Automated call requests with status updates

Patent metadata

Field	Value
Publication number	US-10893141-B2
Application number	US-201815947447-A
Country	US
Kind code	B2
Filing date	Apr 6, 2018
Priority date	Jun 13, 2016
Publication date	Jan 12, 2021
Grant date	Jan 12, 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:
accessing, by a call initiating system for placing telephone calls and conducting conversations between a bot of the call initiating system and human representatives of organizations during the telephone calls, a set of linked nodes that represent a predefined, idealized conversation workflow, each node being linked by a set of one or more respective intents;
accessing training data comprising audio samples of a respective human operator completing a task by conversing with a respective human representative from a group of human representatives of various organizations;
for one or more audio samples corresponding to the respective representative of an organization responding to the respective operator, updating the predefined, idealized conversation workflow by associating a representation of the audio sample with one of the intents in the predefined, idealized conversation workflow or newly connecting nodes of the predefined, idealized conversation workflow using a newly defined intent;
performing, by the call initiating system, the task for a human user by initiating a telephone call with a human representative of an organization that is not included in the group of human representatives from the various organizations; and
using the updated conversation workflow, conducting, by the bot of the call initiating system, a telephone conversation with the human representative of the organization that is not included in the group of human representatives from the various organizations.

2. The method of claim 1 , wherein the representation of the audio sample comprises a transcription of the audio sample.

3. The method of claim 1 , wherein each of the one or more audio samples is manually annotated.

4. The method of claim 1 , comprising annotating each of the one or more audio samples using a machine learning-trained classifier.

5. The method of claim 1 , comprising assigning a likelihood that the one or more audio samples is associated with each respective intent.

6. The method of claim 1 , wherein the idealized conversation workflow is updated before any bot of the call initiating system initiates a telephone call to any human representative of the various organizations or of other organizations not included in the various organizations to perform the task.

7. A call initiating system for placing telephone calls and conducting conversations between a bot and human representatives of organizations during the telephone calls, the system comprising:
a processor configured to execute computer program instructions; and
a computer storage medium encoded with the computer program instructions that, when executed by the processor, cause the system to perform operations comprising:
accessing, by a call initiating system for placing telephone calls and conducting conversations between a bot of the call initiating system and human representatives of organizations during the telephone calls, a set of linked nodes that represent a predefined, idealized conversation workflow, each node being linked by a set of one or more respective intents;
accessing training data comprising audio samples of a respective human operator completing a task by conversing with a respective human representative from a group of human representatives of various organizations;
for one or more audio samples corresponding to the respective representative of an organization responding to the respective operator, updating the predefined, idealized conversation workflow by associating a representation of the audio sample with one of the intents in the predefined, idealized conversation workflow or newly connecting nodes of the predefined, idealized conversation workflow using a newly defined intent;
performing, by the call initiating system, the task for a human user by initiating a telephone call with a human representative of an organization that is not included in the group of human representatives from the various organizations; and
using the updated conversation workflow, conducting, by the bot of the call initiating system, a telephone conversation with the human representative of the organization that is not included in the group of human representatives from the various organizations.

8. The system of claim 7 , wherein the representation of the audio sample comprises a transcription of the audio sample.

9. The system of claim 7 , wherein each of the one or more audio samples is manually annotated.

10. The system of claim 7 , wherein the operations comprise annotating each of the one or more audio samples using a machine learning-trained classifier.

11. The system of claim 7 , wherein the operations comprise assigning a likelihood that the one or more audio samples is associated with each respective intent.

12. The system of claim 7 , wherein the idealized conversation workflow is updated before any bot of the call initiating system initiates a telephone call to any human representative of the various organizations or of other organizations not included in the various organizations to perform the task.

13. A computer-readable storage device encoded with a computer program, the computer program comprising instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:
accessing, by a call initiating system for placing telephone calls and conducting conversations between a bot of the call initiating system and human representatives of organizations during the telephone calls, a set of linked nodes that represent a predefined, idealized conversation workflow, each node being linked by a set of one or more respective intents;
accessing training data comprising audio samples of a respective human operator completing a task by conversing with a respective human representative from a group of human representatives of various organizations;
for one or more audio samples corresponding to the respective representative of an organization responding to the respective operator, updating the predefined, idealized conversation workflow by associating a representation of the audio sample with one of the intents in the predefined, idealized conversation workflow or newly connecting nodes of the predefined, idealized conversation workflow using a newly defined intent;
performing, by the call initiating system, the task for a human user by initiating a telephone call with a human representative of an organization that is not included in the group of human representatives from the various organizations; and
using the updated conversation workflow, conducting, by the bot of the call initiating system, a telephone conversation with the human representative of the organization that is not included in the group of human representatives from the various organizations.

14. The device of claim 13 , wherein the representation of the audio sample comprises a transcription of the audio sample.

15. The device of claim 13 , wherein each of the one or more audio samples is manually annotated.

16. The device of claim 13 , wherein the operations comprise annotating each of the one or more audio samples using a machine learning-trained classifier.

17. The device of claim 13 , wherein the operations comprise assigning a likelihood that the one or more audio samples is associated with each respective intent.

18. The device of claim 13 , wherein the idealized conversation workflow is updated before any bot of the call initiating system initiates a telephone call to any human representative of the various

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