AI Close Note Generation for Incident Management

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current incident management systems face challenges in generating complete and accurate close notes, which are essential for future incident resolution and change requests, due to time constraints and the noisy nature of conversation data.

Innovation Solution

The system automatically generates close notes by analyzing conversations from collaborative channels, separating independent conversations, determining message intents, clustering similar messages, generating summaries for each cluster, and combining these summaries to create a coherent interaction summary.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If experts manually write close notes after incident resolution, then the close notes can capture incident details, but the close notes are often short or incomplete due to time constraints

Engineering Contradiction:

Improvecompleteness of close notesVSAvoidtime required to write close notes

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary action by automatically generating close notes immediately after incident resolution through AI-powered conversation analysis. The system processes collaboration platform data, separates independent conversations, determines message intents, clusters similar messages, and generates comprehensive summaries without requiring additional time from experts, thus capturing complete incident details while eliminating manual documentation time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements self-service by enabling automatic close note generation that serves itself through AI algorithms. The system independently analyzes conversation data, identifies key information, and produces structured close notes without human intervention, allowing the incident management system to automatically document resolutions while maintaining information completeness and eliminating manual writing requirements

Inventive Principle:

Principle #25Self-service

2Quantity of substance

If conversation data from collaborative channels is used directly for incident analysis, then the data contains rich information, but the noisy nature of conversations reduces effectiveness for predictive algorithms

Engineering Contradiction:

Improveamount of conversation dataVSAvoidquality of conversation data for algorithms

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system applies segmentation by dividing the noisy composite conversation into separate independent conversations. The system processes collaboration platform data, identifies distinct conversation threads, and separates them individually. This segmentation isolates relevant information from noise, allowing predictive algorithms to process structured, organized data while retaining the rich information content from multiple conversation sources

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system extracts valuable information from noisy conversation data through intent determination and message clustering. By analyzing each message's intent and grouping similar messages together, the system separates signal from noise, extracting only the relevant incident-related information needed for predictive algorithms while discarding conversational filler and irrelevant content

Inventive Principle:

Principle #2Taking out (Extraction)

3Reliability

If close notes are made more detailed and complete, then the effectiveness for future incident resolution improves, but the time required to create close notes increases

Engineering Contradiction:

Improveeffectiveness of close notes for future resolutionVSAvoidtime to create detailed close notes

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system replaces the mechanical manual writing process with automated AI-powered conversation analysis. Instead of experts manually composing detailed close notes, the system uses natural language processing to analyze collaboration platform conversations, determine message intents, cluster similar messages, and generate comprehensive structured summaries. This substitution maintains high reliability for future incident resolution while eliminating the time investment required for manual detailed documentation

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250182053A1Close note summarization, management and mitigation

Publication Date: 2025.06.05 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A composite conversation from a collaborative channel is obtained and independent conversations within the composite conversation are separated. An intent of each message in each of the independent conversations is determined and those messages with a same intent are clustered together to form artifact clusters. A summary for each artifact cluster is generated and the summaries of the artifact clusters are combined. A final coherent interaction summary is created based on the artifact clusters and a network-based computer system is reconfigured based on the final coherent interaction summary.