Generative LLM Contextualization for Contact Center Interactions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact center agents often lack awareness of a user's past interactions and recent events, leading to inefficient processing and resource wastage due to repeated information requests and limited context in unassisted or assisted interactions.
Innovation Solution
Implementing a generative large language model (LLM) AI system that enhances event data with contextual information, providing contact center agents with summaries of past interactions and personalized greetings, and dynamically updating context as user interactions progress.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If contact center agents handle user interactions without access to past interaction history and contextual information, then the system operation is simpler and requires fewer resources, but the efficiency of user service deteriorates due to repeated information requests and limited context awareness
Solution Approach 1:
The system performs preliminary actions by automatically retrieving and storing contextual information from past user interactions, event data, and interaction history before the agent needs it. This pre-processing of information eliminates the need for agents to manually gather context during interactions, thereby improving service efficiency without requiring agents to navigate complex systems.
Solution Approach 2:
An intermediary system component is introduced that sits between the user interaction channels and the agents. This intermediary automatically processes and contextualizes event data, retrieves relevant historical information, and presents synthesized context to agents. This mediator handles the complexity of data integration and context management, allowing agents to work efficiently without directly managing system complexity.
2Loss of information
If the system retrieves and processes extensive event information and interaction history for every user interaction, then the contextual awareness and personalized service improve, but the computing resources and processing time increase
Solution Approach 1:
The system extracts only the most relevant contextual information from extensive event data and interaction history rather than processing all available data. By identifying and extracting key contextual elements needed for effective agent assistance, the system maintains high contextual awareness while significantly reducing computing resource consumption compared to processing complete interaction histories.
Solution Approach 2:
The system applies local quality by providing different levels of contextual information detail based on specific interaction needs. Rather than uniformly processing all event data at the same level of detail, the system selectively retrieves and processes contextual information appropriate to each specific interaction scenario, optimizing the balance between information availability and resource consumption.
3Loss of time
If contact center agents must manually gather and understand user interaction history and event data, then the system requires minimal processing infrastructure, but the agent effort and interaction time increase significantly
Solution Approach 1:
The system implements self-service by automatically retrieving, processing, and presenting contextual information to agents without requiring manual intervention. The automated system serves itself by gathering interaction history and event data, synthesizing relevant context, and making it available to agents, thereby eliminating the need for agents to manually gather information and significantly reducing agent effort time.
Solution Approach 2:
The system uses feedback mechanisms to continuously improve contextual information provision. By monitoring agent interactions and user responses, the system learns which contextual information is most valuable and adjusts its automated context provision accordingly, further reducing agent effort time while maintaining high relevance of provided information.
Data Source
AI summary
The present disclosure generally relates to systems, software, and computer-implemented methods for using generative artificial intelligence to improve user interactions. One example method includes receiving a notification from a contact center application that user interaction events have been generated during an interaction session. Event descriptions for events generated in the session are located in a contact center application use case definition. Event descriptions are enhanced with event information for to generate contextualized event information. The contextualized event information to is added to a generative large language model artificial intelligence context that is provided to a generative large language model artificial intelligence engine. A query is provided to the generative large language model artificial intelligence engine. A query response is received from the generative large language model artificial intelligence engine and the query response is used in the interaction session.