Automated FAQ Network for IT Incident Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Customer support workers face challenges in resolving IT-related problem tickets due to the need to determine necessary information and pose questions to customers, leading to inefficiencies in incident management and increased time to resolution.
Innovation Solution
A method and system that analyze problem tickets to identify frequently asked question (FAQ) candidates, cluster them, and associate them with an FAQ network, allowing for the refinement and management of FAQ nodes, including identification of broken branches and criticality, to facilitate quicker resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If customer support workers manually analyze each problem ticket to determine necessary information and pose questions, then they can resolve incidents accurately, but the time to resolution increases and productivity decreases
Solution Approach 1:
The system enables self-service by automatically analyzing problem tickets and generating FAQ candidates without requiring manual intervention from customer support workers. The ticket analyzer autonomously processes ticket descriptions, clusters similar issues, and creates FAQ nodes in the FAQ network, allowing the system to serve itself rather than requiring human analysis for each ticket.
Solution Approach 2:
The patent replaces the mechanical manual analysis process with an automated computer-based system. The ticket analyzer uses computational algorithms to process ticket descriptions, while the clustering mechanism automatically groups similar problems, and the FAQ network structure provides automated guidance for resolution, substituting human cognitive processing with machine-based analysis.
2Loss of information
If customer support workers manually determine the type of questions to pose to customers, then they can gather necessary information accurately, but the complexity of the resolution process increases
Solution Approach 1:
The resolution process is segmented into distinct automated components: the ticket analyzer processes individual ticket descriptions, the clustering mechanism groups similar tickets into categories, and the FAQ network provides structured guidance paths. This segmentation divides the complex information gathering task into manageable automated steps, reducing overall process complexity while maintaining information completeness.
Solution Approach 2:
The FAQ network acts as an intermediary between the raw problem ticket and the final resolution. It mediates the information gathering process by providing structured guidance and pre-defined question paths, reducing the complexity of determining what information to collect while ensuring all necessary information is obtained through the automated FAQ traversal.
3Productivity
If the system automates discovery and reuse of ticket resolution content, then productivity increases and time to resolution decreases, but the complexity of managing and calibrating the FAQ network increases
Solution Approach 1:
The system incorporates feedback mechanisms where resolved tickets are analyzed to update and calibrate the FAQ network. The feedback from actual ticket resolutions allows the system to learn what questions are most effective, refine the clustering accuracy, and improve the FAQ nodes, thereby managing the network complexity through continuous learning and adaptation.
Solution Approach 2:
The FAQ network management leverages parameter changes by adjusting the clustering criteria, reweighting importance of different ticket attributes, and modifying FAQ node structures based on resolution patterns. These parameter adjustments allow the system to adapt to changing incident types and resolution patterns, managing complexity through automated optimization rather than manual configuration.
Data Source
AI summary
Building, reusing and calibrating network of authored content, in one aspect, may comprise clustering a plurality of problem tickets into one or more clusters. The clusters may be associated to one or more FAQ nodes in a FAQ network. The associated one or more FAQ nodes may be checked to determine whether the nodes are part of a broken branch. If the one or more FAQ nodes leads to a broken branch, a user may be notified to update the branch, e.g., with an answer or resolution to the one or more FAQ nodes.