Automated call requests with status updates

Patent metadata

Field	Value
Publication number	US-10917522-B2
Application number	US-201916385444-A
Country	US
Kind code	B2
Filing date	Apr 16, 2019
Priority date	Jun 13, 2016
Publication date	Feb 9, 2021
Grant date	Feb 9, 2021

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call status updates. In some implementations, a method includes determining, by a task manager module, that a triggering event has occurred to provide a current status of a user call request. The method may then determine, by the task manager module, the current status of the user call request. A representation of the current status of the user call request is generated. Then, the generated representation of the current status of the user call request is provided to the user.

First claim

What is claimed is:

1. A computer-implemented method comprising:
receiving, by a computing device that is configured to conduct telephone conversations between a bot of the computing device and humans on behalf of a first human, an incoming telephone call from a second human;
causing, by the bot of computing device, the incoming telephone call from the second human to be answered by the bot;
causing, by the bot of the computing device, a corresponding telephone conversation to be conducted with the second human and on behalf of the first human;
receiving, by the computing device, and during the corresponding telephone conversation, unstructured dialog from the second human;
generating, by the computing device, a transcription of the unstructured dialog;
based on the transcription of the unstructured dialog, determining, by the computing device, an intent of the second human;
based on the intent of the second human, generating, by the computing device, a spoken response; and
causing, by the bot of the computing device, the spoken response to be audibly rendered at an additional computing device associated with the second human.

2. The method of claim 1 , comprising:
accessing, by the computing device, data associated with the unstructured dialog, wherein the spoken response is based on the data associated with the unstructured dialog.

3. The method of claim 2 , wherein the data associated with the unstructured dialog is calendar data for the first human.

4. The method of claim 2 , wherein the data associated with the unstructured dialog is a request, by the first human, for the bot to perform a task.

5. The method of claim 1 , wherein generating the spoken response comprises:
based on the intent of the human, generating, by the computing device, an additional transcription of the spoken response; and
providing, to a speech synthesizer, the additional transcription of the spoken response.

6. The method of claim 1 , comprising:
receiving, by the computing device, additional unstructured dialog from the human;
generating, by the computing device, an additional transcription of the additional unstructured dialog; and
based on the additional transcription, generating, by the bot of the computing device, an additional spoken response.

7. The method of claim 1 , comprising:
providing, for presentation to the first human, data indicating a summary of the unstructured dialog from the second human and the spoken response audibly rendered at the additional computing device associated with the second human during the corresponding telephone conversation.

8. 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:
receiving, by a computing device that is configured to conduct telephone conversations between a bot of the computing device and humans on behalf of a first human, an incoming telephone call from a second human;
causing, by the bot of computing device, the incoming telephone call from the second human to be answered by the bot;
causing, by the bot of the computing device, a corresponding telephone conversation to be conducted with the second human and on behalf of the first human;
receiving, by the computing device, and during the corresponding telephone conversation, unstructured dialog from the second human;
generating, by the computing device, a transcription of the unstructured dialog;
based on the transcription of the unstructured dialog, determining, by the computing device, an intent of the second human;
based on the intent of the second human, generating, by the computing device, a spoken response; and
causing, by the bot of the computing device, the spoken response to be audibly rendered at an additional computing device associated with the second human.

9. The system of claim 8 , wherein the operations comprise:
accessing, by the computing device, data associated with the unstructured dialog,
wherein the spoken response is based on the data associated with the unstructured dialog.

10. The system of claim 9 , wherein the data associated with the unstructured dialog is calendar data for the first human.

11. The system of claim 9 , wherein the data associated with the unstructured dialog is a request, by the first human, for the bot to perform a task.

12. The system of claim 8 , wherein generating the spoken response comprises:
based on the intent of the human, generating, by the computing device, an additional transcription of the spoken response; and
providing, to a speech synthesizer, the additional transcription of the spoken response.

13. The system of claim 8 , wherein the operations comprise:
receiving, by the computing device, additional unstructured dialog from the human;
generating, by the computing device, an additional transcription of the additional unstructured dialog; and
based on the additional transcription, generating, by the bot of the computing device, an additional spoken response.

14. The system of claim 8 , wherein the operations comprise:
providing, for presentation to the first human, data indicating a summary of the unstructured dialog from the second human and the spoken response audibly rendered at the additional computing device associated with the second human during the corresponding telephone conversation.

15. A non-transitory 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:
receiving, by a computing device that is configured to conduct telephone conversations between a bot of the computing device and humans, an incoming telephone call from a second human;
causing, by the bot of computing device, the incoming telephone call from the second human to be answered by the bot;
causing, by the bot of the computing device, a corresponding telephone conversation to be conducted with the second human and on behalf of the first human;
receiving, by the computing device, and during the corresponding telephone conversation, unstructured dialog from the second human;
generating, by the computing device, a transcription of the unstructured dialog;
based on the transcription of the unstructured dialog, determining, by the computing device, an intent of the second human;
based on the intent of the second human, generating, by the computing device, a spoken response; and
causing, by the bot of the computing device, the spoken response to be audibly rendered at an additional computing device associated with the second human.

16. The medium of claim 15 , wherein the operations comprise:
accessing, by the computing device, data associated with the unstructured dialog,
wherein the spoken response is based on the data associated with the unstructured dialog.

17. The medium of claim 16 , wherein the data associated with the unstructured dialog is calendar data for the first human.

18. The medium of claim 15 , wherein generating the spoken response comprises:
based on the intent of the human, generating, by the computing device, an additional transcription of the spoken response; and
providing, to a speech synthesizer, the additional transcription of the spoken response.

19. The medium of claim 15 , wherein the operations comprise:
receiving, by the computing device, additional unstructured dialog from the human;
generating, by the computing

Assignees

• Google Llc

Inventors

• Segalis Eyal
• Walevski Daniel
• Leviathan Yaniv
• Matias Yossi

Classifications

• H04M3/58 Primary

  Arrangements for transferring received calls from one subscriber to another; Arrangements affording interim conversations between either the calling or the called party and a third party (substation line holding circuits H04M1/80) · CPC title

• H04M3/527

  Centralised call answering arrangements not requiring operator intervention · CPC title

• G10L25/63

  for estimating an emotional state · CPC title

• H04M2242/18

  Automated outdialling systems · CPC title

• H04M3/4936 Primary

  Speech interaction details (speech recognition per se G10L15/00) · CPC title