US 12,294,480 B2
Methods for network maintenance
Belal Hamzeh, Westminster, CO (US); Bernardo Huberman, Palo Alto, CA (US); Nicolas Joel Metts, Superior, CO (US); and Aarti Munjal, Aurora, CO (US)
Assigned to Cable Television Laboratories, Inc., Louisville, CO (US)
Filed by CABLE TELEVISION LABORATORIES, INC., Louisville, CO (US)
Filed on May 17, 2019, as Appl. No. 16/416,016.
Claims priority of provisional application 62/678,117, filed on May 30, 2018.
Claims priority of provisional application 62/674,875, filed on May 22, 2018.
Claims priority of provisional application 62/672,982, filed on May 17, 2018.
Prior Publication US 2019/0356532 A1, Nov. 21, 2019
Int. Cl. G06F 15/173 (2006.01); G06F 17/18 (2006.01); G06N 20/00 (2019.01); H04L 12/24 (2006.01); H04L 12/26 (2006.01); H04L 41/0273 (2022.01); H04L 41/16 (2022.01); H04L 41/50 (2022.01); H04L 67/61 (2022.01)
CPC H04L 41/0293 (2013.01) [G06N 20/00 (2019.01); H04L 41/16 (2013.01); H04L 41/50 (2013.01); H04L 67/61 (2022.05)] 14 Claims
OG exemplary drawing
 
1. A method for maintaining a network, the method comprising:
receiving first identification data associated with a report indicating a degraded performance of a first network device;
in response to receiving the first identification data associated with the report indicating the degraded performance of the first network device, (i) accessing a record to determine a media access control (MAC) address of the first network device from the first identification data, and (ii) using a central proactive network maintenance (PNM) interface communicatively coupled to a plurality of PNM databases, determining, based on the MAC address of the first network device, which PNM database of the plurality of PNM databases contains PNM data corresponding to the first network device;
obtaining, from a first PNM database of the plurality of PNM databases, first PNM data collected at least in part by the first network device at least partially prior to the report indicating the degraded performance of the first network device;
transmitting the first PNM data to a machine learning (ML) engine;
receiving, from the ML engine, an indication of a predetermined first operation that is predicted to improve the degraded performance of the first network device indicated by the report;
transmitting the indication of the predetermined first operation; and
transmitting, to the ML engine, an indication of whether the degraded performance of the first network device indicated by the report improves after the implementation of the predetermined first operation.