Granted Patent B2

US 8,699,674 · App. 13/919,136 · Granted Apr 15, 2014

Abstract

Claims (92)

1. A computer-implemented method comprising:

receiving a call at an interactive voice response (IVR) system, the call being received from a telephonic device of a caller;

establishing a voice communications session between the IVR system and the telephonic device in response to the call;

receiving, by a dynamic speech allocation (DSA) engine and from the IVR system, a request to allocate a speech resource for processing voice data of the voice communications session;

accessing, by the DSA engine, configuration data associated with a current state of the voice communications session;

accessing, by the DSA engine, dynamic interaction data associated with the caller, wherein the dynamic interaction data includes data representing characteristics associated with the caller or data representing characteristics associated with the caller's calling environment during the voice communications session;

selecting, by the DSA engine, a speech resource from among multiple speech resources based on the configuration data and the dynamic interaction data; and

allocating the selected speech resource to the voice communications session by enabling the IVR system to use the selected speech resource to process voice data received from the caller during the current state of the voice communications session.

2. The method of claim 1 ,

further comprising accessing, by the DSA engine, historical interaction data associated with a previous voice communications session; and

wherein selecting, by the DSA engine, a speech resource from among multiple speech resources further comprises selecting the speech resource based on the configuration data, the dynamic interaction data, and the historical interaction data.

3. The method of claim 2 ,

wherein the previous voice communications session is between the IVR system and the caller, and

wherein the historical interaction data includes data representing one or more speech resources accessed by the IVR system during the previous voice communications session.

4. The method of claim 2 ,

wherein establishing a voice communications session between the IVR system and the telephonic device further comprises initiating a particular voice application that provides a particular product or service to the caller,

wherein the previous voice communications session is between the IVR system and a different caller,

wherein the particular voice application was initiated during the previous voice communications session to provide the particular product or service to the different caller, and

wherein the historical interaction data includes data representing one or more speech resources accessed by the IVR system during the previous voice communications session for the different caller.

5. The method of claim 1 , further comprising:

determining that the selected speech resource does not satisfy a demand of the caller; and

based on determining that the selected speech resource does not satisfy the demand of the caller, selecting, by the DSA engine, a second, different, speech resource from among the multiple speech resources; and

allocating the second speech resource to the voice communications session by enabling the IVR system to use the second speech resource to process subsequent voice data received from the caller during the current state of the voice communications session.

6. The method of claim 5 , wherein determining that the selected speech resource does not satisfy a demand of the caller includes determining that the caller repeats similar voice data after providing the caller with a response based on the processed voice data received from the caller during the current state of the voice communications session.

7. The method of claim 5 ,

wherein determining that the selected speech resource does not satisfy a demand of the caller includes analyzing one or more voice characteristics of the caller based on the processed voice data received from the caller during the current state of the voice communications session, and

wherein the one or more voice characteristics include gender, pitch, speed, volume, tone, preferred spoken language, age group, or accent of the caller.

8. The method of claim 1 , wherein the dynamic interaction data includes an ambient noise level around the caller during the current state of the voice communications session.

9. The method of claim 1 , wherein the dynamic interaction data includes one or more voice characteristics of the caller.

10. The method of claim 1 , wherein the dynamic interaction data includes a location of the caller during the current state of the voice communications session.

11. The method of claim 1 , wherein selecting a speech resource from among multiple speech resources further comprises:

determining two or more different speech resources based on the configuration data or the dynamic interaction data; and

selecting, from among the two or more different speech resources, a speech resource that is associated with a lowest cost for a content provider of the voice communications session.

12. The method of claim 1 , wherein selecting a speech resource from among multiple speech resources further comprises:

determining two or more different speech resources based on the configuration data and the dynamic interaction data; and

selecting, from among the two or more different speech resources, a speech resource that is associated with a lowest cost for a content provider of the voice communications session.

13. The method of claim 1 , wherein selecting a speech resource further comprises selecting an automated speech recognition (ASR) engine from among multiple ASR engines based on one or more ASR engine attributes, and

wherein the one or more ASR engine attributes include a speech type, a supported language, a channel type, a cost per transaction, a recognition accuracy, a security feature, or an interaction type.

14. The method of claim 1 , wherein the dynamic interaction data includes the data representing characteristics associated with the caller and the data representing characteristics associated with the caller's calling environment during the voice communications session.

15. A system comprising:

an interactive voice response (IVR) system configured to:

receive a call from a telephonic device of a caller; and

establish a voice communications session between the IVR system and the telephonic device in response to the call;

one or more speech resources accessible by the IVR system; and

a dynamic speech allocation (DSA) engine that includes one or more computer processors configured to:

receive, from the IVR system, a request to allocate a speech resource for processing voice data of the voice communications session;

access configuration data associated with a current state of the voice communications session;

access dynamic interaction data associated with the caller, wherein the dynamic interaction data includes data representing characteristics associated with the caller or data representing characteristics associated with the caller's calling environment during the voice communications session;

select a speech resource from among multiple speech resources based on the configuration data and the dynamic interaction data; and

allocate the selected speech resource to the voice communications session by enabling the IVR system to use the selected speech resource to process voice data received from the caller during the current state of the voice communications session.

