US 11,928,088 B1
Machine-learned models for predicting database application table growth factor
Deng Zhou, Neckargemund (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Oct. 6, 2022, as Appl. No. 17/961,260.
Int. Cl. G06F 16/00 (2019.01); G06F 16/21 (2019.01); G06F 16/25 (2019.01)
CPC G06F 16/213 (2019.01) [G06F 16/256 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising:
at least one hardware processor; and
a computer-readable medium storing instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
accessing one or more application tables in a software database;
identifying one or more time fields of the one or more application tables, each time field having a time value;
for each of the one or more time fields, counting a number of records appearing in the one or more application tables in the time field having time values falling within each of a plurality of time intervals of a preset length, and forming a time field histogram from the record counts and time intervals;
accessing a label for each of the one or more time field histograms, the label for a given time field histogram indicating a classification of a likelihood that the time field corresponding to the given time field histogram is a predictor of growth; and
training a time field classifier machine learning model by passing the one or more time field histograms and the one or more labels into a first machine learning algorithm.