. ASSELIN, John A. WILKEY, Jamie P. CARLSON, Stephanie L. LEGAULT, Abdul Rahman AL-SHAWA, Anil K. KANDANGATH, George E. WILLIAMS, Jangwon LEE, James D. BATSON, Fabien GONCALVES
-
Publication number: 20230025252Abstract: There is a need for more effective and efficient anomaly detection. This need can be addressed by, for example, solutions for performing/executing graph convolutional anomaly detection. In one example, a method includes identifying related graph database input data associated with a predictive entity; generating related graph feature data for the predictive entity; generating, based on the related graph feature data and using a graph convolutional neural network model, an anomaly detection score for the predictive entity, wherein at least a portion of the graph convolutional neural network model is trained using confirmation feedback data; performing an anomaly confirmation to generate the confirmation feedback data object for the predictive entity, and integrating the confirmation feedback data object for the predictive entity into the confirmation feedback data associated with the graph convolutional anomaly detection.Type: ApplicationFiled: October 3, 2022Publication date: January 26, 2023Inventors: Parker J. Erickson, Gerald Liu, Rex Shen, Devin Uner, George L. Williams, Zachary Babcock, Lydia M. Narum
-
Patent number: 11494787Abstract: There is a need for more effective and efficient anomaly detection. This need can be addressed by, for example, solutions for performing/executing graph convolutional anomaly detection. In one example, a method includes identifying related graph database input data associated with a predictive entity; generating related graph feature data for the predictive entity; generating, based on the related graph feature data and using a graph convolutional neural network model, an anomaly detection score for the predictive entity, wherein at least a portion of the graph convolutional neural network model is trained using confirmation feedback data; performing an anomaly confirmation to generate the confirmation feedback data object for the predictive entity, and integrating the confirmation feedback data object for the predictive entity into the confirmation feedback data associated with the graph convolutional anomaly detection.Type: GrantFiled: June 30, 2020Date of Patent: November 8, 2022Assignee: Optum, Inc.Inventors: Parker J. Erickson, Gerald Liu, Rex Shen, Devin Uner, George L. Williams, Zachary Babcock, Lydia M. Narum
-
Publication number: 20210406917Abstract: There is a need for more effective and efficient anomaly detection. This need can be addressed by, for example, solutions for performing/executing graph convolutional anomaly detection. In one example, a method includes identifying related graph database input data associated with a predictive entity; generating related graph feature data for the predictive entity; generating, based on the related graph feature data and using a graph convolutional neural network model, an anomaly detection score for the predictive entity, wherein at least a portion of the graph convolutional neural network model is trained using confirmation feedback data; performing an anomaly confirmation to generate the confirmation feedback data object for the predictive entity, and integrating the confirmation feedback data object for the predictive entity into the confirmation feedback data associated with the graph convolutional anomaly detection.Type: ApplicationFiled: June 30, 2020Publication date: December 30, 2021Inventors: Parker J. Erickson, Gerald Liu, Rex Shen, Devin Uner, George L. Williams, Zachary Babcock, Lydia M. Narum
-
Publication number: 20040065249Abstract: A vehicle direction indicator system is designed to alert surrounding drivers of the intentions of the vehicle operator. The indicator system has a plurality of end points and each end point is powered by the vehicle's electrical system and includes a housing, a light source holder and a lens attached to the front portion of the housing. The end points may be positioned in various locations such as the grill, spoiler, side markers and the like and may simultaneously emit a color when the vehicle driver actuates the indicator system within the vehicle. The system is preferably mounted onto the front portion of the vehicle and is capable of telling other drivers at a four way intersection that the signaling device is about to continue in a straight direction.Type: ApplicationFiled: July 16, 2003Publication date: April 8, 2004Inventor: George L. Williams