Classifier Set for Accurate Defect Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing defect prediction methods using single decision trees often suffer from overfitting or underfitting, especially when dealing with multiple classification labels, making it difficult to accurately and quickly locate fault points in products.
Innovation Solution
A defect prediction method that selects a training attribute set from pre-stored product fault records, combines it with a target attribute to form a training set, and generates a classifier set comprising multiple tree classifiers, which are combined based on error rates and false prediction rates to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a single decision tree is used for defect prediction, then the prediction process is simple and fast, but the prediction accuracy deteriorates due to overfitting or underfitting
Solution Approach 1:
The patent combines multiple decision tree classifiers into a classifier set to work together for defect prediction. Each tree classifier processes the training data independently, and their results are aggregated through voting or weighted combination, thereby improving prediction accuracy while maintaining reasonable processing speed through parallel operation.
Solution Approach 2:
The patent changes the parameter of classifier quantity from single to multiple, and introduces weighting parameters for different tree classifiers based on their error rates. This parameter transformation allows the system to balance between individual tree simplicity and ensemble accuracy, resolving the overfitting/underfitting issue.
2Measurement precision
If multiple tree classifiers are combined into a classifier set, then prediction accuracy is improved, but the system complexity increases
Solution Approach 1:
The patent segments the defect prediction task into multiple independent decision tree classifiers, each handling specific aspects of the classification problem. This segmentation allows parallel development and training of individual trees, making the overall system more manageable despite the increased number of components.
Solution Approach 2:
Each tree classifier in the set independently processes training data and generates predictions without requiring complex coordination with other trees. The self-service capability of individual classifiers reduces the overall system complexity by minimizing inter-component dependencies and control overhead.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Embodiments of the present invention disclose a defect prediction method and apparatus, which relate to the data processing field, and implement accurate and quick locating of a defect in a faulty product. A specific solution is as follows: selecting a training attribute set from a pre-stored product fault record according to a target attribute, and combining the target attribute and the training attribute set into a training set, where the target attribute is a defect attribute of a historical faulty product; generating a classifier set according to the training set, where the classifier set includes at least two tree classifiers; and predicting a defect of a faulty product by using the classifier set as a prediction model. The present invention is used in a process of predicting a defect of a faulty product.