Information processing device, information processing device control method, program, calculation device, and calculation method
AssigneeCanon Kabushiki Kaisha
InventorsAkihiro Taya, Hidetaka Kawamura, Yutaka Yoshimasa
Life of this patent
Estimating the term…
Abstract
Hitherto, preprocessing for separating impurities and calculation processing, for example, a peak splitting method, are required in order to acquire information on test substances from spectral information. An information processing apparatus according to the present invention includes information acquisition means for acquiring quantitative information on a test substance estimated by inputting spectral information on a sample containing the test substance and impurities into a learning model.
Claims17
An information processing apparatus comprising:
- a processor;
- and
- a memory containing instructions that, when executed by the processor, cause the processor to function as:
- an estimation means for estimating quantitative information on a test substance by inputting spectral information on a sample containing the test substance and impurities into a learning model;
- and
- an information acquisition means for acquiring the quantitative information estimated by the estimation means,
- wherein the learning model is learned through use of training data, the training data being a plurality of combinations of data each formed of (a) quantitative information on a test substance as correct-answer data, and (b) spectral information on the test substance at the respective quantity and random noise added thereto as input data on a virtual sample containing the test substance and impurities.
A control method for an information processing apparatus that includes processor and a memory containing instructions that, when executed by the processor, cause the processor to execute the control method comprising:
- an estimation step of estimating quantitative information on a test substance by inputting spectral information on a sample containing the test substance and impurities into a learning model, and an information acquisition step of acquiring the quantitative information estimated in the estimation step,
- wherein the learning model is learned through use of training data, the training data being a plurality of combinations of data each formed of (a) quantitative information on a test substance as correct-answer data, and (b) spectral information on the test substance at the respective quantity and random noise added thereto as input data on a virtual sample containing the test substance and impurities.
Dependencies are inferred from the claim text.