Automated response system

• US 9,088,655 B2
• Filed: 07/29/2013
• Issued: 07/21/2015
• Est. Priority Date: 07/29/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bhogal, Kulvir S., Griffith, William A., Naick, Indran, Talbot, Mark W.
• Primary Examiner(s): Tsang, Fan
• Assistant Examiner(s): BEZUAYEHU, SOLOMON G
• Application Number:
  US13/953,023
• Publication Number:
  US 20150030141A1
• Time in Patent Office: 722 Days
• Field of Search: 379 8801- 8819, 704/231
• US Class Current: 1/1
• 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 3/5235 Dependent on call type or called number [DNIS]

Abstract

Automated response processing includes receiving a first audible prompt from a called system and a response to the first audible prompt from a calling system during a first phone call. Automated response processing further includes determining, using a processor, a semantic identifier for the first audible prompt using semantic analysis and storing the semantic identifier of the first audible prompt in association with the response. The stored response is played responsive to determining that a semantic identifier for a second audible prompt played to the calling system matches the semantic identifier of the first audible prompt.

Claims

1. A system comprising:

a processor programmed to initiate executable operations comprising;

receiving a first audible prompt from a called system and a response to the first audible prompt from a calling system during a first phone call;

determining a semantic identifier for the first audible prompt using semantic analysis;

storing the semantic identifier of the first audible prompt in association with the response to generate a meaning-response pair;

receiving, from the calling system, a selection of one of a plurality of endpoints associated with the called system and each of the plurality of endpoints are associated with a plurality of meaning-response pairs, wherein the selection is made during, an active phone call;

determining that a semantic identifier for a second audible prompt played to the calling system matches the semantic identifier of the first audible prompt; and

Playing the stored response in responsive to the selection and matching.

2. The system of claim 1, wherein

the response is played during a second phone call.

3. The system of claim 2, wherein

the second phone call is to a same phone number as the first phone call.

4. The system of claim 2, wherein

the second phone call is to a different phone number than the first phone call.

5. The system of claim 2, wherein

the active call is the second phone call.

6. The system of claim 1, wherein

the stored response comprises a spoken utterance of a calling party.

7. The system of claim 1, wherein

the response is stored in the calling system and the semantic identifier of the first audio prompt is stored in a data processing system independent of the calling system.

8. The system of claim 6, wherein

the stored response is played during the first phone call.

9. A computer readable storage device having a program code stored thereon, the program code executed by a processor to perform:

receiving, using the processor, a first audible prompt from a called system and a response to the first audible prompt from a calling system during a first phone call;

determining, using the processor, a semantic identifier for the first audible prompt using semantic analysis;

storing the semantic identifier of the first audible prompt in association with the response to generate a meaning-response pair;

receiving, from the calling system, a selection of one of a plurality of endpoints associated with the called system and each of the plurality of endpoints are associated with a plurality of meaning-response pairs, wherein the selection is made during, an active phone call;

determining that a semantic identifier for a second audible prompt played to the calling system matches the semantic identifier of the first audible prompt; and

Playing the stored response in responsive to the selection and matching.

10. The computer readable storage device of claim 9, wherein

the response is played during a second phone call.

11. The computer readable storage device of claim 10, wherein

the second phone call is to a same phone number as the first phone call.

12. The computer program product of claim 10, wherein

the second phone call is to a different phone number than the first phone call.

13. The computer readable storage device of claim 10, wherein

the active call is the second phone call.

14. The computer readable storage device of claim 9, wherein

the active call is the first phone call.

15. The computer readable storage device of claim 9, wherein

the response is stored in the calling system and the semantic identifier of the first audio prompt is stored in a data processing system independent of the calling system.

16. The computer readable storage device of claim 9, wherein

the stored response is played during the first phone call.

17. The computer readable storage device of claim 9, wherein

storing the semantic identifier of the first audible prompt in association with the response is performed responsive to determining that the semantic identifier of the first audible prompt does not match a semantic identifier of any previously received audible prompts.