Training device, training method, and non-transitory computer-readable medium
AssigneeNEC Corporation
InventorsChenhui HUANG, Fumiyuki NIHEY, Masataka ANDOU
Life of this patent
Estimating the term…
Abstract
A training device according to the present disclosure includes a generation unit that generates analysis data indicating a variation of measurement data in a life cycle, based on a timing at which the measurement data regarding a first subject whose disease risk is known in advance is generated and a training unit that machine learns a training model for estimating the disease risk using the analysis data as an input, using the disease risk of the first subject known in advance and the analysis data regarding the first subject as training data. This makes it possible to support decision making of the first subject regarding healthcare.
Claims18
A training device comprising:
- at least one memory storing instructions;
- and
- at least one processor configured to execute the instructions to:
- generate analysis data indicating a variation of measurement data in a life cycle including days of a week, the measurement data being life log data regarding a first subject and being associated with a date and time including a day of the week, the generating including, for each day of the week, statistically processing the measurement data generated on the day of the week to calculate a statistical amount of the measurement data for the day of the week;
- and
- machine learn a training model that estimates a disease risk of a subject from the analysis data, by using a disease risk regarding the first subject known in advance and the analysis data regarding the first subject as training data.
A training method comprising:
- generating, by a computer, analysis data indicating a variation of measurement data in a life cycle including days of a week, the measurement data being life log data regarding a first subject and being associated with a date and time including a day of the week, the generating including, for each day of the week, statistically processing the measurement data generated on the day of the week to calculate a statistical amount of the measurement data for the day of the week;
- and
- machine learning, by the computer, a training model that estimates a disease risk of a subject from the analysis data, by using a disease risk regarding the first subject known in advance and the analysis data regarding the first subject as training data.
A non-transitory computer-readable medium storing a program for causing a computer to execute:
- generating analysis data indicating a variation of measurement data in a life cycle including days of a week, the measurement data being life log data regarding a first subject and being associated with a date and time including a day of the week, the generating including, for each day of the week, statistically processing the measurement data generated on the day of the week to calculate a statistical amount of the measurement data for the day of the week;
- and
- machine learning a training model that estimates a disease risk of a subject from the analysis data, by using a disease risk regarding the first subject known in advance and the analysis data regarding the first subject as training data.
Dependencies are inferred from the claim text.