Natural language processing system

• US 10,409,916 B2
• Filed: 12/13/2017
• Issued: 09/10/2019
• Est. Priority Date: 12/13/2017
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: Sanders, Mark Steven
• Primary Examiner(s): Guerra-Erazo, Edgar X
• Application Number:
  US15/840,931
• Publication Number:
  US 20190179907A1
• Time in Patent Office: 636 Days
• CPC Class Codes: G06F 16/90332 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• 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: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• 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

Abstract

A natural language processing system identifies an action element, a target element, and command element(s) in a text natural language command. For each identified command element, in the order it appears in the text natural language command, the natural language processing system accesses a playlist access matrix according to a matrix access counter to identify a playlist pointer associated with that command element, determines whether that playlist pointer indicates its associated command element is a best match relative to any other command elements that have already been considered and, if so, updates a playlist entry identifier with that playlist pointer and increments the matrix access counter. When all of the command elements have been considered, the natural language processing system uses the playlist entry identifier to identify a computing language command in a command playlist, and executes the computing language command on the target element based on the action element.

Claims

1. A natural language processing system, comprising:

a chassis;

a storage system included in the chassis and storing at least one natural language processing database including a command playlist and a playlist access matrix;

a natural language processing engine that is included in the chassis, that is coupled to the storage system, and that is configured to;

identify at least one command element in a text natural language command that is also included in the playlist access matrix and, for each command element that is identified and in the order that each command element appears in the text natural language command;

access the playlist access matrix according to a matrix access counter to identify a playlist pointer associated with that command element in the playlist access matrix;

determine whether that playlist pointer associated with that command element indicates that command element is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command;

in response to determining that the associated command element for that playlist pointer is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command, update a playlist entry identifier with that playlist pointer; and

increment the matrix access counter;

determine that all of the command elements have been considered in the text natural language command;

use the playlist entry identifier to identify a computing language command in the command playlist; and

execute the computing language command on a target element that is included in the text natural language command based on an action element that is included in the text natural language command.

2. The system of claim 1, wherein the natural language processing engine is configured to:

identify the action element in the text natural language command.

3. The system of claim 1, wherein the natural language processing engine is configured to:

retrieve the playlist access matrix based on the action element identified in the text natural language command.

4. The system of claim 1, wherein the natural language processing engine is configured to:

identify the target element in the text natural language command.

5. The system of claim 1, wherein the natural language processing engine is configured to:

identify a variable element in the text natural language command, wherein the computing language command is executed on the target element based on the action element and the variable element.

6. The system of claim 1, wherein the natural language processing engine is configured to:

record audio that includes a spoken natural language command; and

convert the spoken natural language command to the text natural language command.

7. The system of claim 1, further comprising:

an input device, wherein the natural language processing engine is configured to;

receive the text natural language command from the input device.

8. An Information Handling System (IHS), comprising:

a processing system; and

a memory system that is coupled to the processing system and that includes instructions that, when executed by the processing system cause the processing system to provide a natural language processing engine that is configured to;

identify at least one command element in a text natural language command that is also included in a playlist access matrix and, for each command element that is identified and in the order that each command element appears in the text natural language command;

access the playlist access matrix according to a matrix access counter to identify a playlist pointer associated with that command element in the playlist access matrix;

determine whether that playlist pointer associated with that command element indicates that command element is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command;

in response to determining that the associated command element for that playlist pointer is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command, update a playlist entry identifier with that playlist pointer; and

increment the matrix access counter;

determine that all of the command elements have been considered in the text natural language command;

use the playlist entry identifier to identify a computing language command in a command playlist; and

execute the computing language command on a target element that is included in the text natural language command based on an action element that is included in the text natural language command.

9. The IHS of claim 8, wherein the natural language processing engine is configured to:

identify the action element and the target element in the text natural language command.

10. The IHS of claim 9, wherein the natural language processing engine is configured to:

retrieve the playlist access matrix based on the action element identified in the text natural language command.

11. The IHS of claim 8, wherein the natural language processing engine is configured to:

identify a variable element in the text natural language command, wherein the computing language command is executed on the target element based on the action element and the variable element.

12. The IHS of claim 8, wherein the natural language processing engine is configured to:

receive, through a network, recorded audio that includes a spoken natural language command; and

convert the spoken natural language command to the text natural language command.

13. The IHS of claim 8, wherein the natural language processing engine is configured to:

receive, through a network, the text natural language command.

14. A method for natural language processing, comprising:

identifying, by a natural language processing system, at least one command element in a text natural language command that is also included in a playlist access matrix and, for each command element that is identified and in the order that each command element appears in the text natural language command;

accessing, by the natural language processing system, the playlist access matrix according to a matrix access counter to identify a playlist pointer associated with that command element in the playlist access matrix;

determining, by the natural language processing system, whether that playlist pointer associated with that command element indicates that command element is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command;

in response to determining that the associated command element for that playlist pointer is a best match in the playlist access matrix relative to any other command elements that have already been considered in the text natural language command, updating, by the natural language processing system, a playlist entry identifier with that playlist pointer; and

incrementing, by the natural language processing system, the matrix access counter;

determining, by the natural language processing system, that all of the command elements have been considered in the text natural language command;

using, by the natural language processing system, the playlist entry identifier to identify a computing language command in a command playlist; and

executing, by the natural language processing system, the computing language command on a target element that is included in the text natural language command based on an action element that is included in the text natural language command.

15. The method of claim 14, further comprising:

identifying, by the natural language processing system, the action element and the target element in the text natural language command.

16. The method of claim 15, further comprising:

retrieving, by the natural language processing system, the playlist access matrix based on the action element identified in the text natural language command.

17. The method of claim 14, further comprising:

identifying, by the natural language processing system, a variable element in the text natural language command, wherein the computing language command is executed on the target element based on the action element and the variable element.

18. The method of claim 14, further comprising:

receiving, by the natural language processing system through a network, recorded audio that includes a spoken natural language command; and

converting, by the natural language processing system, the spoken natural language command to the text natural language command.

19. The method of claim 14, further comprising:

recording, by the natural language processing system, audio that includes a spoken natural language command; and

converting, by the natural language processing system, the spoken natural language command to the text natural language command.

20. The method of claim 14, further comprising:

receiving, by the natural language processing system through a network, the text natural language command.