Data Processing Apparatus for Abnormality Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data analysis methods for identifying the cause of abnormalities in manufactured products are inefficient and inaccurate, relying heavily on human intervention and machine learning algorithms that struggle with large datasets and low abnormality ratios, leading to reduced processing efficiency and accuracy.
Innovation Solution
A data processing method that involves obtaining sample data, displaying a sample distribution diagram, determining a focus threshold to classify positive and negative samples, and screening data based on filtering thresholds, allowing for more accurate analysis and classification of abnormality causes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning algorithms are used to analyze large datasets with low abnormality ratios, then analysis accuracy may be improved, but processing efficiency deteriorates
Solution Approach 1:
The patent segments the dataset into normal samples and abnormal samples based on focus thresholds, allowing the system to process different segments with appropriate methods. This segmentation enables efficient filtering of normal data while concentrating analysis resources on abnormal cases, thus improving both accuracy and efficiency.
Solution Approach 2:
The patent extracts abnormal samples from the large dataset using focus thresholds and sample distribution diagrams. By taking out only the relevant abnormal cases for detailed analysis, the system avoids processing the entire large dataset, thereby maintaining high accuracy while improving processing efficiency.
2Measurement precision
If heavy human intervention is used in data analysis, then analysis accuracy may be improved, but processing efficiency deteriorates
Solution Approach 1:
The patent implements self-service through automated focus threshold determination and sample classification systems. The system automatically calculates focus thresholds based on sample distribution and classifications samples without requiring manual intervention, thereby maintaining accuracy while dramatically improving processing efficiency.
Solution Approach 2:
The patent uses feedback mechanisms where the system continuously refines focus thresholds based on the distribution of classified samples. This automated feedback loop enables the system to improve accuracy over time without requiring human intervention, resolving the contradiction between accuracy and efficiency.
3Productivity
If focus thresholds are determined automatically based on sample distribution, then processing efficiency is improved, but measurement precision may deteriorate
Solution Approach 1:
The system uses feedback from sample distribution analysis to automatically adjust and refine focus thresholds. By continuously monitoring the distribution of classified samples and adjusting thresholds accordingly, the system maintains high measurement precision while benefiting from automated processing efficiency.
Solution Approach 2:
The patent performs preliminary analysis of sample distribution before determining final focus thresholds. This preliminary action allows the system to pre-calculate optimal thresholds based on data characteristics, ensuring both automated efficiency and accurate precision in the subsequent classification process.
Data Source
AI summary
A data processing method, includes: obtaining sample data in response to a user's input operation on a graphical interface, the sample data including characteristic data and detection data of samples; displaying a sample distribution diagram on the graphical interface based on the sample data; obtaining a focus threshold used for classifying positive and negative samples, the focus threshold being determined based on the detection data of the samples; displaying a mark of the focus threshold in the sample distribution diagram on the graphical interface; distinguishing data display effects of the positive and negative samples based on the focus threshold; and determining a cause of abnormality of the samples based on the positive and negative samples.