Using artificial intelligence to select and chain models for robotic process automation
Using artificial intelligence (AI) to select and/or chain robotic process automation (RPA) models a given problem is disclosed. A model of models (e.g., an RPA robot or an ML model) may serve as an additional layer on an existing system that makes the existing models more effective. This model of models may incorporate AI that learns an improved or best set of rules or an order from existing models, potentially taking certain activities from a model, feeding input from one model into another, and/or chaining models in some embodiments.
1. A computer-implemented method for using artificial intelligence (AI) to chain machine learning (ML) models for robotic process automation (RPA), comprising:
executing a model of models that analyzes performance of individual ML models and chains of ML models in an ML model pool to be called in a workflow of an RPA robot; and
when superior performance outcome to an existing ML model or chain of ML models is discovered by the model of models:
deploying the discovered ML model or chain of ML models, thereby replacing the existing ML model or chain of ML models, and
modifying the workflow of the RPA robot to call the discovered ML model or chain of ML models, wherein
the analysis of the performance of the individual ML models and chains of ML models comprises performing AI-based experimentation on permutations of chained ML models in series, in parallel, or a combination thereof, and analyzing results output by the individual ML models and chains of ML models.
2. The computer-implemented method of claim 1 , further comprising:
generating a new version of the RPA robot that implements the modified workflow of the RPA robot; and
deploying the generated new version of the RPA robot.
3. The computer-implemented method of claim 2 , further comprising:
calling the discovered ML model or chain of ML models, by the generated new version of the RPA robot, when executing the modified workflow of the RPA robot.
4. The computer-implemented method of claim 1 , wherein the permutations of chained ML models comprise multiple instances of a same ML model in a chain of ML models.
5. The computer-implemented method of claim 1 , wherein the superior performance outcome is governed by a reward function that explores intermediate transitions and steps with rewards to guide a search of a state space and an attempt to achieve a goal.
6. The computer-implemented method of claim 1 , wherein at least one permutation of chained ML models in series and in parallel comprises alternating between ML models in series and in parallel.
7. The computer-implemented method of claim 1 , wherein the model of models is an ML model or an RPA robot.