Method and electronic device for performing voice based actions

• US 10,276,162 B2
• Filed: 02/10/2017
• Issued: 04/30/2019
• Est. Priority Date: 02/12/2016
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Choudhury, Arunabha, Nagaswamy, Sriram
• Primary Examiner(s): Riley, Marcus T
• Application Number:
  US15/429,715
• Publication Number:
  US 20170236513A1
• Time in Patent Office: 809 Days
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/1822 Parsing for meaning understanding
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method performing voice based actions by an electronic device includes receiving a voice command from a user; determining a relationship between the voice command and a context a historic voice command of the user, and performing an action by executing the voice command based on the context of the historic voice command.

Claims

1. A method for performing voice based actions by an electronic device, the method comprising:

receiving, by the electronic device, a first voice command associated with a first application;

determining, by the electronic device, a relationship between the first voice command and a context of at least one historic voice command associated with the first application;

based on determining that there is the relationship between the first voice command and the context of the at least one historic voice command associated with the first application, performing, by the electronic device, at least one first action by executing the first voice command based on the context of the at least one historic voice command associated with the first application;

receiving, by the electronic device, a second voice command associated with a second application different from the first application;

determining, by the electronic device, a relationship between the second voice command and the context of the at least one historic voice command associated with the first application; and

based on determining that there is the relationship between the second voice command and the context of the at least one historic voice command associated with the first application, performing, by the electronic device, at least one second action by executing the second voice command with respect to the second application based on the context of the at least one historic voice command associated with the first application.

2. The method of claim 1, further comprising:

based on determining that there is no relationship between the first voice command and the context of the at least one historic voice command, beginning a new context based on the first voice command, and performing, by the electronic device, the at least one first action by executing the first voice command based on the new context.

3. The method of claim 1, wherein the context of the at least one historic voice command is pre-analyzed and stored in the electronic device.

4. The method of claim 1, wherein the context of the at least one historic voice command is dynamically updated.

5. The method of claim 1, wherein the determining the relationship between the first voice command and the context of the at least one historic voice command comprises determining the relationship between the first voice command and the context of the at least one historic voice command based on at least one among a semantic similarity, a latent semantic similarity, and an action performed based on the at least one historic voice command.

6. The method of claim 1, further comprising:

based on determining that there is no relationship between the second voice command and the context of the at least one historic voice command associated with the first application, beginning a new context based on the second voice command, and performing, by the electronic device, the at least one second action by executing the second voice command based on the new context.

7. The method of claim 1, wherein the at least one first action comprises a search, and

the performing the at least one first action comprises:

beginning a new context based on the first voice command,

performing the search based on the first voice command, and

presenting a result of the search based on the first voice command.

8. The method of claim 1, wherein the at least one first action is performed by executing the first voice command based on a most recent context.

18. The method of claim 1, wherein the at least one first action is executed based on a content used in the first application, and the at least one second action is executed based on at least a part of the content used in the first application.

9. An electronic device for performing voice based actions, the electronic device comprising:

an audio receiver configured to receive a first voice command associated with a first application; and

at least one microprocessor configured to;

determine a relationship between the first voice command and a context of at least one historic voice command associated with the first application,

based on determining that there is the relationship between the first voice command and the context of the at least one historic voice command associated with the first application, perform at least one first action by executing the first voice command based on the context of the at least one historic voice command associated with the first application,

wherein the audio receiver is further configured to;

receive a second voice command associated with a second application different from the first application, and

wherein the at least one microprocessor is further configured to;

determine a relationship between the second voice command and the context of the at least one historic voice command associated with the first application, and

based on determining that there is the relationship between the second voice command and the context of the at least one historic voice command associated with the first application, perform at least one second action by executing the second voice command with respect to the second application based on the context of the at least one historic voice command associated with the first application.

10. The electronic device of claim 9, wherein the at least one microprocessor is further configured to, based on determining that there is no relationship between the first voice command and the context of the at least one historic voice command, begin a new context based on the first voice command, and perform the at least one first action by executing the first voice command based on the new context.

11. The electronic device of claim 9, wherein the context of the at least one historic voice command is pre-analyzed and stored in the electronic device.

12. The electronic device of claim 9, wherein the context of the at least one historic voice command is dynamically updated.

13. The electronic device of claim 9, wherein the at least one microprocessor is further configured determine the relationship between the first voice command and the context of the at least one historic voice command based at least one among a semantic similarity, a latent semantic similarity, and an action performed based on the at least one historic voice command.

14. The electronic device of claim 9, wherein the at least one microprocessor is further configured to, based on determining that there is no relationship between the second voice command and the context of the at least one historic voice command associated with the first application, begin a new context based on the second voice command, and perform the at least one second action by executing the second voice command based on the new context.

15. The electronic device of claim 9, wherein the at least one first action comprises a search, and

the at least one microprocessor is further configured to:

begin a new context based on the first voice command,

perform the search based on the first voice command, and

present a result of the search based on the first voice command.

16. The electronic device of claim 9, wherein the at least one first action is performed by executing the first voice command based on a most recent context.

19. The electronic device of claim 9, wherein the at least one first action is executed based on a content used in the first application, and the at least one second action is executed based on at least a part of the content used in the first application.

17. A method comprising:

receiving, by a mobile device, a first voice command associated with a first application;

determining a first intent for the first voice command by parsing the first voice command;

matching the first intent with a pre-stored context of a previous user command;

performing, by the mobile device, a first action associated with the first application by executing the first voice command based on the matching of the first intent with the pre-stored context;

receiving, by the mobile device, a second voice command associated with a second application different from the first application;

determining a second intent for the second voice command by parsing the second voice command;

matching the second intent with the pre-stored context of the previous user command and the first application; and

performing, by the mobile device, a second action by executing the second voice command with respect to the second application based on the matching of the second intent with the pre-stored context within the first application.

20. The method of claim 17, wherein the first action is executed based on a content used in the first application, and the second action is executed based on at least a part of the content used in the first application.