Cognitive RPA Architecture Using Neural Graphs for Software Agnostic Automation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current robotic process automation (RPA) lacks a software agnostic solution, making it challenging to automate tasks across different software systems effectively, especially when moving from one automation to another.

Innovation Solution

The implementation of a cognitive RPA architecture using neural processing graphs to generate a policy from a single video demonstration of actions, allowing the system to dynamically generate source code for application execution bots to replicate the actions on various application programming interfaces.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional RPA is used to automate tasks, then automation capability is achieved for specific applications, but adaptability to different software systems deteriorates due to lack of software agnostic solution

Engineering Contradiction:

Improveadaptability to different software systemsVSAvoidintegration complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal RPA architecture that can execute automated tasks across multiple different software systems and applications. The system uses a common automation framework that works with various applications without requiring system-specific customization, thereby achieving software agnosticism and multi-functionality across diverse platforms

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent introduces an intermediary layer between the automation engine and application-specific interfaces. This intermediary component translates generic automation commands into application-specific actions, enabling the system to adapt to different software systems without modifying the core automation logic, thus reducing integration complexity while maintaining versatility

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If RPA automates repetitive tasks, then productivity increases, but difficulty in detecting and measuring task variability worsens

Engineering Contradiction:

Improveautomation efficiencyVSAvoidtask variability detection

Core Design Contradiction:

ProductivityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent incorporates feedback mechanisms that continuously monitor and capture task execution data, including variations in task performance, timing, and outcomes. This feedback is fed back into the system to detect and measure task variability, enabling the RPA system to adapt to changing conditions while maintaining high productivity through automated execution

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11436830B2Cognitive robotic process automation architecture

Publication Date: 2022.09.06 BANK OF AMERICA CORP

AI summary

Systems, computer program products, and methods are described herein for implementing a cognitive robotic process automation (RPA) architecture. The present invention is configured to electronically receive a video file from a repository, wherein the video file demonstrating one or more actions to be executed in a sequential manner on an application programming interface associated with an application; initiate a neural processing graph generator on the video file; generate, using the neural processing graph generator, a conjugate task graph comprising one or more nodes and one or more edges; initiate a neural task engine on the conjugate task graph; and execute, using the neural task engine, the conjugate task graph.