Using a speech analytics system to offer callbacks

• US 9,350,866 B1
• Filed: 10/05/2015
• Issued: 05/24/2016
• Est. Priority Date: 11/06/2013
• Status: Active Grant

• Current Assignee: Alvaria Cayman
• Original Assignee: Noble Systems Corporation
• Inventors: Ouimette, Jason P., Mekonnen, Eyob, Lillard, Brian T., Patel, Parimal R.
• Primary Examiner(s): Huynh, Van D
• Application Number:
  US14/875,130
• Time in Patent Office: 232 Days
• Field of Search: 379/88.02, 379/210.01, 379/266.06
• US Class Current: 1/1
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: H04M 3/42195 Arrangements for calling back a calling subscriber when the wanted subscriber ceases to be busy H04M3/48
• CPC Class Codes: H04M 3/42221 Conversation recording systems at the subscriber's set H04M1/656
• CPC Class Codes: H04M 3/428 Arrangements for placing incoming calls on hold
• CPC Class Codes: H04M 3/4285 Notifying, informing or entertaining a held party while on hold, e.g. Music On Hold
• CPC Class Codes: H04M 3/48 Arrangements for recalling a calling subscriber when the wanted subscriber ceases to be busy
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: H04M 3/5231 with call back arrangements

Abstract

Various embodiments of the invention provide methods, systems, and computer-program products for setting up a callback for a party placed on hold. In particular embodiments, speech analytics is used to listen in on a party once the party has been placed on hold for a keyword spoken by the party indicating the party would like to receive a callback. In response to detecting the keyword spoken by the party, a notification is sent to a component such as an IVR and in turn, the IVR interacts with the party to obtain information from the party with respect to placing a callback to the party. Accordingly, this information is recorded so that a callback can be placed to the party at a later time by some type of call handler component such as, for example, a dialer or PBX.

Claims

1. A system for setting up a callback for a party placed on hold, the system comprising:

a speech analytics component configured to;

listen in on audio of a telephone call involving the party once the telephone call has been placed on hold to detect an event indicating to offer the callback to the party, the event comprising at least one of a word spoken by the party, a sound made by the party, and an emotion displayed by the party; and

in response to detecting the event, send a notification to offer the callback to the party; and

an interactive voice response component configured to;

in response to the notification being sent by the speech analytics component, interact with the party to inquire whether the party would like to receive the callback;

in response to the party indicating the party would like to receive the callback, interact with the party to obtain information from the party with respect to placing the callback to the party; and

record the information so that the callback can be placed to the party at a later time.

2. The system of claim 1 further comprising a call hander component configured to place the callback to the party at the later time.

3. The system of claim 1, wherein the event is frustration displayed by the party and the speech analytics component is configured to detect the frustration based on the audio having a higher average pitch and a high-frequency energy.

4. The system of claim 1, wherein the information comprises at least one of a telephone number to place the callback to and a time to place the callback.

5. The system of claim 1, wherein the interactive voice response component is further configured to interact with the party after a predetermined period of time the party has been on hold to determine whether the party would like to receive the callback or whether the party would like to remain on hold.

6. The system of claim 5, wherein the interactive voice response component is further configured to also provide the party with an approximate time the party is expected to remain on hold.

7. The system of claim 1, wherein the interactive voice response component is configured to, prior to the telephone call being placed on hold, provide the party with an option to receive the callback.

8. The system of claim 1 further comprising a call hander component configured to:

receive the telephone call from the party; and

after receiving the telephone call;

place the telephone call on hold; and

establish a call leg so that the speech analytics component can listen in on the audio of the telephone call using the call leg.

9. A non-transitory, computer-readable medium comprising computer-executable instructions when executed by at least one computer processor cause the at least one computer processor to:

listen in on audio of a telephone call involving a party once the telephone call has been placed on hold to detect an event indicating to offer a callback to the party, the event comprising at least one of a word spoken by the party, a sound made by the party, and an emotion displayed by the party; and

in response to detecting the event, interact with the party to inquire whether the party would like to receive the callback;

in response to the party indicating the party would like to receive the callback, interact with the party to obtain information from the party with respect to placing the callback to the party; and

record the information so that the callback can be placed to the party at a later time.

10. The non-transitory, computer-readable medium of claim 9, wherein the computer-readable instructions when executed by the at least one computer processor cause the at least one computer processor to place the callback to the party at the later time.

11. The non-transitory, computer-readable medium of claim 9, wherein the event is frustration displayed by the party and the speech analytics component is configured to detect the frustration based on the audio having a higher average pitch and a high-frequency energy.

12. The non-transitory, computer-readable medium of claim 9, wherein the information comprises at least one of a telephone number to place the callback to and a time to place the callback.

13. The non-transitory, computer-readable medium of claim 9, wherein the computer-readable instructions when executed by the at least one computer processor cause the at least one computer processor to interact with the party after a predetermined period of time the party has been on hold to determine whether the party would like to receive the callback or whether the party would like to remain on hold.

14. The non-transitory, computer-readable medium of claim 13, wherein the computer-readable instructions when executed by the at least one computer processor cause the at least one computer processor to also provide the party with an approximate time the party is expected to remain on hold.

15. The non-transitory, computer-readable medium of claim 9, wherein the computer-readable instructions when executed by the at least one computer processor cause the at least one computer processor to, prior to the telephone call being placed on hold, provide the party with an option to receive the callback.

16. The non-transitory, computer-readable medium of claim 9, wherein the computer-readable instructions when executed by the at least one computer processor cause the at least one computer processor to:

place the telephone call on hold upon receiving the telephone call from the party; and

establish a call leg used to listen in on the audio of the telephone call.

17. A method for setting up a callback for a party placed on hold comprising the steps of:

listening in on audio of a telephone call involving the party once the telephone call has been placed on hold by a speech analytics system to detect an event indicating to offer the callback to the party, the event comprising at least one of a word spoken by the party, a sound made by the party, and an emotion displayed by the party;

in response to detecting the event, sending a notification to offer the callback to the party;

in response to the notification being sent, interacting with the party by an interactive voice response system to inquire whether the party would like to receive the callback;

in response to the party indicating the party would like to receive the callback, interacting with the party by the interactive voice response system to obtain information from the party with respect to placing the callback to the party; and

recording the information so that the callback can be placed to the party at a later time.

18. The method of claim 17 further comprising the step of placing the callback to the party by a call handler system at the later time.

19. The method of claim 17, wherein the event is frustration displayed by the party and the speech analytics component is configured to detect the frustration based on the audio having a higher average pitch and a high-frequency energy.

20. The method of claim 17, wherein the information comprises at least one of a telephone number to place the callback to and a time to place the callback.

21. The method of claim 17 further comprising the step of interacting with the party by the interactive voice response system after a predetermined period of time the party has been on hold to determine whether the party would like to receive the callback or whether the party would like to remain on hold.

22. The method of claim 21 further comprising the step of providing the party with an approximate time the party is expected to remain on hold by the interactive voice response system.

23. The method of claim 17 further comprising the step of, prior to the telephone call being placed on hold, providing the party with an option to receive the callback.

24. The method of claim 17 further comprising the steps of:

receiving the telephone call from the party by a call hander system; and

after receiving the telephone call;

placing the telephone call on hold by the call hander system; and

establishing a call leg by the call hander system so that the speech analytics system can listen in on the audio of the telephone call.