Dynamic learning system for intelligent authentication
US11368457B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jul 30, 2018 |
| Grant date | Jun 21, 2022 |
| Priority date | — |
| Expiry date | Dec 18, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L2463/082
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
Techniques for intelligently deciding the optimal authenticator(s) from amongst those supported by an electronic device are described. The authentication system according to some embodiments may include a dynamic machine learner that incorporates the attributes of: (i) user behavior attributes (e.g., preferred authenticator); (ii) device attributes (e.g., hardware and software specifications, applications, etc.); and (iii) operating environment attributes (e.g., ambient light, noise, etc.), as well as the interplay between the aforementioned attributes over time to make the decision. In some embodiments, the authentication activities and patterns of other users of similar type (e.g., users exhibiting similar behavior across different operating environments) can also be learned and employed to improve the decision making process over time.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.