Patents by Inventor Shilpi Kumar
Shilpi Kumar 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: 20240161109Abstract: Aspects of the disclosure relate to a distributed evaluation platform. The distributed evaluation platform may train a machine learning model based on historical nonfungible tokens. The distributed evaluation platform may receive client information from a client device. The distributed evaluation platform may generate NFTs corresponding to the client information. The distributed evaluation platform may generate soft tokens corresponding to each NFT. The distributed evaluation platform may apply test cases to the soft tokens. The distributed evaluation platform may generate remedial tokens based on the soft tokens and remediation actions. The distributed evaluation platform may apply the test cases to the remedial tokens. The distributed evaluation platform may overwrite the NFTs using the remedial tokens. The distributed evaluation platform may send an event processing request to an event processing system. The distributed evaluation platform may refine the machine learning model based on the NFTs.Type: ApplicationFiled: November 11, 2022Publication date: May 16, 2024Inventors: Sakshi Bakshi, Durga Prasad Kutthumolu, Shilpi Choudhari, Ankit Kumar, Saurabh Rajpal, Hwee Leng Toh
-
Publication number: 20240087104Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: ApplicationFiled: August 3, 2023Publication date: March 14, 2024Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green
-
Patent number: 11763443Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: GrantFiled: August 30, 2021Date of Patent: September 19, 2023Assignee: Instrumental, Inc.Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green
-
Publication number: 20220335589Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: ApplicationFiled: June 30, 2022Publication date: October 20, 2022Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green
-
Publication number: 20210390678Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: ApplicationFiled: August 30, 2021Publication date: December 16, 2021Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green
-
Patent number: 11132787Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: GrantFiled: July 9, 2019Date of Patent: September 28, 2021Assignee: Instrumental, Inc.Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green
-
Publication number: 20200013156Abstract: One variation of a method for monitoring manufacture of assembly units includes: receiving selection of a target location hypothesized by a user to contain an origin of a defect in assembly units of an assembly type; accessing a feature map linking non-visual manufacturing features to physical locations within the assembly type; for each assembly unit, accessing an inspection image of the assembly unit recorded by an optical inspection station during production of the assembly unit, projecting the target location onto the inspection image, detecting visual features proximal the target location within the inspection image, and aggregating non-visual manufacturing features associated with locations proximal the target location and representing manufacturing inputs into the assembly unit based on the feature map; and calculating correlations between visual and non-visual manufacturing features associated with locations proximal the target location and the defect for the set of assembly units.Type: ApplicationFiled: July 9, 2019Publication date: January 9, 2020Inventors: Samuel Bruce Weiss, Anna-Katrina Shedletsky, Simon Kozlov, Tilmann Bruckhaus, Shilpi Kumar, Isaac Sukin, Ian Theilacker, Brendan Green