US 11,915,481 B1
Capturing and analyzing security events and activities and generating corresponding natural language descriptions
Yannik S. Nager, Zürich (CH); Christian Eheim, Fällanden (CH); and Alexander S. Pachikov, San Carlos, CA (US)
Assigned to Sunflower Labs Inc., San Carlos, CA (US)
Filed by Sunflower Labs Inc., San Carlos, CA (US)
Filed on Mar. 8, 2021, as Appl. No. 17/194,386.
Claims priority of provisional application 62/990,659, filed on Mar. 17, 2020.
Int. Cl. G06K 9/00 (2022.01); G06V 20/40 (2022.01); G06F 40/56 (2020.01); G08B 13/196 (2006.01); G06F 40/35 (2020.01); G06F 18/2431 (2023.01)
CPC G06V 20/41 (2022.01) [G06F 18/2431 (2023.01); G06F 40/35 (2020.01); G06F 40/56 (2020.01); G08B 13/19613 (2013.01); G06V 20/44 (2022.01)] 26 Claims
OG exemplary drawing
 
1. A method of detecting security events and generating corresponding natural language descriptors, comprising:
monitoring an area to capture data corresponding to moving objects in the area;
classifying the moving objects;
generating events based on classifying the moving objects;
building an event graph by connecting related ones of the events;
using the event graph to detect security events; and
building natural language activity descriptors for the security events of the event graph using semantic analysis to filter and prioritize the events with respect to corresponding security threats and using natural language templates that include a plurality of constructs to convert filtered and prioritized ones of the security events to create natural language phrases.