Virtual Assistant Engine for Accurate Call Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Call centers face inefficiencies in determining the correct department for call transfers, relying on agents' experience and knowledge, leading to time-consuming searches, incorrect transfers, and reduced customer satisfaction.
Innovation Solution
A call routing assistant system using a speech recognition subsystem and virtual assistant engine that extracts keywords from conversations and generates follow-up questions to quickly and accurately identify the appropriate department for call transfers, reducing reliance on agent knowledge and improving search efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If agents rely on their own experience and knowledge to determine call routing, then they can handle simple inquiries quickly, but they make incorrect transfers and require extensive training
Solution Approach 1:
The patent introduces a virtual assistant engine as an intermediary between the agent and the call routing decision-making process. The engine receives keywords from the customer-agent conversation, generates follow-up questions, and determines the appropriate department for transfer. This intermediary system handles the complex routing logic, allowing agents to focus on customer interaction while the system ensures accurate routing decisions.
Solution Approach 2:
The system enables self-service by allowing the virtual assistant engine to automatically analyze conversation keywords, generate relevant follow-up questions, and determine call routing without human intervention. The engine processes the information independently, reducing reliance on agent knowledge and experience while maintaining high transfer accuracy.
2Measurement precision
If agents perform manual searches to find the correct department, then they can handle complex routing scenarios, but it increases customer waiting time
Solution Approach 1:
The virtual assistant engine performs preliminary actions by proactively generating follow-up questions based on initial keywords extracted from the conversation. Instead of waiting for the agent to manually search through departments, the system anticipates the routing decision needs and prepares relevant questions in advance, significantly reducing the time required to identify the correct department while maintaining accuracy.
Solution Approach 2:
The system implements a feedback mechanism where the virtual assistant engine continuously refines its routing decisions based on agent responses to generated questions. The engine adjusts its questioning strategy based on previous answers, narrowing down the appropriate department more efficiently. This iterative feedback process accelerates the routing decision while ensuring accurate department identification.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a transfer option for transferring a call. One of the methods include receiving, by a call assistant engine, a keyword related to information provided by a user to an agent during a call; generating, by the call assistant engine, follow-up questions to be displayed on a user device of the agent in an interactive format, the first follow-up question being generated based on the keyword, each of the following follow-up questions being generated based on an answer of the agent to the previous question; and determining, by the call assistant engine, based on answers of the agent to the follow-up questions, a transfer option for transferring the call.