Multi-Model Output Selection for Reliable Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data analysis systems using single machine learning models are prone to errors and overfitting, leading to unreliable results, especially in critical applications where accuracy estimation is crucial.
Innovation Solution
A method involving multiple data processing operations with differing characteristics, each producing outputs that are compared for similarity and accuracy, using a relationship derived from training data to select the operation with the highest predicted accuracy for further analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single machine learning model is used for data analysis, then the system complexity is low, but the reliability and accuracy of results deteriorate due to errors and overfitting
Solution Approach 1:
The patent divides the data analysis task into multiple independent processing operations, each performing the same function but with different characteristics. These segmented operations are executed in parallel, and their outputs are combined to produce the final result. This segmentation approach improves reliability by distributing the analytical burden across multiple independent paths, reducing the impact of any single operation's errors or overfitting.
Solution Approach 2:
The patent merges the outputs from multiple data processing operations through a combination process. The outputs are aggregated and integrated to form a consolidated result, which leverages the strengths of individual operations while compensating for their weaknesses. This merging process enhances the overall reliability and accuracy of the data analysis by combining multiple perspectives on the same input data.
2Measurement precision
If multiple data processing operations are used to improve reliability, then the accuracy of results improves, but the device complexity increases
Solution Approach 1:
The patent implements multiple data processing operations that share a common functional framework and structure. Each operation is designed to perform the same core analytical function but with different parameters or characteristics, making them universally applicable to the same type of data. This universality reduces system complexity compared to having entirely different processing systems, while still achieving improved measurement precision through the diversity of operational characteristics.
3Reliability
If multiple data processing operations are implemented, then the reliability of results improves, but the processing time increases
Solution Approach 1:
The patent employs periodic action by executing multiple data processing operations in a structured sequence or parallel fashion, where each operation contributes to the final result at different stages or simultaneously. This periodic execution pattern allows the system to maintain high reliability through multiple processing passes while managing time loss through efficient scheduling and parallelization of operations.
Solution Approach 2:
The patent creates multiple copies of the data processing pipeline, each instance performing the same analytical function with different operational characteristics. These copied operations are executed in parallel, which improves reliability through redundancy while minimizing time loss by utilizing concurrent processing. The copying approach allows the system to leverage multiple identical processing paths simultaneously rather than sequentially.
Data Source
AI summary
A method of selecting an operation for analysis of data, the method comprising: processing the data using at least two operations, wherein each of the at least two operations are different, to obtain a set of outputs including the output associated with each operation; determining an output from the set of outputs with the highest predicted accuracy; and selecting the operation associated with the determined output for further analysis of data; wherein the determination of the output with the highest predicted accuracy comprises: selecting an output from the set of outputs; calculating a degree of similarity between the selected output and another output of the set of outputs; using the degree of similarity to predict the accuracy of the selected output based on a relationship between the similarity of the outputs and the accuracy of the outputs, the relationship being derived from an analysis of the degrees of similarity between the outputs of the operations on training data including ground truth and the accuracy of each output compared to the ground truth; selecting a further output from the set of outputs; calculating a further degree of similarity between the selected further output and another output of the set of outputs; using the further degree of similarity to predict the accuracy of the further selected output based on the relationship; and determining the output with the highest predicted accuracy of the selected outputs.