Generative AI Automation Program Creation Through Iterative Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems using generative AI for program automation require significant manual input and lack accuracy in handling unknown problems.
Innovation Solution
A creation support device that includes a processor, storage, and communication interface to interact with a computer trained to generate answers, processing creation, specification, search, and re-creation requests to automate work procedures, reducing manual input and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If generative AI is used to create automation programs, then program development is supported, but significant manual input load is required
Solution Approach 1:
The system performs preliminary actions by automatically generating initial automation program code based on natural language descriptions of work procedures. The generative AI creates a draft program structure, variable definitions, and logic flow before the user provides feedback, reducing the manual input required from scratch.
Solution Approach 2:
The system implements iterative feedback loops where the generated automation program is evaluated against the original work procedure description, and corrections are automatically applied. User feedback on generated code triggers re-generation and refinement cycles, progressively improving accuracy while reducing manual coding time.
2Productivity
If generative AI generates automation programs directly, then program creation is accelerated, but accuracy decreases for unknown problems
Solution Approach 1:
The system dynamically adjusts its generation approach based on the complexity and familiarity of the work procedure. For known, routine tasks, it generates code quickly using templates. For unknown or complex problems, it engages in multi-turn dialogue to clarify requirements, ask clarifying questions, and iteratively refine the generated program to ensure accuracy.
Solution Approach 2:
The system introduces an intermediary evaluation layer that checks generated code against the original work procedure description, identifies gaps or inaccuracies, and requests clarification when encountering unknown problems. This intermediary step mediates between rapid generation and accuracy verification, allowing the system to maintain high speed for routine tasks while ensuring reliability for complex scenarios.
3Manufacturing precision
If detailed work procedures are manually input, then accurate automation programs are created, but the input load increases
Solution Approach 1:
The system performs self-service by automatically analyzing the natural language work procedure description, extracting key steps, variables, and logic, and generating appropriate automation code without requiring the user to manually specify every detail. The generative AI autonomously infers missing information and makes reasonable assumptions, reducing the operational burden on users while maintaining accuracy.
Solution Approach 2:
The system replaces the mechanical process of manual code writing and detailed procedure specification with an intelligent generative AI system. Instead of requiring users to mechanically input every detail, the AI naturally processes language descriptions and automatically translates them into structured automation programs, substituting human cognitive effort with machine intelligence.
Data Source
AI summary
A creation support device configured to implement generative AI, transmits, to the computer, a creation request of an automation program for automating a procedure of an operation target, receives an answer to the creation request from the computer, transmits, to the computer, a specification request for specifying the operation target and a command for executing the procedure from a program code in the answer to the creation request, receives an answer to the specification request from the computer, transmits, to the computer, a search request of an output result of data acquired from the command in the answer to the specification request, receives an answer to the search request from the computer, generates a re-creation request for re-creating the automation program using the output result in the answer to the search request, transmits the re-creation request to the computer, and receives an answer to the re-creation request from the computer.