Speech Analytics System for Contact Center Compliance Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contact center agents often fail to provide required information to remote parties due to lack of training, experience, or forgetfulness, leading to non-compliance with regulations, which can result in financial liabilities for the contact center.
Innovation Solution
A speech analytics system that monitors audio calls to detect specific keywords, providing agents with text-based reminders or icons to play pre-recorded scripts, ensuring compliance with contact center and regulatory requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If agents rely on memory and training to recall policy information during calls, then agent autonomy and natural conversation flow are maintained, but compliance reliability deteriorates due to forgetfulness and lack of experience
Solution Approach 1:
The system performs preliminary actions by analyzing call audio in real-time to detect contexts where policy information should be provided, and proactively displays icons to agents before the information is needed. This allows agents to easily access required information without relying on memory, thereby improving compliance reliability without significant system complexity
Solution Approach 2:
The system introduces an intermediary component (the speech analytics system with icon displays) that mediates between policy requirements and agent actions. The system monitors call content and provides timely reminders through icons, serving as a bridge that ensures compliance without disrupting the natural agent-customer interaction
2Reliability
If the system provides real-time speech analysis and icon reminders to agents, then compliance reliability improves, but processing time and system complexity increase
Solution Approach 1:
The speech analytics system operates continuously throughout the call, constantly analyzing audio content and monitoring for contexts requiring policy information. This continuous monitoring ensures that reminders are provided at the exact moment needed, improving compliance without requiring additional call time or interrupting the natural flow of conversation
Solution Approach 2:
The system replaces the manual mechanical process of agent memory recall with automated speech recognition and analysis technology. By using audio analysis to detect contexts and automatically displaying relevant icons, the system eliminates the time agents would spend recalling policies, thereby improving compliance reliability without increasing call processing time
3Loss of information
If agents are provided with comprehensive policy scripts and guidance materials, then information completeness improves, but ease of operation deteriorates due to information overload
Solution Approach 1:
Instead of providing agents with comprehensive policy manuals or extensive guidance materials, the system applies local quality by delivering specific, context-relevant information precisely when and where it is needed. The speech analytics system detects the current call context and displays only the specific policy information relevant to that situation, eliminating information overload while ensuring completeness of required information
Solution Approach 2:
The system segments policy information into discrete, context-specific units delivered as individual icons rather than presenting agents with large blocks of text. Each icon represents a specific policy requirement or piece of information relevant to the current call context, making it easy for agents to quickly identify and access the exact information needed without being overwhelmed by comprehensive policy documents
Data Source
AI summary
A speech analytics system (“SAS”) monitors speech from a remote party and agent to determine when text-based guidance information (“TBGI”) and a script control icon is to be provided to the agent. The agent may respond to a particular context with certain information, either by verbally informing the remote party or causing a prerecorded script to be played to the remote party. In one embodiment, the SAS monitors the agent's speech to ascertain if an expected speech response is provided by the agent within a first time period. If not, the SAS may cause another TBGI and script control icon to be presented to the agent, and again monitor the agent's speech to ascertain if an expected speech response is provided by the agent within a second time period. If the agent again fails to respond properly, then data may be written indicating a compliance failure.