Code Change Tracing With Logic Linking for AI Code Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In network environments, determining the logic underlying code changes and optimizing code commands efficiently and dynamically is challenging, especially when unexpected changes occur, leading to inefficient computing resource consumption and unnecessary duplication of code commands.
Innovation Solution
A system utilizing a large language model (LLM) and generative AI engine to identify code changes, link them to logic modules, and generate optimized code commands, reducing redundant script commands and improving tracing accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If code commands are recorded and inputs are used to generate new outputs regularly in large batches, then productivity is improved, but it becomes difficult to determine the logic underlying each code command or code change
Solution Approach 1:
The patent introduces an intermediary system comprising a large language model and a generative AI engine that acts as a mediator between code commands and their underlying logic. This intermediary automatically traces and documents the logic behind each code change, preserving information that would otherwise be lost in batch processing operations.
Solution Approach 2:
The system enables self-service by allowing the AI engine to autonomously identify code changes, trace their underlying logic, and generate optimized code commands without human intervention. This maintains productivity while ensuring logic traceability through automated documentation.
2Adaptability or versatility
If unexpected code changes are applied to the code commands, then adaptability is improved, but the logic needs to be determined efficiently, accurately, and dynamically becomes more challenging
Solution Approach 1:
The patent implements a feedback mechanism where the generative AI engine continuously monitors code changes, traces their logic, and verifies the links between logic modules and code commands. This feedback loop ensures that even unexpected code changes are accurately tracked and their logic determined with high precision.
Solution Approach 2:
The system dynamically adapts to unexpected code changes by using the large language model to identify changes in real-time and the generative AI engine to trace their logic on-demand. This dynamic approach maintains measurement precision regardless of how frequently or unexpectedly code changes occur.
3Use of energy by moving object
If code optimization is performed to improve computing resource consumption, then energy efficiency is improved, but duplicate code commands may be generated and used when unnecessary
Solution Approach 1:
The patent replaces manual code optimization processes with an AI-driven system that automatically identifies optimization opportunities. The generative AI engine analyzes code commands, traces their logic, and generates optimized alternatives only when necessary, eliminating duplicate commands while maintaining correctness through automated verification.
4Measurement precision
If manual tracing of code changes and logic is performed, then measurement precision is improved, but productivity decreases due to time-consuming analysis
Solution Approach 1:
The patent substitutes manual logic tracing with an automated AI system comprising a large language model and generative AI engine. This system maintains high measurement precision in tracing code logic while dramatically improving productivity by performing analysis automatically without human intervention.
Solution Approach 2:
The AI system acts as an intermediary that automatically performs the tedious task of logic tracing, preserving measurement precision while freeing human developers to focus on higher-value activities. The intermediary handles the time-consuming analysis at machine speed.
Data Source
AI summary
Systems, computer program products, and methods are described herein for tracing code changes and underlying logic for code optimization. The present disclosure is configured to identify a code command(s) associated with an application; apply a large language model (LLM) to the code command(s); identify, by the LLM, code change(s) in the code command(s); identify, by the LLM and based on the code change(s), a logic module(s) for the code change(s); verify, by a generative artificial intelligence (AI) engine, a link between the logic module(s) and the code command(s) comprising the code change(s), wherein the link indicates a causation of the code change(s) with the logic module(s); and generate, by the generative AI engine and based on the verification of the link, the optimized code command(s) based on the code command(s) and the logic module(s).