Category analysis method-based near-infrared spectrum material content indexing method, equipment and medium

Abstract

The invention discloses a category analysis method-based near-infrared spectrum material content indexing method, which comprises the following steps of an instrument portrait building step, namely obtaining a feature information through an instrument portrait, dividing the feature information into multiple tags and obtaining tag weight of each tag; a content indexing step, namely creating a content indexing table through a category analysis method to obtain a classification mode of the component content and obtaining a content prediction value of the component content of the substance according to the classification mode of the component content and the corresponding tag weight; and a gradient prediction step, building a gradient prediction value according to the content prediction value and pushing the gradient prediction value to a user. The invention further discloses electronic equipment for executing the method and a computer readable storage medium of storing the method. Regression analysis is replaced with a category analysis method, so that the problem of an interstation difference is effectively solved, and model sharing between similar instruments is achieved under the condition of not using model transfer.

Description

technical field [0001] The present invention relates to the technical field of quantitative analysis in near-infrared spectroscopy, and specifically relates to a large data analysis technology based on a category analysis-based near-infrared spectrum material content index method (that is, a method that does not establish a regression model through traditional chemometrics) to predict Substance content information, so as to solve the problem of inter-stage difference between instruments. Background technique [0002] Near-infrared light (NIR) is an electromagnetic wave between ultraviolet-visible light (UV-Vis) and mid-infrared light (MIR), with a wavelength range of 700-2500nm. Near-infrared light can reflect the double frequency and combined frequency absorption of the vibration of hydrogen-containing groups X—H (such as C—H, N—H, O—H, etc.), and different groups (such as methyl, methylene, benzene ring, etc.) ) or the same group has obvious differences in the near-infrar...

AI Technical Summary

Problems solved by technology

[0008] In (2), due to the manufacturing process (the same batch of instruments, or different batches of instruments, differences between platforms due to subtle differences in the manufacturing process), the environment (instruments are affected by the current environment, such as temperature, humidity, etc., resulting in the same Different results obtained from different samples), instrument loss (due to the service life and the use loss of the instrument itself, there are differences between different instruments) and other issues, so that the same model of the same batch of near-infrared spectrometers can measure the same sample. There are differences in near-infrared spectral data, that is, the problem of inter-station difference

[0012] Although the model transfer method is widely applied to the problem of inter-station difference, it generally has the following disadvantages: (1) The amount of correction calculation is too much, and it is impossible to transfer a large number of models

(3) Lack of dynamic changes, once the instrument is calibrated, the model is fixed

And the consumption of instruments over time makes the model no longer accurate

(4) User participation is low, and the relationship between users and merchants is limited to buying and selling

Therefore, when the number of instruments increases sharply, the method of model transfer is difficult to realize, and the near-infrared spectroscopy technology cannot be popularized and used in large quantities.

Images