APPARATUS AND METHOD FOR PROCESSING CONTROL COMMAND BASED ON VOICE AGENT, AND AGENT DEVICE

• US 20170103755A1
• Filed: 09/20/2016
• Published: 04/13/2017
• Est. Priority Date: 10/12/2015
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: JEON, Joo Hyuk, WOO, Kyoung Gu
• Granted Patent: US 10,607,605 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/226 using non-speech characteristics
• CPC Class Codes: H04L 12/282 based on user interaction within the home receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204
• CPC Class Codes: H04L 12/2821 Avoiding conflicts related to the use of home appliances cryptographic protocols H04L9/00; protocols for network security H04L63/00

Abstract

Disclosed are apparatuses and methods for processing a control command for an electronic device based on a voice agent. The apparatus includes a command tagger configured to receive at least one control command for the electronic device from at least one voice agent and to tag additional information to the at least one control command, and a command executor configured to, in response to the command tagger receiving a plurality of control commands, integrate the plurality of control commands based on additional information tagged to each of the plurality of control commands and to control the electronic device based on a result of the integration.

Claims

1. An apparatus for processing a control command for an electronic device, the apparatus comprising:

a processor configured to;

receive at least one control command for the electronic device from at least one voice agent and to tag additional information to the at least one control command; and

in response to receiving a plurality of control commands, integrate the plurality of control commands based on additional information tagged to each of the plurality of control commands and to control the electronic device based on a result of the integration.

2. The apparatus of claim 1, wherein the processor comprises:

a command tagger configured to receive at least one control command for the electronic device from at least one voice agent and to tag additional information to the at least one control command; and

a command executor configured to, in response to the command tagger receiving a plurality of control commands, integrate the plurality of control commands based on additional information tagged to each of the plurality of control commands and to control the electronic device based on a result of the integration.

3. The apparatus of claim 2, wherein the received control command is a voice prompt or a text into which the voice prompt is converted through voice recognition technology.

4. The apparatus of claim 2, wherein the additional information comprises one or more of a time at which a voice corresponding to the at least one control command is uttered, a time at which the at least one control command is received from the at least one voice agent, a recognition accuracy of the voice corresponding to the at least one control command, a signal strength of the voice, a length of the at least one control command, a hash value extracted from the at least one control command, a feature value, information regarding a user, information regarding the agent device, and information regarding the electronic device.

5. The apparatus of claim 2, wherein the command executor comprises:

a command integrator configured to integrate the plurality of control commands into one or more clusters based on the additional information tagged to each control command of the plurality of commands; and

a final-command determiner configured to determine a final control command to control the electronic device based on the integration.

6. The apparatus of claim 5, wherein the command integrator is further configured to calculate similarity between the plurality of control commands and to integrate the plurality of control commands into the one or more clusters based on the calculated similarity and the tagged additional information.

7. The apparatus of claim 5, wherein the command integrator is further configured to integrate the plurality of control commands into the one or more clusters based on control commands received between a time interval at the command tagger.

8. The apparatus of claim 5, wherein the final-command determiner is further configured to determine a control command corresponding to a centroid of each of the one or more clusters as the final control command.

9. The apparatus of claim 5, wherein,

the command executor further comprises an interactor configured to send a query about processing of the redundant command, in response to a redundant command being present in the one or more clusters, and

the final-command determiner is further configured to determine the final control command based on a result of the query.

10. The apparatus of claim 1, wherein the command executor further comprises an agent selector configured to select a voice agent to interact with a user from among the plurality of voice agents, in response to the command tagger receiving the plurality of control commands from a plurality of voice agents.

11. The apparatus of claim 10, wherein the agent selector is further configured to select the voice agent to interact with a user based on any one or any combination of distances between the user and the voice agent, user preferences for the voice agent, frequencies of use of the voice agent, a voice signal strength, and voice recognition accuracy of the control commands received from the voice agent.

