Prediction Network for Automated Error Report Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual correlation of error reports and issue tickets is time-consuming and inefficient, especially when dealing with numerous repeating reports, as it requires significant manual effort from technical experts.
Innovation Solution
A system using a prediction network, trained on error reports and issue tickets, automatically correlates them by generating embeddings and determining categories with confidence scores, allowing for automated resolution association and issue ticket creation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual correlation of error reports and issue tickets is performed, then accuracy of correlation can be maintained, but time consumption and labor effort increase significantly
Solution Approach 1:
The patent replaces the manual mechanical correlation process with an automated prediction network system. The prediction network uses machine learning models to automatically correlate error reports with issue tickets, eliminating the need for manual human effort while maintaining correlation accuracy through trained algorithms and confidence score thresholds.
Solution Approach 2:
The patent introduces embeddings as an intermediary representation layer between error reports and issue tickets. These embeddings transform the input data into a standardized vector space where the prediction network can effectively measure similarity and perform correlation, bridging the gap between different data formats and enabling automated matching.
2Reliability
If manual correlation is performed by technical experts, then quality of correlation can be ensured, but productivity decreases due to significant manual effort required
Solution Approach 1:
The patent substitutes human technical experts with an automated prediction network system. The system processes error reports and issue tickets through trained machine learning models that automatically determine correlations, eliminating manual effort while maintaining quality through configurable confidence score thresholds and expert-system-like decision rules.
Solution Approach 2:
The prediction network system is self-sufficient in performing correlation tasks without requiring continuous human intervention. Once trained, the system autonomously processes incoming error reports and issue tickets, generating correlations based on its internal learned patterns and confidence score evaluations, thereby achieving high throughput independently.
3Productivity
If automated prediction network is implemented, then productivity and speed increase, but system complexity increases
Solution Approach 1:
The patent implements a multi-functional prediction network system that handles multiple tasks: generating embeddings for error reports and issue tickets, calculating similarity scores, determining correlations based on confidence thresholds, and managing the correlation database. This universal system replaces multiple separate manual processes, achieving high productivity while consolidating complexity into a single integrated platform.
4Measurement precision
If numerous repeating error reports are processed manually, then each report can be carefully analyzed, but the number of manual hours required increases significantly
Solution Approach 1:
The patent replaces manual analysis of numerous repeating error reports with an automated prediction network. The system efficiently processes large volumes of reports by generating embeddings and calculating similarities in vector space, maintaining analysis thoroughness through learned patterns while handling high quantities of reports that would be impractical to process manually.
Solution Approach 2:
The patent uses embeddings as simplified copies or representations of the original error reports and issue tickets. These vector representations capture the essential features and semantics of the reports, enabling efficient comparison and correlation without requiring detailed manual analysis of each full report, thus handling large quantities effectively.
Data Source
AI summary
In some embodiments, a method receives a trained model for a prediction network, wherein the trained model was trained based on machine generated input and user generated input being correlated to a plurality of categories. Machine generated input is input into the prediction network. The machine generated input is automatically generated based on an execution of an application. The method correlates the machine generated input to one or more of the plurality of categories using the trained model. A score for a respective category is output based on a confidence of the machine generated input being associated with the category. A category is selected from the plurality of categories based on the respective score of the category. The method outputs a resolution for the machine generated input based on the category. The resolution is determined from user generated input that is associated with the category.