Script detection service

• US 8,503,715 B2
• Filed: 11/09/2011
• Issued: 08/06/2013
• Est. Priority Date: 06/26/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Georgiev, Dimiter, Ye, Shenghua, Villarreal Guzman, Gerardo, Snyder, Kieran, Cavalcante, Ryan M., Sayed, Tarek M., Feinberg, Yaniv, Lin, Yung-Shin
• Primary Examiner(s): Johns, Andrew W
• Application Number:
  US13/292,957
• Publication Number:
  US 20120059646A1
• Time in Patent Office: 636 Days
• Field of Search: 382/100, 382/112, 382/185, 382/187, 704/1, 715/256, 715/264, 715/268
• US Class Current: 382/100
• CPC Class Codes: G06F 40/129 Handling non-Latin characters, e.g. kana-to-kanji conversion
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/263 Language identification

Abstract

Script detection service techniques are described. In an implementation, values representing individual text characters in a string of one or more text characters are identified to determine which human writing system is associated with the individual text characters. The values are compared to a table that associates subsets of values with individual human writing systems. The values are determined to be within a particular subset of values in the table that correspond to a particular human writing system. A particular human writing system is designated as associated with the string based on the values associated with the individual text characters in the string being within the particular subset of values that corresponds with the particular human writing system.

Claims

1. A method implemented by one or more computing devices, the method comprising:

identifying values representing individual text characters in a string of one or more text characters to determine which human writing system is associated with the individual text characters;

comparing the values to a table that associates subsets of values with individual human writing systems;

determining that the values representing the individual text characters are within a particular subset of values in the table that correspond to a particular said human writing system; and

designating that the particular said human writing system is associated with the string based on the values associated with the individual text characters being within the particular subset of values that corresponds with the particular said human writing system.

2. The method of claim 1, further comprising indicating a range of positions in a text for the one or more text characters.

3. The method of claim 1, further comprising:

indicating a range of positions in a text for the one or more text characters; and

forming a communication that associates the particular said human writing system with the range of positions.

4. The method of claim 1, further comprising indicating a service available to perform a function with the one or more text characters based on the particular said human writing system.

5. The method of claim 1, further comprising analyzing substrings in the string to identify which said human language is associated with the string, the substrings including prefixes or suffixes.

6. The method of claim 1, further comprising scoring weighted values for substrings in the string to identify the particular said human language.

7. The method of claim 1, wherein said comparing includes scanning Unicode values representing the one or more text characters with a table of Unicode values associated with the particular said human writing system.

8. The method of claim 1, wherein the particular said human writing system incorporates text characters from a base said human writing system.

9. One or more computer-readable storage memory comprising instructions that are executable by a computer to:

identify values representing individual text characters in a string of one or more text characters to determine which human writing system is associated with the individual text characters;

use a table that associates subsets of values with individual human writing systems to determine which said human writing system is associated with the individual text characters based on a comparison between the subsets of values and the values representing the individual text characters; and

designate that a particular human writing system is associated with the string based on the values representing the individual text characters being within a particular subset of values in the table, the particular subset of values corresponding with the particular said human writing system.

10. One or more computer-readable storage memory as described in claim 9, wherein the instructions are further executable to use a punctuation module to analyze punctuation in the string to identify which said human writing system is associated with the string.

11. One or more computer-readable storage memory as described in claim 9, wherein the instructions are further executable to use a morphology module to analyze one or more substrings in the string of text characters to identify which said human writing system is associated with the string, the one or more substrings including prefixes or suffixes.

12. One or more computer-readable storage memory as described in claim 9, wherein the instructions are further executable to use a frequency module to analyze a frequency with which the string occurs in a given human language to determine which human writing system is associated with the string.

13. One or more computer-readable storage memory as described in claim 9, wherein the instructions are further executable to indicate a service available to perform a function with the one or more text characters based on the particular said human writing system.

14. A system comprising:

a script detection service implemented by at least one computing device, the script detection service configured to;

identify values representing individual text characters in a string of one or more text characters to determine which human writing system is associated with the individual text characters;

compare the values to a table that associates subsets of values with individual human writing systems;

determine that the values representing the individual text characters are within a particular subset of values in the table that correspond to a particular said human writing system; and

designate that the particular said human writing system is associated with the string based on the values associated with the individual text characters being within the particular subset of values that corresponds with the particular said human writing system.

15. The system of claim 14, wherein the script detection service is further configured to:

indicate a range of positions in a text for the one or more text characters; and

form a communication that associates the particular said human writing system with the range of positions.

16. The system of claim 14, wherein the script detection service is further configured to indicate a service available to perform a function with the one or more text characters based on the particular said human writing system.

17. The system of claim 14, further comprising a punctuation module to analyze punctuation in the string to identify which said human writing system is associated with the string.

18. The system of claim 14, further comprising a frequency module to analyze a frequency with which the string occurs in a given human language to determine which human writing system is associated with the string.

19. The system of claim 14, further comprising a morphology module configured to analyze one or more substrings in the string to identify which said human writing system is associated with the string, the one or more substrings including prefixes or suffixes.

20. The system of claim 14, wherein the values include Unicode values, and wherein the table comprises a table of Unicode values associated with the particular said human writing system.