13. The method of claim 8, wherein the integrating of the plurality of control commands comprises:

integrating the plurality of control commands into one or more clusters based on the additional information tagged to each control command of the plurality of commands; and

determining a final control command to control the electronic device based on the integration.

14. The method of claim 9, wherein the integrating of the plurality of control commands into one or more clusters comprises calculating similarity between the plurality of control commands and performing the integration based on the calculated similarity and the additional information.

15. The method of claim 9, wherein the determining of a final control command comprises determining a control command corresponding to a centroid of each of the one or more clusters as the final control command.

16. The method of claim 9, wherein,

the integrating of the plurality of control commands comprises sending a query about processing of the redundant command, in response to there being a redundant command in the one or more clusters and

the determining of the final control command comprises determining the final control command based on a result of the query.

17. The method of claim 8, wherein, when the integrating of the plurality of control commands further comprises selecting a voice agent to interact with a user from among the plurality of voice agents, in response to receiving the plurality of control commands from a plurality of voice agents.

18. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform the method of claim 8.

12. A method of processing a control command for an electronic device, the method comprising:

receiving at least one control command from at least one voice agent;

tagging additional information to the received at least one control command; and

in response to a plurality of control commands being received, integrating the plurality of control commands based on additional information tagged to each of the plurality of control commands.

19. An apparatus for processing a control command for an electronic device, the apparatus comprising:

a processor configured to;

receive at least one control command for an electronic device from at least one voice agent and to tag additional information to the received at least one control command;

integrate the received at least one control command and a control command being executed by the electronic device based on the additional information tagged to the at least one control command; and

control the electronic device based on a result of the integration.

20. The apparatus of claim 19, wherein the processor comprises:

a command tagger configured to receive at least one control command for an electronic device from at least one voice agent and to tag additional information to the received at least one control command; and

a command executor configured to integrate the received at least one control command and a control command being executed by the electronic device based on the additional information tagged to the at least one control command and to control the electronic device based on a result of the integration.

21. The apparatus of claim 20, wherein the command executor comprises:

a command integrator configured to determine whether the received control command and the control command being executed conflict with each other; and

a final-command determiner configured to determine a final control command to control the electronic device, in response to the control commands conflicting with each other.

22. The apparatus of claim 21, wherein,

the command executor further comprises a command database (DB) configured to store control commands being executed by electronic devices, and

the command integrator is further configured to detect the control command being executed by the electronic device from the command DB.

23. The apparatus of claim 21, wherein,

the command executor further comprises an interactor configured to send a query about processing of the conflicting commands, in response to the determination that the control commands conflict with each other, and

the final-command determiner is further configured to determines the final control command based on a result of the query.

24. The apparatus of claim 21, wherein the command executor further comprises:

a policy DB configured to store policies for selecting a voice agent; and

an agent selector configured to select a voice agent to interact with a user by referencing the policy DB.

25. An agent device comprising:

a voice agent configured to transfer the entered control command to a command tagger, in response to a voice-type control command for controlling an electronic device being entered; and

the command tagger configured to tag additional information to the transferred control command, the additional information being used to integrate one or more control commands for controlling the electronic device.

26. The agent device of claim 25, further comprising a communicator configured to send the control command with the tagged additional information to a control command processing device that integrates and processes the one or more control commands for controlling the electronic device.

27. The agent device of claim 26, wherein the voice agent is further configured to convert the result of processing the control command into audio and to output the audio, in response to receiving the processed control command from the control command processing device.

28. The agent device of claim 27, wherein the processed control command comprises at least one of a query about processing of a plurality of redundant commands for controlling the electronic device or a result of executing the control command.

29. The agent device of claim 25, wherein, the voice agent is further configured to collect at least one of a time at which the control command is uttered, a signal strength of the voice, information regarding the user, or a recognition accuracy of the voice and to transfer the collected information to the command tagger, in response the control command being entered.