JP2020009502A5

JP2020009502A5 -

Info

Publication number: JP2020009502A5
Application number: JP2019191665A
Authority: JP
Filing date: 2019-10-21
Publication date: 2020-08-27
Anticipated expiration: 2037-07-10

Claims

A learning unit that performs learning based on the training data to generate a trained model,
A correction unit that corrects the learned model based on the correction information input to the learned model to generate a corrected model,
An evaluation unit that evaluates the modified model using evaluation data different from the training data,
An output unit that outputs an evaluation result of the modified model by the evaluation unit,
Equipped with
An information processing device capable of correcting, as the correction information, at least one of the items used in the learned model by an input from a user operation unit.

The information processing apparatus according to claim 1, wherein a weight for an item used in the learned model can be adjusted.

The information processing apparatus according to claim 1, wherein the definition of the item used in the modified model can be modified by an input from the user operation unit.

The information processing apparatus according to claim 1, wherein the learning unit uses an item regarding selection of applicants as an item used in the learned model.

The information processing device according to claim 1, further comprising an abnormality detection unit that detects that information that should not be used is used.

The information processing apparatus according to any one of claims 1 to 5, wherein correction can be repeatedly performed by the correction unit while observing the accuracy when the corrected model is evaluated by the evaluation unit.

The learning unit is
A first learning unit that generates first evaluation information based on a document created by the applicant,
A second learning unit that generates second evaluation information of the applicant based on the applicant information regarding the applicant and the first evaluation information,
The information processing apparatus according to claim 1, further comprising:

A step of performing learning based on the training data by the learning unit to generate a learned model,
A step of correcting the learned model based on the correction information input to the learned model by the correction unit to generate a corrected model;
An evaluation unit evaluates the modified model using evaluation data different from the training data,
A step of outputting, by the output section, an evaluation result of the modified model by the evaluation section;
Equipped with
An information processing method, wherein, as the correction information, at least one of the items used in the learned model can be corrected by an input from a user operation unit.

A program to be installed in an information processing device,
The information processing device in which the program is installed,
A learning function that performs learning based on training data to generate a trained model, and
A correction function for generating a corrected model by correcting the learned model based on the correction information input to the learned model,
An evaluation function that evaluates the corrected model using evaluation data different from the training data,
An output function of outputting an evaluation result of the modified model by the evaluation unit,
Equipped with
A program capable of being modified so that at least one of the items used in the learned model is not used as the correction information by an input from a user operation unit.