Ticket Knowledge Graph for IT Routing Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information technology ticketing systems face inefficiencies in ticket creation, routing, and resolution, as they often require manual analysis to determine the proper routing destination and lack automated recommendations for resolution, leading to time-consuming and suboptimal processes.
Innovation Solution
A computer-implemented method and system that extracts media data from IT tickets, extracts data elements, and generates a ticket knowledge graph to facilitate ticket management, where nodes represent data elements and edges represent correlations, enabling automated routing and resolution recommendations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis is used to determine routing destination, then routing accuracy can be maintained through human judgment, but ticket processing time increases and efficiency decreases
Solution Approach 1:
The system performs preliminary extraction of data elements from ticket media data and pre-processes this information into structured formats before routing decisions are needed. By preparing the data in advance and organizing it into extractable elements, the system enables faster automated routing without sacrificing accuracy, as the preliminary structuring work has already been completed.
Solution Approach 2:
The patent introduces an intermediary layer between manual ticket submission and routing decision-making. This intermediary system automatically extracts data elements from media data, structures them, and presents them in a format suitable for routing algorithms. This intermediary processing layer enables automated routing decisions to be made quickly and accurately without requiring manual analysis of raw ticket data.
2Productivity
If automated routing recommendations are implemented, then ticket processing efficiency improves, but system complexity increases
Solution Approach 1:
The system segments the complex task of automated routing into distinct, manageable components: media data extraction, data element identification, element structuring, and routing recommendation generation. By dividing the overall process into these separate functional modules, the system achieves automated routing efficiency while keeping individual components relatively simple and maintainable.
Solution Approach 2:
The patent extracts essential data elements from unstructured media data, separating the critical routing-relevant information from the rest of the ticket content. This extraction process isolates the key elements needed for routing decisions, allowing the automated system to focus on processing only the necessary information rather than analyzing entire ticket documents, thereby reducing effective system complexity.
3Measurement precision
If real-time reference information is provided during ticket creation, then ticket creation accuracy improves, but processing overhead increases
Solution Approach 1:
The system provides real-time reference information during ticket creation by processing only the essential portions of ticket data that are most relevant to routing and classification. Rather than analyzing every aspect of the ticket in real-time, the system focuses on extracting and providing key reference elements, achieving improved creation accuracy with reduced processing overhead by being selective about what information is processed and when.
Data Source
AI summary
A computer-implemented method includes: extracting, by one or more processors, media data from an information technology ticket; extracting, by one or more processors, a plurality of data elements from the media data; and generating, by one or more processors, a ticket knowledge graph based on the plurality of data elements, wherein a node of the ticket knowledge graph represents a data element, and an edge between a first node and a second node in the ticket knowledge graph represents a correlation between a first data element represented by the first node and a second data element represented by the second node.