Task Execution Order Determination for Machine Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Determining an appropriate execution order for multiple tasks in machine learning models is challenging, especially when there are a large number of tasks, as it affects prediction accuracy and is difficult for humans to optimize independently.
Innovation Solution
A device and method for determining the execution order of tasks by creating frequency distributions of correct answer labels, calculating statistics, and training provisional models to evaluate prediction accuracy, allowing outputs from previous tasks to be input to subsequent tasks, and considering user-designated orders or auxiliary tasks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple machine learning models are connected and trained independently, then each model can be optimized for its specific task, but the overall prediction accuracy for sequential tasks is limited
Solution Approach 1:
The system automatically determines the optimal execution order of tasks by analyzing the relationships between tasks and training data, without requiring manual intervention. The processor autonomously evaluates task dependencies and sequences them to maximize prediction accuracy, allowing the system to serve itself in optimizing its own performance.
Solution Approach 2:
The system changes the parameter of task execution order from a fixed or manual configuration to a dynamically determined sequence based on statistical analysis of task relationships. By optimizing the ordering parameter, the system achieves improved prediction accuracy while maintaining manageable complexity through automated determination.
2Adaptability or versatility
If a large number of tasks are present, then the system can handle more complex prediction scenarios, but it becomes difficult for humans to determine appropriate execution orders
Solution Approach 1:
The system performs self-optimization by automatically analyzing task relationships and determining execution orders without human intervention. The processor evaluates the complexity of task relationships and autonomously sequences them, making the system adaptable to large numbers of tasks while eliminating the operational burden on users.
Solution Approach 2:
The system introduces an intermediary processing layer that automatically handles the complex determination of task execution orders. This intermediary function translates complex task relationships into optimized sequences, allowing users to simply define tasks while the system manages the complexity of ordering them appropriately.
3Reliability
If outputs of previous tasks are input to subsequent tasks, then prediction accuracy is improved, but the complexity of coordinating task outputs increases
Solution Approach 1:
The system automatically identifies and establishes the coordination relationships between task outputs and inputs. The processor analyzes task dependencies and autonomously configures the data flow between tasks, eliminating the need for manual coordination while achieving improved prediction accuracy through sequential task execution.
Solution Approach 2:
The system performs preliminary analysis of task relationships and pre-determines the execution order and data flow requirements before actual task execution. By preparing the coordination framework in advance, the system simplifies the runtime complexity of coordinating task outputs while maintaining high prediction accuracy.
Data Source
AI summary
There is provided a device for determining an execution order of a plurality of tasks, the device including: processor; and a memory connected to or built in the processor, in which the processor is configured to execute execution order determination processing of determining an execution order of the plurality of tasks under a condition that an output of at least one task of the tasks is input to the task in a subsequent stage.