US 11,842,158 B2
Interpretable semantic indication of machine learning output
Alexander Schreiber, Wimsheim (DE); Vladimir Shapiro, Sinsheim (DE); and Joachim Sander, Bensheim (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Feb. 12, 2021, as Appl. No. 17/174,425.
Prior Publication US 2022/0261549 A1, Aug. 18, 2022
Int. Cl. G06F 40/30 (2020.01); G06F 3/14 (2006.01); G06N 20/00 (2019.01); G06F 40/51 (2020.01)
CPC G06F 40/30 (2020.01) [G06F 3/14 (2013.01); G06F 40/51 (2020.01); G06N 20/00 (2019.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method for providing user-interpretable semantic indications of machine learning (ML) predictions, the method comprising:
receiving, by a semantic translation service of a ML platform, an output data set from a ML model, the output data set comprising a predicted value and a set of metrics;
determining, by the semantic translation service, a numerical value based on at least two or more metrics in the set of metrics;
selecting, by the semantic translation service, a semantic result by mapping the numerical value to a projection comprising two or more semantic values;
transmitting, by the ML platform, a prediction result at least partially comprising the semantic result for selective display to a user using one or more user interfaces; and
receiving, from an explanation service of the ML platform, an explanation data set representative of a quantitative result at least partially based on the output data set, the explanation data set comprising a natural language explanation and a set of indicators, the prediction result comprising the explanation data set.