Voice response apparatus and method of providing automated voice responses with silent prompting

• US 8,964,949 B2
• Filed: 07/01/2013
• Issued: 02/24/2015
• Est. Priority Date: 05/11/1999
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: McAllister, Alexander I.
• Primary Examiner(s): SING, SIMON P
• Application Number:
  US13/932,411
• Publication Number:
  US 20130294590A1
• Time in Patent Office: 603 Days
• Field of Search: 379 8822- 8825, 379/142.06, 379/88.03, 379/88.04
• US Class Current: 379/88.03
• CPC Class Codes: H04M 2201/14 Delay circuits; Timers
• CPC Class Codes: H04M 2201/40 using speech recognition
• 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

Abstract

A voice response unit (VRU) includes a silent prompt feature in the form of an intentional delay inserted after a message is given to a caller, during which delay the caller may invoke alternative processing or interrupt current processing. If appropriate alternative or interrupt commands are not received during the delay period, then processing continues as provided in accordance with the previously played message. The duration of this silent prompt delay is carefully selected to provide sufficient response time for the caller to request alternative processing, while avoiding a perceptible or objectionable delay to the average caller not requiring alternative processing.

Claims

1. A computer-implemented method comprising:

determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller, where each of the two or more, different content-equivalent messages are associated with a different identifier;

in response to determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages are available for output to a caller;

generating a pseudo-random number;

selecting the message that is associated with the identifier corresponding to the pseudo-random number; and

providing an audio representation of the selected message over the call to the caller;

receiving an audio representation of a first utterance in response to providing the audio representation of the selected message over the call to the caller;

determining that the first utterances matches a first identifier and a second identifier;

transmitting an audio representation of the first identifier;

receiving, after transmitting the audio representation of the first identifier, an audio representation of a second utterance;

determining that the second utterance matches a command that cancels a default process based on the first identifier; and

in response to determining that the second utterance matches a command that cancels a default process based on the first identifier, transmitting an audio representation of the second identifier.

2. The method of claim 1, wherein the method further comprises:

initiating a default process based on the second identifier after transmitting the audio representation of the second identifier.

3. The method of claim 1, wherein the particular stage comprises a stage for requesting the caller provide an identifier for a called party, and the messages include messages that request the caller provide the identifier.

4. The method of claim 1, comprising:

determining that the audio representation of the first utterance represents speech,

wherein determining that the first utterances matches a first identifier and a second identifier is in response to determining that the audio representation of the first utterance represents speech.

5. The method of claim 1, wherein determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller comprises:

determining that speech from the caller has not been received within a pre-determined time period.

6. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller, where each of the two or more, different content-equivalent messages are associated with a different identifier;

in response to determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages are available for output to a caller;

generating a pseudo-random number;

selecting the message that is associated with the identifier corresponding to the pseudo-random number; and

providing an audio representation of the selected message over the call to the caller;

receiving an audio representation of a first utterance in response to providing the audio representation of the selected message over the call to the caller;

determining that the first utterances matches a first identifier and a second identifier;

transmitting an audio representation of the first identifier;

receiving, after transmitting the audio representation of the first identifier, an audio representation of a second utterance;

determining that the second utterance matches a command that cancels a default process based on the first identifier; and

in response to determining that the second utterance matches a command that cancels a default process based on the first identifier, transmitting an audio representation of the second identifier.

7. The system of claim 6, wherein the operations further comprise:

initiating a default process based on the second identifier after transmitting the audio representation of the second identifier.

8. The system of claim 6, wherein the particular stage comprises a stage for requesting the caller provide an identifier for a called party, and the messages include messages that request the caller provide the identifier.

9. The system of claim 6, the operations comprising:

determining that the audio representation of the first utterance represents speech,

wherein determining that the first utterances matches a first identifier and a second identifier is in response to determining that the audio representation of the first utterance represents speech.

10. The system of claim 6, wherein determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller comprises:

determining that speech from the caller has not been received within a pre-determined time period.

11. A computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller, where each of the two or more, different content-equivalent messages are associated with a different identifier;

in response to determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages are available for output to a caller;

generating a pseudo-random number;

selecting the message that is associated with the identifier corresponding to the pseudo-random number; and

providing an audio representation of the selected message over the call to the caller;

receiving an audio representation of a first utterance in response to providing the audio representation of the selected message over the call to the caller;

determining that the first utterances matches a first identifier and a second identifier;

transmitting an audio representation of the first identifier;

receiving, after transmitting the audio representation of the first identifier, an audio representation of a second utterance;

determining that the second utterance matches a command that cancels a default process based on the first identifier; and

in response to determining that the second utterance matches a command that cancels a default process based on the first identifier, transmitting an audio representation of the second identifier.

12. The medium of claim 11, wherein the operations further comprise:

initiating a default process based on the second identifier after transmitting the audio representation of the second identifier.

13. The medium of claim 11, wherein the particular stage comprises a stage for requesting the caller provide an identifier for a called party, and the messages include messages that request the caller provide the identifier.

14. The medium of claim 11, the operations comprising:

determining that the audio representation of the first utterance represents speech,

wherein determining that the first utterances matches a first identifier and a second identifier is in response to determining that the audio representation of the first utterance represents speech.

15. The medium of claim 11, wherein determining that a call handling process has reached a particular stage in which two or more, different content-equivalent messages associated with the particular stage are available for output to a caller comprises:

determining that speech from the caller has not been received within a pre-determined time period.