Mapping device capabilities to a predefined set

Patent metadata

Field	Value
Publication number	US-9984686-B1
Application number	US-201514752257-A
Country	US
Kind code	B1
Filing date	Jun 26, 2015
Priority date	Mar 17, 2015
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Techniques for defining a set of predefined device capabilities generally offered by available voice-controllable devices are described herein. Thereafter, as a particular user introduces new secondary devices into his environment and registers these devices, the techniques may identify the capabilities of the new device and map these capabilities to one or more of the predefined device capabilities of the set.

First claim

What is claimed is:

1. A method implemented at least in part by a speech-recognition service, the method comprising:
receiving a first indication that a first device is in an environment;
based at least in part on receiving the first indication:
identifying a first capability associated with the first device;
determining that the first capability corresponds to a first predefined device capability included within a predefined set of predefined device capabilities;
generating a first association between the first capability associated with the first device and the first predefined capability; and
storing the first association between the first capability associated with the first device and the first predefined device capability;

identifying a second capability associated with a second device;
determining that the second capability corresponds to the first predefined device capability of the set of predefined device capabilities;
generating a second association between the second capability associated with the second device and the first predefined capability;
storing the second association between the second capability associated with the second device and the first predefined device capability;
storing, based at least in part on the first association, a third indication of a device driver associated with the first device, the device driver being configured to, when executed, generate a first command to cause the first device to perform the first predefined device capability;
receiving an audio signal from the environment in which the first device resides;
performing speech-recognition on the audio signal;
determining, based at least in part on performing the speech-recognition on the audio signal, that the audio signal includes a request to associate a word or phrase with at least the first device and the second device performing an operation associated with the first predefined device capability; and
associating, the word or phrase with the first device and the second device performing the operation.

2. The method as recited in claim 1 , further comprising:
storing, based at least in part on the second association, a fourth indication of a second device driver associated with the second device, the second device driver being configured to, when executed, generate a second command to cause the second device to perform the second predefined device capability.

3. The method as recited in claim 1 , wherein the audio signal comprises a first audio signal, further comprising:
receiving a second audio signal from the environment in which the second device resides;
performing speech-recognition on the second audio signal;
determining, based at least in part on performing the speech-recognition on the second audio signal, that the second audio signal includes the word or phrase;
causing the device driver to execute to generate the command; and
sending the command to a device in the environment in which the first device resides.

4. A system comprising:
one or more processors; and
one or more computer-readable media storing computer-executable instructions that, when executed on the one or more processors, cause the one or more processors to perform acts comprising:
receiving a first indication that a first device is in an environment;
identifying a first capability of the first device;
generating a first association between the first capability of the first device and a first predefined capability included within predefined device capabilities;
storing the first association between the first capability and the first predefined device capability;
storing a second indication of a first voice command to cause the first device to perform the first predefined device capability;
determining that a second capability associated with a second device is configured to perform the first predefined device capability;
generating a second association between the second capability of the second device and the first predefined capability;
storing the second association between the second capability and the first predefined device capability;
storing a third indication of a second voice command to cause the second device to perform the first predefined device capability, the second voice command being different from the first voice command; and
storing, based at least in part on the first association, a fourth indication of a first device driver associated with the first device, the first device driver being configured to, when executed by the one or more processors, generate a first command to cause the first device to perform the first predefined device capability.

5. The system as recited in claim 1 , the acts further comprising storing one or more fifth indications of additional voice commands to cause the first device to perform the first predefined device capability, each of the additional voice commands being unique relative to one another and relative to the first voice command.

6. The system as recited in claim 4 , the acts further comprising:
storing a fifth indication of a second device driver, associated with the second device, configured to generate a second command to cause the second device to perform the first predefined device capability.

7. The system as recited in claim 6 , the acts further comprising:
receiving a second audio signal generated in the environment in which the second device resides;
identifying, from the second audio signal, the second voice command;
sending information indicative of the second voice command to the second device driver; and
receiving, from the second device driver, the second command to cause the second device to perform the first predefined device capability.

8. The system as recited in claim 4 , the acts further comprising:
receiving a first audio signal generated in the environment in which the first device resides;
identifying, from the first audio signal, the first voice command;
sending information indicative of the first voice command to the first device driver; and
receiving, from the first device driver, the first command to cause the first device to perform the first predefined device capability.

9. The system as recited in claim 4 , wherein the first predefined device capability comprises turning on or off, changing a volume, changing a channel, changing a brightness, changing a color, and changing a temperature.

10. The system as recited in claim 4 , wherein the first device comprises a light, a television, an audio system, a lock, a garage door, a washing machine, a dryer, a dishwasher, a coffee maker, a refrigerator, a door, or shades.

11. The system as recited in claim 4 , the acts further comprising:
receiving a first audio signal generated in the environment in which the first device resides;
performing-speech recognition on the audio signal;
determining, based at least in part on performing-speech recognition on the audio signal, that the audio signal includes the first voice command;
based at least in part on determining that the audio signal includes the voice command, the second indication of the first voice command to cause the first device to perform the first predefined device capability, and the fourth indication of the first device driver configured to generate the first command to cause the first device to perform the first predefined device capability, causing the first device driver to execute to generate a command that, when executed by the first device, causes the first device to perform the first predefined device capability; and
sending the command to at least one of the first device or a device in the environment of the first device.

12. A method com

Assignees

• Amazon Tech Inc

Inventors

• Mutagi Rohan
• Lew Yuk Vong Willy
• Whiteley Michael Dale
• Lu He

Classifications

• H04L12/2816

  Controlling appliance services of a home automation network by calling their functionalities (arrangements in telecontrol or telemetry systems for selectively calling a substation from a main station; in which substation desired apparatus is selected for applying a control signal thereto or for obtaining measured values therefrom H04Q9/00) · CPC title

• G10L17/22

  Interactive procedures; Man-machine interfaces · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title