US 11,991,148 B2
Automated creation of trusted network perimeter
Jinlong Fu, Oakville (CA); and RaghuRam Pamidimarri, Union City, CA (US)
Filed by Okta, Inc., San Francisco, CA (US)
Filed on Jul. 28, 2023, as Appl. No. 18/361,512.
Application 18/361,512 is a continuation of application No. 17/161,398, filed on Jan. 28, 2021, granted, now 11,765,129.
Prior Publication US 2023/0379299 A1, Nov. 23, 2023
Int. Cl. H04L 9/40 (2022.01); G06N 20/00 (2019.01)
CPC H04L 63/0209 (2013.01) [G06N 20/00 (2019.01); H04L 63/0236 (2013.01); H04L 63/1433 (2013.01); H04L 63/20 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method comprising:
receiving connection data corresponding to network requests of client devices associated with a network, wherein an item of the connection data includes at least one network address;
training a machine learning model using the connection data, wherein the machine learning model is configured to output scores for network zones input into the machine learning model;
receiving a network zone;
inputting the network zone into the machine learning model to obtain a corresponding score, the corresponding score representing a security of the network zone relative to the network;
displaying data to a network administrator, the data representing the corresponding score and a recommendation;
receiving an approval of the recommendation from the network administrator; and
modifying a network operation of the network based on the corresponding score after receiving the approval.