US 12,260,347 B2
Systems and methods for predicting storage device failure using machine learning
Qinling Zheng, San Jose, CA (US); Nima Elyasi, San Jose, CA (US); Vikas Sinha, Sunnyvale, CA (US); and Changho Choi, San Jose, CA (US)
Assigned to SAMSUNG ELECTRONICS CO., LTD., (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 15, 2023, as Appl. No. 18/197,717.
Application 18/197,717 is a continuation of application No. 15/931,573, filed on May 13, 2020, granted, now 11,657,300.
Claims priority of provisional application 62/982,055, filed on Feb. 26, 2020.
Prior Publication US 2023/0281489 A1, Sep. 7, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 5/04 (2023.01); G06F 11/16 (2006.01); G06N 20/00 (2019.01)
CPC G06N 5/04 (2013.01) [G06F 11/16 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method for determining an event in a target storage device, the method comprising:
training a machine learning scheme with a dataset of events from one or more storage devices;
receiving parameter data from the target storage device; and
inputting the parameter data from the target storage device into the machine learning scheme;
wherein the machine learning scheme outputs a first determination and a second determination of the event for the target storage device based at least in part on the parameter data.