Routing of contacts based on predicted escalation time
Systems and methods that employ contact escalation periods as criterion for managing routing procedures of a contact center. A prediction component can predict when a customer is likely to escalate a contact that is forwarded to a contact center, and hence facilitate resource matching based on such prediction. Accordingly, proactive and anticipatory contact interaction is enabled, wherein routing of contacts occur in-part based on predicted likelihood of escalations.
1. A system, comprising:
a storage device, coupled to a processing device, that stores computer-executable components, comprising:
a prediction component that predicts a time period associated with a likelihood of an escalation for a contact, the time period is based on a defined criterion changeable from one user to another user, wherein the escalation is an abandonment of an initial request in favor of another request requiring a first resource of the contact center that is determined to be more expensive than a second resource required by the initial request;
a routing component that routes the contact based on the likelihood of the escalation; and
an artificial intelligence component that determines the likelihood of the escalation for the contact based on an artificial intelligence model.
2. The system of claim 1 , wherein the computer-executable components further comprise an analysis component that performs a cost-benefit analysis for contacts and resources of the system.
3. The system of claim 1 , wherein the computer-executable components further comprise a queuing model generated based at least in part on the likelihood of the escalation for the contact.
4. The system of claim 1 , wherein the escalation is a follow-up of the initial request, via a channel that is determined to be more expensive than an original channel via which the initial request is sent to the system.
5. The system of claim 1 , wherein the prediction component is associated with a monitor component that monitors social networking data associated with a social network.
6. The system of claim 5 , wherein the monitor component further comprises a search engine that searches queries submitted to the social network.
7. The system of claim 1 , wherein the computer-executable components further comprise an evaluation component that evaluates historical data representing a history of a customer with the system, to facilitate prediction of the escalation of the contact.
8. The system of claim 7 , wherein the computer-executable components further comprise an instigation component that initiates operation for the routing component.
9. The system of claim 1 , wherein the artificial intelligence component determines the likelihood of the escalation of the contact based on a Markov model.
10. A method of routing a contact, comprising:
predicting, by a contact center device comprising a processor, a time for an escalation likelihood of a contact received by the contact center device via a prediction component, wherein the time period is based on a first criterion changeable from one user identity to another user identity;
employing the time for the escalation likelihood as a second criterion for resource matching by the contact center;
routing the contact based on the escalation likelihood; and
determining a percentage chance of the likelihood of the escalation of the contact based on an artificial intelligence model.
11. The method of claim 10 , further comprising prioritizing the contact based on the escalation likelihood.
12. The method of claim 10 , wherein the predicting is based on at least one of a subject matter of the contact, or a character trait of a customer identity generating the contact, or an environment of the contact.
13. The method of claim 10 , wherein the contact is submitted to a social network data store before being received by the contact center device.
14. The method of claim 10 , further comprising:
engaging in a remedial measure to appease a customer identity determined to have submitted the contact; and
prolonging an escalation period.
15. The method of claim 10 , wherein the predicting is based on employing a queuing model with Markov chains.
16. The method of claim 15 , further comprising updating the queuing model responsive to model update data received or determined by the contact center device.
17. The method of claim 10 , further comprising matching the contact to a resource of the contact center device based on the predicting.
18. The method of claim 10 , further comprising facilitating the predicting via an inference supplied by an inference component.
19. A contact center system, comprising:
means for predicting a time for an escalation likelihood of a contact, wherein the time for the escalation likelihood is employed as at least part of a model for resource matching in the contact center system and the time period is based on a criterion changeable from one user identity to another user identity;
means for routing the contact based on the escalation likelihood; and
means for determining a percentage chance of the likelihood of the escalation of the contact based on an artificial intelligence model.
20. The contact center system of claim 19 , further comprising means for analyzing defined costs relative to defined benefits of contacts and resources associated with the contact center system.