Electronic Device Neural-Network Code Descriptions With User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing programming technologies struggle to provide personalized code descriptions that cater to individual user preferences, leading to inefficiencies in understanding and modifying code due to varying levels of user understanding and preferences.
Innovation Solution
An electronic device equipped with a neural network model that analyzes code in a programming language, generates intermediate and final answers in natural language, and adapts to user preferences by storing and updating preference information to determine priority orders and provide tailored answers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a neural network model is used to provide code descriptions, then code comprehension efficiency is improved, but the ability to match individual user preferences deteriorates
Solution Approach 1:
The system implements feedback by receiving user selections from multiple intermediate answers and using this feedback to generate a final answer. The user preference information derived from selections is stored and used to train the neural network model, creating a feedback loop that continuously improves the model's ability to match user preferences while maintaining high code comprehension efficiency
Solution Approach 2:
The system performs preliminary action by generating multiple intermediate answers before the final answer is produced. This allows the system to present users with various options and derive preference information from their selections, enabling personalized code descriptions that adapt to individual user needs while maintaining efficient comprehension
2Adaptability or versatility
If multiple intermediate answers are generated, then user preference identification is improved, but system complexity increases
Solution Approach 1:
The system segments the code description generation process into multiple intermediate answers, each representing a potential description direction. This segmentation allows the system to present diverse options to users for preference identification while keeping each individual answer generation step relatively simple, managing overall system complexity through structured division of the generation process
Data Source
AI summary
An electronic device and a controlling method of an electronic device are disclosed. The electronic device includes: a memory storing at least one instruction and at least one processor, comprising processing circuitry, individually and/or collectively, configured to execute at least one instruction, and to: input, based on a code written in a programming language being obtained, the code in a neural network model, and obtain a plurality of intermediate answers describing at least a portion of the code in a natural language, provide the plurality of intermediate answers, and input, based on an input selecting one intermediate answer from among the plurality of intermediate answers being received, information on the selected intermediate answer in the neural network model, and obtain a final answer describing the code in the natural language.