Inbound Email Routing for Automatic ITSM Issue Creation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large organizations face difficulties in routing and servicing unstructured service requests, such as those in free-form emails, to the appropriate help desk within ITSM systems, leading to inefficiencies in ticket processing and self-help options.
Innovation Solution
An inbound request handler service analyzes email content using feature extraction and categorization metrics to automatically generate issue objects in an ITSM system, identifying the appropriate portal endpoint based on predefined ticket types and sub-types, and optionally requesting additional information to ensure accurate categorization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional issue tracking systems are used to handle unstructured service requests, then the system structure remains simple, but the routing efficiency and service quality deteriorate
Solution Approach 1:
An inbound request handler service is introduced as an intermediary component between email receivers and the issue tracking system. This handler extracts features from unstructured email content, generates feature vectors, compares them with predetermined categorization vectors, and automatically routes requests to appropriate portal endpoints. This intermediary layer enables efficient handling of unstructured requests without requiring complex modifications to the core issue tracking system.
Solution Approach 2:
The patent replaces manual routing mechanisms with an automated machine learning-based classification system. Instead of manual analysis of unstructured email content, the system uses feature extraction, vector generation, and automated comparison with predetermined categorization vectors to determine the appropriate portal endpoint, thereby substituting mechanical/manual processes with automated computational methods.
2Loss of time
If manual analysis of unstructured email content is performed, then categorization accuracy can be maintained, but the processing time and labor costs increase
Solution Approach 1:
The system performs preliminary actions by pre-defining categorization vectors for different portal endpoints based on historical issue objects. These predetermined vectors serve as reference templates that enable rapid automated classification of incoming requests. By preparing the classification framework in advance, the system can quickly process new requests without manual intervention while maintaining consistent categorization accuracy.
Solution Approach 2:
The patent uses copying by creating feature vectors from extracted email content and comparing them against predetermined categorization vectors. Instead of manually analyzing each email, the system creates computational representations (feature vectors) that can be rapidly processed and compared, enabling automated classification that maintains accuracy while significantly reducing processing time.
3Measurement precision
If automated routing is implemented without additional information collection, then processing speed increases, but categorization accuracy decreases
Solution Approach 1:
The system implements feedback mechanisms where the inbound request handler automatically requests additional information from users when the initial email content is insufficient for accurate categorization. The handler analyzes the feature vector against predetermined categorization vectors, and when confidence is low or required fields are missing, it triggers automated follow-up requests. This feedback loop ensures high categorization accuracy while keeping the information collection process streamlined and automated.
Data Source
AI summary
A computer-implemented method for handling inbound service requests analyzes content of the message to extract a set of features, and generating a feature vector based on the set of extracted features. A categorization metric for the feature vector is then determined, using a set of predetermined categorization vectors, wherein each predetermined categorization vector corresponds to a respective portal endpoint associated with one or more predefined ticket types and sub-types of an information technology service management system. In response to the categorization metric satisfying a comparison criteria with respect to one or more predetermined categorization vectors, a particular portal endpoint is selected. Content from the email message is then extracted. A new issue object request is then automatically generated in accordance with a particular object requirement set associated with the particular portal endpoint for submission to an issue tracking system to create a new issue object.