Emotion recognition to match support agents with customers
An application determines an emotional state of a user based on evaluating facial recognition data of the user captured from the user interacting with the application. The application receives a request from the user to initiate a support call. The request identifies the emotional state of the user. The application predicts, from a set of outcomes of support calls processed by support agents interacting with users having different emotional states, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on the emotional state of the user. The application identifies an available support agent having the predicted emotional state, and assigns the user to interact with the identified support agent for the support call.
1. A computer-implemented method for matching a user of an application to a support agent, comprising:
receiving facial recognition data of the user captured from the user interacting with the application;
evaluating the facial recognition data to determine at least one emotional state of the user; and
upon receiving a request from the user to initiate a support call, wherein the request identifies the at least one emotional state of the user:
predicting, from a set of outcomes of support calls processed by support agents interacting with users having different emotional states, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on the at least one emotional state of the user;
identifying an available support agent having the predicted emotional state; and
assigning the user to interact with the identified support agent for the support call.
2. The computer-implemented method of claim 1 , wherein the at least one emotional state comprises a first set of emotional states of the user corresponding to facial recognition data of the user from a first portion of the interaction, and a second set of emotional states of the user corresponding to facial recognition data of the user from a second portion of the interaction.
3. The computer-implemented method of claim 2 , wherein each emotional state in the first and second sets of emotional states comprises a confidence score for the emotional state.
4. The computer-implemented method of claim 1 , wherein the specified outcome is determined by one or more of a duration of the support call, and feedback providing an indication of user experience during the support call.
5. The computer-implemented method of claim 1 , wherein the support agent having the predicted emotional state is identified based on evaluating a history of each available support agent's emotional states responsive to different emotional states of users.
6. The computer-implemented method of claim 1 , wherein the request further identifies a topic of the support call.
7. The computer-implemented method of claim 6 , wherein the support agent is further identified based on evaluating a history of each available support agent's emotional states responsive to the topic of the support call.
8. A non-transitory computer-readable storage medium storing instructions, which when executed on a processor, perform an operation for matching a user of an application to a support agent, the operation comprising:
receiving facial recognition data of the user captured from the user interacting with the application;
evaluating the facial recognition data to determine at least one emotional state of the user; and
upon receiving a request from the user to initiate a support call, wherein the request identifies the at least one emotional state of the user:
predicting, from a set of outcomes of support calls processed by support agents interacting with users having different emotional states, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on the at least one emotional state of the user;
identifying an available support agent having the predicted emotional state; and
assigning the user to interact with the identified support agent for the support call.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the at least one emotional state comprises a first set of emotional states of the user corresponding to facial recognition data of the user from a first portion of the interaction, and a second set of emotional states of the user corresponding to facial recognition data of the user from a second portion of the interaction.
10. The non-transitory computer-readable storage medium of claim 9 , wherein each emotional state in the first and second sets of emotional states comprises a confidence score for the emotional state.
11. The non-transitory computer-readable storage medium of claim 8 , wherein the specified outcome is determined by one or more of a duration of the support call, and feedback providing an indication of user experience during the support call.
12. The non-transitory computer-readable storage medium of claim 8 , wherein the support agent having the predicted emotional state is identified based on evaluating a history of each available support agent's emotional states responsive to different emotional states of users.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the request further identifies a topic of the support call.
14. The non-transitory computer-readable storage medium of claim 13 , wherein the support agent is further identified based on evaluating a history of each available support agent's emotional states responsive to the topic of the support call.
15. A system, comprising:
a processor; and
a memory containing a program which, when executed on the processor, performs an operation for matching a user of an application to a support agent, the operation comprising:
receiving facial recognition data of the user captured from the user interacting with the application;
evaluating the facial recognition data to determine at least one emotional state of the user; and
upon receiving a request from the user to initiate a support call, wherein the request identifies the at least one emotional state of the user:
predicting, from a set of outcomes of support calls processed by support agents interacting with users having different emotional states, an emotional state that increases a likelihood of achieving a specified outcome for the support call based on the at least one emotional state of the user;
identifying an available support agent having the predicted emotional state; and
assigning the user to interact with the identified support agent for the support call.
16. The system of claim 15 , wherein the at least one emotional state comprises a first set of emotional states of the user corresponding to facial recognition data of the user from a first portion of the interaction, and a second set of emotional states of the user corresponding to facial recognition data of the user from a second portion of the interaction.
17. The system of claim 15 , wherein the specified outcome is determined by one or more of a duration of the support call, and feedback providing an indication of user experience during the support call.
18. The system of claim 15 , wherein the support agent having the predicted emotional state is identified based on evaluating a history of each available support agent's emotional states responsive to different emotional states of users.
19. The system of claim 15 , wherein the request further identifies a topic of the support call.
20. The system of claim 19 , wherein the support agent is further identified based on evaluating a history of each available support agent's emotional states responsive to the topic of the support call.