Virtual voice response agent individually configured for a user

• US 10,091,355 B2
• Filed: 02/19/2016
• Issued: 10/02/2018
• Est. Priority Date: 02/19/2016
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Flores, Romelia H., Loza, Christian E., Loza, Olivia G., Pannell, John S.
• Primary Examiner(s): Hashem, Lisa
• Application Number:
  US15/048,679
• Publication Number:
  US 20170244834A1
• Time in Patent Office: 956 Days
• CPC Class Codes: H04M 1/645 with speech synthesis
• CPC Class Codes: H04M 2203/255 comprising a personalized user interface
• CPC Class Codes: H04M 3/42068 where the identifier is used to access a profile
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A call can be received from a user. At least one input can be received from the user. Responsive to receiving the input(s) from the user, a user profile for the user can be identified or created. The user profile can indicate one or more speech traits of the user. A virtual intelligent voice response (VIVR) agent individually configured for the user can be identified or created. The VIVR agent can be configured to include, or identify, one or more VIVR agent features corresponding to the speech trait(s) of the user. The user can be interacted with on the call by generating synthesized speech using parameters specified by the VIVR agent feature(s) included in, or identified by, the VIVR agent individually configured for the user.

Claims

1. A method, comprising:

receiving a first call from a user;

receiving at least a first input from the user on the first call;

responsive to receiving at least the first input from the user on the first call, identifying or creating a user profile for the user, the user profile indicating at least a first speech trait of the user;

responsive to identifying or creating the user profile for the user, automatically identifying or creating, using a processor, a virtual intelligent voice response (VIVR) agent individually configured for the user, the VIVR agent configured to include, or identify, at least a first VIVR agent feature corresponding to at least a first speech trait of the user; and

interacting with the user on the first call by generating first synthesized speech using the VIVR agent individually configured for the user to perform linguistic analysis when generating the first synthesized speech, using the VIVR agent individually configured for the user to perform the linguistic analysis comprising using parameters specified by at least the first VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

2. The method of claim 1, further comprising:

responsive to receiving at least the first input received from the user on the first call, identifying at least the first speech trait of the user; and

responsive to identifying at least the first speech trait of the user, updating the VIVR agent to include at least the first VIVR agent feature corresponding to at least the first speech trait of the user.

3. The method of claim 1, further comprising:

receiving at least a second call from the user;

responsive to receiving the second call from the user, identifying the VIVR agent individually configured for the user;

receiving at least a second input received from the user on the second call;

responsive to receiving at least the second input received from the user on the second call, identifying at least a second speech trait of the user;

responsive to identifying at least the second speech trait of the user, updating the VIVR agent to include at least a second VIVR agent feature corresponding to at least the second speech trait of the user; and

interacting with the user on the second call by generating second synthesized speech using parameters specified by at least the second VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

4. The method of claim 1, wherein creating the VIVR agent individually configured for the user comprises:

identifying user profile features contained in the user profile of the user;

determining average user profile features for each of a plurality of user groups;

comparing the user profile features contained in the user profile of the user to the determined average user profile features of each of the plurality of user groups;

based on the comparing, identifying a user group from among the plurality of user groups for which the determined average user profile features most closely correspond to the user profile features contained in the user profile of the user;

selecting from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile corresponding to the identified user group; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile corresponding to the identified user group.

5. The method of claim 1, wherein creating the VIVR agent individually configured for the user comprises:

identifying user profile features contained in the user profile of the user;

selecting from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile to which the user profile features most closely correspond; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile to which the user profile features most closely correspond.

6. The method of claim 1, further comprising:

monitoring utterances spoken by the user during the first call;

analyzing the utterances spoken by the user during the first call; and

based on analyzing the utterances spoken by the user during the first call, updating, in real time, the user profile of the user to add, remove or update user profile features contained in the user profile.

7. The method of claim 6, further comprising:

dynamically updating, in real time, the VIVR agent individually configured for the user to add or remove VIVR agent features corresponding to the added, removed or updated user profile features contained in the user profile.

8. A system, comprising:

a processor programmed to initiate executable operations comprising;

receiving a first call from a user;

receiving at least a first input from the user on the first call;

responsive to receiving at least the first input from the user on the first call, identifying or creating a user profile for the user, the user profile indicating at least a first speech trait of the user;

responsive to identifying or creating the user profile for the user, automatically identifying or creating a virtual intelligent voice response (VIVR) agent individually configured for the user, the VIVR agent configured to include, or identify, at least a first VIVR agent feature corresponding to at least a first speech trait of the user; and

interacting with the user on the first call by generating first synthesized speech using the VIVR agent individually configured for the user to perform linguistic analysis when generating the first synthesized speech, using the VIVR agent individually configured for the user to perform the linguistic analysis comprising using parameters specified by at least the first VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

9. The system of claim 8, the executable operations further comprising:

responsive to receiving at least the first input received from the user on the first call, identifying at least the first speech trait of the user; and

responsive to identifying at least the first speech trait of the user, updating the VIVR agent to include at least the first VIVR agent feature corresponding to at least the first speech trait of the user.

