US 11,853,161 B2
Image models to predict memory failures in computing systems
Gufeng Zhang, San Jose, CA (US); Milad Olia Hashemi, San Francisco, CA (US); and Ashish V. Naik, Los Altos, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Apr. 22, 2022, as Appl. No. 17/727,454.
Prior Publication US 2023/0342245 A1, Oct. 26, 2023
Int. Cl. G11C 29/00 (2006.01); G06F 11/10 (2006.01); G06F 11/07 (2006.01); G06N 3/04 (2023.01); G06F 18/214 (2023.01)
CPC G06F 11/1068 (2013.01) [G06F 11/076 (2013.01); G06F 11/0757 (2013.01); G06F 11/0772 (2013.01); G06F 18/214 (2023.01); G06N 3/04 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented comprising:
receiving a log of correctable memory error data that describes correctable errors that occurred in a computer memory;
generating, from the log of correctable memory error data, one or more image representations of the correctable memory error data, wherein the one or more image representations are generated by converting the correctable memory error data to matrix codes or graphs that provide visualizations of patterns of errors that occurred in the computer memory;
inputting the one or more image representations to an image recognition machine learning model, wherein the image recognition machine learning model is trained to predict a likelihood of a future failure of a computer memory from input image representations generated by converting a log of correctable memory error data that describes correctable errors that occurred in the computer memory to matrix codes or graphs that provide visualizations of patterns of errors that occurred in the computer memory; and
receiving, from the image recognition machine learned model, a likelihood of the future failure based on the input of the one or more image representations.