Recursive adaptive interaction management system
View Patent ↗A management system for guiding an agent in a media-specific dialogue has a conversion engine for instantiating ongoing dialogue as machine-readable text, if the dialogue is in voice media, a context analysis engine for determining facts from the text, a rules engine for asserting rules based on fact input, and a presentation engine for presenting information to the agent to guide the agent in the dialogue. The context analysis engine passes determined facts to the rules engine, which selects and asserts to the presentation engine rules based on the facts, and the presentation engine provides periodically updated guidance to the agent based on the rules asserted.
1. A computer-based management system for guiding a human agent during an interaction with a customer of a contact center, comprising:
a processor; and
a memory, wherein the memory has computer instructions stored therein that, when executed by the processor, cause the processor to:
display an initial script on an agent display device during the interaction for guiding the human agent on suggested dialogue or other actions to be taken during the interaction between the agent and the customer, wherein the displayed initial script includes first and second script components;
monitor the interaction between the human agent and the customer for context analysis and generate context analysis output in response;
monitor performance of the contact center and output statistical performance data in response;
identify a change in the statistical performance data, wherein the change indicates decrease of the contact center performance; and
identify a rule based on both the context analysis output and the identified change in the statistical performance data, wherein the identified rule is for increasing contact center performance in response to the change indicating decrease of the contact center performance;
select a third script component based on the identified rule;
dynamically update the initial script to replace the second script component with the selected third script component; and
update the agent display device to display the modified initial script replacing the second script component with the third script component.
2. The system of claim 1 , wherein the rule is a business rule.
3. The system of claim 1 , wherein the instructions further cause the processor to:
receive feedback from the agent in response to the display of the modified initial script, wherein the feedback triggers assertion of other rules.
4. The system of claim 1 , wherein the display of the modified initial script is customized based on detected agent preferences.
5. The system of claim 1 , wherein the context analysis is based on input from both the agent and the customer during the interaction.
6. The system of claim 1 , wherein the interaction is a voice dialog, wherein the instructions further cause the processor to:
convert the voice dialog to machine-readable text, wherein the context analysis is based on the machine-readable text.
7. The system of claim 1 , wherein context analysis output is based on analysis of context other than context provided by communication exchanged between the agent and the customer.
8. The system of claim 7 , wherein the data includes volume, inflection, sentence structure, or rate of dialogue.
9. The system of claim 1 , wherein the modified initial script includes prompts displayed to the agent.
10. The system of claim 9 , wherein the prompts are annotated with indicia indicating importance or other characteristics of the prompts.
11. A method for guiding an agent during an interaction with a customer of a contact center comprising:
displaying, by a processor, an initial script on an agent display device during the interaction for guiding the agent on suggested dialogue or other actions to be taken during the interaction between the agent and the customer, wherein the displayed initial script includes first and second script components;
monitoring, by the processor, the interaction between the agent and the customer for context analysis and generate context analysis output in response;
monitoring, by the processor, performance of the contact center and outputting statistical performance data in response;
identifying, by the processor, a change in the statistical performance data, wherein the change indicates decrease of the contact center performance; and
identifying, by the processor, a rule based on both the context analysis output and the identified change in the statistical performance data, wherein the identified rule is for increasing contact center performance in response to the change indicating decrease of the contact center performance;
selecting, by the processor, a third script component based on the identified rule;
dynamically updating, by the processor, the initial script to replace the second script component with the selected third script component; and
updating, by the processor, the agent display device to display the modified initial script replacing the second script component with the third script component.
12. The method of claim 11 , wherein the rule is a business rule.
13. The method of claim 11 further comprising:
receiving, by the processor, feedback from the agent in response to the display of the modified initial script, wherein the feedback triggers assertion of other rules.
14. The method of claim 11 , wherein the display of the modified initial script is customized based on detected agent preferences.
15. The method of claim 11 , wherein the context analysis is based on input from both the agent and the customer during the interaction.
16. The method of claim 11 , wherein the interaction is a voice dialog, and the method further comprises:
converting, by the processor, the voice dialog to machine-readable text, wherein the context analysis is based on the machine-readable text.
17. The method of claim 11 , wherein context analysis output is based on analysis of context other than context provided by communication exchanged between the agent and the customer.