Profile-Based Prompt Engineering for Industrial Design Customization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial design applications face challenges in maintaining user-specific customization information due to storage constraints, requiring users to repeatedly select configuration options and struggle with novice users navigating complex industrial parameters.
Innovation Solution
Utilizing a Generative Artificial Intelligence (GAI) model, such as a Large Language Model (LLM) or Multi-Modal Model (MMM), to generate user-specific customized designs based on learned preferences and industry standards, reducing the need for repeated selections and simplifying the design process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If user-specific customization information is stored in a centralized repository, then user preferences can be leveraged for future projects, but storage costs and system complexity increase
Solution Approach 1:
The patent uses prompt templates that copy and structure user preferences and base design metadata into standardized formats for the GAI model. This allows user-specific customization to be maintained through reusable prompt patterns rather than storing complete customized designs, reducing storage requirements while preserving adaptability
Solution Approach 2:
The patent extracts only the essential metadata and configurable attributes from complete customized designs to create compact prompt representations. This extraction approach maintains user preference information needed for future customizations while eliminating the need to store entire design configurations, thereby reducing storage costs and system complexity
2Adaptability or versatility
If users manually select configuration options for each project, then design flexibility is maintained, but time consumption and user burden increase
Solution Approach 1:
The patent performs preliminary action by having users provide their preferences and selection criteria once, which are then stored as prompt templates. The GAI model uses these pre-established preferences to automatically configure designs for future projects, eliminating repeated manual selections while maintaining design flexibility through the structured prompt framework
Solution Approach 2:
The GAI model acts as an intermediary between user preferences and design configuration. It receives structured prompts containing user preferences and base design metadata, then generates customized designs that reflect user choices without requiring users to manually navigate complex parameter selections, thereby reducing time consumption while preserving adaptability
3Adaptability or versatility
If novice users are presented with all industrial parameters, then complete design options are available, but ease of operation decreases
Solution Approach 1:
The patent extracts and prioritizes only the most relevant configurable attributes for each base design, presenting them to users through simplified prompt templates. This extraction approach maintains access to complete design options through the GAI model's full parameter knowledge while presenting only essential selections to users, thereby improving ease of operation without sacrificing design option completeness
Solution Approach 2:
The GAI model serves as an intermediary that manages the complexity of industrial parameters. It receives user preferences through simple prompt templates, accesses the complete parameter space through base design metadata, and generates comprehensive designs without requiring users to navigate complex parameter interfaces, thus maintaining ease of operation while preserving design option completeness
Data Source
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.