Automatically updating a card-scan machine learning model based on predicting card characters

US12026926B2 · kind B2 · utility

Assignee

• Lyft, Inc. · US

Inventors

• Ritwik Subir Das · Redmond, US
• Joan Devassy · San Mateo, US
• Nadha Nafeeza Gafoor · Sunnyvale, US
• Aahel Iyer · San Francisco, US
• Swarn Avinash Kumar · Mountain View, US
• Angela Lam · Seattle, US
• Kia Nishimine · Fairfax, US
• Wiebke Poerschke · San Francisco, US
• John Michael Sparks · San Francisco, US
• Hristo Stefanov Stefanov · San Francisco, US
• Wei You · Taoyuan, TW

Key dates

• Filing date: Oct 5, 2020
• Grant date: Jul 2, 2024
• Expiry date: Oct 31, 2042

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V30/19147
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

This disclosure describes a card-scan system that can update a card-scan machine learning model to improve card-character predictions for payment cards, driver licenses, or other character-bearing cards by using an active-learning technique that learns from card-scan representations indicating corrections by users to predicted card characters. In particular, the disclosed systems can use a client device to capture and analyze a set of card images of a character-bearing card to predict card characters using a card-scan machine learning model. The disclosed systems can further receive card-scan gradients representing one or more corrections to incorrectly predicted card characters. Based on the card-scan gradients, the disclosed systems can generate active-learning metrics and retrain or update the card-scan machine learning model based on such active-learning metrics. By utilizing and updating the card-scan machine learning model, the disclosed systems can improve the accuracy with which card-character-detection systems predict card characters while preserving data security and verifying the presence of a physical character-bearing card.