公开(公告)号：US11551570B2

公开(公告)日：2023-01-10

申请号：US16277619

申请日：2019-02-15

Applicant: Smarthink Srl

Inventor： Lucilla Crosta ,  Riccardo Cattaneo ,  Giovanni Bettinazzi ,  Andrea Solazzo ,  Luca Butera

IPC: G09B7/02 ,  G06N20/20 ,  G09B7/04 ,  G09B5/14 ,  G06Q50/20 ,  G09B5/12 ,  G09B5/06 ,  G06Q10/06

Abstract: A skills learning method for a student gathers objective data relating to the student in response to various stimuli, and produces a predicted feedback units as a function of the objective data using a machine learning-base classifier. The method can include training a neural network using objective data of student interactions and associated subjective assessments of a skill of each objective data. The method includes receiving a new dataset with objective data of a new student and an associated subjective assessment of a skill of the first student represented by the new objective data. A predicted assessment of the skill of the new objective data is calculated by inputting the new objective data into the neural network. The method can include updating the neural network by combining the initial dataset and the new dataset and recompiling the neural network to fit the model dataset based on a learning algorithm.

公开(公告)号：US20190251477A1

公开(公告)日：2019-08-15

申请号：US16277619

申请日：2019-02-15

Applicant: Smarthink Srl

Inventor： Lucilla Crosta ,  Riccardo Cattaneo ,  Giovanni Bettinazzi ,  Andrea Solazzo ,  Luca Butera

IPC: G06N20/20 ,  G06Q50/20 ,  G06K9/62 ,  G06K9/00

CPC classification number: G06N20/20 ,  G06K9/00302 ,  G06K9/6256 ,  G06K9/6267 ,  G06Q10/06398 ,  G06Q50/20 ,  G06Q50/205 ,  G09B5/065 ,  G09B5/12 ,  G09B5/14 ,  G09B7/04

Abstract: A skills learning method for a student gathers objective data relating to the student in response to various stimuli, and produces a predicted feedback units as a function of the objective data using a machine learning-base classifier. The method can include training a neural network using objective data of student interactions and associated subjective assessments of a skill of each objective data. The method includes receiving a new dataset with objective data of a new student and an associated subjective assessment of a skill of the first student represented by the new objective data. A predicted assessment of the skill of the new objective data is calculated by inputting the new objective data into the neural network. The method can include updating the neural network by combining the initial dataset and the new dataset and recompiling the neural network to fit the model dataset based on a learning algorithm.