Cognitive AI Layer for Automatic RPA Code Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current RPA workflow development requires programming knowledge and is prone to errors, limiting its accessibility to advanced users and introducing inefficiencies.
Innovation Solution
A cognitive AI layer is used to automatically generate computer program code from various input sources, including natural language text and user actions, enabling non-programmers to create RPA workflows with reduced manual effort and errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual code writing is used for RPA workflows, then programming precision is improved, but device complexity and ease of operation deteriorate
Solution Approach 1:
The patent introduces a natural language processing intermediary layer that translates human-readable text into executable RPA code. This mediator system includes language models and code generation modules that act as an intermediary between the user's natural language input and the programming system, eliminating the need for users to write code directly while maintaining precision through automated code synthesis and validation.
Solution Approach 2:
The patent replaces the mechanical process of manual code writing with an automated intelligent system. Instead of requiring users to manually type and debug code, the system uses AI-driven code generation, automatic syntax validation, and intelligent error correction to substitute the manual coding mechanism, thereby improving ease of operation while maintaining programming precision.
2Reliability
If programming knowledge is required for RPA development, then code reliability is improved, but ease of operation deteriorates
Solution Approach 1:
The patent implements self-service mechanisms where the system automatically performs code generation, validation, and error correction without requiring user expertise. The intelligent system includes automated syntax checking, logical error detection, and self-correction capabilities that enable non-programmers to develop reliable RPA workflows independently, thereby improving ease of operation while maintaining code reliability.
Solution Approach 2:
The patent incorporates feedback loops where the system provides real-time validation, error messages, and suggestions to users during code generation. The feedback mechanism includes automated testing, performance monitoring, and iterative improvement suggestions that help non-programming users understand and correct issues, ensuring code reliability while maintaining ease of operation through guided development.
3Manufacturing precision
If advanced users develop RPA workflows, then manufacturing precision is improved, but productivity deteriorates
Solution Approach 1:
The patent implements preliminary action by pre-configuring templates, common code patterns, and best practice frameworks that users can leverage. The system includes pre-built workflow templates, standardized code structures, and automated setup procedures that eliminate the need for users to start from scratch, thereby accelerating workflow implementation while maintaining precision through proven methodologies.
Solution Approach 2:
The patent enables copying and reuse of proven workflow patterns, code snippets, and best practices through a library of pre-validation templates. Users can copy validated workflows and adapt them to new scenarios, ensuring precision through proven designs while significantly accelerating development speed. The system includes template inheritance and parameter customization capabilities that maintain precision while improving productivity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Automatic code generation for robotic process automation (RPA) that uses a cognitive artificial intelligence (AI) layer to automatically generate computer program code, text, or other items based on an input source is disclosed. Expressions and/or code snippets may be generated for RPA workflows that provide code in a programming language or convert code from one language to another. The input source may include natural language sentence(s), source document(s), pseudocode written by a user for a desired task, etc. These inputs may be used to modify an RPA workflow, generate a new RPA workflow, create a document describing a task, generate an application, etc.