Identifying and ranking networked biographies and referral paths corresponding to selected qualifications
View Patent ↗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.
1. A non-transitory information-storage device programmed with data and instructions comprising:
a reference set of stored expressions distilled from biographies scored by a human expert,
instructions for finding the biographies stored on a network,
instructions for reducing the biographies to distilled expressions,
instructions for comparing the distilled expressions to the reference set to derive a qualification score,
instructions for identifying the biographies of candidates exhibiting a qualification selected by a searcher,
instructions for collecting network-stored indications of published connections between the searcher and each of the candidates,
instructions for extrapolating additional possible connections between the searcher and each of the candidates,
instructions for synthesizing a referral path from the searcher to each of the candidates through intermediaries identified by the published connections or the additional possible connections,
instructions for computing a connectivity score for the referral path based on the relevance of the intermediaries' biographies or the intermediaries' connections to the qualification selected, and
displaying the results ranked by at least one of the qualification score, the connectivity score, and the geographic proximity of each of the candidates to the searcher.
2. The non-transitory information-storage device of claim 1 , further comprising instructions for aggregating multiple networked biographies of one of the candidates and reducing the multiple networked biographies to a single distilled expression.
3. The non-transitory information-storage device of claim 1 , where the stored expressions and the distilled expressions comprise one of a vector, a tensor, an expression suitable for an independent-feature model, an expression suitable for a random-forest model, and an expression suitable for a boosted-tree model.
4. The non-transitory information-storage device of claim 1 , where the distilled expressions comprise source information for the biographies, and further comprising instructions for detecting updates to the biographies and updating the distilled expressions accordingly.
5. The non-transitory information-storage device of claim 1 , further comprising instructions for detecting a missing quantity in the biographies and bracketing a possible range for the missing quantity based on other information in the biographies.
6. The non-transitory information-storage device of claim 1 , further comprising a look-up table, a heuristic, or an inferential algorithm assigning consistent values to named entities in the distilled expressions.
7. The non-transitory information-storage device of claim 1 , further comprising a plurality of profession filters and instructions for routing the biographies through the relevant profession filters.
8. The non-transitory information-storage device of claim 1 , further comprising instructions for fitting a probability distribution to the qualification score or the connectivity score.
9. The non-transitory information-storage device of claim 1 , further comprising an archive of datasets representing categorized and scored biographies, and instructions for adding new datasets to the archive as new biographies are categorized and scored.
10. The non-transitory information-storage device of claim 1 , further comprising instructions for collecting statistical data on the qualifications selected by the searcher and other searchers.