Identifying and ranking networked biographies and referral paths corresponding to selected qualifications

• US 8,396,867 B2
• Filed: 07/13/2011
• Issued: 03/12/2013
• Est. Priority Date: 07/13/2011
• Status: Active Grant

• Current Assignee: Graph, Inc.
• Original Assignee: Nimblecat, Inc.
• Inventors: Mehta, Sunil, Murgai, Poonam, Meyer, David
• Primary Examiner(s): MORRISON, JAY A
• Application Number:
  US13/182,438
• Publication Number:
  US 20130018871A1
• Time in Patent Office: 608 Days
• Field of Search: None
• US Class Current: 707/723
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 30/0631 Item recommendations

Abstract

The most common automated search methods produce less-than-ideal results when searching online resumes, profiles, and the like (“biographies”) for the identities of people with a searcher-selected qualification (“candidates”). Keywords, their proximities, and their repetitions are less informative in biographies than in other informational documents. Similarly, chains of social connection (“referral paths”) do not always reveal the likelihood or ease of a searcher'"'"'s introduction to a candidate. In both cases, the display order of results may be unrelated to any estimate of merit. To answer the question “Whom do I need and how do I reach them?” a classifier system uses heuristics or algorithms adapted to match the reactions of human experts on the selected qualifications. Terms in biographies, regardless of structure, are standardized and disambiguated for accurate comparisons, meaningful context is preserved, and biographies and referral paths are scored based on expected usefulness to the searcher.

Claims

1. A method of identifying a candidate with a selected qualification and deriving a referral path from a searcher to the candidate, the method comprising:

retrieving a biography from networked storage,

reducing the biography to a distilled expression comprising reference terms, qualification-related terms, and meaningful context,

classifying the biography by comparing the distilled expression to a reference set of expressions distilled from human-scored reference biographies,

assigning a qualification category and a qualification score to the biography responsive to a match of the distilled expression to a subset of the reference set,

storing a dataset comprising the qualification category, the qualification score, and an identifier of the biography in an archive,

enabling a searcher to select a qualification and search the archive for a candidate with the qualification,

extracting published connections between the searcher, the candidate, and any mutually connected intermediary from the networked storage,

detecting possible unpublished connections as overlaps in the biographies of the searcher, the candidate, and the intermediary,

deriving a referral path from the searcher to the candidate from the published or the possible unpublished connections, and

calculating a connectivity score for the referral path reflecting likelihood and ease of an introduction of the searcher to the candidate through the intermediary.

2. The method of claim 1, where the networked storage comprises a plurality of dissimilarly constructed databases.

3. The method of claim 1, where the distilled expression is made substantially independent of an original structure of the biography by standardizing variably-expressed terms having identical meanings.

4. The method of claim 1, where the distilled expression comprises an array of coefficients.

5. The method of claim 4, where the array comprises a tensor.

6. The method of claim 5, where the tensor is a first-rank tensor.

7. The method of claim 4, where a position of a coefficient in the array conveys a separate meaning from a value of the coefficient.

8. The method of claim 1, where the comparing of the distilled expression to the reference set comprises calculating a correlation coefficient.

9. The method of claim 1, where the comparing of the distilled expression to the reference set comprises calculating a root-mean-square difference.

10. The method of claim 1, where the comparing of the distilled expression to the reference set comprises calculating a dot product in vector space.

11. The method of claim 1, where the classifying of the biography comprises at least one of a heuristic and an algorithm derived from the reference set.

12. The method of claim 1, where the classifying of the biography comprises a naive-Bayes analysis.

13. The method of claim 1, further comprising adjusting the qualification score based on an external metric.

14. The method of claim 1, where the qualification score is normalized to be substantially independent of the qualification category.

15. The method of claim 14, where the qualification score is normalized to a percentile rank.

16. The method of claim 1, where the calculating of the connectivity score comprises assessing a link strength for each link in the referral path.

17. The method of claim 16, where the connectivity score partly depends on an average link strength over the referral path.

18. The method of claim 16, where the connectivity score partly depends on a weakest link strength within the referral path.

19. The method of claim 16, where the connectivity score partly depends on a qualification score of the intermediary calculated from a retrieved biography of the intermediary.