Methods, systems and techniques for personalized search query suggestions

1. A method, implemented on at least one computing device each of which has at least one processor, storage, and a communication platform connected to a network for query suggestion, the method comprising:

generating a person corpus based on data cross linked from a plurality of data sources some of which are private to the person, wherein the data is cross-linked based on cross-linking keys identified from the data;

receiving a first portion of an input from a person;

obtaining, with respect to the first portion of the input, a first set of query suggestions based on the person corpus;

receiving, subsequent to the first portion of the input, a second portion of the input from the person;

obtaining, with respect to the first and second portions of the input, a second set of query suggestions from the person corpus, wherein the obtaining includes:

determining, for each query suggestion of the first set and the second set of query suggestions, a type of data source from which the query suggestion is obtained, and

determining, based on the type of data source, an information extraction model to be applied to the data source to obtain the query suggestion; and

presenting at least some of the first set and second set of query suggestions.

2. The method of claim 1 , wherein the at least one data source private to the person includes:

private electronic mails;

a private calendar;

a private contact list;

private messages;

private bookmarks;

private visual information;

private voice information; and

private log information.

3. The method of claim 1 , further comprising:

obtaining at least one query suggestion generated based on information from an additional data source; and

presenting the at least one query suggestion.

4. The method of claim 3 , wherein the additional data source includes:

a person search history; and

an archive of regular suggestions.

5. The method of claim 1 , wherein the first portion of the input corresponds to a prefix of a search query.

6. A system having at least one processor, storage, and a communication platform, to provide query suggestion, the system comprising:

a person-centric system implemented using the at least one processor and configured for generating a person corpus based on data cross linked from a plurality of data sources some of which are private to the person, wherein the data is cross-linked based on cross-linking keys identified from the data;

a request processing unit implemented using the at least one processor and configured to receive a first portion of an input from a person;

a first suggestion retrieving module implemented using the at least one processor and configured to

obtain, with respect to the first portion of the input, a first set of query suggestions based on the person corpus,

obtain, with respect to the first portion of the input and a second portion of the input that is received subsequent to the first portion, a second set of query suggestions from the person corpus, wherein the first suggestion retrieval module is further configured to:

determine, for each query suggestion of the first set and the second set of query suggestions, a type of data source from which the query suggestion is obtained, and

determine, based on the type of data source, an information extraction model to be applied to the data source to obtain the query suggestion; and

a query suggestion generation module implemented using the at least one processor and configured to provide at least some of the first set and second set of query suggestions.

7. The system of claim 6 , wherein the at least one data source private to the person includes:

private electronic mails;

a private calendar;

a private contact list;

private messages;

private bookmarks;

private visual information;

private voice information; and

private log information.

8. The system of claim 6 , further comprising:

a second suggestion retrieving module implemented using the at least one processor and configured to obtain at least one query suggestion generated based on information from an additional data source,

wherein the query suggestion generation module is further configured to present the at least one query suggestion.

9. The system of claim 8 , wherein the additional data source includes:

a person search history; and

an archive of regular suggestions.

10. The system of claim 6 , wherein the first portion of the input corresponds to a prefix of a search query.

11. A non-transitory machine-readable medium having information recorded thereon to provide query suggestions, wherein the information, when read by the machine, causes the machine to perform operations comprising:

generating a person corpus based on data cross linked from a plurality of data sources some of which are private to the person, wherein the data is cross-linked based on cross-linking keys identified from the data;

receiving a first portion of an input from a person;

obtaining, with respect to the first portion of the input, a first set of query suggestions based on the person corpus;

receiving, subsequent to the first portion of the input, a second portion of the input from the person;

obtaining, with respect to the first and second portions of the input, a second set of query suggestions from the person corpus, wherein the obtaining includes:

determining, for each query suggestion of the first set and the second set of query suggestions, a type of data source from which the query suggestion is obtained, and

determining, based on the type of data source, an information extraction model to be applied to the data source to obtain the query suggestion; and

presenting at least some of the first set and second set of query suggestions.

12. The medium of claim 11 , wherein the at least one data source private to the person includes:

private electronic mails;

a private calendar;

a private contact list;

private messages;

private bookmarks;

private visual information;

private voice information; and

private log information.

13. The medium of claim 11 , further comprising:

obtaining at least one query suggestion generated based on information from an additional data source; and

presenting the at least one query suggestion.

14. The medium of claim 13 , wherein the additional data source includes:

a person search history; and

an archive of regular suggestions.

15. The medium of claim 11 , wherein the first portion of the input corresponds to a prefix of a search query.

16. The method of claim 1 , wherein the one or more query suggestions are presented to the person simultaneously.

17. The method of claim 3 , wherein the at least one query suggestion generated based on information from an additional data source is presented replacing the at least some query suggestions.

18. The system of claim 8 , wherein the at least one query suggestion generated based on information from an additional data source is presented replacing the at least some query suggestions.

19. The medium of claim 13 , wherein the at least one query suggestion generated based on information from an additional data source is presented replacing the at least some query suggestions.

20. The method of claim 1 , further comprising:

determining an order of presenting the first set and second set of query suggestions based on at least one of a first criterion associated with the at least one data source from which the query is obtained, and a second criterion associated with metadata related to the input.

21. The method of claim 1 , wherein each query suggestion of the first set and second set of query suggestions is mapped to a common feature space based on at least one attribute associated with the query suggestion.

22. The method of claim 1 , wherein the person corpus is generated automatically without any input from the user.