Real-Time Support Ticket Information Augmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Technical support for user issues is often time-consuming and inconsistent due to the variability in technical expertise among support agents and the lack of access to relevant external resources, leading to repetitive and inefficient handling of support tickets.
Innovation Solution
A system that automatically generates queries from user-written text in support tickets, cleans the text by removing non-relevant information, and executes these queries across multiple document repositories to provide real-time relevant information to support agents, enhancing their ability to resolve issues efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If support agents rely on their own technical expertise to handle support tickets, then they can provide personalized support, but the resolution time increases and consistency decreases
Solution Approach 1:
The system performs preliminary actions by automatically generating queries from support messages before agents need to manually search. The automated query generation and document retrieval happen in real-time, preparing relevant information in advance so agents can immediately access it without spending time on manual research, thus reducing resolution time while maintaining consistency.
Solution Approach 2:
The system acts as an intermediary between support agents and the document repositories. It automatically generates queries from support messages, executes them against multiple document repositories, and retrieves relevant information, thereby mediating the information search process and providing consistent, high-quality support resources to all agents regardless of their individual expertise levels.
2Loss of information
If support agents manually search for relevant information in document repositories, then they can find external resources, but the process is time-consuming and repetitive
Solution Approach 1:
The system enables self-service by automatically generating queries from support messages and executing them against document repositories without requiring manual agent intervention. The automated process retrieves relevant external resources and presents them to agents, eliminating the need for time-consuming manual searches while ensuring consistent access to information across all tickets.
Solution Approach 2:
The system replaces the mechanical process of manual information searching with an automated computational system. Instead of agents manually browsing document repositories, the system automatically generates queries, executes them across multiple repositories, and retrieves relevant documents, thereby substituting manual mechanical search operations with efficient automated information retrieval.
3Ease of operation
If support agents handle tickets independently without automated assistance, then they maintain autonomy, but the process becomes repetitive and inefficient
Solution Approach 1:
The system applies partial automation by assisting agents only with the specific task of information retrieval while leaving them autonomous in handling the overall support process. The automated query generation and document retrieval handle the repetitive search tasks, while agents maintain control over ticket resolution decisions, providing the right amount of automation without removing agent autonomy.
Data Source
AI summary
In an embodiment, a method includes identifying a support ticket for handling by a support agent, where the support ticket is associated in storage with a support message. The support message includes user-written text. The method also includes detecting non-user-written text in the support message and cleaning the support message. The cleaning includes removing the detected non-user-written text. The method also includes generating a query based, at least in part, on the cleaned support message. The method also includes causing the query to be executed on a data storage system that includes a first document repository and a second document repository. The method also includes receiving information identifying a first document from the first document repository and a second document from the second document repository. The method also includes publishing information related to the first document and the second document in relation to the support ticket.