Digital assistant

• US 10,339,926 B2
• Filed: 12/31/2016
• Issued: 07/02/2019
• Est. Priority Date: 12/31/2016
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Oath Inc. (Verizon Communications Inc.)
• Inventors: Gupta, Ankur Kumar, Tan, Chao, Daly, Jr., Timothy Patrick
• Primary Examiner(s): Guerra-Erazo, Edgar X
• Application Number:
  US15/396,555
• Publication Number:
  US 20180190278A1
• Time in Patent Office: 913 Days
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

One or more computing devices, systems, and/or methods for dynamically selecting a personality for a digital assistant are provided. For example, audio associated with a conversation with a digital assistant may be received from a user. The audio may be converted into a request comprising text. A task may be determined based upon the request. One or more sentences associated with information associated with the task may be determined. A context of the conversation may be determined based upon the request and a user profile of the user. A first personality may be selected for the digital assistant from one or more personalities based upon the context of the conversation. The first personality may be used to generate audio of the one or more sentences. The audio of the one or more sentences may be presented as part of the conversation to the user.

Claims

1. A method for dynamically selecting a personality for a digital assistant, comprising:

receiving audio, from a user via a microphone, associated with a conversation with a digital assistant;

using speech recognition to convert the audio into a request comprising text;

determining a task based upon the request;

determining one or more sentences associated with the task;

determining a context of the conversation based upon the request and a user profile of the user;

calculating a first degree of relevance of a first personality, of a plurality of personalities, to the context of the conversation, wherein the first personality corresponds to a voice of a first person and the plurality of personalities corresponds to voices of a plurality of people;

calculating a second degree of relevance of a second personality, of the plurality of personalities, to the context of the conversation;

in response to determining that the first degree of relevance is greater than the second degree of relevance, selecting the first personality from the plurality of personalities, wherein the first personality is stored in a database in association with a first topic and each personality of the plurality of personalities is stored in the database in association with one or more topics, wherein the selecting the first personality is based upon a determination that at least one of the context of the conversation or the task is associated with the first topic;

generating audio of the one or more sentences with the voice of the first person using the first personality; and

presenting the audio of the one or more sentences with the voice of the first person as part of the conversation, via a speaker, to the user.

2. The method of claim 1, wherein the one or more sentences comprise one or more questions associated with information required to perform the task.

3. The method of claim 1, comprising:

after the presenting the audio, receiving second audio, from the user via the microphone, associated with the conversation with the digital assistant;

using speech recognition to convert the second audio into a second request comprising text; and

determining a second task based upon the second request.

4. The method of claim 1, wherein the second personality corresponds to a voice of a second person.

5. The method of claim 3, comprising:

determining one or more second sentences associated with the second task;

determining a second context of the conversation based upon the second request and the user profile of the user;

selecting the second personality, for the digital assistant, from the plurality of personalities based upon the second context of the conversation; and

generating audio of the one or more second sentences using the second personality.

6. The method of claim 5, comprising:

presenting the audio of the one or more second sentences as part of the conversation, via the speaker, to the user.

7. The method of claim 1, comprising:

selecting a first agent from a plurality of agents stored in a second database based upon the task.

8. The method of claim 7, comprising:

providing instructions to perform the task via the first agent; and

receiving confirmation that the task has been performed via the first agent; and

presenting audio indicative of the confirmation as part of the conversation, via the speaker, to the user.

9. The method of claim 7, wherein:

calculating a first degree of relevance of the first agent to the task;

calculating a second degree of relevance of a second agent of the plurality of agents to the task; and

in response to determining that the first degree of relevance is greater than the second degree of relevance, performing the selecting the first agent.

10. The method of claim 1, wherein a third personality of the plurality of personalities is stored in the database in association with a second topic, the first topic different than the second topic.

11. The method of claim 10, comprising:

determining a second task; and

in response to determining that the second task is associated with the second topic more than the first topic, selecting the third personality.

12. The method of claim 1, wherein:

the generating audio is performed in response to determining that the user prefers that the conversation be continued in an audio format of a plurality of formats of communication stored in a second database than in one or more other formats of the plurality of formats of communication.

13. The method of claim 1, wherein:

the generating audio is performed in response to determining that the user prefers that the conversation be continued in an audio format of a plurality of formats of communication stored in a second database than in a written format.

14. The method of claim 1, comprising:

after the presenting the audio, receiving feedback associated with the conversation; and

lower the first personality in a ranking of personalities for the user based upon the feedback.

15. A computing device comprising:

a processor; and

memory comprising processor-executable instructions that when executed by the processor cause performance of operations, the operations comprising;

receiving audio, from a user, associated with a conversation with a digital assistant;

using speech recognition to convert the audio into a request comprising text;

determining a task based upon the request;

determining one or more sentences associated with the task;

determining a context of the conversation based upon the request and a user profile of the user;

calculating a first degree of relevance of a first personality, of a plurality of personalities, to the context of the conversation, wherein the first personality corresponds to a voice of a first person and the plurality of personalities corresponds to voices of a plurality of people;

calculating a second degree of relevance of a second personality, of the plurality of personalities, to the context of the conversation;

in response to determining that the first degree of relevance is greater than the second degree of relevance, selecting the first personality from the plurality of personalities;

generating audio of the one or more sentences with the voice of the first person using the first personality; and

presenting the audio of the one or more sentences with the voice of the first person as part of the conversation to the user.

16. The computing device of claim 15, the operations comprising:

after the presenting the audio, receiving second audio, from the user, associated with the conversation with the digital assistant;

using speech recognition to convert the second audio into a second request comprising text;

determining a second task based upon the second request;

determining one or more second sentences associated with the second task;

determining a second context of the conversation based upon the second request and the user profile of the user;

selecting the second personality, for the digital assistant, from the plurality of personalities based upon the second context of the conversation;

generating audio of the one or more second sentences using the second personality; and

presenting the audio of the one or more second sentences as part of the conversation to the user.

17. A non-transitory machine readable medium having stored thereon processor-executable instructions that when executed cause performance of operations, the operations comprising:

receiving a request, from a user, associated with a conversation with a digital assistant;

determining a task based upon the request;

determining one or more sentences associated with the task;

determining a context of the conversation based upon the request and a user profile of the user;

calculating a first degree of relevance of a first personality, of a plurality of personalities stored in a database, to the context of the conversation;

calculating a second degree of relevance of a second personality, of the plurality of personalities, to the context of the conversation;

in response to determining that the first degree of relevance is greater than the second degree of relevance, selecting the first personality, for the digital assistant, from the plurality of personalities, wherein each personality of the plurality of personalities is stored in the database in association with one or more topics, wherein the selecting the first personality is based upon a determination that at least one of the context of the conversation or the task is associated with a first topic in association with which the first personality is stored in the database;

generating output of the one or more sentences using the first personality; and

presenting the output of the one or more sentences as part of the conversation to the user.

18. The non-transitory machine readable medium of claim 17, wherein:

the output comprises audio of the one or more sentences.

19. The non-transitory machine readable medium of claim 17, wherein:

the output comprises text of the one or more sentences.

20. The non-transitory machine readable medium of claim 17, wherein:

the output comprises video of the one or more sentences.