Dictionary Word and Phrase Determination

• US 20110282903A1
• Filed: 07/26/2011
• Published: 11/17/2011
• 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 8,412,517 B2
• Time in Patent Office: Days
• US Class Current: 707/769
• 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

Context signals in documents are identified, characters bounded by the context signals are identified, one or more candidate words defined by the characters bounded by the context signals are identified, and one or more of the candidate words are added to an input method editor dictionary.

Claims

1. A method performed by a system comprising one or more computers, the method comprising:

identifying, in a search query, one or more candidate terms, wherein each candidate term corresponds to one or more sequences of consecutive characters in the search query, and wherein a delimiter separates each sequence of consecutive characters when more than one sequence is identified in the search query;

for each candidate term,

determining a first count that is a number of times that the candidate term is an entire search query in a collection of search queries, and

determining a second count that is a number of times that the candidate term is in, but less than, an entire search query in the collection of search queries;

identifying using one or more computing devices one or more of the candidate terms as being candidate entries; and

adding the candidate entries to an input method editor dictionary.

2. The method of claim 1, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count.

3. The method of claim 1, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count and a threshold value.

4. The method of claim 1, wherein the delimiter is a white space or a punctuation mark.

5. The method of claim 1, wherein the collection of search queries comprises search queries previously submitted by users of a search service.

6. The method of claim 1 wherein determining the second count comprises counting a number of search queries that include the candidate term and one or more other terms.

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

8. A system comprising one or more computers and one or more storage devices storing that instructions that, when executed by the one or more computers, cause the one or more computers to perform operations comprising:

identifying, in a search query, one or more candidate terms, wherein each candidate term corresponds to one or more sequences of consecutive characters in the search query, and wherein a delimiter separates each sequence of consecutive characters when more than one sequence is identified in the search query;

for each candidate term,

determining a first count that is a number of times that the candidate term is an entire search query in a collection of search queries, and

determining a second count that is a number of times that the candidate term is in, but less than, an entire search query in the collection of search queries;

identifying using one or more computing devices one or more of the candidate terms as being candidate entries; and

adding the candidate entries to an input method editor dictionary.

9. The system of claim 8, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count.

10. The system of claim 8, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count and a threshold value.

11. The system of claim 8, wherein the delimiter is a white space or a punctuation mark.

12. The system of claim 8, wherein the collection of search queries comprises search queries previously submitted by users of a search service.

13. The system of claim 8, wherein determining the second count comprises counting a number of search queries that include the candidate term and one or more other terms.

14. A computer storage medium encoded with a computer program, the computer program comprising instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

identifying, in a search query, one or more candidate terms, wherein each candidate term corresponds to one or more sequences of consecutive characters in the search query, and wherein a delimiter separates each sequence of consecutive characters when more than one sequence is identified in the search query;

for each candidate term,

determining a first count that is a number of times that the candidate term is an entire search query in a collection of search queries, and

determining a second count that is a number of times that the candidate term is in, but less than, an entire search query in the collection of search queries;

identifying using one or more computing devices one or more of the candidate terms as being candidate entries; and

adding the candidate entries to an input method editor dictionary.

15. The computer storage medium of claim 14, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count.

16. The computer storage medium of claim 14, wherein identifying one or more of the candidate terms as being candidate entries includes:

identifying, as being candidate entries, only candidate terms that are associated with a respective first count greater than a respective second count and a threshold value.

17. The computer storage medium of claim 14, wherein the delimiter is a white space or a punctuation mark.

18. The computer storage medium of claim 14, wherein the collection of search queries comprises search queries previously submitted by users of a search service.

19. The computer storage medium of claim 14, wherein determining the second count comprises counting a number of search queries that include the candidate term and one or more other terms.

20. The computer storage medium of claim 14, wherein the candidate words comprise Hanzi characters.