| CPC B25J 9/163 (2013.01) [G05B 13/0265 (2013.01)] | 18 Claims |
|
1. A computing platform comprising:
at least one processor;
a memory storing computer-readable instructions that, when executed by the at least one processor, cause the computing platform to:
initiate, automatically by a machine learning (ML)-based smart change evaluation engine, operation of robotics process automation (RPA) activity operating with a first instance of an automated process;
capture, by a data extraction engine, first information corresponding to the operation of the RPA activity with the first instance of the automated process;
initiate, automatically by the machine learning (ML)-based smart change evaluation engine, operation of an RPA process with a second instance of the automated process;
capture, by the data extraction engine, second information corresponding to the operation of the RPA process with the second instance of the automated process;
validate, by the ML-based smart change evaluation engine, the first information and the second information using rules and a scoring algorithm;
generate, by the ML-based smart change evaluation engine based on the validated first information and the validated second information, RPA change output parameters;
generate, automatically by the ML-based smart change evaluation engine based on the RPA change output parameters, an updated RPA activity for testing of the second instance of the automated process;
generate, automatically, RPA rules;
generate, based on the generated RPA rules, RPA change output parameters, and a number of identified reusable RPA process components, a new RPA process to run post change operations;
retrain, by the ML-based smart change evaluation engine and based the RPA change output parameters and the generated RPA rules, the new RPA process as part of a self-learning process;
derive, by the ML-based smart change evaluation engine and from recordings of the RPA activity with the first instance of the automated process, change estimates corresponding to component changes of the second instance of the automated process from the first instance of the automated process;
identify, by the ML-based smart change evaluation engine and based on the change estimates, changes to existing code components of the automated process to identify changed objects; and
generate, automatically by a machine learning engine and based on identified change objects of the existing code components of the automated process, new rules for generating the change estimates; and
improve, via a self-learning process of the machine learning engine, future estimates derived during validation of recorded future instances of the automated process.
|