Personalized search results

1. A method performed by one or more processors, the method comprising:

constructing a probability model from information regarding computer based search result interactions of a user, to estimate a probability that the user will select a certain type of specialized search result,

wherein constructing the probability model from information regarding the computer based search result interactions of the user comprises constructing the probability model based on a quantity of past selections by the user of search results that are members of the certain type of specialized search result, the search results being past search results responsive to past search queries;

in response to receiving a search query from the user, the search query being submitted by the user via a computing device of the user:

searching sources of information, based on the search query, to determine a set of search results that match the search query;

using the estimated probability, determined using the constructed probability model, to select, from the set of search results, one or more search results that are of the certain type of specialized search result, the selected one or more search results that are of the certain type of specialized search result including at least a given document that is of the certain type of specialized search result; and

outputting, for presentation to the user via the computing device of the user, the selected one or more search results that are of the certain type of specialized search result.

2. The method of claim 1 , wherein each of the sources of information includes information related to a respective one of news, stock quotes, weather, music, movies, travel, maps, images, shopping, search history, definitions, questions, patents, or a local time.

3. The method of claim 1 , wherein the estimated probability includes at least one of:

a probability that the user will select news results;

a probability that the user will select stock quote results;

a probability that the user will select weather results;

a probability that the user will select music results;

a probability that the user will select movie results;

a probability that the user will select travel results;

a probability that the user will select map results;

a probability that the user will select image results;

a probability that the user will select shopping results;

a probability that the user will select search history results;

a probability that the user will select word definition results;

a probability that the user will select patent results; or

a probability that the user will select local time results.

4. The method of claim 1 , wherein outputting the one or more search results that are of the certain type comprises outputting at least the given document that is of the certain type of specialized search result, and outputting an additional search result of the one or more search results that are of the certain type of specialized search result.

5. The method of claim 1 , further comprising outputting additional search results, of the set of search results, that are not of the certain type of specialized search result.

6. The method of claim 5 , wherein outputting the selected one or more search results that are of the certain type of specialized search result comprises outputting the selected one or more search results featured prominently relative to the additional search results.

7. A computer-implemented system, comprising:

one or more processors to:

construct a probability model from information regarding computer based search result interactions of a user, to estimate a probability that the user will select a certain type of specialized search result, wherein the one or more processors, in constructing the probability model from information regarding the computer based search result interactions of the user, are to construct the probability model based on a quantity of past selections by the user of search results that are members of the certain type of specialized search result, the search results being past search results responsive to past search queries;

in response to receiving a search query from the user, the search query being submitted by the user via a computing device of the user:

search sources of information, based on the search query, to determine a set of search results that match the search query;

use the estimated probability, determined using the constructed probability model, to select, from the set of search results, one or more search results that are of the certain type of specialized search result, the selected one or more search results that are of the certain type of specialized search result including at least a given document that is of the certain type of specialized search result; and

output, for presentation to the user via the computing device of the user, the selected one or more search results that are of the certain type of specialized search result.

8. The system of claim 7 , wherein each of the sources of information includes information related to a respective one of news, stock quotes, weather, music, movies, travel, maps, images, shopping, search history, definitions, questions, patents, or a local time.

9. The system of claim 7 , wherein the estimated probability includes at least one of:

a probability that the user will select news results;

a probability that the user will select stock quote results;

a probability that the user will select weather results;

a probability that the user will select music results;

a probability that the user will select movie results;

a probability that the user will select travel results;

a probability that the user will select map results;

a probability that the user will select image results;

a probability that the user will select shopping results;

a probability that the user will select search history results;

a probability that the user will select word definition results;

a probability that the user will select patent results; or

a probability that the user will select local time results.

10. The system of claim 7 , wherein the one or more processors, in outputting the one or more search results that are of the certain type, are to output at least the given document that is of the certain type of specialized search result, and output an additional search result of the one or more search results that are of the certain type of specialized search result.

11. The system of claim 7 , wherein the one or more processors are further to output additional search results, of the set of search results, that are not of the certain type of specialized search result.

12. The system of claim 11 , wherein the one or more processors, in outputting the selected one or more search results that are of the certain type of specialized search result, are to output the selected one or more search results featured prominently relative to the additional search results.

13. One or more non-transitory computer readable storage media storing computer instructions executable by a processor, the instructions including instructions to:

construct a probability model from information regarding computer based search result interactions of a user, to estimate a probability that the user will select a certain type of specialized search result, wherein the instructions to construct the probability model from information regarding the computer based search result interactions of the user include instructions to construct the probability model based on a quantity of past selections by the user of search results that are members of the certain type of specialized search result, the search results being past search results responsive to past search queries;

in response to receiving a search query from the user, the search query being submitted by the user via a computing device of the user:

search sources of information, based on the search query, to determine a set of search results that match the search query;

use the estimated probability, determined using the constructed probability model, to select, from the set of search results, one or more search results that are of the certain type of specialized search result, the selected one or more search results that are of the certain type of specialized search result including at least a given document that is of the certain type of specialized search result; and

output, for presentation to the user via the computing device of the user, the selected one or more search results that are of the certain type of specialized search result.

14. The one or more non-transitory computer readable storage media of claim 13 , wherein each of the sources of information includes information related to a respective one of news, stock quotes, weather, music, movies, travel, maps, images, shopping, search history, definitions, questions, patents, or a local time.

15. The one or more non-transitory computer readable storage media of claim 13 , wherein the instructions to output the one or more search results that are of the certain type include instructions to output at least the given document that is of the certain type of specialized search result, and instructions to output an additional search result of the one or more search results that are of the certain type of specialized search result.

16. The one or more non-transitory computer readable storage media of claim 13 , wherein the instructions further include instructions to output additional search results, of the set of search results, that are not of the certain type of specialized search result.

17. The one or more non-transitory computer readable storage media of claim 16 , wherein the instructions to output the one or more search results that are of the certain type include instructions to output the selected one or more search results featured prominently relative to the additional search results.