US 12,477,011 B1
Systems and methods configured for automatically predicting device types for scanned devices on a network
Vaibhav Anand, Chicago, IL (US); Charles Joseph Bonfield, Raleigh, NC (US); Jae Gook Ro, Chantilly, VA (US); Brandon Lee Knight, South Lake Tahoe, CA (US); Sarthak Sahu, Pasadena, CA (US); Ciro Donalek, Pasadena, CA (US); and Michael Amori, Pasadena, CA (US)
Assigned to Virtualitics, Inc., Pasadena, CA (US)
Filed by Virtualitics, Inc., Pasadena, CA (US)
Filed on May 14, 2025, as Appl. No. 19/208,115.
Application 19/208,115 is a continuation of application No. 18/818,320, filed on Aug. 28, 2024, granted, now 12,309,205.
Claims priority of provisional application 63/649,193, filed on May 17, 2024.
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 21/57 (2013.01); H04L 9/40 (2022.01); H04L 29/06 (2006.01); H04L 41/12 (2022.01); G06F 21/56 (2013.01)
CPC H04L 63/20 (2013.01) [H04L 41/12 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating, by the processor, a type label for at least one device by:
comparing type information of the at least one device to other type information of a plurality of other devices to generate a confidence score for the at least one device indicative of a measure of similarity between the at least one device and the plurality of other devices,
wherein generating the confidence score comprises calculating a device-specific confidence score based on a scan of a network, the confidence score comprising one or more values assigned to a plurality of features associated with the type information of the at least one device,
grouping the type information of the at least one device with the other type information of the plurality of other devices based on the confidence score meeting a predetermined threshold, and
determining the type label for the at least one device based on of the grouping of the type information; and
generating, by the processor, a security object based at least in part on the type label of the at least one device so as to facilitate causing at least one security action with respect to the at least one device, wherein the at least one security action is correlated with the confidence score of the at least one device.