Interacting with a user device to provide automated testing of a customer service representative

1. A method, comprising:

processing, by a device and using a machine learning model, historical information concerning a customer service representative to determine scores for a plurality of test issues capable of being presented to the customer service representative;

selecting, by the device and based on the scores, a test issue, of the plurality of test issues, to be presented to the customer service representative;

selecting, by the device and based on the test issue, a virtual assistant, of a plurality of virtual assistants, for conversing with the customer service representative;

initiating, by the device, based on the test issue, and via the virtual assistant, a communication session between the virtual assistant and a user device associated with the customer service representative;

obtaining, by the device, a plurality of data points relating to a performance of the customer service representative during the communication session; and

training, by the device and based on the plurality of data points and the test issue, a different virtual assistant to perform one or more functions of the customer service representative and to handle future communications associated with the test issue.

2. The method of claim 1 , further comprising:

selecting the customer service representative, from a plurality of customer service representatives, based on one or more of:

a measure of availability of the customer service representative,

test performance information associated with the customer service representative, or

real-life performance information associated with the customer service representative.

3. The method of claim 1 , wherein each test issue, of the plurality of test issues, comprises a customer service scenario for testing customer service representatives.

4. The method of claim 1 , wherein selecting the test issue further comprises:

selecting the test issue based on the test issue having not been selected for the customer service representative within a threshold period of time.

5. The method of claim 1 , wherein the scores indicate, for the customer service representative, a measure of predicted performance with respect to a respective test issue of the plurality of test issues.

6. The method of claim 1 , further comprising:

processing, using one or more preprocessing procedures, historical data regarding a plurality of customer service communications to generate generic historical data; and

training, using the generic historical data, the machine learning model to predict customer service representative performance.

7. The method of claim 1 , wherein each virtual assistant, of the plurality of virtual assistants, is associated with one or more voice characteristics differentiating each virtual assistant from each other virtual assistant of the plurality of virtual assistants, the one or more voice characteristics comprising one or more of:

a rate of speech characteristic,

a cadence characteristic,

a dialect characteristic,

a loudness characteristic,

a timbre characteristic,

a language characteristic,

an accent characteristic, or

a grammar characteristic.

8. A device, comprising:

one or more memories; and

one or more processors communicatively coupled to the one or more memories, configured to:

process, using a machine learning model, historical information concerning a customer service representative to determine scores for a plurality of test issues capable of being presented to the customer service representative;

select, based on the scores, a test issue, of the plurality of test issues, to be presented to the customer service representative;

select, based on the test issue, a virtual assistant, of a plurality of virtual assistants, for conversing with the customer service representative;

initiate based on the test issue, and via the virtual assistant, a communication session between the virtual assistant and a user device associated with the customer service representative;

obtain a plurality of data points relating to a performance of the customer service representative during the communication session; and

train, based on the plurality of data points and the test issue, a different virtual assistant to perform one or more functions of the customer service representative and to handle future communications associated with the test issue.

9. The device of claim 8 , wherein the one or more processors are further configured to:

select the customer service representative, from a plurality of customer service representatives, based on one or more of:

a measure of availability of the customer service representative,

test performance information associated with the customer service representative, or

real-life performance information associated with the customer service representative.

10. The device of claim 8 , wherein each test issue, of the plurality of test issues, comprises a customer service scenario for testing customer service representatives.

11. The device of claim 8 , wherein the one or more processors, when selecting the test issue, are further configured to:

select the test issue based on the test issue having not been selected for the customer service representative within a threshold period of time.

12. The device of claim 8 , wherein the scores indicate, for the customer service representative, a measure of predicted performance with respect to a respective test issue of the plurality of test issues.

13. The device of claim 8 , wherein the one or more processors are further configured to:

process, using one or more preprocessing procedures, historical data regarding a plurality of customer service communications to generate generic historical data; and

train, using the generic historical data, the machine learning model to predict customer service representative performance.

14. The device of claim 8 , wherein each virtual assistant, of the plurality of virtual assistants, is associated with one or more voice characteristics differentiating each virtual assistant from each other virtual assistant of the plurality of virtual assistants,

the one or more voice characteristics comprising one or more of:

a rate of speech characteristic,

a cadence characteristic,

a dialect characteristic,

a loudness characteristic,

a timbre characteristic,

a language characteristic,

an accent characteristic, or

a grammar characteristic.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to:

process, using a machine learning model, historical information concerning a customer service representative to determine scores for a plurality of test issues capable of being presented to the customer service representative;

select, based on the scores, a test issue, of the plurality of test issues, to be presented to the customer service representative;

select, based on the test issue, a virtual assistant, of a plurality of virtual assistants, for conversing with the customer service representative;

initiate based on the test issue, and via the virtual assistant, a communication session between the virtual assistant and a user device associated with the customer service representative;

obtain a plurality of data points relating to a performance of the customer service representative during the communication session; and

train, based on the plurality of data points and the test issue, a different virtual assistant to perform one or more functions of the customer service representative and to handle future communications associated with the test issue.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

select the customer service representative, from a plurality of customer service representatives, based on one or more of:

a measure of availability of the customer service representative,

test performance information associated with the customer service representative, or

real-life performance information associated with the customer service representative.

17. The non-transitory computer-readable medium of claim 15 , wherein each test issue, of the plurality of test issues, comprises a customer service scenario for testing customer service representatives.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, that cause the one or more processors to select the test issue further, cause the one or more processors to:

select the test issue based on the test issue having not been selected for the customer service representative within a threshold period of time.

19. The non-transitory computer-readable medium of claim 15 , wherein the scores indicate, for the customer service representative, a measure of predicted performance with respect to a respective test issue of the plurality of test issues.

20. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:

process, using one or more preprocessing procedures, historical data regarding a plurality of customer service communications to generate generic historical data; and

train, using the generic historical data, the machine learning model to predict customer service representative performance.