Insight based routing for help desk service
Non-limiting examples of the present disclosure describe insight-based routing that is used to improve processing of a service request through a help desk service. A request for support (e.g. technical support) can be received through a modality of a help desk service. The request is evaluated, where an evaluation of the request comprises analyzing an issue associated with the request as well as user-specific signal data associated with a customer and generating insights. A support agent is matched to the customer based on an evaluation of the request. The support agent is selected from a pool of support agents based on application of a model that analyzes support agent data in correlation with the generated insights. An interaction between the matched support agent and the customer may be initiated through a modality of the help desk service.
1. A method comprising:
analyzing, through a help desk service, a request for technical support, wherein the analyzing comprises an evaluation of lexical and prosodic features of voice communication data associated with the request;
generating one or more routing insights based on a result of the analyzing including the evaluation of the lexical and prosodic features of the voice communication data;
matching a support agent to the request for technical support, from a pool of support agents, based on an application of a model that analyzes support agent data for the pool of support agents in correlation with the one or more routing insights, wherein the support agent data is three or more selected from:
customer performance reviews of support agents from the pool of support agents,
organizational reviews of the support agents, wherein the organizational reviews comprise data evaluating previous interactions, through the help desk service, involving the support agents,
agent self-evaluations that include a review of a technical expertise of the support agents and a review of communication skills of the support agents, and
availability information for the support agents; and
assigning the support agent to the request based on a result of the matching.
2. The method of claim 1 , further comprising: initiating, through the help desk service, an interaction between the support agent and a customer associated with the request for technical support.
3. The method of claim 2 , wherein the interaction between the support agent and the customer is an indication of an automatic resolution of an issue associated with the request for technical support.
4. The method of claim 2 , wherein the interaction between the support agent and the customer comprises automatically patching the support agent into an ongoing call communication involving the customer and another support agent of the pool of support agents.
5. The method of claim 1 , wherein the one or more routing insights further comprise: two or more selected from a group consisting of: a frustration level of the customer, an indication of one or more recent poor customer experiences and a rating indicating likelihood that a user is a risk to leaving the help desk service.
6. The method of claim 1 , wherein the organizational reviews of the support agents comprise peer reviews, from other support agents of the pool of support agents, that have the same technical expertise as the support agent.
7. The method of claim 1 , wherein the support agent, assigned to the request for technical support, is a chat bot.
8. The method of claim 1 , further comprising: receiving, through a modality of the help desk service, the request for technical support from a customer of the help desk service.
9. A system comprising:
at least one processor; and
a memory, operatively connected with the at least one processor, storing computer-executable instructions that, when executed by the at least one processor, causes the at least one processor to execute a method that comprises:
analyzing, through a help desk service, a request for technical support, wherein the analyzing comprises an evaluation of lexical and prosodic features of voice communication data associated with the request;
generating one or more routing insights based on a result of the analyzing including the evaluation of the lexical and prosodic features of the voice communication data;
matching a support agent to the request for technical support, from a pool of support agents, based on an application of a model that analyzes support agent data for the pool of support agents in correlation with the one or more routing insights, wherein the support agent data is three or more selected from:
customer performance reviews of support agents from the pool of support agents,
organizational reviews of the support agents, wherein the organizational reviews comprise data evaluating previous interactions, through the help desk service, involving the support agents,
agent self-evaluations that include a review of a technical expertise of the support agents and a review of communication skills of the support agents, and
availability information for the support agents; and
assigning the support agent to the request based on a result of the matching.
10. The system of claim 9 , wherein the method, executed by the at least one processor, further comprises: initiating, through the help desk service, an interaction between the support agent and a customer associated with the request for technical support.
11. The system of claim 10 , wherein the interaction between the support agent and the customer is an indication of an automatic resolution of an issue associated with the request for technical support.
12. The system of claim 10 , wherein the interaction between the support agent and the customer comprises automatically patching the support agent into an ongoing call communication involving the customer and another support agent of the pool of support agents.
13. The system of claim 9 , wherein the one or more routing insights further comprise: two or more selected from a group consisting of: a frustration level of the customer, an indication of one or more recent poor customer experiences and a rating indicating likelihood that a user is a risk to leaving the help desk service.
14. The system of claim 9 , wherein the organizational reviews of the support agents comprise peer reviews, from other support agents of the pool of support agents, that have the same technical expertise as the support agent.
15. The system of claim 9 , wherein the support agent, assigned to the request for technical support, is a chat bot.
16. The system of claim 9 , wherein the method, executed by the at least one processor, further comprises: receiving, through a modality of the help desk service, the request for technical support from a customer of the help desk service.
17. A computer storage media storing computer-executable instructions that, when executed by at least one processor, causes the at least one processor to execute a method comprising:
analyzing, through a help desk service, a request for technical support, wherein the analyzing comprises an evaluation of lexical and prosodic features of voice communication data associated with the request;
generating one or more routing insights based on a result of the analyzing including the evaluation of the lexical and prosodic features of the voice communication data;
matching a support agent to the request for technical support, from a pool of support agents, based on an application of a model that analyzes support agent data for the pool of support agents in correlation with the one or more routing insights, wherein the support agent data is three or more selected from:
customer performance reviews of support agents from the pool of support agents,
organizational reviews of the support agents, wherein the organizational reviews comprise data evaluating previous interactions, through the help desk service, involving the support agents,
agent self-evaluations that include a review of a technical expertise of the support agents and a review of communication skills of the support agents, and
availability information for the support agents; and
assigning the support agent to the request based on a result of the matching.
18. The computer storage media of claim 17 , wherein the executed method further comprising: initiating, through the help desk service, an interaction between the support agent and a customer associated with the request for technical support.
19. The computer storage media of claim 18 , wherein the interaction between the support agent and the customer is one or more selected from a group consisting of: an indication of an automatic resolution of an issue associated with the request;
and automatically patching the support agent into an ongoing call communication involving the customer and another support agent of the pool of support agents.
20. The computer storage media of claim 17 , wherein the one or more routing insights further comprise: two or more selected from a group consisting of: a frustration level of the customer, an indication of one or more recent poor customer experiences and a rating indicating likelihood that a user is a risk to leaving the help desk service.