Automated Functional Design Generation via Natural Language

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing process of transforming static software application designs into functional designs is time-consuming and costly due to the need for multiple revisions, and the ultimate design may not be optimal for its intended purpose.

Innovation Solution

A system architecture that includes a designer system, application design management server, and test systems, utilizing natural language commands to generate functional software application designs, where design tools use speech-to-text and natural language processing to create and refine designs, and machine learning models to improve design effectiveness based on user interactions and feedback.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a designer creates static user interface mockups and a software developer manually codes functional implementations, then the design can be transformed into a working application, but the process becomes time-consuming and expensive due to multiple revisions

Engineering Contradiction:

Improvedesign effectivenessVSAvoiddevelopment time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical process of coding with an automated system that uses machine learning models to generate functional code from design mockups. The system automatically analyzes design elements, generates corresponding code structures, and creates working applications without manual programming, thereby reducing development time while maintaining design effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary automated design system that acts as a bridge between static design mockups and functional code. This intermediary system uses natural language processing and machine learning to translate design elements into working code, eliminating the need for manual coding and reducing revision cycles.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If multiple revisions are made throughout an application's design, then the design can be optimized to achieve its original purpose, but the process becomes time-consuming and expensive

Engineering Contradiction:

Improvedesign adaptabilityVSAvoiddevelopment efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a self-service system where the automated design tool enables designers to independently make and test design revisions without requiring software developers for each change. The system automatically generates functional code from design mockups, allowing designers to iterate rapidly and optimize their designs while maintaining high productivity.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent incorporates feedback mechanisms where the system automatically tests generated code and provides information about design effectiveness. This feedback loop enables rapid iteration and optimization of designs while maintaining high productivity, as designers can quickly see the impact of their changes without manual re-coding.

Inventive Principle:

Principle #23Feedback

3Ease of manufacture

If a software developer manually codes functional implementations from design mockups, then the design can be transformed into a working application, but extensive coding is required which increases cost and time

Engineering Contradiction:

Improvedesign implementation easeVSAvoidcoding complexity

Core Design Contradiction:

Ease of manufactureVSDevice complexity

Solution Approach 1:

The patent replaces the complex manual coding process with an automated system that uses machine learning models to generate functional code from design mockups. The system automatically analyzes design elements, generates corresponding code structures, and creates working applications without manual programming, thereby simplifying the implementation process while maintaining design effectiveness.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses copying by training machine learning models on existing design patterns and code structures. The system learns from examples of successful design-to-code transformations and applies these learned patterns to generate functional code from new design mockups, reducing the complexity of the implementation process.

Inventive Principle:

Principle #26Copying

Data Source

PatentUS20190034172A1Systems and methods for generating functional application designs

Publication Date: 2019.01.31 HUMA AI

AI summary

A method and apparatus for generating functional application designs is described. The method may include receiving one or more natural language utterances corresponding to natural language design commands for editing an application being designed. The method may also include editing one or more components of the application being designed based on each of the natural language utterances. Furthermore, the method may include generating a functional instance of the application being designed.