US 12,407,632 B2
Training a bot orchestrator for chatbots
Sebastian Schuetz, Mannheim (DE); and Johannes Knoll, Mannheim (DE)
Assigned to SAP SE, Walldorf (DE)
Filed by SAP SE, Walldorf (DE)
Filed on Jun. 21, 2022, as Appl. No. 17/845,297.
Prior Publication US 2023/0412530 A1, Dec. 21, 2023
Int. Cl. G06F 17/27 (2006.01); G06F 18/214 (2023.01); G06F 40/35 (2020.01); H04L 51/02 (2022.01)
CPC H04L 51/02 (2013.01) [G06F 18/214 (2023.01); G06F 40/35 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method for training a bot orchestrator for chatbot selection, comprising:
collecting a set of expressions from a training data set of a first chatbot and a training data set of a second chatbot;
for each respective pair of expressions in the set of expressions:
calculating a mathematical distance between an expression for the first chatbot in the respective pair of expressions and an expression for the second chatbot in the respective pair of expressions; and
filtering the set of expressions based on the calculated mathematical distance, thereby generating a filtered set of expressions; and
training a machine learning-based classification model of the bot orchestrator using the filtered set of expressions, wherein the bot orchestrator is being trained to select a particular chatbot among the first and second chatbots based on the machine learning-based classification model of the bot orchestrator using the filtered set of expressions.