Ladder Logic Conversion for AI-Assisted Industrial Programming

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing language models, such as those used in AI chatbots, are unable to directly process or generate graphic programming languages used in industrial automation, like contact plans and ladder diagrams, due to their text-based nature.

Innovation Solution

A procedure and programming device that convert graphic program constructs into a text-based format, allowing AI voice models to interpret and generate graphic programming languages by representing them in a Boolean expression format and integrating non-Boolean expressions between Boolean ones.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If graphical programming languages are used for industrial automation, then ease of operation and visualization are improved, but compatibility with text-based language models deteriorates

Engineering Contradiction:
Improveease of programmingVSAvoidcompatibility with language models
Core Design Contradiction:
Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent introduces an intermediary conversion process that transforms graphical program constructs into text-based representations with semantic annotations. This intermediary format serves as a bridge between graphical programming languages (preferred by automation engineers) and text-based language models, enabling both to work together without direct compatibility requirements.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter representation by converting visual/spatial parameters of graphical constructs into textual parameters with semantic meanings. The conversion process transforms graphical elements into annotated text strings that preserve the essential semantic information needed for language model processing while maintaining the original graphical program's functionality.

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If graphical languages are converted to text format for language model processing, then compatibility with AI systems is improved, but information loss and readability deterioration may occur

Engineering Contradiction:
Improvecompatibility with language modelsVSAvoidsemantic information loss
Core Design Contradiction:
Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent applies preliminary action by pre-annotating the text-based representation with semantic information before processing by the language model. The conversion process embeds metadata and semantic markers into the text format in advance, ensuring that crucial information is preserved and readily available for AI processing without requiring complex real-time interpretation.

Inventive Principle:
Principle #10Preliminary action

3Extent of automation

If complex graphical program constructs are converted to text, then AI processing capability is improved, but text complexity and processing difficulty increase

Engineering Contradiction:
ImproveAI processing capabilityVSAvoidtext format complexity
Core Design Contradiction:
Extent of automationVSDevice complexity

Solution Approach 1:

The patent applies segmentation by breaking down complex graphical program constructs into smaller, manageable text segments with clear semantic boundaries. Each graphical element or sub-construct is converted into a discrete text unit with annotations, making the overall complex program representable as a sequence of simpler, independently processable text segments for the language model.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4530824A1Method and apparatus for using graphical industrial program structures with a language model
Publication Date: 2025.04.02 SIEMENS AG
  • EP4530824A1 patent drawingFigure 1~2
  • EP4530824A1 patent drawingFigure 3
  • EP4530824A1 patent drawing

AI summary

The invention relates to a method and a programming device for using an artificial intelligence system with a text-based language model, in particular a generative pre-trained chatbot, to process at least one graphical program construct (GP1, GP2) with a number of program expressions in a graphical industrial programming language, in particular a coupling plan. For inputting the graphical program construct (GP1, GP2) into the system, the graphical program expressions are converted into a sequence of Boolean program expressions in text form (TP1), wherein non-Boolean, in particular text-based, program expressions (MOVE; CMP) of the graphical program construct (GP1, GP2) are integrated between the adjacent Boolean program expressions.Thus, language models can be used to learn and use the structures of ladder logic programs, especially as an aid for analyzing program constructs and for AI-based assistance in the creation and further development of industrial software in automation technology.