Building software applications using natural language and machine learning models.

A natural language and machine learning-based system simplifies software development by translating user instructions into executable code, addressing the challenge of diverse skill requirements and enhancing accessibility and efficiency.

JP2026522237APending Publication Date: 2026-07-07BRAIN TECHNOLOGIES INC
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
BRAIN TECHNOLOGIES INC
Filing Date
2024-05-31
Publication Date
2026-07-07

AI Technical Summary

Technical Problem

The high specialization and diverse skill sets required in software development make it difficult for individuals to create fully functional applications, as most people lack proficiency in multiple programming aspects, such as web design, back-end development, and specific languages like Python or Java.

Method used

A system utilizing natural language and machine learning models to translate user instructions into executable code, allowing non-technical users to construct software applications by specifying ideas in a conversational manner, with machine learning models enhancing accuracy and efficiency in code generation.

Benefits of technology

This approach simplifies software development by making it accessible to non-programmers, reduces development time, minimizes errors, and enables continuous learning and adaptation through user interaction, improving accessibility, efficiency, and responsiveness.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026522237000001_ABST
    Figure 2026522237000001_ABST
Patent Text Reader

Abstract

The system can receive nodes and edges representing a dynamic layout software program. The program is represented by nodes and edges, where at least one node represents an initial state for an end user to provide input, and at least one edge represents an executable routine whose functionality is specified in natural language by the software developer. At runtime, the system executes the program's initial state, receives input from the end user, and extracts the program's executable elements. The executable elements include the input and the executable routine specified in one of the edges. The system applies a machine learning model to analyze the executable elements and generates a machine learning-enabled scripting language that connects the executable elements. The machine learning-enabled scripting language contains the program's runtime layout parameters. When the machine learning-enabled scripting language is executed, the program displays one or more layout elements determined at runtime.
Need to check novelty before this filing date? Find Prior Art