DICTIONARY WORD AND PHRASE DETERMINATION

• US 20080312910A1
• Filed: 10/10/2007
• Published: 12/18/2008
• Est. Priority Date: 06/14/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Zhang, Po
• Granted Patent: US 8,010,344 B2
• Time in Patent Office: Days
• US Class Current: 704/10
• CPC Class Codes: G06F 16/3338 Query expansion
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/53 Processing of non-Latin text kana-to-kanji conversion G06F40/129; vowelisation G06F40/232

Abstract

Candidate words in search queries are identified, each candidate word including one or more consecutive characters. For each candidate word, a first count is determined, the first count representing a number of times that the candidate word is the only word in the search queries, and a second count is determined, the second count representing a number of times that the candidate word and one or more other words are included in each of the search queries. One or more of the candidate words are added to an input method editor dictionary based on a relationship between the first count and the second count.

Claims

1. A computer-implemented method comprising:

identifying candidate words in search queries, each candidate word comprising one or more consecutive characters;

for each candidate word;

determining a first count representing a number of times that the candidate word is the only word in the search queries, and

determining a second count representing a number of times that the candidate word and one or more other words are included in each of the search queries; and

adding one or more of the candidate words to an input method editor dictionary based on a relationship between the first count and the second count.

2. The method of claim 1 wherein adding one or more of the candidate words to the input method editor dictionary comprises adding a candidate word to the input method editor dictionary when the first count is larger than the second count.

3. The method of claim 1 wherein adding one or more of the candidate words to the input method editor dictionary comprises adding a candidate word to the input method editor dictionary when the first count is larger than the second count and the first count is larger than a threshold value.

4. The method of claim 1 wherein determining the second count comprises counting a number of search queries that each includes the candidate word and one or more other words, in which the candidate word and the one or more other words are separated by one or more white spaces or punctuation marks entered by users who submitted the search queries.

5. The method of claim 1, comprising obtaining the search queries from a search log.

6. The method of claim 5 wherein the search log comprises search queries submitted by users of a search service.

7. The method of claim 1 wherein the candidate words comprise Hanzi characters.

8. The method of claim 1 wherein the input method editor dictionary comprises a Chinese input method editor dictionary.

9. A system, comprising:

a data store to store search queries; and

a processing engine stored in computer readable medium and comprising instructions executable by a processing device that upon such execution cause the processing device to;

identify candidate words in the search queries, each candidate word comprising one or more consecutive characters;

for each candidate word;

determine a first count representing a number of times that the candidate word is the only word in the search queries, and

determine a second count representing a number of times that the candidate word and one or more other words are included in each of the search queries; and

add one or more of the candidate words to an input method editor dictionary based on a relationship between the first count and the second count.

10. The system of claim 9 wherein the processing engine comprises instructions executable by the processing device and upon such execution cause the processing device to add a candidate word to the input method editor dictionary when the first count is larger than the second count.

11. The system of claim 9 wherein the processing engine comprises instructions executable by the processing device and upon such execution cause the processing device to add a candidate word to the input method editor dictionary when the first count is larger than the second count and the first count is larger than a threshold value.

12. The system of claim 9 wherein the processing engine comprises instructions executable by the processing device and upon such execution cause the processing device to count a number of search queries that each includes the candidate word and one or more other words, in which the candidate word and the one or more other words are separated by one or more white spaces or punctuation marks entered by users who submitted the search queries.

13. The system of claim 9 wherein the processing engine comprises instructions executable by the processing device and upon such execution cause the processing device to obtain the search queries from a search log.

14. The system of claim 13 wherein the search log comprises search queries submitted by users of a search service.

15. The system of claim 9 wherein the candidate words comprise Hanzi characters.

16. An apparatus comprising:

a dictionary having words identified based on a first count representing a number of times that the word is the only word in search queries and a second count representing a number of times that the word and one or more other words are in each of the search queries;

an input method editor configured to select words from the dictionary.

17. The apparatus of claim 16 wherein the input method editor comprises a Chinese input method editor.

18. The apparatus of claim 16 wherein the words comprise Hanzi characters.

19. The apparatus of claim 16 wherein for each word in the dictionary, the first count associated with the word is larger than the second count associated with the word.

20. A system comprising:

means for identifying candidate words in search queries, each candidate word comprising one or more consecutive characters;

means for processing each candidate word by;

determining a first count representing a number of times that the candidate word is the only word in the search queries, and

determining a second count representing a number of times that the candidate word and one or more other words are included in each of the search queries; and

means for adding one or more of the candidate words to an input method editor dictionary based on a relationship between the first count and the second count.

21. The system of claim 20, comprising means for obtaining the search queries from a search log.

22. The system of claim 20 wherein the means for adding one or more of the candidate words to an input method editor dictionary comprises means for adding a candidate word to the input method editor dictionary when the first count is larger than the second count.

23. The system of claim 20 wherein the means for processing each candidate word comprises means for determining the second count by counting a number of search queries that each includes the candidate word and one or more other words, in which the candidate word and the one or more other words are separated by one or more white spaces or punctuation marks entered by users who submitted the search queries.

24. A system, comprising:

means for identifying candidate words based on a first count representing a number of times that the word is the only word in search queries and a second count representing a number of times that the word and one or more other words are included in each of the search queries; and

means for adding one or more of the candidate words to an input method editor dictionary.

25. The system of claim 24, comprising means for obtaining the search queries from a search log.