VOICE INPUT COMMAND

• US 20160358603A1
• Filed: 01/31/2014
• Published: 12/08/2016
• Est. Priority Date: 01/31/2014
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Inventors: Azam, Syed S, Huang, Jason
• Granted Patent: US 10,978,060 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• 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 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method is provided in accordance with an aspect of the present disclosure. The method includes detecting at least one voice input from a user of an electronic device, transforming the at least one voice input into a text structure including at least one word, and determining a current context scope of the electronic device. The method also includes comparing the text structure to a plurality of existing text structures, where each of the existing text structure associated with a command for an action on the electronic device. The method further includes identifying, when the text structure matches with at least one of the existing text structures, a command to correspond to the at least one voice input from the user, and performing an action on the electronic device based on the identified command.

Claims

1. A method, comprising;

detecting at least one voice input from a user of an electronic device;

transforming the at least one voice input into a text structure including at least one word;

determining a current context, scope of the electronic device;

comparing the text structure to a plurality of existing text structures, wherein each of the existing text structure is associated with a command for an action on the electronic device;

identifying, when the text structure matches with at least one of the existing text structures, a command to correspond to the at least one voice input from the user; and

performing an action on the electronic device based on the identified command.

2. The method of claim 1, wherein the plurality of existing text structures are associated with the current context scope of the electronic device.

3. The method of claim 2, further comprising comparing the text structure to a plurality of existing teat structures that are not associated with the current context scope of the electronic device, when the text structure does not match the existing text structures that are associated with the current context scope of the electronic device

4. The method of claim 1, further comprising connecting at least two sequential voice inputs from a user and performing an action based on the connected sequential voice inputs.

5. The method of claim 4, further comprising:

identifying a first command from a first of the at least two sequential voice inputs;

identifying a second command from a second of the at least two sequential voice inputs;

determining whether a time between the first voice input and the second voice input exceeds a predetermined threshold;

determining whether the second command is a semantic continuation of the first command; and

correlating the second command with the first command to perform an action on the electronic device when the time between the first voice input and the second voice input does not exceed a predetermined threshold and when the second command is a semantic continuation of the first command.

6. The method of claim 1, wherein identifying a command to correspond to the at least one voice input further includes:

computing a possibility score for a target command based on the at least one voice input, when the text structure of the at least one voice input does not match with at least one of the existing text structures;

comparing the possibility score of the target command to a predetermined tolerance threshold associated with the target command;

identifying a command when the possibility score of the target command exceeds the threshold;

proposing to create a new command, wherein the new command includes an action on the electronic device; and

receiving a conformation from the user regarding the validity of the new command.

7. The method of claim 1, further comprising:

creating a new command based on voice input from the user, wherein the new command is associated with the current context scope;

associating the new command with at least one action device;

saving the new command.

8. A system comprising:

an electronic device having at least one processing device with a control unit to

create a new command for the electronic device, wherein the new command is associated with a context scope of the electronic device and includes an action on the electronic device,

detect at feast one voice input from a user of an electronic device, transform the at least one voice input into a text structure including at least one word,

determine the current context scope of the electronic device,

compare the text structure to a plurality of existing text structures,

identify a command when the text structure matches with at least one of the existing text structures.

9. The system of claim 8, wherein the control unit is to:

receive a new voice input from the user;

transform the new voice input into a new text structure;

determine the current context scope of the electronic device;

identify a number of occurrences of the new text structure in the current context scope;

associate the new text structure to the new command for the electronic device when the text structure is identified only once In the current context scope;

identify a command text structure when the text structure is identified more than once m the current context scope; and

associate the command text structure with the new command.

10. The system of claim 8, wherein the control unit is to:

transition the electronic device into a command training mode;

determine the current context scope of the electronic device;

identify an action on the electronic device performed m the current context scope;

receive a new voice input from the user directed to the performed action; and

associate the action in the current context scope to the new voice input to create the new command for the electronic device.

11. The system of claim 8, wherein the control unit is to compare the text structure to a plurality of existing text structures that are associated with the current context scope of the electronic device, and wherein the control unit is to compare the text structure to a plurality of existing text structures that are not associated with the current context scope of the electronic device when the text structure does not match the existing text structures that are associated with the current context scope of the electronic device.

12. A non-transitory machine-readable storage medium encoded with instructions executable by at least one processing device of an electronic device, the machine-readable storage medium comprising instructions to:

process at least one voice input received from a user of the electronic device;

transform the at least one voice input into a text structure including at least one word;

determine the current context scope of the electronic device;

determine whether the text structure matches with at least one existing text structure from a plurality of existing text structures that are associated with the current context;

determine whether the text structure matches with at feast one existing text structure from a plurality of existing text structures that are not associated with the current context;

identify, when the text structure matches with at least one of the existing text structures, a command to correspond to the at least one voice input from the user; and

create a new command for the electronic device when the when the text structure does not match with at least one of the existing text structures, wherein the new command is associated with the current context scope.

13. The non-transitory machine-readable storage medium of claim 12, further comprising instructions to connect at least two sequential voice inputs from a user to perform an action based on the connected sequential voice inputs.

14. The non-transitory machine-readable storage medium of claim 13, further comprising instructions to:

identify a first command from a first of the at least two sequential voice inputs;

identify a second command from a second of the at least two sequential voice inputs;

determine whether a time between the first voice input and the second voice input exceeds a predetermined threshold;

determine whether the second command is a semantic continuation of the first command; and

correlate the second command with the first command to perform an action on the electronic device when the time between the first voice input and the second voice input does not exceed a predetermined threshold and when the second command is a semantic continuation of the first command.

15. The non-transitory machine-readable storage medium of claim 12, further comprising instructions to:

compute a possibility score for a target command based on the at least one voice input, when the text structure of the at least one voice input does not match with at least one of the existing text structures,

compare the possibility score of the target command to a predetermined tolerance threshold associated with the target command;

identify a command when the possibility score of the target command exceeds the tolerance threshold;

propose to create a new command, wherein the new command includes an action on the electronic device; and

receiving a conformation from the user regarding the validity of the new command.