Classifying behavior through system-generated timelines and deep learning

US11823216B2 · kind B2 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Eugene Irving Kelton · Mechanicsburg, US
• Brandon Harris · Palo Alto, US
• Willie Robert Patten, JR. · Hurdle Mills, US
• Eliza Salkeld · Raleigh, US
• Russell Gregory Lambert · Wake Forest, US
• Yi-Hui Ma · New York, US
• Shuyan Lu · Cary, US
• Shanna Hayes · Cary, US

Key dates

• Filing date: May 5, 2020
• Grant date: Nov 21, 2023
• Expiry date: Aug 18, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V10/764
• WIPO field: IT methods for management
• WIPO sector: Electrical engineering

Abstract

Computer vision and deep learning techniques are leveraged to detect behavior patterns in transaction histories. A transaction timeline is built for a series of transactions, e.g., financial, and a graphic image is constructed representing the transaction timeline. The graphic image is then matched to a known behavior pattern using a cognitive system. The cognitive system is trained with historical timeline images having associated labels. In one example the graphic image is a bar chart and each financial transaction is represented as a bar in the bar chart having a height proportional to a transaction amount, the bar being located along a time axis of the bar chart according to the transaction date and being color coded according to the transaction type.