Software Tag Dataset Creation for Faster Model Retraining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The traditional software application lifecycle delays improvements and their accessibility to end users due to manual code modifications and testing, hindering the timely update and deployment of deep learning models.
Innovation Solution
A method for creating datasets using tagged data to automatically retrieve and improve deep learning models, allowing for efficient retraining without manual code changes by associating metadata with software application data and using it to gather required input data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual code modifications and testing are used to update software applications, then reliability is improved, but speed of deployment deteriorates
Solution Approach 1:
The system performs preliminary actions by automatically creating datasets and preparing model updates before deployment. The automated dataset creation system pre-processes and prepares training data in advance, allowing models to be updated without waiting for manual code modifications and testing cycles to complete.
Solution Approach 2:
The system enables self-service by automatically generating datasets and updating deep learning models without requiring manual intervention. The automated system serves itself by retrieving data, creating datasets, and deploying model updates independently, eliminating the need for manual code modifications while maintaining reliability through systematic processes.
2Productivity
If automated dataset creation is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The system achieves universality by creating a multi-functional automated dataset creation platform that can serve multiple deep learning models across different applications. The same automated system retrieves data, creates datasets, and updates models universally, increasing productivity without proportionally increasing complexity for each individual model.
Solution Approach 2:
The system uses an intermediary automated dataset creation service that mediates between data sources and deep learning models. This intermediary layer handles the complexity of data retrieval and processing internally, presenting a simplified interface to users while maintaining high productivity through automation.
Data Source
AI summary
Traditionally, a software application is developed, tested, and then published for use by end users. Any subsequent update made to the software application is generally in the form of a human programmed modification made to the code in the software application itself, and further only becomes usable once tested, published, and installed by end users having the previous version of the software application. This typical software application lifecycle causes delays in not only generating improvements to software applications, but also to those improvements being made accessible to end users. To help avoid these delays and improve performance of software applications, deep learning models may be made accessible to the software applications for use in providing inferenced data to the software applications, which the software applications may then use as desired. These deep learning models can furthermore be improved independently of the software applications using manual and/or automated processes.