Bug Deduplication via Neural Encoding and Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing bug tracking systems generate duplicate bugs, leading to a high cognitive burden for users in identifying and addressing redundant issues, as they often document the same problem multiple times, resulting in inefficient corrective actions.

Innovation Solution

A bug deduplication system that encodes sections of bugs using neural network algorithms, applies classification models to generate confidence scores, and provides a deduplication report to clients for initiating corrective actions, thereby identifying and removing redundant bugs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If bug tracking systems monitor applications to identify issues, then system reliability is improved, but duplicate bugs increase leading to user cognitive burden

Engineering Contradiction:

Improvesystem reliabilityVSAvoidbug management complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses encoding to create simplified representations (copies) of bug reports. Instead of manually comparing full bug texts, the system encodes bugs into compact forms that preserve essential similarity information, enabling efficient duplicate detection without processing the complete complexity of original bug reports

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces manual mechanical comparison of bug reports with automated classification models. These models automatically analyze encoded bug representations and determine duplicates, substituting human cognitive effort with computational processes that scale efficiently

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If users manually identify and address duplicate bugs, then corrective actions are taken, but time and cognitive resources are wasted

Engineering Contradiction:

Improvecorrective action efficiencyVSAvoidtime for identifying duplicates

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent performs preliminary classification and encoding of bugs as they are reported, preparing them for duplicate detection in advance. This preliminary processing enables rapid duplicate identification when new bugs arrive, rather than performing comprehensive comparisons only when duplicates are suspected

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent implements feedback mechanisms where classification results and confidence scores are provided to users, enabling them to quickly verify or correct automated duplicate detections. This feedback loop accelerates the overall process by reducing manual inspection time while maintaining accuracy

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11507451B2System and method for bug deduplication using classification models

Publication Date: 2022.11.22 EMC IP HLDG CO LLC

AI summary

A method for managing bugs includes obtaining, by a bug deduplication system, a set of bugs, performing an encoding on each section of a first bug of the set of bugs to obtain encoded sections, wherein the encoded sections comprise a first encoded section and a second encoded section, applying a first classification model to the first encoded section to obtain a first section score, applying a second classification model to the second encoded section to obtain a second section score, generating a confidence score based on the first encoded section and the second section, and providing the confidence score to a client, wherein the client initiates a corrective action for the first bug based on the confidence score.