Determining sequences of interactions, process extraction, and robot generation using generative artificial intelligence / machine learning models
AssigneeUiPath, Inc.
InventorPrabhdeep Singh
Life of this patent
Estimating the term…
Abstract
Use of generative artificial intelligence (AI)/machine learning (ML) models is disclosed to determine sequences of user interactions with computing systems, extract common processes, and generate robotic process automation (RPA) robots. The generative AI/ML model may be trained to recognize matching n-grams of user interactions and/or a beneficial end state. Recorded real user interactions may be analyzed, and matching sequences may be implemented as corresponding activities in an RPA workflow.
Claims23
A computer-implemented method, comprising:
- providing, by a computing system, a generative artificial intelligence (AI)/machine learning (ML) model with data comprising time-ordered interactions of a plurality of users with respective user computing systems;
- training the generative AI/ML model, by the computing system, to recognize an outcome of the time-ordered interactions and to determine one or more processes that lead to the outcome;
- and
- deploying the trained generative AI/ML model, wherein
- the training of the generative AI/ML model to recognize the outcome comprises training the generative AI/ML model to look backwards in data pertaining to the user interactions, the user interactions themselves, or both, and
- the outcome comprises an end state of the generative AI/ML model.
A non-transitory computer-readable medium storing a computer program, the computer program configured to cause at least one processor to:
- analyze recorded real user interactions of a plurality of users with respective computing systems and determine user interactions in the recorded real user interactions that lead to an outcome, via a generative artificial intelligence (AI)/machine learning (ML) model;
- and
- generate one or more respective robotic process automation (RPA) workflows comprising activities that implement the user interactions that lead to the outcome by recreating a sequence of the user interactions that lead to the outcome, wherein
- the outcome comprises an end state of the generative AI/ML model.
A system, comprising:
- memory storing computer program instructions;
- and
- at least one processor configured to execute the computer program instructions, wherein the computer program instructions are configured to cause the at least one processor to:
- analyze recorded real user interactions of a plurality of users with respective computing systems and determine an outcome based on the analysis, via a generative artificial intelligence (AI)/machine learning (ML) model, and
- analyze recorded real user interactions of a plurality of users with respective computing systems and determine user interactions in the recorded real user interactions that lead to the outcome, strengthen nodes in neural network priors using backpropagation until the outcome can be replicated, or both, by the generative AI/ML model, wherein
- the outcome comprises an end state of the generative AI/ML model.
Dependencies are inferred from the claim text.