Automatic correction of user input based on dictionary

• US 8,386,237 B2
• Filed: 07/23/2012
• Issued: 02/26/2013
• Est. Priority Date: 08/31/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Davtchev, Ivan D., Coccaro, Noah, Avidor, Adi, Andelman, Nir, Tanev, Mario
• Primary Examiner(s): ALBERTALLI, BRIAN LOUIS
• Application Number:
  US13/555,979
• Publication Number:
  US 20120290286A1
• Time in Patent Office: 218 Days
• Field of Search: None
• US Class Current: 704/8
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232

Abstract

Methods, systems, and apparatus, including computer program products, in which input keystroke data can be interpreted using a current mapping and a determination can be made whether the current mapping is valid based upon the characters identified by the mapping and the keystroke data. Invalid mappings can be corrected by identifying a transliteration of the characters in an alternative language.

Claims

1. A computer implemented method comprising:

receiving keystroke data for a keyboard input device, the keyboard input device having a current mapping for a language;

identifying groups of characters responsive to the keystroke data and the current mapping;

determining that at least one of the groups of characters is not a word in the language, and in response;

determining one or more spell corrected versions of the at least one of the groups of characters, each spell corrected version matching a word in the language resulting in first phrases of two or more words defined by the groups of characters including the spell corrected version;

scoring each of the first phrases in the language;

identifying one or more phonetic transliterations of at least one of the groups of characters in an alternative language, each phonetic transliteration of the characters comprising a transliteration of at least one of the groups of characters to alternative words in the alternative language resulting in second phrases of two or more words;

scoring each of the second phrases;

for each second phrase including a word in the language and a word in the alternative language, reducing the score of the second phrase; and

selecting from among the first and second phrases the phrase with the highest score as input.

2. The computer implemented method of claim 1, further comprising:

providing the selected phrase with the highest score to a user device.

3. The computer implemented method of claim 1, wherein the keystroke data is received through a search engine interface and the method further comprises:

providing the selected phrase with the highest score to the search engine.

4. The computer implemented method of claim 1, wherein the second phrases are scored according to corresponding frequency of use.

5. The computer implemented method of claim 1, wherein identifying the one or more phonetic transliteration of the at least one of the groups of characters in the alternative language comprises:

identifying a phonetic pronunciation of the at least one of the groups of characters in the alternative language; and

comparing the phonetic pronunciation of the at least one of the groups of characters in the alternative language to phonetic pronunciations of the one or more alternative words in the alternative language.

6. The computer implemented method of claim 5, further comprising:

identifying browser settings for a browser on a computing device comprising the keyboard input device; and

identifying one or more alternative languages according to the browser settings.

7. The computer implemented method of claim 1, wherein identifying one or more phonetic transliterations comprises identifying transliterations from documents included in a network or queries received through a search engine interface.

8. The computer implemented method of claim 7, wherein identifying one or more transliterations from documents included in a network or queries received through a search engine interface comprises:

analyzing query logs and documents to identify words that occur with a frequency greater than a threshold frequency; and

identifying words that occur with a frequency greater than a threshold frequency as the identified transliterations.

9. The method of claim 1, wherein reducing the score of the second phrase comprises reducing the score in proportion to a number of words in the alternative language.

10. The method of claim 1, wherein reducing the score of the second phrase comprises reducing the score based on a first number of words in the phrase that are in the alternative language and a second number of words in the phrase that are in the language.

11. The method of claim 1, wherein reducing the score of the second phrase comprises reducing the score based on likelihood of a phrase including words in the phrase that are in the first language and words in the phrase that are in the second language.

12. A computer readable storage device having instructions stored thereon that, when executed by a processing system, cause the processing system to perform operations comprising:

receiving keystroke data for a keyboard input device, the keyboard input device having a current mapping for a language;

identifying groups of characters responsive to the keystroke data and the current mapping;

determining that at least one of the groups of characters is not a word in the language and in response;

determining one or more spell corrected versions of the at least one of the groups of characters, each spell corrected version matching a word in the language resulting in first phrases of two or more words defined by the groups of characters including the spell corrected version;

scoring each of the first phrases in the language;

identifying one or more phonetic transliterations of at least one of the groups of characters in an alternative language, each phonetic transliteration of the characters comprising a transliteration of at least one of the groups of characters to alternative words in the alternative language resulting in second phrases of two or more words;

scoring each of the second phrases;

for each second phrase including a word in the language and a word in the alternative language, reducing the score of the second phrase; and

selecting from among the first and second phrases the phrase with the highest score as input.

13. The computer-readable storage device of claim 12, having instructions stored thereon that, when executed by a processing system, cause the processing system to perform operations comprising:

providing the selected phrase with the highest score to a user device.

14. The computer-readable storage device of claim 12, having instructions stored thereon that, when executed by a processing system, cause the processing system to perform operations comprising:

providing the selected phrase with the highest score to a search engine;

wherein the keystroke data is received through a search engine interface.

15. The computer-readable storage device of claim 12, wherein the second phrases are scored based on their corresponding frequency of use.

16. The computer-readable storage device of claim 12, wherein identifying the one or more phonetic transliteration of the at least one of the groups of characters in the alternative language comprises:

identifying a phonetic pronunciation of the at least one of the groups of characters in the alternative language; and

comparing the phonetic pronunciation of the at least one of the groups of characters in the alternative language to phonetic pronunciations of the one or more alternative words in the alternative language.

17. The computer-readable storage device of claim 12, wherein reducing the score of the second phrase comprises reducing the score in proportion to a number of words in the alternative language.

18. The computer-readable storage device of claim 12, wherein reducing the score of the second phrase comprises reducing the score based on a first number of words in the phrase that are in the alternative language and a second number of words in the phrase that are in the language.

19. The computer-readable storage device of claim 12, wherein reducing the score of the second phrase comprises reducing the score based on likelihood of a phrase including words in the phrase that are in the first language and words in the phrase that are in the second language.

20. A system comprising:

a data processing apparatus in data communication with a memory system storing instructions executable by the data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising;

receiving keystroke data for a keyboard input device, the keyboard input device having a current mapping for a language;

identifying groups of characters responsive to the keystroke data and the current mapping;

determining that at least one of the groups of characters is not a word in the language, and in response;

determining one or more spell corrected versions of the at least one of the groups of characters, each spell corrected version matching a word in the language resulting in first phrases of two or more words defined by the groups of characters including the spell corrected version;

identifying one or more phonetic transliterations of at least one of the groups of characters in an alternative language, each phonetic transliteration of the characters comprising a transliteration of at least one of the groups of characters to alternative words in the alternative language resulting in second phrases of two or more words;

scoring each of the first phrases in the language;

scoring each of the second phrases;

for each second phrase including a word in the language and a word in the alternative language, reducing the score of the second phrase; and

selecting from among the first and second phrases the phrase with the highest score as input.

21. The system of claim 20, wherein reducing the score of the second phrase comprises reducing the score in proportion to a number of words in the alternative language.

22. The system of claim 20, wherein reducing the score of the second phrase comprises reducing the score based on a first number of words in the phrase that are in the alternative language and a second number of words in the phrase that are in the language.

23. The system of claim 20, wherein reducing the score of the second phrase comprises reducing the score based on likelihood of a phrase including words in the phrase that are in the first language and words in the phrase that are in the second language.