Hybrid language processing

• US 9,659,003 B2
• Filed: 03/26/2014
• Issued: 05/23/2017
• Est. Priority Date: 03/26/2014
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Raux, Antoine Roland
• Primary Examiner(s): Bodden, Evral E
• Application Number:
  US14/226,659
• Publication Number:
  US 20150278193A1
• Time in Patent Office: 1,154 Days
• Field of Search: None
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

For hybrid language processing, a method is disclosed that includes identifying, by use of a processor, one or more user specific terms in a user generated portion of text, modifying the portion of text by replacing one or more of the user specific terms with general tokens, and converting the modified portion of text to one or more commands to be executed by the processor.

Claims

1. An apparatus comprising:

a processor;

a memory that stores code executable by the processor, the code comprising;

code that identifies one or more user specific terms in a user generated portion of text, wherein the one or more user specific terms each have a user specific meaning;

code that determines the user specific meaning corresponding to the one or more user specific terms, wherein the user specific meaning has a meaning local to the apparatus and stored on the apparatus, and the meaning local to the apparatus comprises a meaning found in a location selected from the group comprising a contact list, a browser, and a list of installed applications;

code that dynamically modifies the portion of text by replacing one or more of the user specific terms with general tokens as a direct result of the code identifying the one or more user specific terms in the user generated portion of text;

code that converts the modified portion of text using the user specific meaning corresponding to the one or more user specific terms to one or more commands to be executed by the processor as a direct result of the code dynamically modifying the portion of the text; and

code that executes the one or more commands in response to converting the modified portion.

2. The apparatus of claim 1, wherein the general tokens comprise template tokens.

3. The apparatus of claim 2, wherein the code that modifies further replaces the template tokens with general language.

4. The apparatus of claim 1, wherein the general tokens comprise general language.

5. The apparatus of claim 1, wherein the code further comprises code that generates a structure to encapsulate the modified text and the user specific terms, and code that transmits the structure to a remote server for conversion.

6. The apparatus of claim 1, wherein the code that identifies further identifies the one or more user specific terms by looking up the user specific terms in a local library.

7. A method comprising:

identifying, by use of a processor, one or more user specific terms in a user generated portion of text, wherein the one or more user specific terms each have a user specific meaning;

determining the user specific meaning corresponding to the one or more user specific terms, wherein the user specific meaning has a meaning local to an apparatus and stored on the apparatus, and the meaning local to the apparatus comprises a meaning found in a location selected from the group comprising a contact list, a browser, and a list of installed applications;

dynamically modifying the portion of text by replacing one or more of the user specific terms with general tokens as a direct result of identifying the one or more user specific terms in the user generated portion of text;

converting the modified portion of text using the user specific meaning corresponding to the one or more user specific terms to one or more commands to be executed by the processor as a direct result of dynamically modifying the portion of the text; and

executing the one or more commands in response to converting the modified portion.

8. The method of claim 7, wherein the general tokens comprise template tokens.

9. The method of claim 8, further comprising replacing the template tokens with general language.

10. The method of claim 7, wherein the general tokens comprise general language.

11. The method of claim 7, further comprising generating a structure to encapsulate the modified portion of text and the user specific terms.

12. The method of claim 7, wherein identifying the one or more user specific terms comprises looking up terms in a local library.

13. A program product comprising a non-transitory computer readable storage medium that stores code executable by a processor to perform:

identifying one or more user specific terms in a user generated portion of text, wherein the one or more user specific terms each have a user specific meaning;

determining the user specific meaning corresponding to the one or more user specific terms, wherein the user specific meaning has a meaning local to an apparatus and stored on the apparatus, and the meaning local to the apparatus comprises a meaning found in a location selected from the group comprising a contact list, a browser, and a list of installed applications;

dynamically modifying the portion of text by replacing one or more of the user specific terms with general tokens as a direct result of identifying the one or more user specific terms in the user generated portion of text;

converting the modified portion of text using the user specific meaning corresponding to the one or more user specific terms to one or more commands to be executed by the processor as a direct result of dynamically modifying the portion of the text; and

executing the one or more commands in response to converting the modified portion.

14. The program product of claim 13, wherein the general tokens comprise template tokens.

15. The program product of claim 14, the code further replaces the template tokens with general language.

16. The program product of claim 13, wherein the general tokens comprise general language.

17. The program product of claim 13, wherein the code identifies the one or more user specific terms by looking up terms in a local library.