Back to results
US 11,238,394 B2Granted
Assessment-based qualified candidate delivery
AssigneeMicrosoft Technology Licensing, LLC
InventorsChristian V. Mathiesen, Emrecan Dogan, Alp Artar, Mustafa Emre Kazdagli
Life of this patent
Estimating the term…
Abstract
The disclosed embodiments provide a system for processing data. During operation, the system obtains answers by a candidate to assessments related to qualifications for one or more opportunities. Next, the system applies a machine learning model to the answers and additional qualifications for an additional opportunity to produce a match score between the candidate and the additional opportunity. The system then compares the match score to a threshold to determine a recommendation related to applying to the additional opportunity by the candidate. Finally, the system outputs the recommendation in association with the additional opportunity.
Claims18
A method, comprising:
- training a machine learning model to output a match score for a first candidate and an employment opportunity, by:
- obtaining from a plurality of candidates a plurality of answers to a plurality of assessments, each assessment associated with a qualification requirement for an employment opportunity, each answer indicating an extent to which a candidate satisfies the qualification requirement for the employment opportunity;
- obtaining information indicating outcomes relating to employment applications submitted by the plurality of candidates for employment opportunities associated with the plurality of assessments;
- generating positive labels for positive outcomes and negative labels for negative outcomes;
- and;
- providing as training data the plurality of answers and the positive labels and negative labels for training the machine learning model;
- and
- obtaining answers by the first candidate to assessments relating to qualification requirements for one or more employment opportunities;
- applying, by one or more computer systems, the machine learning model to the answers provided by the first candidate, additional features of the first candidate, and qualification requirements for an additional employment opportunity, to produce a match score between the first candidate and the additional employment opportunity;
- comparing the match score to a threshold to determine that a recommendation relating to the additional employment opportunity is to be presented to the first candidate;
- and
- causing the recommendation relating to the additional employment opportunity to be presented to the first candidate via a user interface.
9 more elements
A system, comprising:
- one or more processors;
- and
- memory storing instructions that, when executed by the one or more processors, cause the system to:
- train a machine learning model to output a match score for a first candidate and an employment opportunity, by:
- obtaining from a plurality of candidates a plurality of answers to a plurality of assessments, each assessment associated with a qualification requirement for an employment opportunity, each answer indicating an extent to which a candidate satisfies the qualification requirement for the employment opportunity;
- obtaining information indicating outcomes relating to employment applications submitted by the plurality of candidates for employment opportunities associated with the plurality of assessments;
- generating positive labels for positive outcomes and negative labels for negative outcomes;
- and;
- providing as training data the plurality of answers and the positive labels and negative labels for training the machine learning model;
- and
- generate the match score for the first candidate and the employment opportunity, by:
- obtaining answers by the first candidate to assessments relating to qualifications for one or more employment opportunities;
- applying the machine learning model to the answers, additional features of the candidate, and qualification requirements for an additional employment opportunity to produce a match score between the candidate and the additional employment opportunity;
- comparing the match score to a threshold to determine that a recommendation relating to the additional employment opportunity is to be presented to the candidate;
- and
- causing the recommendation relating to the additional employment opportunity to be presented to the candidate via a user interface.
13 more elements
A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method, the method comprising:
- training a machine learning model to output a match score for a first candidate and an employment opportunity, by:
- obtaining from a plurality of candidates a plurality of answers to a plurality of assessments, each assessment associated with a qualification requirement for an employment opportunity, each answer indicating an extent to which a candidate satisfies the qualification requirement for the employment opportunity;
- obtaining information indicating outcomes relating to employment applications submitted by the plurality of candidates for employment opportunities associated with the plurality of assessments;
- generating positive labels for positive outcomes and negative labels for negative outcomes;
- and;
- providing as training data the plurality of answers and the positive labels and negative labels for training the machine learning model;
- and
- generating the match score for the first candidate and the employment opportunity, by:
- obtaining answers by the first candidate to assessments relating to qualification requirements for one or more employment opportunities;
- applying the machine learning model to the answers, additional features of the candidate, and qualification requirements for an additional employment opportunity to produce the match score between the candidate and the additional employment opportunity;
- comparing the match score to a threshold to determine that a recommendation relating to the additional employment opportunity is to be presented to the candidate;
- and
- causing the recommendation relating to the additional employment opportunity to be presented to the candidate via a user interface.
10 more elements
Dependencies are inferred from the claim text.