US 11,727,334 B2
Machine learning enabled supplier monitor
Sagar Gupta, Kalka (IN); and Rajkishore Sahoo, Bangalore (IN)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Dec. 7, 2021, as Appl. No. 17/544,402.
Prior Publication US 2023/0177438 A1, Jun. 8, 2023
Int. Cl. G06Q 10/06 (2023.01); G06Q 10/0637 (2023.01); G06F 40/284 (2020.01); G06F 40/40 (2020.01); G06Q 10/0635 (2023.01)
CPC G06Q 10/06375 (2013.01) [G06F 40/284 (2020.01); G06F 40/40 (2020.01); G06Q 10/0635 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A system, comprising:
at least one processor; and
at least one memory including program code which when executed by the at least one processor provides operations comprising:
training, based at least on a training dataset including a plurality of text samples, a machine learning model, each text sample in the training dataset being associated with a ground truth label corresponding to an objective affected by a type of incident described in the text sample, and the training of the machine learning model including adjusting the machine learning model to minimize a difference in a label output by the machine learning model applied to each text sample in the training dataset and the ground truth label associated with the text sample;
upon training the machine learning model, applying, to a first content associated with a first supplier, the machine learning model to determine one or more objectives of an enterprise affected by a first incident associated with the first content;
detecting, based at least on the one or more objectives of the enterprise affected by the first incident associated with the first content, a first change in a first risk associated with the first supplier;
in response to detecting the first change in the first risk of the first supplier, determining a first cost associated with replacing the first supplier with a second supplier based at least on a first electronic document associated with the first supplier, the first cost associated with replacing the first supplier with the second supplier being determined by at least
applying the machine learning model to analyze a second content of the first electronic document;
generating, based at least on an output of the machine learning model applied to analyze the second content of the first electronic document, metadata associated with the first electronic document,
identifying, based at least on the metadata associated with the first electronic document, one or more clauses associated with terminating a contract with the first supplier, and
extracting one or more corresponding values;
determining a second risk associated with the second supplier; and
in response to the first cost of replacing the first supplier with the second supplier and the second risk of the second supplier satisfying one or more thresholds, generating a second electronic document having one or more clauses, terms, and/or line items addressing the second risk of the second supplier in order to form another contract with the second supplier.