Interactive voice response system with partial human monitoring
View Patent ↗The present invention enables service agents in a call center to monitor portions of calls that are especially error-prone (e.g., automated speech recognition of an address, etc.), while portions of calls that are not error-prone occur without any human monitoring. An interactive voice response (IVR) system script (e.g., a VXML script, etc.) is divided into a plurality of independent dialog sequences, each of which is assigned a human-monitoring requirement that indicates whether (and optionally, to what degree) the dialog sequence requires monitoring by a service agent. In the first illustrative embodiment, a partial ordering enables some dialog sequences to appear in a different order in that of the IVR script when it is advantageous to do so. In the second illustrative embodiment, each dialog sequence that requires human monitoring is recorded and packaged into an agent-review task that is subsequently sent to an available service agent for review.
1. A method comprising:
selecting a dialog sequence from a non-empty set S of dialog sequences, wherein each of said dialog sequences has a human-monitoring requirement; and
executing said dialog sequence during a call that involves an interactive voice response system;
wherein the selection of said dialog sequence is based on:
(i) said human-monitoring requirements,
(ii) the availability of one or more service agents, and
(iii) a partial ordering on said set S; and
wherein when none of said service agents is available, the selected dialog sequence:
(i) is a member of set T={d ∈S |d has no predecessors}, and
(ii) has the least human-monitoring requirement in set T.
2. The method of claim 1 further comprising generating said plurality of dialog sequences from a script for said interactive voice response system.
3. The method of claim 1 wherein when none of said service agents is available, the selected dialog sequence has the least human-monitoring requirement.
4. The method of claim 1 wherein when one or more of said service agents is available and when two or more of said human-monitoring requirements are different, the selected dialog sequence does not have the least human-monitoring requirement.
5. The method of claim 1 further comprising:
bridging one of said service agents into said call during the execution of said dialog sequence when said dialog sequence requires human monitoring; and
dropping said one of said service agents from said call after said dialog sequence has completed.
6. The method of claim 1 further comprising, when said dialog sequence requires human monitoring, generating an agent-review task that comprises one or both of:
(i) a recording of said call during said dialog sequence, and
(ii) an output of automated speech recognition.
7. The method of claim 6 further comprising transmitting a signal based on said agent-review task to an available one of said service agents.
8. A method comprising:
selecting a dialog sequence from a non-empty set S of dialog sequences, wherein each of said dialog sequences has a human-monitoring requirement; and
executing said dialog sequence during a call that involves an interactive voice response system;
wherein the selection of said dialog sequence is based on:
(i) said human-monitoring requirements,
(ii) the availability of one or more service agents, and
(iii)a partial ordering on said set S; and
wherein when one or more of said service agents is available, the selected dialog sequence:
(i) is a member of set T={d∈S|d has no predecessors}, and
(ii) does not have the least human-monitoring requirement in set T when set T has two or more dialog sequences with different human-monitoring requirements.
9. The method of claim 8 further comprising generating said plurality of dialog sequences from a script for said interactive voice response system.
10. The method of claim 8 wherein when none of said service agents is available, the selected dialog sequence has the least human-monitoring requirement.
11. The method of claim 8 wherein when one or more of said service agents is available and when two or more of said human-monitoring requirements are different, the selected dialog sequence does not have the least human-monitoring requirement.
12. The method of claim 8 further comprising:
bridging one of said service agents into said call during the execution of said dialog sequence when said dialog sequence requires human monitoring; and
dropping said one of said service agents from said call after said dialog sequence has completed.
13. The method of claim 8 further comprising, when said dialog sequence requires human monitoring, generating an agent-review task that comprises one or both of:
(i) a recording of said call during said dialog sequence, and
(ii) an output of automated speech recognition.
14. The method of claim 13 further comprising transmitting a signal based on said agent-review task to an available one of said service agents.