Electronic apparatus and controlling method thereof

Patent metadata

Field	Value
Publication number	US-12020710-B2
Application number	US-202217573103-A
Country	US
Kind code	B2
Filing date	Jan 11, 2022
Priority date	Mar 5, 2021
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

An electronic apparatus is disclosed. The electronic apparatus includes: a memory storing task information and keyword information regarding a voice recognition agent function related to execution of an application, and a processor connected with the memory and configured to control the electronic apparatus. The processor may be configured to: apply a first weight to first step information including the keyword information among a plurality of step information included in the task information, apply a second weight different from the first weight to second step information including a motion among the plurality of step information, update the task information based on the first step information to which the first weight was applied and the second step information to which the second weight was applied, and based on a voice command for the application being input, execute the voice recognition agent function based on the updated task information.

First claim

What is claimed is:

1. An electronic apparatus comprising:
a memory storing task information and keyword information regarding a voice recognition agent function related to execution of an application; and
a processor connected with the memory and configured to control the electronic apparatus,
wherein the processor is configured to:
apply a first weight to first step information including the keyword information among a plurality of step information included in the task information,
apply a second weight different from the first weight to second step information including a motion among the plurality of step information,
update the task information based on the first step information to which the first weight was applied and the second step information to which the second weight was applied, and
based on a voice command for the application being input, execute the voice recognition agent function based on the updated task information.

2. The electronic apparatus of claim 1 ,
wherein the processor is configured to:
apply the second weight to the second step information including a motion of a first type among the plurality of step information, and
apply a third weight different from the second weight to third step information including a motion of a second type different from the first type among the plurality of step information.

3. The electronic apparatus of claim 1 ,
wherein the processor is configured to:
based on the second weight applied to the second step information being less than a threshold numerical value, exclude the second step information from the task information, and
based on the second weight applied to the second step information being greater than or equal to the threshold numerical value, maintain the second step information in the task information.

4. The electronic apparatus of claim 3 ,
wherein the processor is configured to:
based on excluding the second step information from the task information, identify whether a task is performed normally, and based on the task being performed normally, exclude the second step information from the task information.

5. The electronic apparatus of claim 4 ,
wherein the processor is configured to:
based on the task not being performed normally in a state wherein the second step information has been excluded from the task information, maintain the second step information and exclude step information different from the second step information from the task information, and identify whether the task is performed normally,
wherein the step information different from the second step information is step information including a motion of a different type from the type of the motion corresponding to the second step information.

6. The electronic apparatus of claim 5 ,
wherein the processor is configured to:
based on the task not being performed normally in a state wherein the second step information has been excluded from the task information, maintain the second step information and preferentially exclude step information to which a relatively low weight was applied among the plurality of step information different from the second step information from the task information, and identify whether the task is performed normally.

7. The electronic apparatus of claim 4 ,
wherein the processor is configured to:
based on the task not being performed normally in a state wherein only the second step information has been excluded from the task information, exclude the second step information and step information related to the second step information from the task information, and identify whether the task is performed normally,
wherein the other step information related to the second step information is step information including a motion of the same type as the type of the motion corresponding to the second step information.

8. The electronic apparatus of claim 1 ,
wherein the processor is configured to:
identify a fourth weight based on the type of the motion corresponding to the first step information, and
apply the first weight and the fourth weight to the first step information.

9. The electronic apparatus of claim 1 ,
wherein the processor is configured to:
maintain preset essential step information among the plurality of step information in the task information and update the task information.

10. The electronic apparatus of claim 1 ,
wherein the motion includes at least one of a scroll motion, a button click motion, an image click motion, a typing motion, or an application execution motion.

11. A method of controlling an electronic apparatus storing task information and keyword information regarding a voice recognition agent function related to execution of an application, the method comprising:
applying a first weight to first step information including the keyword information among a plurality of step information included in the task information;
applying a second weight different from the first weight to second step information including a motion among the plurality of step information;
updating the task information based on the first step information to which the first weight was applied and the second step information to which the second weight was applied; and
based on a voice command for the application being input, executing the voice recognition agent function based on the updated task information.

12. The method of claim 11 ,
wherein the applying the second weight comprises:
applying the second weight to the second step information including a motion of a first type among the plurality of step information; and
applying a third weight different from the second weight to third step information including a motion of a second type different from the first type among the plurality of step information.

13. The method of claim 11 ,
wherein the applying the second weight comprises:
based on the second weight applied to the second step information being less than a threshold numerical value, excluding the second step information from the task information, and based on the second weight applied to the second step information being greater than or equal to the threshold numerical value, maintaining the second step information in the task information.

14. The method of claim 13 ,
wherein the updating the task information comprises:
based on excluding the second step information from the task information, identifying whether a task is performed normally, and based on the task being performed normally, excluding the second step information from the task information.

15. The method of claim 14 ,
wherein the updating the task information further comprises:
based on the task not being performed normally in a state wherein the second step information has been excluded from the task information, maintaining the second step information and excluding step information different from the second step information from the task information, and identifying whether the task is performed normally,
wherein the step information different from the second step information is step information including a motion of a different type from the type of the motion corresponding to the second step information.

16. The method of claim 15 ,
wherein the identifying whether the task is performed normally comprises:
based on the task not being performed normally in a state wherein the second step information has been excluded from the task information, maintaining the second step information and preferentially excluding step information to which a relatively low weight was applied among the plurality of ste

Assignees

• Samsung Electronics Co Ltd

Inventors

• Son Yusun
• Choi Hyungjun
• Hyung Jiwon
• RYU Jongyoub

Classifications

• G10L15/22 Primary

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/1822

  Parsing for meaning understanding · CPC title

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title