US 11,810,547 B2
Machine learning for intelligent dictation of analysis of multidimensional objects
Ramalingam Tv, Calgary (CA)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Apr. 8, 2021, as Appl. No. 17/225,550.
Prior Publication US 2022/0328034 A1, Oct. 13, 2022
Int. Cl. G10L 13/08 (2013.01); G06F 16/28 (2019.01); G06N 20/00 (2019.01); G10L 13/047 (2013.01); G06F 40/30 (2020.01); G06F 40/242 (2020.01); G06N 5/04 (2023.01)
CPC G10L 13/08 (2013.01) [G06F 16/283 (2019.01); G06F 40/242 (2020.01); G06F 40/30 (2020.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G10L 13/047 (2013.01)] 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:
obtaining a model identifying one or more multidimensional objects stored in an enterprise data warehouse, the model having a context identification stored as metadata;
identifying a context of the model using the context identification;
retrieving a plurality of multidimensional objects, stored in the enterprise data warehouse, with contexts that match the identified context;
aggregating the retrieved multidimensional objects;
combining portions of the aggregated multidimensional objects and adding one or more symbols indicating differences between the combined portions to produce a first output having pairs of field names and values;
adding a symbol dividing one or more pairs in the first output, producing runtime information;
feeding the runtime information to a predictive engine trained by a machine learning algorithm to predict text output for the runtime information; and
synthesizing speech for the predicted text output based on a language dictionary and pronunciation rules.