US 12,074,771 B2
Enhanced device classification including crowdsourced classifications for increased accuracy
Erick Ingleby, San Francisco, CA (US); and Nirmal F. Rajarathnam, Fremont, CA (US)
Assigned to FORESCOUT TECHNOLOGIES, INC., San Jose, CA (US)
Filed by FORESCOUT TECHNOLOGIES, INC., San Jose, CA (US)
Filed on Dec. 30, 2022, as Appl. No. 18/148,951.
Claims priority of provisional application 63/325,299, filed on Mar. 30, 2022.
Prior Publication US 2023/0318927 A1, Oct. 5, 2023
Int. Cl. H04L 41/14 (2022.01); G06N 5/022 (2023.01)
CPC H04L 41/14 (2013.01) [G06N 5/022 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method, comprising:
capturing device information corresponding to a device on a network;
analyzing network traffic on the network to identify a destination device that receives data sent from the device, wherein the network traffic comprises the device information of the device;
inputting, by a processor, unstructured crowdsourced data on the network into a machine learning model to produce structured crowdsourced data, wherein the unstructured crowdsourced data comprises metadata and the structured crowdsourced data comprises data types assigned by the machine learning model based on the metadata;
performing data analytics on the structured crowdsourced data and the device information to produce a classification prediction; and
classifying the device based on the classification prediction, the device information, the structured crowdsourced data, and the destination device.