System and method for prompt modification based on caller hang Ups in IVRs

• US 9,621,723 B2
• Filed: 04/20/2016
• Issued: 04/11/2017
• Est. Priority Date: 04/04/2007
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property II LP (AT&T, Inc.)
• Inventors: Blanchard, Harry E., Lewis, Steven H., Pulz, Gregory, Zhang, Lan
• Primary Examiner(s): GAY, SONIA L
• Application Number:
  US15/134,003
• Publication Number:
  US 20160234385A1
• Time in Patent Office: 356 Days
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 2250/66 user interface aspects for indicating selection options for a communication line
• CPC Class Codes: H04M 3/2218 Call detail recording
• CPC Class Codes: H04M 3/36 Statistical metering, e.g. recording occasions when traffic exceeds capacity of trunks
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• 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 3/5175 Call or contact centers supervision arrangements

Abstract

In a method for use in Interactive Voice Response (IVR) systems, an IVR is configured such that voice prompts provided to a caller vary systematically and caller hang-up activity is attributed to the particular version of a prompt played to the caller. Voice prompt modifications are chosen based on how long the caller willingly listens to the voice prompt. A relatively short time listening to a prompt before hang-up, indicates dissatisfaction with that prompt. The system compares caller hang-up rates for each of the phrases in a prompt and chooses the optimum solution, which is the variant of the prompt with the longest caller listening time. Optionally, the system compares hang up rates to a threshold and contingent on that comparison chooses an alternative version of the prompt.

Claims

1. A method, comprising:

collecting, by a system comprising a processor, call data during playing to callers of a prompt sequence, wherein the prompt sequence comprises a plurality of phrases, and wherein the call data comprises rates of caller events during individual phrases of the plurality of phrases;

identifying, by the system, a particular one of the individual phrases based on the call data;

collecting, by the system, other call data during playing to callers of an alternate prompt sequence comprising an alternative phrase replacing the particular one of the individual phrases, and wherein the other call data includes a rate of caller events during the alternative phrase;

comparing, by the system, a rate of caller events during the particular one of the individual phrases with the rate of caller events during the alternative phrase to obtain a comparison; and

replacing, by the system, the particular one of the individual phrases with the alternative phrase based on the comparison.

2. The method of claim 1, wherein the playing of the prompt sequence and the playing of the alternate prompt sequence comprise a pattern of playing such that call data collection during one of the prompt sequence and the alternate prompt sequence is not complete before initiating call data collection during the other of the prompt sequence and the alternate prompt sequence.

3. The method of claim 2, wherein the pattern of playing comprises playing to alternate callers the prompt sequence and the alternate prompt sequence.

4. The method of claim 1, further comprising:

normalizing, by the system, the caller event rates for lengths of the phrases.

5. The method of claim 1, wherein collecting call data further comprises collecting data comprising one of rates of caller hang ups, rates of caller requests for a human operator or both.

6. The method of claim 1, wherein collecting call data further comprises collecting timestamps of the caller events.

7. The method of claim 6, further comprising:

compensating, by the system, the timestamps for one of a system processing time, a caller reaction time or both.

8. A non-transitory machine-readable storage medium, comprising machine-readable instructions that, when executed by a processor, facilitate performance of operations, comprising:

collecting call data during playing of a prompt sequence to callers, wherein the prompt sequence comprises a plurality of phrases, and wherein the call data comprises rates of caller events during individual phrases of the plurality of phrases;

identifying a particular one of the individual phrases based on the call data;

collecting other call data during playing to callers of an alternate prompt sequence comprising an alternative phrase replacing the particular one of the individual phrases, and wherein the other call data includes a rate of caller events during the alternative phrase;

comparing a rate of caller events during the particular one of the individual phrases with the rate of caller events during the alternative phrase to obtain a comparison; and

replacing the particular one of the individual phrases with the alternative phrase based on the comparison.

9. The non-transitory machine-readable storage medium of claim 8, wherein the playing of the prompt sequence and the playing of the alternate prompt sequence comprise a pattern of playing such that call data collection during one of the prompt sequence and the alternate prompt sequence is not complete before initiating call data collection during the other of the prompt sequence the alternate prompt sequence, thereby avoiding systematic errors due to a time of day of a call.

10. The non-transitory machine-readable storage medium of claim 9, wherein the pattern of playing comprises playing to alternate callers the prompt sequence and the alternate prompt sequence.

11. The non-transitory machine-readable storage medium of claim 8, wherein the operations further comprise:

normalizing the caller event rates for lengths of the phrases.

12. The non-transitory machine-readable storage medium of claim 8, wherein the operation of collecting call data further comprises collecting data comprising one of rates of caller hang ups, rates of caller requests for a human operator or both.

13. The non-transitory machine-readable storage medium of claim 8, wherein the collecting of the call data further comprises collecting timestamps of the caller events.

14. The non-transitory machine-readable storage medium of claim 13, wherein the operations further comprise:

compensating the timestamps for one of a system processing time, a caller reaction time or both.

15. A system, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

facilitating a collection of call data as a prompt sequence plays to callers, wherein the prompt sequence comprises a plurality of phrases, and wherein the call data comprises rates of caller events during individual phrases of the prompt sequence;

identifying, a particular one of the individual phrases based on the call data;

facilitating a collection of other call data during playing of an alternate prompt sequence to callers, wherein the alternate prompt sequence comprises an alternate phrase replacing the particular one of the individual phrases, and wherein the other call data comprising a rate of caller events during the alternate phrase;

comparing a rate of caller events during the particular one of the individual phrases with the rate of caller events during the alternate phrase to obtain a comparison; and

replacing the particular one of the individual phrases with the alternate phrase based on the comparison.

16. The system of claim 15, wherein the operations further comprise playing the prompt sequence and the alternate prompt sequence in a pattern of playing such that facilitating call data collection during one of the prompt sequence and the alternate prompt sequence is not complete before facilitating call data collection during the other of the prompt sequence and the alternate prompt sequence.

17. The system of claim 16, wherein the pattern of playing comprises playing to alternate callers the prompt sequence and the alternate prompt sequence.

18. The system of claim 15, wherein the operations further comprise:

normalizing the caller event rates for lengths of the phrases.

19. The system of claim 15, wherein the collection data comprises one of rates of caller hang ups, rates of caller requests for a human operator or both.

20. The system of claim 15, wherein the operations further comprise collecting timestamps of the caller events.