Feedback-based training for anomaly detection

US12147878B2 · kind B2 · utility

Assignee

• AMAZON TECHNOLOGIES, INC. · US

Inventors

• Barath Balasubramanian · Cambridge, US
• Rahul Bhotika · Albany, US
• Niels Brouwers · New York, US
• Ranju Das · Seattle, US
• Prakash Krishnan · Santa Clara, US
• Shaun Ryan James McDowell · Great Neck, US
• Anushri Mainthia · Seattle, US
• Rakesh Madhavan Nambiar · Seattle, US
• Anant Patel · Seattle, US
• Avinash Aghoram Ravichandran · Baltimore, US
• Joaquin Zepeda Salvatierra · Mercer Island, US
• Gurumurthy Swaminathan · Redmond, US

Key dates

• Filing date: Nov 27, 2020
• Grant date: Nov 19, 2024
• Expiry date: Jul 23, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V2201/06
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Techniques for feedback-based training may include selecting a scoring machine learning model based at least in part on a test metric, and applying the model on an unlabeled dataset to generate, per dataset item of the unlabeled dataset, a prediction and an importance ranking score for the prediction. Techniques for feedback-based training may further include selecting, based on the importance ranking scores, a result of the application of the model on the unlabeled dataset, providing the result and requesting feedback on the result via a graphical user interface, receiving the feedback via the graphical user interface, adding data from the unlabeled dataset into a training dataset when the feedback indicates a verified result, and retraining the model using the training dataset with the data added from the unlabeled dataset to generate a retrained model.