Crash Component Prediction Using Machine Learning for Bug Assignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Modern software systems with large and complex source code face challenges in efficiently identifying the root cause of software crashes, leading to incorrect assignment of bugs to development teams, inefficiencies in crash management systems, and delayed resolution of bugs.

Innovation Solution

A crash bug component prediction (CBCP) system that processes crash reports using machine learning (ML) models to predict software components as bug components likely responsible for crashes, allowing for accurate assignment of bugs to development teams.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual review of crash reports is used to identify bug sources, then accuracy in identifying root causes may be maintained, but time consumption and labor requirements increase significantly

Engineering Contradiction:

Improveaccuracy in identifying root causesVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical review processes with an automated machine learning-based system. The ML model automatically analyzes crash reports, stack traces, and component information to predict bug components, eliminating the need for manual examination while maintaining high accuracy in root cause identification.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by automatically processing crash reports and assigning bugs to development teams without requiring manual intervention. The ML model independently analyzes the crash data, determines bug components, and facilitates automatic assignment, allowing the system to serve itself rather than requiring continuous human oversight.

Inventive Principle:

Principle #25Self-service

2Measurement precision

If comprehensive analysis of crash reports is performed, then identification accuracy improves, but processing speed and efficiency decrease

Engineering Contradiction:

Improveidentification accuracyVSAvoidprocessing speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent substitutes manual comprehensive analysis with an automated ML-based processing system that efficiently handles crash reports. The machine learning model rapidly processes stack traces, component information, and crash data to identify bug components with high accuracy, significantly improving processing speed compared to manual methods.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes the approach by transforming crash report data into structured features and representations that the ML model can process efficiently. By converting raw crash data into standardized feature vectors and using optimized ML algorithms, the system achieves both high accuracy and fast processing speeds.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If more detailed component information is collected and processed, then prediction accuracy improves, but system complexity and computational requirements increase

Engineering Contradiction:

Improveprediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts only the essential features and information needed for accurate bug component prediction from the crash reports. By selectively extracting relevant features such as stack trace patterns, component call relationships, and crash context, the system avoids processing unnecessary data while maintaining high prediction accuracy and reducing system complexity.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system segments the crash report analysis into distinct components: extracting stack traces, identifying components, determining features, and making predictions. This segmentation allows each component to be processed independently and efficiently, reducing overall system complexity while maintaining comprehensive analysis capability.

Inventive Principle:

Principle #1Segmentation

4Productivity

If automatic bug assignment is implemented, then processing efficiency improves, but accuracy in assigning bugs to correct development teams may decrease

Engineering Contradiction:

Improveprocessing efficiencyVSAvoidassignment accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent replaces manual bug assignment with an automated ML-based system that achieves both high efficiency and accuracy. The machine learning model analyzes crash reports, identifies bug components, and automatically assigns bugs to development teams with high accuracy, eliminating the trade-off between automation and accuracy that plagues simpler automated systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12346237B2Crash bug component prediction system to identify components as potential bug sources

Publication Date: 2025.07.01 SAP SE

AI summary

Methods, systems, and computer-readable storage media for receiving a crash report provided as a computer-readable file, providing a stack trace from the crash report, adding component information to the stack trace, for each component identified in the stack trace, determining a set of features, processing sets of features through a ML model to provide a prediction identifying a component as a bug component, and assigning the bug component for resolution through a crash management system.