Ticket Criticality Validation Using Similar-Item Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing customer service ticket processing systems often misclassify high-priority items as false positives, leading to inefficiencies in resource allocation and potential wasting time when personnel could have been resolving customer service tickets that should not have been classified correctly.

Innovation Solution

A binary classification model is used to solve the aforementioned technical problems. This solution employs a binary classification model to classify and prioritize customer service tickets, utilizing a self-supervised learning approach to identify false positives and false negatives, and a robustness evaluation module to ensure accurate classification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated classification models are used to prioritize customer service tickets, then processing efficiency is improved, but misclassification of high priority tickets as false positives occurs

Engineering Contradiction:

Improveticket processing efficiencyVSAvoidclassification accuracy

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent introduces an intermediary validation process between the automated binary classification model and the final ticket prioritization. This intermediary step involves operators reviewing candidate false positive items and providing feedback, which mediates between the automated system's output and the actual classification decision, thereby reducing misclassification while maintaining efficiency

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements a feedback mechanism where operator validations of candidate false positive items are fed back into the system. This feedback loop allows the classification model to learn from operator corrections and improve its accuracy over time, resolving the contradiction between automated efficiency and classification reliability

Inventive Principle:

Principle #23Feedback

2Measurement precision

If strict validation criteria are applied to reduce false positives, then classification precision is improved, but processing time increases

Engineering Contradiction:

Improveclassification precisionVSAvoidvalidation processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial validation by focusing operator attention only on candidate false positive items identified by the binary classification model, rather than validating all tickets. This selective approach maintains high precision for critical items while minimizing the time loss associated with comprehensive validation

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12614189B2Evaluating criticality classifications of items using binary classification models and a validation of similar items

Publication Date: 2026.04.28 DELL PROD LP

AI summary

Techniques are provided for evaluating criticality classifications of items using a binary classification model. One method includes obtaining information characterizing an item having a designated criticality classification; applying at least a portion of the information characterizing the item to an encoder that generates an encoded vector characterizing the item; applying the encoded vector characterizing the item to a binary classification model, wherein the binary classification model identifies candidate false positive items; evaluating the candidate false positive items by comparing the candidate false positive items to similar previously processed items having a validated false positive classification; and initiating an automated action based on a result of the evaluating. The items may comprise customer service tickets that may be labeled with the designated criticality classification by a customer service ticketing system.