Example: Identification Rules and identity verification

With identity verification Feature in voice biometrics where the speaker’s voice is compared to a collection of employee or customer voiceprints that should match the call. If a match occurs, the speaker is said to be verified., the system uses the Identification Rule attribute to locate the voiceprint File containing a mathematical summary of the vocal patterns of a person’s voice used in the IAFD product to assist with identity verification and detection. model for a specific user when that user participates in an interaction In Speech Analytics, an interaction represents a single part of the contact between one employee and the same customer. In Text Analytics, an interaction is the communication session between one or more employees and the same customer with a unifying contextual element.. The system requires the user’s voiceprint model to perform identity verification.

The following example illustrates how the system uses Identification Rules in the identity verification process.

This example assumes you are performing identity verification on customers (people contacted by employees of the enterprise capturing interactions.

  1. To perform identity verification of customers, you create a Customer Identification Rule.

    In this example, we assume you create a Customer Identification Rule that includes a custom attribute named AccountNumber (where the value of AccountNumber is a unique account number for a specific user).

  2. You assign this Customer Identification Rule to a Recorder Analytics Rule when creating a Recorder Analytics Rule that performs identity verification on customers.

  3. When the Recorder Analytics Rule is invoked on an interaction, the rule uses the Customer Identification Rule attribute to analyze the audio channel that carries the customer’s voice. In this example, the system determines the value of the AccountNumber attribute in the metadata on this channel.

  4. The system retrieves the voiceprint model associated with the value for the AccountNumber attribute from the Biometrics database.

  5. The system compares the voice of the speaker on the interaction to the voice on the voiceprint model to perform the identity verification analysis.

  6. The system returns a result such as Verified (the speaker’s voice matches the voiceprint model), or Not Verified (the speaker’s voice does not match the voiceprint model).

    The Recorder Analytics Rule logic (or Conditions) then use this result to determine whether to trigger or not trigger the Recorder Analytics Rule action.

The identity verification process for employees is basically the same as for customers. The differences are:

  • In steps 1 and 2, you create an Employee Identification Rule (rather than a Customer Identification Rule) that uses Employee Name, which refers to the unique employee ID.

  • In step 3, the system uses the Employee Identification Rule attribute to analyze the audio channel of the employee (rather than the Customer Identification Rule to analyze the audio channel of the customer).

  • In step 4, the system retrieves the voiceprint model associated with the value of the Employee Name from the Employee Identification Rule (rather than the value of the attribute in the Customer Identification Rule).

Related topics 

Identification Rule basics