CPC G06F 16/353 (2019.01) [G06F 16/316 (2019.01); G06N 3/042 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 5/025 (2013.01)] | 19 Claims |
1. A computer-implemented method, comprising:
receiving master data, transaction data, and a process model of a domain, the process model using a first software agent of a plurality of available software agents;
aggregating, based on domain knowledge ontology of the domain, the master data and the transaction data to generate a fact table;
converting entries in the fact table into vectors;
receiving a performance indicator;
identifying, based on the vectors, an attribute that appears to be statistically significant on impacting the performance indicator of the process model, the identifying including
inputting the vectors into an algorithm to identify a correlation between the attribute and the performance indicator,
determining a p-value of the attribute, and
determining, based on the p-value, whether the attribute is statistically significant on impacting the performance indicator of the process model;
determining an action associated with the attribute to improve the process model, the action identifying a second software agent of the plurality of available software agents to replace the first software agent or to include in the process model;
executing the action to replace the first software agent with the second software agent in the process model or to include the second software agent in the process model; and
providing a notification of the action to a client device associated with the domain.
|