US 12,379,983 B2
Training and using a memory failure prediction model
Jasmine Grace Schlichting, Seattle, WA (US); Bhuvan Malladihalli Shashidhara, Bellevue, WA (US); Ramakoti R. Bhimanadhuni, Bothell, WA (US); Emily Nicole Wilson, Seattle, WA (US); Farah Farzana, Redmond, WA (US); Michael Wayne Stephenson, Woodinville, WA (US); Pallavi Baral, Redmond, WA (US); Josh Charles Moore, Lynnwood, WA (US); Christina Margaret Tobias, Seattle, WA (US); John A. Strange, Everett, WA (US); Peter Hanpeng Jiang, Kirkland, WA (US); Sebastien Nathan R Levy, Seattle, WA (US); Brett Kenneth Dodds, Boise, ID (US); Arhatha Bramhanand, Redmond, WA (US); Juan Arturo Herrera Ortiz, Seattle, WA (US); Ahu Oral, Seattle, WA (US); Charlotte Gauchet, Redmond, WA (US); and Daniel Sebastian Berger, Seattle, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on Nov. 19, 2021, as Appl. No. 17/531,158.
Prior Publication US 2023/0161655 A1, May 25, 2023
Int. Cl. G06F 11/07 (2006.01); G06F 18/214 (2023.01); G06N 3/008 (2023.01); G06N 20/00 (2019.01)
CPC G06F 11/073 (2013.01) [G06F 11/0757 (2013.01); G06F 11/0772 (2013.01); G06F 18/214 (2023.01); G06N 3/008 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
8. A computerized method comprising:
generating, by a processor, a set of uncorrectable error (UE) state labels based on a first set of collected telemetry data, wherein each UE state label references-includes a reference to a UE event and telemetry data of a time interval prior to the referenced UE event;
generating, by the processor, a set of non-UE state labels based on the collected telemetry data, wherein each non-UE state label references-includes a reference to a correctable error (CE) event and telemetry data of a time interval, prior to the referenced CE event, that does not include a UE event;
extracting, by the processor, statistical features from telemetry data of the set of UE state labels and from telemetry data of the set of non-UE state labels, wherein extracting the statistical features includes extracting statistical features associated with UE state labels and non-UE state labels based on a plurality of different memory hierarchy levels, wherein the plurality of memory hierarchy levels includes at least one of the following: memory page levels, memory row levels, or node levels;
training, by the processor, a UE state prediction model using the set of UE state labels, the set of non-UE state labels, and the extracted statistical features;
obtaining, by the processor, a second set of collected telemetry data;
predicting, by the processor, a UE event based on the second set of collected telemetry data using the trained UE state prediction model, wherein the predicted UE event is associated with a memory page of a system; and
performing, by the processor, a preventative operation on the memory page of the system, whereby the predicted UE event is prevented from occurring.