Cognitive offense analysis using enriched graphs
US10313365B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Aug 15, 2016 |
| Grant date | Jun 4, 2019 |
| Priority date | — |
| Expiry date | Jul 7, 2037 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04L63/1425
- WIPO fieldDigital communication
- WIPO sectorElectrical engineering
Abstract
An automated method for processing security events begins upon receipt of information representing an offense. Based in part on context data extracted from the offense, an offense context graph is built. The offense context graph comprises nodes and edges, with an edge therein representing a relationship between a pair of nodes, at least one of the nodes being a root node representing an entity associated with the offense. The method then continues by mining information about other events that are determined to share a local contextual relationship with the offense represented by the offense context graph. This operation generates an enriched offense context graph. The enriched offense context graph is then pruned to identify an offense context for further examination. Pruning may involve applying a metric to events associated with the offense and removing nodes that, based on evaluation of the metric, do not contribute to the offense.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.