Semi-Supervised ML Clustering for Trouble Ticket Resolution

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems for tracking and resolving system performance issues, or trouble tickets, face inefficiencies due to recurring problems and resolutions, leading to redundant ticket generation and manual processing burdens.

Innovation Solution

A machine learning-based system that clusters and labels trouble tickets, generates resolution summaries, and predicts resolutions for new tickets by analyzing historical data, enabling automated classification and assignment to relevant clusters.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual processing of trouble tickets is used, then human judgment and flexibility are maintained, but productivity is low and manual effort is high

Engineering Contradiction:

Improveticket resolution productivityVSAvoidmanual processing effort

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system enables self-service by automatically clustering similar tickets, generating resolution summaries, and predicting resolutions without human intervention. The machine learning models autonomously process tickets, extract resolutions from log texts, and suggest fixes for new tickets, reducing the need for manual human effort in ticket management.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual processing system with an automated machine learning-based system. Instead of human operators manually reviewing and resolving tickets, the system uses trained ML models to cluster tickets, generate summaries, and predict resolutions, substituting human mechanical effort with automated computational processes.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If historical ticket data is analyzed manually, then accurate resolutions can be identified, but time consumption increases

Engineering Contradiction:

Improveresolution accuracyVSAvoiddata analysis time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by pre-processing and clustering historical ticket data during training phases. The machine learning models are trained in advance on historical data to learn patterns and relationships, so when new tickets arrive, the system can quickly retrieve and apply pre-learned knowledge without time-consuming manual analysis of historical records.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system creates copies of resolution patterns from historical data by generating resolution summaries for each cluster. These summarized resolution patterns are stored and can be quickly referenced and applied to similar future tickets, eliminating the need to manually re-analyze original historical tickets while maintaining resolution accuracy.

Inventive Principle:

Principle #26Copying

3Productivity

If recurring problems are addressed individually each time, then specific ticket details are handled, but redundancy increases and efficiency decreases

Engineering Contradiction:

Improveresolution efficiencyVSAvoidredundant processing

Core Design Contradiction:

ProductivityVSLoss of substance

Solution Approach 1:

The system merges similar tickets by clustering them based on problem characteristics and patterns. Tickets with similar issues, symptoms, and resolutions are grouped together into clusters, allowing the system to handle multiple similar tickets as a unified group rather than individually, thereby eliminating redundant processing and improving productivity.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system creates universal resolution summaries for each cluster that can be applied to multiple tickets within that cluster. A single resolution summary serves multiple similar tickets, making the resolution process universal rather than specific to each individual ticket, thus reducing redundancy and increasing efficiency.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11556843B2Predictive resolutions for tickets using semi-supervised machine learning

Publication Date: 2023.01.17 AT&T INTELLECTUAL PROPERTY I L P

AI summary

Aspects of the subject disclosure may include, for example, a method in which a processing system collects information associated with trouble tickets each including a problem abstract and a log text. The method includes analyzing the log text to obtain a problem resolution for that ticket; defining ticket clusters according to the problem abstracts, and labeling the clusters. The processing system creates a library of the labeled clusters, each entry including a cluster label, a problem abstract for that cluster, and a resolution summary for that problem abstract, indicating a mapping of the problem abstract to the resolution summary for that cluster. The method includes training, based on the mapping, machine-learning applications for a predicted resolution summary for each cluster and for classifying a new ticket. The method includes assigning the new ticket to a cluster according to the classifying. Other embodiments are disclosed.