Automated Calling System Voice Authentication Logic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated calling systems often connect with individuals who are not the intended customer, leading to inefficient use of customer service representatives' time as they need to verify the identity of the customer before proceeding with account-related tasks, especially for accounts with adverse status.
Innovation Solution
An automated calling system that uses speech signal generation and authentication logic to pre-authenticate customers by determining if the responding voice is that of the intended customer with an adverse account status, routing the call to a live agent only after successful authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated calling systems connect with any individual answering the phone, then the system can quickly reach potential customers, but customer service representatives waste time verifying the identity of the person who answered
Solution Approach 1:
The system performs voice authentication before transferring the call to a customer service representative. The automated calling system plays authentication questions and verifies the respondent's answers match stored customer information, completing the identity verification process in advance so that customer service representatives receive only authenticated customers without needing to perform additional verification
Solution Approach 2:
The system enables customers to authenticate themselves automatically through voice-based questions and answers. Customers respond to authentication questions using their voice, and the system automatically verifies their identity by comparing their responses against stored information, eliminating the need for manual verification by customer service representatives
2Reliability
If the system transfers all calls to live agents, then customer service can be provided, but the cost and resource utilization increase unnecessarily
Solution Approach 1:
The call handling process is divided into two distinct segments: an automated authentication segment that handles identity verification through voice-based questions and answers, and a manual service segment that handles authenticated customers. This segmentation allows the system to automatically filter and prepare calls before human intervention, reducing unnecessary transfers while maintaining service quality
Solution Approach 2:
The system performs preliminary authentication actions before calls are transferred to live agents. By completing voice verification and identity confirmation in advance, the system ensures that only authenticated customers reach customer service representatives, thereby maintaining high service reliability while reducing the volume of unnecessary transfers
3Measurement precision
If the system uses multiple authentication questions, then authentication accuracy improves, but the call duration and customer frustration increase
Solution Approach 1:
The system uses a limited number of authentication questions (typically one or two) rather than extensive verification sequences. This partial action approach provides sufficient authentication accuracy for high-risk accounts while keeping the interaction brief and customer-friendly, avoiding the frustration that would result from excessive questioning
Data Source
AI summary
An automated calling system authenticates and subsequently communicates via a telephone network with a person such as a current or prospective customer. The communication may be in regards to an account having an adverse account status (e.g. a payment delinquency, an overdrawn checking account, being over the credit limit on a credit card, excessive transactions on one account, suspicious or fraudulent transactions on an account, and so on).