10. The system of claim 8, the executable operations further comprising:

receiving at least a second call from the user;

responsive to receiving the second call from the user, identifying the VIVR agent individually configured for the user;

receiving at least a second input received from the user on the second call;

responsive to receiving at least the second input received from the user on the second call, identifying at least a second speech trait of the user;

responsive to identifying at least the second speech trait of the user, updating the VIVR agent to include at least a second VIVR agent feature corresponding to at least the second speech trait of the user; and

interacting with the user on the second call by generating second synthesized speech using parameters specified by at least the second VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

11. The system of claim 8, wherein creating the VIVR agent individually configured for the user comprises:

identifying user profile features contained in the user profile of the user;

determining average user profile features for each of a plurality of user groups;

comparing the user profile features contained in the user profile of the user to the determined average user profile features of each of the plurality of user groups;

based on the comparing, identifying a user group from among the plurality of user groups for which the determined average user profile features most closely correspond to the user profile features contained in the user profile of the user;

selecting from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile corresponding to the identified user group; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile corresponding to the identified user group.

12. The system of claim 8, wherein creating the VIVR agent individually configured for the user comprises:

selecting user profile features contained in the user profile of the user;

identifying from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile to which the user profile features most closely correspond; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile to which the user profile features most closely correspond.

13. The system of claim 8, the executable operations further comprising:

monitoring utterances spoken by the user during the first call;

analyzing the utterances spoken by the user during the first call; and

based on analyzing the utterances spoken by the user during the first call, updating, in real time, the user profile of the user to add, remove or update user profile features contained in the user profile.

14. The system of claim 13, the executable operations further comprising:

dynamically updating, in real time, the VIVR agent individually configured for the user to add or remove VIVR agent features corresponding to the added, removed or updated user profile features contained in the user profile.

15. A computer program product comprising a computer readable storage medium having program code stored thereon, the program code executable by a processor to perform a method comprising:

receiving, by the processor, a first call from a user;

receiving, by the processor, at least a first input from the user on the first call;

responsive to receiving at least the first input from the user on the first call, identifying or creating, by the processor, a user profile for the user, the user profile indicating at least a first speech trait of the user;

responsive to identifying or creating the user profile for the user, automatically identifying or creating, by the processor, a virtual intelligent voice response (VIVR) agent individually configured for the user, the VIVR agent configured to include, or identify, at least a first VIVR agent feature corresponding to at least a first speech trait of the user; and

interacting, by the processor, with the user on the first call by generating first synthesized speech using the VIVR agent individually configured for the user to perform linguistic analysis when generating the first synthesized speech, using the VIVR agent individually configured for the user to perform the linguistic analysis comprising using parameters specified by at least the first VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

16. The computer program product of claim 15, the method further comprising:

responsive to receiving at least the first input received from the user on the first call, identifying at least the first speech trait of the user; and

responsive to identifying at least the first speech trait of the user, updating the VIVR agent to include at least the first VIVR agent feature corresponding to at least the first speech trait of the user.

17. The computer program product of claim 15, the method further comprising:

receiving at least a second call from the user;

responsive to receiving the second call from the user, identifying the VIVR agent individually configured for the user;

receiving at least a second input received from the user on the second call;

responsive to receiving at least the second input received from the user on the second call, identifying at least a second speech trait of the user;

responsive to identifying at least the second speech trait of the user, updating the VIVR agent to include at least a second VIVR agent feature corresponding to at least the second speech trait of the user; and

interacting with the user on the second call by generating second synthesized speech using parameters specified by at least the second VIVR agent feature included in, or identified by, the VIVR agent individually configured for the user.

18. The computer program product of claim 15, wherein creating the VIVR agent individually configured for the user comprises:

identifying user profile features contained in the user profile of the user;

determining average user profile features for each of a plurality of user groups;

comparing the user profile features contained in the user profile of the user to the determined average user profile features of each of the plurality of user groups;

based on the comparing, identifying a user group from among the plurality of user groups for which the determined average user profile features most closely correspond to the user profile features contained in the user profile of the user;

selecting from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile corresponding to the identified user group; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile corresponding to the identified user group.

19. The computer program product of claim 15, wherein creating the VIVR agent individually configured for the user comprises:

identifying user profile features contained in the user profile of the user;

selecting from among a plurality of baseline VIVR agent profiles a baseline VIVR agent profile to which the user profile features most closely correspond; and

creating the VIVR agent individually configured for the user using the selected baseline VIVR agent profile to which the user profile features most closely correspond.

20. The computer program product of claim 15, the method further comprising:

monitoring utterances spoken by the user during the first call;

analyzing the utterances spoken by the user during the first call; and

based on analyzing the utterances spoken by the user during the first call, updating, in real time, the user profile of the user to add, remove or update user profile features contained in the user profile.