NLP Issue Description Generation for IT Incident Labeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In the information technology services industry, extracting appropriate descriptions and labels from user-inputted incident descriptions is a challenging task due to the presence of noise in user data, such as missing punctuation, misspellings, and free text, which leads to incorrect label assignment and inefficiencies in identifying repeating issues and problem areas.

Innovation Solution

A method and system that uses a processor to analyze user-input data, select and prompt issue descriptions, and generate concise issue descriptions while labeling them with confidence tags, utilizing machine learning techniques and natural language processing to improve accuracy and efficiency in issue identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If administrators manually analyze and categorize user-inputted incident descriptions, then they can understand and label issues, but it requires significant time and resources

Engineering Contradiction:

Improvelabel assignment accuracyVSAvoidtime required to understand and categorize issues

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by automatically analyzing incident descriptions and generating issue labels without requiring administrator intervention. The natural language processing engine autonomously categorizes incidents, extracting key information and assigning appropriate labels, thereby eliminating the time-consuming manual analysis process while maintaining accurate label assignment.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual analysis process with an automated natural language processing system. The processor-based engine uses machine learning algorithms to analyze incident descriptions, identify patterns, and generate labels, substituting human cognitive work with computational processing that is both faster and consistently accurate.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If administrators manually categorize IT issues, then they can identify problem areas, but the process is inefficient and resource-intensive

Engineering Contradiction:

Improveidentification of repeating issues and problem areasVSAvoidefficiency in issue identification

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system autonomously identifies repeating issues and problem areas by continuously analyzing incident descriptions without administrator involvement. The natural language processing engine automatically detects patterns, correlates incidents across multiple dimensions, and generates reliable identifications of problem areas, thereby improving both reliability and productivity simultaneously.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent implements continuous automated analysis of incident descriptions, allowing the system to constantly identify and track repeating issues and problem areas. This continuous processing enables real-time insights into system-wide patterns without interrupting administrative workflows, significantly improving productivity while maintaining high reliability through consistent pattern recognition.

Inventive Principle:

Principle #20Continuity of useful action

3Ease of operation

If user data is accepted as free text input, then users can describe issues in their own words, but noise such as misspellings and missing punctuation leads to incorrect label assignment

Engineering Contradiction:

Improveuser ability to describe issuesVSAvoidlabel assignment accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces a natural language processing engine as an intermediary between user input and label assignment. This intermediary layer processes free-text incident descriptions, corrects misspellings, handles missing punctuation, and extracts meaningful information before generating labels. This intermediary processing maintains ease of operation by accepting any user input while ensuring high label assignment accuracy through systematic data cleaning and analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11694025B2Cognitive issue description and multi-level category recommendation

Publication Date: 2023.07.04 KYNDRYL INC

AI summary

A processor may receive first issue data. The first issue data may be associated with input data entered by a user into a user interface on the issue submission application. The processor may analyze the first issue data. The processor may select a first set of prompted issue descriptions. The first set of prompted issue descriptions may be selected based on analyzing the first issue data. The processor may prompt the user to select a subset of the first set of prompted issue descriptions. The processor may receive from the user a selected subset of the first set of prompted issue descriptions. The processor may output an identified issue description. The identified issue description may be generated based on the selected subset of the first set of prompted issue descriptions.