Natural Language Comprehension Tables for Software Change Histories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Managing and organizing a large number of change histories in software development becomes complicated when the number of updates is high or time has elapsed since the latest update, especially in collaborative environments like Git.
Innovation Solution
Utilizing a natural language model to generate comprehension tables from change history data, allowing users to query and manage software development information more effectively by interpreting user prompts and organizing change history data into structured tables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Git is used to track change histories in software development, then the ability to record and track changes is improved, but the complexity of managing and understanding a large number of change histories increases
Solution Approach 1:
The patent introduces an intermediary system that acts as a mediator between the raw change history data and the user. This intermediary automatically generates natural language explanations and summaries of change histories, transforming complex technical data into understandable information without requiring users to directly analyze the raw change logs themselves.
Solution Approach 2:
The patent replaces the manual mechanical process of analyzing change histories with an automated AI-based system. Instead of users manually reviewing and understanding each change history entry, an automated natural language generation system processes the change data and produces comprehensible explanations, substituting human cognitive effort with computational processing.
2Quantity of substance
If the number of updates increases in software development, then the amount of information recorded is improved, but the difficulty of tracking and understanding each change increases
Solution Approach 1:
The patent extracts the essential meaning and purpose from large volumes of change history data using natural language generation. Instead of presenting all raw change information, the system extracts and presents only the relevant explanatory content in natural language, separating the essential understanding from the voluminous raw data.
Solution Approach 2:
The patent transforms the parameter of change history presentation from raw technical data format to natural language explanation format. This parameter change in how information is expressed makes the data more accessible and easier to understand while maintaining the complete information content.
3Duration of action of stationary object
If change histories are tracked over long periods, then the completeness of software evolution record is improved, but the complexity of reviewing and comprehending changes increases
Solution Approach 1:
The patent replaces the manual cognitive process of reviewing long-term change histories with an automated natural language generation system. The AI system processes accumulated change data over time and automatically produces comprehensible explanations, eliminating the need for users to manually comprehend complex historical change patterns.
Solution Approach 2:
The patent introduces a natural language explanation system as an intermediary between long-term change history data and users. This intermediary continuously processes and explains changes as they accumulate over time, maintaining comprehensibility regardless of the time period or volume of changes.
Data Source
AI summary
In an information processing device, a data acquisition means acquires change history data concerning a change of software. A prompt acquisition means acquires a prompt which is described and instructs to create a comprehension table based on the change history data. A table creation means interprets the prompt using a natural language model and creates a comprehension table based on the change history data. A storage means stores the comprehension table in a storage unit.