Invoking application programming interface calls using voice commands

• US 9,589,578 B1
• Filed: 10/29/2013
• Issued: 03/07/2017
• Est. Priority Date: 10/29/2013
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Dippenaar, Andries Petrus Johannes
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US14/065,776
• Time in Patent Office: 1,225 Days
• US Class Current: 1/1
• 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: H04L 67/00 Network arrangements or protocols for supporting network services or applications user-to-user messaging H04L51/00; network arrangements, protocols or services for supporting real-time applications in data packet communications networks H04L65/00
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04L 67/565 Conversion or adaptation of application format or content adding application control or application functional data H04L67/561

Abstract

Technologies are described herein for invoking API calls through voice commands. An annotated API description is received at a voice API interface. The annotated API description comprises descriptions of one or more APIs and speech annotations for the one or more APIs. The voice API interface further receives a voice API command from a client. By utilizing the annotated API description and the speech annotations contained therein, the voice API interface converts the voice API command into an API call request, which is then sent to the corresponding service for execution. Once the service returns an API call result, the voice API interface interprets the API call result and further converts it into an audio API response based on the information contained in the annotated API description and the speech annotations. The audio API response is then sent to the client.

Claims

1. A computer-implemented method for invoking application programming interface (“

API”

) calls through voice commands, the method comprising executing instructions in a computer system to perform the operations of;

receiving an annotated API description comprising descriptions of one or more APIs and speech annotations for the one or more APIs;

receiving a voice API command from a user;

converting the voice API command into a text API command using the speech annotations in the annotated API description;

translating the text API command into an API call request based on the annotated API description;

invoking an API call by sending the API call request to a corresponding API;

receiving an API call result from the corresponding API;

generating a text result interpretation based on the API call result using the annotated API description;

converting the text result interpretation into an audio API response using the speech annotations in the annotated API description; and

generating the audio API response.

2. The computer-implemented method of claim 1, further comprising:

determining if the text API command is to be verified; and

in response to determining that the text API command is to be verified, verifying the text API command with the user prior to translating the text API command into the API call request.

3. The computer-implemented method of claim 1, wherein generating the text result interpretation based on the API call result comprises processing the API call result based on a preference specified by the user through a user account.

4. The computer-implemented method of claim 1, wherein the speech annotations for the one or more APIs comprise acoustic models for one or more keywords of the one or more APIs.

5. The computer-implemented method of claim 1, wherein the annotated API description further comprises interpretation of API call results of the one or more APIs in human-understandable language.

6. The computer-implemented method of claim 1, wherein the speech annotations for the one or more APIs are adapted to a preferred language of the user.

7. The computer-implemented method of claim 1, wherein the one or more APIs comprise web service APIs.

8. A computer system for invoking application programming interface (“

API”

) calls through voice commands, the system comprising;

at least one computing device executing a voice API interface configured to

receive an annotated API description describing the one or more APIs, the annotated API description comprising speech annotations for the one or more APIs and a mapping of API call results of the one or more APIs to a text result,

receive a voice API command from a user,

convert the voice API command into an API call request based on the annotated API description,

send the API call request to one or more APIs exposed by services hosted by one or more computing devices and receive an API call result from the one or more APIs, and

generate an audio API response based on the API call result by generating text result based on the API call results using the annotated API description and by converting the text result into the audio API response using the speech annotations in the annotated API description.

9. The computer system of claim 8, wherein the voice API interface is further configured to:

determine if the voice API command is to be verified; and

in response to determining that the voice API command is to be verified, verifying the voice API command with the user prior to converting the voice API command into the API call request.

10. The computer system of claim 8, wherein the voice API interface comprises:

a speech to text engine configured to convert the voice API command into a text API command using the speech annotations in the annotated API description; and

an API call interpreter configured to translate the text API command into an API call request based on the annotated API description.

11. The computer system of claim 10, wherein the API call interpreter is further configured to perform the generating of the text result based on the API call results using the annotated API description;

and wherein the voice API interface further comprises a text to speech engine that is configured to perform the converting of the text result into the audio API response using the speech annotations in the annotated API description.

12. The computer system of claim 8, wherein the speech annotations for the one or more APIs comprise acoustic models for one or more keywords of the one or more APIs.

13. The computer system of claim 8, wherein the APIs are web service APIs.

14. The computer system of claim 8, wherein generating the text result interpretation based on the API call result comprises processing the API call result based on a preference specified by the user through a user account.

15. A non-transitory computer-readable storage medium having computer-executable instructions stored thereupon which, when executed by a computer, cause the computer to:

convert a voice API command received from a user into an API call request using speech annotations contained in an annotated API description for one or more APIs, the annotated API description further comprising interpretation of API call results of the one or more APIs in human-understandable language;

send the API call request to a corresponding API;

receive an API call result from the corresponding API; and

generate an audio API response based on the API call result by generating a text result interpretation based on the API call result using the annotated API description and by converting the text result interpretation into the audio API response using the speech annotations in the annotated API description.

16. The non-transitory computer-readable storage medium of claim 15, comprising further computer executable instructions which, when executed by the computer, cause the computer to:

determine if the voice API command is to be verified; and

in response to determining that the voice API command is to be verified, verify the voice API command with the user prior to converting the voice API command into the API call request.

17. The non-transitory computer-readable storage medium of claim 15, wherein converting the voice API command into the API call request comprises:

converting the voice API command into a text API command using the speech annotations in the annotated API description; and

translating the text API command into the API call request based on the annotated API description.

18. The non-transitory computer-readable storage medium of claim 15, wherein the speech annotations for the one or more APIs comprise acoustic models for one or more keywords of the one or more APIs.

19. The non-transitory computer-readable storage medium of claim 15, wherein the one or more APIs comprise web service APIs.

20. The non-transitory computer-readable storage medium of claim 15, wherein generating the text result interpretation based on the API call result comprises processing the API call result based on a preference specified by the user through a user account.