Virtual Agents for Metaverse Call Center Service
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies do not provide an efficient and effective solution to process user inquiries and provide customized solutions in call centers when real-world agents are unavailable.
Innovation Solution
A system is developed to generate an expandable pool of virtual agents with skills based on historical data from real-world agents, allowing these virtual agents to interact with user avatars in a metaverse to provide customized solutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If real-world agents are used to handle service inquiries, then service quality and customization are improved, but wait time and operational efficiency deteriorate when agents are unavailable
Solution Approach 1:
The system creates virtual agents that are digital copies of real-world agents, capturing their knowledge, skills, and interaction patterns through machine learning models. These virtual agents can handle service inquiries without requiring the physical presence of real agents, thereby eliminating wait times while maintaining service quality.
Solution Approach 2:
The system performs preliminary training of virtual agents using historical interaction data and observation operations before they are needed to handle inquiries. This advance preparation ensures that virtual agents are ready to immediately assist users without causing delays when real agents are unavailable.
2Productivity
If more real-world agents are hired to reduce wait times, then service availability is improved, but operational cost and system complexity increase
Solution Approach 1:
Instead of hiring additional real-world agents, the system creates multiple virtual agent instances that can simultaneously handle numerous service inquiries. These digital copies can be deployed and scaled without the logistical complexity of recruiting, training, and managing additional human staff.
Solution Approach 2:
The system changes the fundamental parameter of agent availability from human-dependent to digitally-infinite. Virtual agents can operate continuously without breaks, shifts, or fatigue, transforming service availability from a limited resource to an abundant one without increasing organizational complexity.
3Loss of time
If virtual agents are deployed to handle inquiries, then wait time is reduced, but service customization and interaction quality may deteriorate
Solution Approach 1:
The system implements feedback mechanisms where virtual agents learn from historical interaction data and observation operations of real agents. This continuous learning process enables virtual agents to refine their response quality and customization capabilities while maintaining the speed advantages of automated service.
Solution Approach 2:
The system performs preliminary training of virtual agents using extensive historical data and observation operations before deployment. This advance preparation ensures that virtual agents possess the knowledge and skills necessary to provide customized, high-quality interactions from the start, eliminating the need for trade-offs between speed and service quality.
4Measurement precision
If historical data from real agents is used to train virtual agents, then service knowledge accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system performs comprehensive training of virtual agents using historical data and observation operations in advance, before the virtual agents are needed to handle service inquiries. This preliminary action ensures that knowledge transfer is completed beforehand, so that when virtual agents go live, they immediately possess accurate service knowledge without causing operational delays.
Data Source
AI summary
A system for generating an expandable pool of virtual agents to provide solutions in a virtual environment comprises a call center server in communication with a metaverse server. The call center server generates the virtual agents with corresponding skills of each real-world agent using a machine learning model based on historical observation operations performed by each particular real-world agent and a historical rule set to address the service issue. The metaverse server identifies the virtual agents in the virtual environment. The call center server routes a service inquiry with a service issue from a user equipment of a user to the metaverse server. The metaverse server identifies a first virtual agent with a first skill and conducts a first interaction between the first virtual agent and a user avatar to generate the customized solution to address the service issue.