US 12,093,743 B2
Cloud based machine learning notebook feature engineering command recommender
Hari Bhaskar Sankaranarayanan, Bangalore (IN); and Viral Rathod, Bangalore (IN)
Assigned to Oracle International Corporation, Redwood Shores, CA (US)
Filed by Oracle International Corporation, Redwood Shores, CA (US)
Filed on Dec. 14, 2021, as Appl. No. 17/550,955.
Prior Publication US 2023/0185626 A1, Jun. 15, 2023
Int. Cl. G06F 9/50 (2006.01); G06F 9/38 (2018.01); G06N 20/00 (2019.01)
CPC G06F 9/5072 (2013.01) [G06F 9/3836 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method of operating a machine learning (ML) notebook in a cloud infrastructure executing a plurality of ML notebooks, wherein each of the ML notebooks comprise an interactive ML software environment with a plurality of cells, the method comprising:
receiving a plurality of previously executed ML notebook commands corresponding to feature engineering tasks for one or more ML models from the plurality of ML notebooks;
storing the plurality of previously executed ML notebook commands, including a relationship between the ML notebook commands;
mining the stored ML notebook commands to generate sets of ML notebook commands, the sets comprising commands that are used together and an order of use of the commands;
receiving a context of a current ML notebook command and data used in the context; and
recommending a next ML notebook command to be executed after the current ML notebook command, wherein the next ML notebook command is recommended based at least on exceeding a threshold of a transition probability in reference to a previous ML notebook command.