Natural Language MDE Generation With Skill Chains for CAD Portability

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing CAD applications for multi-dimensional entity (MDE) design are labor-intensive, require skilled developers, and limit the portability and ease of transfer between different design applications and environments.

Innovation Solution

A system that generates MDEs using natural language input, employing a machine learning model with a skill chain approach, allowing users to describe MDEs through natural language prompts, which are processed by multiple skills to produce MDE output in various formats.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If traditional CAD applications are used for MDE design, then manufacturing precision and design control are improved, but device complexity and skill requirements increase

Engineering Contradiction:

Improvedesign controlVSAvoidskill requirements

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent introduces natural language as an intermediary between the user and the CAD system. Users can describe design intentions in natural language, which is then translated by the machine learning model into precise MDE specifications, eliminating the need for users to master complex CAD software while maintaining design precision

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical interaction with complex CAD software interfaces with an automated machine learning-based system. The ML model automatically interprets natural language input and generates MDE outputs, substituting manual操作 with automated intelligent processing

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If traditional CAD applications are used for MDE creation, then design precision is improved, but productivity and time efficiency deteriorate

Engineering Contradiction:

Improvedesign precisionVSAvoidtime efficiency

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The machine learning model performs self-service by automatically interpreting natural language input and generating complete MDE specifications without requiring iterative manual adjustments. The system autonomously completes the design process from concept to specification

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary action by pre-processing natural language input through embedding and skill chain identification before generating the final MDE output. This preliminary processing structure enables rapid and accurate design generation

Inventive Principle:

Principle #10Preliminary action

3Manufacturing precision

If MDEs are created in specific CAD applications, then manufacturing precision is improved, but adaptability and portability worsen

Engineering Contradiction:

Improvedesign accuracyVSAvoidportability

Core Design Contradiction:

Manufacturing precisionVSAdaptability or versatility

Solution Approach 1:

The patent creates a universal MDE representation that can be used across multiple applications and environments. The standardized output format from the machine learning model enables the same MDE to be utilized in different CAD systems, manufacturing processes, and design tools without loss of precision

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent segments the design process into distinct components: natural language input processing, skill chain identification, MDE generation, and output formatting. This segmentation allows the MDE to be independently extracted and transferred between different applications while maintaining its integrity and precision

Inventive Principle:

Principle #1Segmentation

4Manufacturing precision

If skilled developers are used for MDE design, then design quality is improved, but productivity and accessibility worsen

Engineering Contradiction:

Improvedesign qualityVSAvoidaccessibility

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The machine learning model performs the work previously requiring skilled developers autonomously. By embedding design expertise within the ML model, the system provides self-service capabilities that maintain high design quality while making the tool accessible to users without specialized training

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The natural language interface acts as an intermediary that translates user intentions into professional-grade design specifications. This intermediary layer eliminates the need for users to acquire expert knowledge while preserving design quality through the ML model's trained capabilities

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12499314B2Multi-dimensional entity generation from natural language input

Publication Date: 2025.12.16 MICROSOFT TECHNOLOGY LICENSING LLC

AI summary

Aspects of the present disclosure relate to systems and methods for creating a multi-dimensional entity (MDE) based on natural language (NL) input. A user may provide NL input into an application. One or more skills may be identified for the NL input, each of which has an associated prompt template. For example, a skill is associated with a computer-aided design and/or three-dimensional manufacturing application and/or file format, thereby enabling the generation of output associated with such applications and/or file formats. In examples, a skill chain may be generated that includes one or more skills with which to generate MDE output accordingly.