AI Task Time Estimation for Repeatable Software Operations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Estimating software project and task completion time is a manual, time-consuming process due to the heterogeneity of software development tasks, making accurate estimation difficult.
Innovation Solution
A machine-learning enabled time estimation engine utilizing large-language models and image processing AI to automatically estimate task completion time based on a training dataset of predictable and repeatable software tasks, such as compliance, security patching, and upgrading tasks, by analyzing text or video descriptions of the tasks and their steps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual estimation methods are used for software tasks, then flexibility in handling heterogeneous tasks is maintained, but estimation time and resource consumption increase significantly
Solution Approach 1:
The system performs preliminary actions by collecting historical task data, operations, and time-to-complete information in advance. This training data is used to pre-train machine learning models before actual estimation is needed, enabling rapid automated estimations without manual analysis during the estimation phase itself.
Solution Approach 2:
The patent introduces an intermediary machine learning model that acts as a mediator between historical task data and new task estimations. The model processes and learns from historical operations and time-to-complete data, then applies this learned knowledge to automatically estimate completion times for new tasks without requiring manual estimation for each task.
2Measurement precision
If automated machine learning estimation is implemented, then estimation speed and consistency improve, but system complexity and data processing requirements increase
Solution Approach 1:
The system segments the estimation problem into distinct components: historical data collection, data preprocessing, model training, and deployment. By dividing the complex task into manageable segments with specific functions, the system reduces overall complexity while maintaining estimation accuracy through specialized processing at each stage.
Solution Approach 2:
The machine learning model performs self-service by automatically learning from historical task data and operations without requiring manual configuration or adjustment for each new task. The system trains on its own historical data and applies the learned patterns autonomously to generate estimations, reducing the need for complex manual intervention and system management.
Data Source
AI summary
Software compliance, security patching, and upgrading tasks may have similarities with one other. These peculiarities of this sort of software projects and tasks and underlying steps lend to automation of estimating completion time thereof. The presently disclosed technology leverages the peculiarities of a subset of predictable and repeatable software tasks to apply large-language models (LLMs) and image processing artificial-intelligence (AI) to automatically estimate the completion time of a task given the steps required. The presently disclosed technology further includes a software tool backed by an artificial intelligence model that iteratively tunes a training data set to update and optimize the completion time of a task given the steps required.