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 method, comprising:
receiving emotion recognition data of a support agent generated during each call with each user of a set of users that indicates a set of emotional states of the support agent;
receiving metadata associated with each call that indicates:
a type of user interacting with the support agent, or
a topic of the call between the user and the support agent;
receiving feedback for each call from each user of the set of users that indicates an outcome of the call; and
generating, based on the emotion recognition data, the metadata, and the feedback of each call, an emotion profile of the support agent indicating the support agent's average emotional state to the type of user or the topic by:
correlating each outcome with the set of emotional states of the support agent.
2. The method of claim 1 , wherein generating the emotion profile further comprises determining which emotional state of the support agent produces a type of outcome.
3. The method of claim 1 , wherein the method further comprises:
receiving a request for a support call from a user, wherein the request includes metadata indicating the type of user or the topic of the call; and
matching, based on the emotion profile, the user to the support agent, wherein the support agent has the average emotional state to produce a type of outcome.
4. The method of claim 1 , wherein the method further comprises monitoring a real-time emotional state of the support agent.
5. The method of claim 4 , wherein the method further comprises determining the real-time emotional state of the support agent is deviating from the average emotional state in the emotion profile.
6. The method of claim 5 , wherein the method further comprises adjusting the emotion profile of the support agent based on the deviated emotional state.
7. The method of claim 5 , wherein the method further comprises generating a notification to the support agent indicating the real-time emotional state is deviating from the average emotional state of the emotion profile.
8. A non-transitory computer-readable storage medium storing instructions, Which when executed on a processor, perform an operation, comprising:
receiving emotion recognition data of a support agent generated during each call with each user of a set of users that indicates a set of emotional states of the support agent;
receiving metadata associated with each call that indicates:
a type of user interacting with the support agent, or
a topic of the call between the user and the support agent;
receiving feedback for each call from each user of the set of users that indicates an outcome of the call; and
generating, based on the emotion recognition data, the metadata, and the feedback of each call, an emotion profile of the support agent indicating the support agent's average emotional state to the type of user or the topic by:
correlating each outcome with the set of emotional states of the support agent.
9. The non-transitory computer-readable storage medium of claim 8 , wherein generating the emotion profile further comprises determining which emotional state of the support agent produces a type of outcome.
10. The non-transitory computer-readable storage medium of claim 8 , wherein the operation further comprises:
receiving a request for a support call from a user, wherein the request includes metadata indicating the type of user or the topic of the call; and
matching, based on the emotion profile, the user to the support agent, wherein the support agent has the emotional state to produce a type of outcome.
11. The non-transitory computer-readable storage medium of claim 8 , wherein the operation further comprises monitoring a real-time emotional state of the support agent.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the method further comprises determining the real-time emotional state of the support agent is deviating from the average emotional state in the emotion profile.
13. The non-transitory computer-readable storage medium of claim 11 , wherein the operation further comprises adjusting the emotion profile of the support agent based on the deviated emotional state.
14. The non-transitory computer-readable storage medium of claim 12 , wherein the operation further comprises generating a notification to the support agent indicating the real-time emotional state is deviating from the average emotional state of the emotion profile.
15. A system, comprising:
a processor; and
a memory containing a program, which when executed on the processor performs an operation, comprising:
receiving emotion recognition data of a support agent generated during each call with each user of a set of users that indicates a set of emotional states of the support agent;
receiving metadata associated with each call that indicates:
a type of user interacting with the support agent, or
a topic of the call between the user and the support agent;
receiving feedback for each call from each user of the set of users that indicates an outcome of the call; and
generating, based on the emotion recognition data, the metadata, and the feedback of each call, an emotion profile of the support agent indicating the support agent's average emotional state to the type of user or the topic by:
correlating each outcome with the set of emotional states of the support agent.
16. The system of claim 15 , wherein generating the emotion profile further comprises determining which emotional state of the support agent produces a type of outcome.
17. The system of claim 15 , wherein the method further comprises:
receiving a request for a support call from a user, wherein the request includes metadata indicating the type of user or the topic of the call; and
matching, based on the emotion profile, the user to the support agent, wherein the support agent has the emotional state to produce a type of outcome.
18. The system of claim 15 , wherein the method further comprises monitoring real-time emotional state of the support agent.
19. The system of claim 18 , wherein the method further comprises determining the real-time emotional state of the support agent is deviating from the average emotional state in the emotion profile.
20. The system of claim 19 , wherein the method further comprises adjusting the emotion profile of the support agent based on the deviated emotional state.