US 2026/0311136 A1Published application

Neural network-based systems and methods for personalized vocational guidance using dynamic aptitude-based clustering

AssigneeYouScience, LLC

InventorsJohn Philip Hardin, Thomas Bertoli Cunningham, Derek Damian Curtis, James Matthew Barkley, Bridget Leigh Flowers, Bradley Jay Barton, Pablo Ifrán, Maria Virginia Rodríguez Rocha, Joaquin Manuel Olego Tiscornia

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A predictive system and method for matching users to careers and/or career groupings comprises a model training stage wherein training input data is collected for various training users, the training data comprising aptitude testing performance values and career interest values. Models are trained to generate aptitude data clusters which correlate to respective careers, preferably minimizing number of aptitude tests required while providing sufficient correlation. A current user assessment stage includes collecting first aptitude and interest input data for current users, identifying a cluster of training input data corresponding to similarly performing training users, and selecting additional aptitude tests to provide requisite career correlation while minimizing the number of tests required, or satisfying a threshold number of tests. A user-specific data set is generated representing correlations for the input aptitude and interest data with respect to one or more careers, and in some embodiments with recommended pathways correlating to such careers.

Claims20

Dependent claims

A predictive method for matching users to careers and/or career groupings,

the method comprising, during a model training stage:
collecting training input data comprising, for each of a plurality of training users, a plurality of aptitude testing performance values, and user input corresponding to interest values for one or more of a plurality of careers;
and
training one or more neural network-based models to generate clusters of the input data, including at least aptitude testing performance value combinations, which correlate to respective careers, wherein training parameters are selected for each combination corresponding to a respective number of aptitude testing performance values and a respective degree of correlation;
and
the method comprising, during a current user assessment stage:
collecting current input data comprising, for a current user, a plurality of aptitude testing performance values for a corresponding first set of aptitude tests, and current user input corresponding to interest values for one or more of the plurality of careers;
by reference to the trained model, identifying a cluster of training input data corresponding to similarly performing training users with respect to the collected current input data, and selecting a second set of aptitude tests based on a predicted combination of aptitude tests optimizing a minimal number of aptitude testing performance values and/or maximizing a respective degree of correlation to respective careers;
collecting further current input data comprising, for the current user, aptitude testing performance values for the corresponding second set of aptitude tests, and generating an aggregate set of aptitude testing performance values;
and
generating a user-specific data set representing correlations for the collected current input data and further current input data with respect to one or more of the plurality of careers.

8 more elements

A system for predictive matching of users to careers and/or career groupings, the system comprising one or more processors associated with one or more computing devices and configured to direct the performance of:

during a model training stage:
collecting training input data comprising, for each of a plurality of training users, a plurality of aptitude testing performance values, and user input corresponding to interest values for one or more of a plurality of careers;
and
training one or more neural network-based models to generate clusters of the input data, including at least aptitude testing performance value combinations, which correlate to respective careers, wherein training parameters are selected for each combination corresponding to a respective number of aptitude testing performance values and a respective degree of correlation;
and
during a current user assessment stage:
collecting current input data comprising, for a current user, a plurality of aptitude testing performance values for a corresponding first set of aptitude tests, and current user input corresponding to interest values for one or more of the plurality of careers;
by reference to the trained model, identifying a cluster of training input data corresponding to similarly performing training users with respect to the collected current input data, and selecting a second set of aptitude tests based on a predicted combination of aptitude tests optimizing a minimal number of aptitude testing performance values and/or maximizing a respective degree of correlation to respective careers;
collecting further current input data comprising, for the current user, aptitude testing performance values for the corresponding second set of aptitude tests, and generating an aggregate set of aptitude testing performance values;
and
generating a user-specific data set representing correlations for the collected current input data and further current input data with respect to one or more of the plurality of careers.

8 more elements

Dependencies are inferred from the claim text.