Profile-Based Prompt Engineering for Industrial Design Customization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing industrial design applications struggle with maintaining user-specific customization information due to storage constraints, requiring users to repeatedly select configuration options and lack centralized repositories for past customizations, especially for novice users unfamiliar with numerous parameters.

Innovation Solution

An industrial design application utilizing a Generative Artificial Intelligence (GAI) model, such as a Large Language Model (LLM) or Multi-Modal Model (MMM), generates user-specific customized designs based on learned preferences and industry standards, reducing the need for repeated user selections and storing extensive user preference data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If user-specific customization information is stored in a centralized repository, then user preferences can be maintained across projects, but storage costs and data management complexity increase

Engineering Contradiction:
Improveuser preference informationVSAvoidstored data volume
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent extracts and stores only the essential user preference parameters (such as component brand preferences, configuration templates, and selection patterns) rather than storing complete design histories. This selective extraction reduces data volume while preserving the core information needed for personalization.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of storing complete customization data, the system creates a simplified representation or copy of user preferences in a compact format. This allows the system to reference and apply preferences without storing the full historical data, reducing storage requirements while maintaining functionality.

Inventive Principle:
Principle #26Copying

2Manufacturing precision

If users manually select configuration options for each project, then customization accuracy is maintained, but time consumption and operational complexity increase

Engineering Contradiction:
Improveconfiguration accuracyVSAvoiddesign time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by automatically applying user's historical preference patterns and configuration templates to new projects before the user completes their selections. This pre-configures common parameters based on learned preferences, reducing the time users need to spend on manual selection while maintaining accuracy through user verification.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system provides self-service functionality where it automatically retrieves and applies configuration settings based on the user's identity and historical data. This eliminates the need for users to manually re-select common options, as the system serves itself by retrieving appropriate configurations from stored preference patterns.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If the system provides comprehensive configuration options, then design flexibility is improved, but user confusion and difficulty in selection increase

Engineering Contradiction:
Improvedesign flexibilityVSAvoiduser selection ease
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system applies local quality by providing different levels of configuration detail at different stages. For novice users, the system presents simplified pre-configured options; for experienced users, it provides access to comprehensive parameters. This localized adaptation of interface complexity ensures ease of operation while maintaining design flexibility when needed.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The configuration interface dynamically adapts its complexity based on user interaction patterns and expertise level. The system learns from user behavior to adjust the number and type of options presented, making the interface easier to operate for common tasks while preserving access to comprehensive configurations for specialized requirements.

Inventive Principle:
Principle #15Dynamics

4Productivity

If a centralized repository stores all past customizations, then user-specific designs are readily available, but system complexity and maintenance difficulty increase

Engineering Contradiction:
Improvedesign speedVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the centralized repository into modular preference categories (component preferences, configuration templates, safety standards, etc.). This segmentation allows the system to manage and retrieve specific preference types independently, reducing overall system complexity while maintaining fast access to user-specific designs through targeted queries.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4672073A1Profile-based prompt engineering for user-specific industrial automation project customization
Publication Date: 2025.12.31 ROCKWELL AUTOMATION TECH INC
  • EP4672073A1 patent drawingFigure 1
  • EP4672073A1 patent drawingFigure 2
  • EP4672073A1 patent drawingFigure 3

AI summary

The disclosure relates to an industrial design application that provides a customized user experience. In response to a user request for a design of an industrial system, the industrial design application selects generic base designs from a base design repository. Embodiments include a Generative Artificial Intelligence (GAI) model trained to generate user-customizations of the generic base designs. Once a user receives a customized base design, the user may make modifications to the customized base designs. Finalized designs may be provided to the GAI model for training on common selections made by users of the industrial design application.