16. The system of claim 15 , wherein the DSA engine is further configured to:

access historical interaction data associated with a previous voice communications session, and

wherein selecting a speech resource from among multiple speech resources further comprises selecting the speech resource based on the configuration data, the dynamic interaction data, and the historical interaction data.

17. The system of claim 15 , wherein the DSA engine is further configured to:

determine that the selected speech resource does not satisfy a demand of the caller; and

based on determining that the selected speech resource does not satisfy the demand of the caller, select a second, different, speech resource from among the multiple speech resources; and

allocate the second speech resource to the voice communications session by enabling the IVR system to use the second speech resource to process subsequent voice data received from the caller during the current state of the voice communications session.

18. The system of claim 15 , wherein the dynamic interaction data includes an ambient noise level around the caller during the current state of the voice communications session, one or more voice characteristics of the caller, or a location of the caller during the current state of the voice communications session.

19. The system of claim 15 , wherein selecting a speech resource from among multiple speech resources further comprises:

determining two or more different speech resources based on the configuration data or the dynamic interaction data; and

selecting, from among the two or more different speech resources, a speech resource that is associated with a lowest cost for a content provider of the voice communications session.

20. The system of claim 15 , wherein selecting a speech resource further comprises selecting an automated speech recognition (ASR) engine from among multiple ASR engines based on one or more ASR engine attributes, and

wherein the one or more ASR engine attributes include a speech type, a supported language, a channel type, a cost per transaction, a recognition accuracy, a security feature, or an interaction type.

21. A system comprising:

one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

receiving a call at an interactive voice response (IVR) system, the call being received from a telephonic device of a caller;

establishing a voice communications session between the IVR system and the telephonic device in response to the call;

receiving, by a dynamic speech allocation (DSA) engine and from the IVR system, a request to allocate a speech resource for processing voice data of the voice communications session;

accessing, by the DSA engine, configuration data associated with a current state of the voice communications session;

accessing, by the DSA engine, dynamic interaction data associated with the caller, wherein the dynamic interaction data includes data representing characteristics associated with the caller or data representing characteristics associated with the caller's calling environment during the voice communications session;

selecting, by the DSA engine, a speech resource from among multiple speech resources based on the configuration data and the dynamic interaction data; and

allocating the selected speech resource to the voice communications session by enabling the IVR system to use the selected speech resource to process voice data received from the caller during the current state of the voice communications session.

22. The system of claim 21 ,

wherein the operations further comprise accessing, by the DSA engine, historical interaction data associated with a previous voice communications session; and

wherein selecting, by the DSA engine, a speech resource from among multiple speech resources further comprises selecting the speech resource based on the configuration data, the dynamic interaction data, and the historical interaction data.

23. The system of claim 21 , wherein the operations further comprise:

determining that the selected speech resource does not satisfy a demand of the caller; and

based on determining that the selected speech resource does not satisfy the demand of the caller, selecting, by the DSA engine, a second, different, speech resource from among the multiple speech resources; and

allocating the second speech resource to the voice communications session by enabling the IVR system to use the second speech resource to process subsequent voice data received from the caller during the current state of the voice communications session.

24. The system of claim 21 , wherein the dynamic interaction data includes an ambient noise level around the caller during the current state of the voice communications session, one or more voice characteristics of the caller, or a location of the caller during the current state of the voice communications session.

25. The system of claim 21 , wherein selecting a speech resource from among multiple speech resources further comprises:

determining two or more different speech resources based on the configuration data or the dynamic interaction data; and

selecting, from among the two or more different speech resources, a speech resource that is associated with a lowest cost for a content provider of the voice communications session.

26. The system of claim 21 , wherein selecting a speech resource further comprises selecting an automated speech recognition (ASR) engine from among multiple ASR engines based on one or more ASR engine attributes, and

wherein the one or more ASR engine attributes include a speech type, a supported language, a channel type, a cost per transaction, a recognition accuracy, a security feature, or an interaction type.

27. A computer-implemented method comprising:

receiving a call at an interactive voice response (IVR) system, the call being received from a telephonic device of a caller;

establishing a voice communications session between the IVR system and the telephonic device in response to the call;

receiving, by a dynamic speech allocation (DSA) engine and from the IVR system, a request to allocate a speech resource for processing voice data of the voice communications session;

accessing, by the DSA engine, configuration data associated with a current state of the voice communications session;

selecting, by the DSA engine, a speech resource from among multiple speech resources based on the configuration data; and

allocating the selected speech resource to the voice communications session by enabling the IVR system to use the selected speech resource to process voice data received from the caller during the current state of the voice communications session.

Assignments (11)