Fraud detection in contact centers using deep learning model
US10721350B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Sep 21, 2018 |
| Grant date | Jul 21, 2020 |
| Priority date | — |
| Expiry date | Sep 27, 2038 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04M2203/6027
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
An example method is described. The method includes receiving, by a computing system, data indicative of a call into an interactive voice response (IVR) system from a user device and determining, by the computing system and based on the data, a set of actions performed by the user device within the IVR system and a corresponding set of results performed by the IVR system during the call. Additionally, the method includes converting, by the computing system, the set of actions and the corresponding set of results into a sequence of code pairs using a dictionary established based on training data, determining, by the computing system, an activity pattern during the call based on the sequence of code pairs; and calculating, by the computing system, a probability that the call is fraudulent based on the activity pattern during the call.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.