US 11,886,961 B2
Preparing data for machine learning processing
Manuel Zeise, Karlsruhe (DE); Isil Pekel, Mannheim (DE); and Steven Jaeger, Heidelberg (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Sep. 25, 2019, as Appl. No. 16/582,950.
Prior Publication US 2021/0089970 A1, Mar. 25, 2021
Int. Cl. G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06N 3/04 (2023.01); G06N 20/20 (2019.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 3/08 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 18/214 (2023.01); G06F 18/2414 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06N 20/10 (2019.01); G06N 20/20 (2019.01)] 18 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one data processor; and
at least one memory storing instructions which, when executed by the at least one data processor, result in operations comprising:
preparing data for processing by a first machine learning model by at least embedding a second portion of the data including a textual data, the textual data being embedded by at least applying a second machine learning model trained to embed the textual data;
preparing the data for processing by the first machine learning model, the data being prepared by at least encoding a first portion of the data including a spatial data, the spatial data including a first spatial coordinate including one or more values identifying a geographical location, wherein the encoding of the first portion of the data includes mapping, to a first cell in a grid system, the first spatial coordinate such that the first spatial coordinate is represented by a first identifier of the first cell instead of the one or more values;
executing, based on the embedded textual data, a plurality of machine learning trials, each of the plurality of machine learning trials being executed by at least retrieving, from a cache, the embedded textual data, wherein each of the plurality of machine learning trials includes a different machine learning model and/or a different set of trial parameters, and wherein the first machine learning model is selected based at least on a result of the plurality of machine learning models; and
applying, to the prepared data, the first machine learning model.