Method and system for identifying job candidates

• US 9,053,157 B2
• Filed: 11/29/2013
• Issued: 06/09/2015
• Est. Priority Date: 10/30/2010
• Status: Active Grant

• Current Assignee: Employ, Inc.
• Original Assignee: Jobvite Incorporated
• Inventors: Ali, Syed Mohammed, Hyder, Adam, Chen, Changsheng, Chu, Kam Wing
• Primary Examiner(s): Trujillo, James
• Assistant Examiner(s): PARK, GRACE A
• Application Number:
  US14/093,331
• Publication Number:
  US 20140089303A1
• Time in Patent Office: 557 Days
• Field of Search: 707/748
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06Q 10/1053 Employment or hiring

Abstract

A method for ranking profile records. The method includes receiving a search request from a user, obtaining a user profile associated with the user, generating a query based on the search request, issuing the query to a profile database, receiving search results in response to the query, wherein the search results comprise a plurality of profile records, and wherein each of the plurality of profile records comprises a plurality of action records and is associated with a potential job candidate, ranking the plurality of profile records using the user profile and a plurality of network scores to obtain ranked profile records, and transmitting the ranked profile records to the user.

Claims

1. A method for ranking profile records comprising:

receiving a search request from a user;

obtaining a user profile associated with the user;

generating a query based on the search request;

issuing the query to a profile database;

receiving search results in response to the query, wherein the search results comprise a plurality of profile records;

ranking the plurality of profile records to obtain ranked profile records, wherein ranking the plurality of profile records comprises;

selecting a profile record of the plurality of profile records, wherein the profile record is associated with a potential job candidate, determining a user score for the profile record using the user profile and a first plurality of action records associated with the profile record that specify actions performed by the user on the profile record, wherein at least one action in the first plurality of action records comprises at least one selected from a group consisting of an indication of a positive interview evaluation based on an interview conducted with the potential job candidate of a plurality of potential job candidates and an indication of a negative interview evaluation based on the interview conducted with the potential job candidate,

determining a network score for the profile record using a second plurality of action records associated with the profile record that specify actions performed by a second user on the profile record, wherein at least one action of the second plurality of action records is at least one selected from a group consisting of a positive action performed a second user on the profile record and a negative action performed by the second user on the profile record, wherein the negative action is one selected from a group consisting of a delete action specifying that the profile record was deleted from second search results by the second user and a rejection action specifying that the second user has previously rejected a job application from the potential job candidate, and

generating a score for the profile record using the user score and the network score, wherein the score is used in ranking the plurality of profile records; and

transmitting the ranked profile records to the user.

2. The method of claim 1, wherein the user profile comprises user preferences associated with the user.

3. The method of claim 2, wherein the user preferences comprise general preferences and search-specific preferences.

4. The method of claim 3, wherein the general preferences comprise user-specified preferences and learned preferences.

5. The method of claim 3, wherein the search-specific preferences comprise user-specified preferences and learned preferences.

6. The method of claim 1, wherein each of the first plurality of action records associated with one of the plurality of profile records comprises an action and a user ID associated with a user that performed the action on the profile record.

7. The method of claim 1, wherein generating the query based on the search request comprises obtaining additional keywords for the query from a keyword intelligence engine.

8. The method of claim 1, wherein generating the query based on the search request comprises obtaining additional keywords for the query based on the user record.

9. The method of claim 1, further comprising:

generating a second query based on the search request;

issuing the second query to a network, wherein the search results further comprise results from issuing the second query to the network.

10. The method of claim 9, wherein the network is the Internet.

11. The method of claim 9, further comprising:

generating a second query based on the search request;

issuing the second query to a service, wherein the search results further comprise a result from issuing the second query to the service.

12. The method of claim 11, wherein the service is a social network service.

13. A non-transitory computer readable storage medium comprising instructions for ranking profile records, the instructions comprising functionality to:

receive a search request from a user;

obtain a user profile associated with the user;

generate a query based on the search request;

issue the query to a profile database;

receive search results in response to the query, wherein the search results comprise a plurality of profile records;

ranking the plurality of profile records to obtain ranked profile records, wherein ranking the plurality of profile records comprises;

selecting a profile record of the plurality of profile records, wherein the profile record is associated with a potential job candidate,

determining a user score for the profile record using the user profile and a first plurality of action records associated with the profile record that specify actions performed by the user on the profile record, wherein at least one action in the first plurality of action records comprises at least one selected from a group consisting of an indication of a positive interview evaluation based on an interview conducted with the potential job candidate of a plurality of potential job candidates and an indication of a negative interview

evaluation based on the interview conducted with the potential job candidate,

determining a network score for the profile record using a second plurality of action records associated with the profile record that specify actions performed by any other user on the profile record, wherein at least one action of the second plurality of action records is at least one selected from a group consisting of a positive action performed by a second user on the profile record and a negative action performed by the second user on the profile record, wherein the negative action is one selected from a group consisting of a delete action specifying that the profile record was deleted from second search results by the second user and a rejection action specifying that the second user has previously rejected a job application from the potential job candidate, and

generating a score for the profile record using the user score and the network score, wherein the score is used in ranking the plurality of profile records; and

transmit the ranked profile records to the user.

14. The non-transitory computer readable storage medium of claim 13, wherein the user profile comprises user preferences associated with the user.

15. The non-transitory computer readable storage medium of claim 14, wherein the user preferences comprise general preferences and search-specific preferences.

16. The non-transitory computer readable storage medium of claim 15, wherein the general preferences comprise user-specified preferences and learned preferences.

17. The non-transitory computer readable storage medium of claim 15, wherein the search-specific preferences comprise user-specified preferences and learned preferences.