US 12,406,202 B2
Predicting component lifespan information by processing user install base data and environment-related data using machine learning techniques
Parminder Singh Sethi, Punjab (IN); and Madhuri Dwarakanath, Bangalore (IN)
Assigned to Dell Products L.P., Round Rock, TX (US)
Filed by Dell Products L.P., Round Rock, TX (US)
Filed on Dec. 30, 2020, as Appl. No. 17/137,670.
Prior Publication US 2022/0207415 A1, Jun. 30, 2022
Int. Cl. G06F 18/23 (2023.01); G06N 20/00 (2019.01)
CPC G06N 20/00 (2019.01) [G06F 18/23 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining install base data associated with at least one system component and environment-related data associated with usage of the at least one system component;
performing feature analysis on at least a portion of the install base data and at least a portion of the environment-related data using at least a first set of one or more machine learning techniques;
clustering, based at least in part on the feature analysis, at least a portion of the install base data and at least a portion of the environment-related data into one or more groups using at least a second set of one or more machine learning techniques, wherein clustering comprises using a density-based clustering algorithm, having as parameters thereof at least one designated threshold number of data points associated with establishing at least one cluster and at least one designated distance measure associated with establishing at least one cluster, to cluster the at least one system component into the one or more groups, wherein the one or more groups comprise other instances of the at least one system component associated with (i) at least one workload intensity range at least partially overlapping with a workload intensity range attributed to the at least one system component and (ii) at least one ambient temperature range associated with a given geographic region, the at least one ambient temperature range at least partially overlapping with an ambient temperate range associated with at least one geographic region attributed to the at least one system component;
generating at least one lifespan information prediction attributed to the at least one system component based at least in part on the clustering, wherein generating at least one lifespan information prediction comprises determining at least one end-of-life value for the other instances of the at least one system component in the one or more groups, and using the at least determined one end-of-life value in generating the at least one lifespan information prediction attributed to the at least one system component; and
performing at least one automated action based at least in part on the at least one lifespan information prediction, wherein performing at least one automated action comprises automatically initiating replacement of the at least one system component in accordance with the at least one lifespan information prediction;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.