US 12,069,082 B2
Interpreting and remediating network risk using machine learning
Qihong Shao, Clyde Hill, WA (US); Xinjun Zhang, San Jose, CA (US); Yue Liu, Santa Clara, CA (US); Kevin Broich, Cary, NC (US); Kenneth Charles Croley, Oakland, CA (US); and Gurvinder P. Singh, San Jose, CA (US)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Jun. 11, 2021, as Appl. No. 17/345,640.
Prior Publication US 2022/0400131 A1, Dec. 15, 2022
Int. Cl. H04L 9/40 (2022.01); G06F 21/57 (2013.01); G06F 40/295 (2020.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01)
CPC H04L 63/1433 (2013.01) [G06F 21/577 (2013.01); G06F 40/295 (2020.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
processing a plurality of risk reports corresponding to a plurality of network devices in a network to determine a multidimensional risk score for the network;
analyzing the plurality of risk reports using a semantic analysis model to identify one or more factors that contribute to the multidimensional risk score;
determining one or more actions using a trained learning model to mitigate one or more dimensions of the multidimensional risk score, wherein the trained learning model comprises a generative adversarial network that is trained using training data that includes text of risk reports and an ontology that represents a hierarchical relationship between devices, predefined conditions, and symptoms of problems associated with one or more network device of the plurality of network devices; and
presenting outcomes of applying the one or more actions to a user to indicate an effect of each of the one or more actions on the multidimensional risk score for the network.