18462055. ERROR CHECKING FOR CODE simplified abstract (State Farm Mutual Automobile Insurance Company)

ERROR CHECKING FOR CODE

Organization Name

State Farm Mutual Automobile Insurance Company

Inventor(s)

Brian Mark Fields of Phoenix AZ (US)

Nathan L. Tofte of Downs IL (US)

Joseph Robert Brannan of Bloomington IL (US)

Vicki King of Bloomington IL (US)

Justin Davis of Bloomington IL (US)

ERROR CHECKING FOR CODE - A simplified explanation of the abstract

This abstract first appeared for US patent application 18462055 titled 'ERROR CHECKING FOR CODE

Simplified Explanation: The patent application describes apparatuses, systems, and methods for checking code for errors using a machine learning chatbot.

Key Features and Innovation:

• Utilizes a machine learning chatbot to check target code for errors.
• Determines errors in the code based on responses from the chatbot.
• Interacts with the chatbot to determine solutions for fixing errors.
• Allows the chatbot to fix errors and present solutions to the user.

Potential Applications: This technology can be used in software development companies, coding education platforms, and automated code review systems.

Problems Solved:

• Streamlines the process of checking and fixing errors in code.
• Enhances the efficiency of code review and debugging.
• Provides real-time feedback and solutions for coding errors.

Benefits:

• Increases productivity in software development.
• Improves code quality and reliability.
• Reduces the time and effort required for code review and debugging.

Commercial Applications: The technology can be commercialized as a code review tool for software development teams, an educational tool for coding students, and an automated debugging system for programming languages.

Questions about Code Checking Technology: 1. How does the machine learning chatbot determine errors in the code? 2. What are the potential limitations of using a chatbot for code checking?

Original Abstract Submitted

Apparatuses, systems and methods are provided for checking code for errors. The apparatuses, systems and methods may send a target code and a prompt for code checking to a machine learning (ML) chatbot to cause the ML chatbot to check the target code for errors. The apparatuses, systems and methods may determine whether there is an error in the target code based at least partially on a response from the ML chatbot. The apparatuses, systems and methods may, responsive to determining that there is an error in the target code, determine, via an interaction with the ML chatbot, whether there is a solution to fix the error. The apparatuses, systems and methods may, responsive to determining that there is a solution to fix the error, cause the ML chatbot to (i) fix the error, and/or (ii) present the error and/or the solution to a user.