EP-4741487-A1 - DATA EXTRACTION SYSTEM, DATA EXTRACTION METHOD, AND DATA EXTRACTION PROGRAM

EP4741487A1EP 4741487 A1EP4741487 A1EP 4741487A1EP-4741487-A1

Abstract

This data extraction system includes: a setting unit that sets an input criterion indicating performance required for data analysis; an input unit that acquires an input signal indicating a measurement result of a measurement object in bioproduction; a preprocessing unit that performs a preprocessing operation on the input signal for comparison with the input criterion to generate a preprocessed signal; a postprocessing unit that, when the preprocessed signal does not satisfy the input criterion, performs a postprocessing operation using another signal obtained by measuring the measurement object on the preprocessed signal, and generates a postprocessed signal; and an extraction unit that extracts the preprocessed signal as extracted data when the preprocessed signal satisfies the input criterion, and extracts the postprocessed signal as extracted data when the postprocessed signal satisfies the input criterion.

Inventors

TAKASHIMA, MASATOSHI
HORII, Shumpei
SAKAGUCHI, KOHEI
OKADA, KATSUNORI
SUZUKA, Satoshi
KAWAI, Tetsushi

Assignees

Chitose Laboratory Corp.

Dates

Publication Date: 20260513
Application Date: 20240710

Claims (13)

A data extraction system comprising: a setting unit that sets an input criterion indicating performance required for data analysis; an input unit that acquires an input signal indicating a measurement result of a measurement object in bioproduction; a preprocessing unit that performs a preprocessing operation on the input signal for comparison with the input criterion to generate a preprocessed signal; a postprocessing unit that performs a postprocessing operation using another signal indicating the measurement result of the measurement object on the preprocessed signal when the preprocessed signal does not satisfy the input criterion, to generate a postprocessed signal; and an extraction unit that extracts the preprocessed signal as extracted data when the preprocessed signal satisfies the input criterion, and extracts the postprocessed signal as extracted data when the postprocessed signal satisfies the input criterion.
The data extraction system according to claim 1, wherein the input signal is an optical spectrum measured by optical spectroscopic measurement in bioproduction, and the preprocessing unit generates the preprocessed signal by calculating a relative intensity with a signal level in a wavelength range that does not respond to a change in a culture medium and where a transmittance does not become zero.
The data extraction system according to claim 2, wherein the optical spectroscopic measurement is near-infrared spectroscopic measurement, and the preprocessing unit generates the preprocessed signal by calculating a relative intensity with a signal level in a wavelength range that does not respond to organic molecule fluctuation and where light intensity necessary for the near-infrared spectroscopic measurement is not affected by water absorption as the wavelength range.
The data extraction system according to claim 3, wherein the preprocessing unit generates a first preprocessed signal for which the relative intensity is not calculated, and generates a second preprocessed signal for which the relative intensity is calculated, the setting unit sets a first input criterion that is an input criterion corresponding to the first preprocessed signal, and sets a second input criterion that is an input criterion corresponding to the second preprocessed signal, the postprocessing unit performs the postprocessing operation on the first preprocessed signal when the first preprocessed signal does not satisfy the first input criterion, to generate a first postprocessed signal, the extraction unit extracts the first preprocessed signal as first extracted data when the first preprocessed signal satisfies the first input criterion, and extracts the first postprocessed signal as first extracted data when the first postprocessed signal satisfies the first input criterion, the postprocessing unit performs the postprocessing operation on the second preprocessed signal when the second preprocessed signal does not satisfy the second input criterion, to generate a second postprocessed signal, and the extraction unit extracts the second preprocessed signal as second extracted data when the second preprocessed signal satisfies the second input criterion, and extracts the second postprocessed signal as second extracted data when the second postprocessed signal satisfies the second input criterion.
The data extraction system according to claim 4, wherein the input criterion is a signal-to-noise ratio.
The data extraction system according to claim 5, wherein the postprocessing unit performs arithmetic mean or moving average as the postprocessing operation.
The data extraction system according to claim 1, wherein the setting unit further sets another input criterion different from the input criterion, the postprocessing unit performs the postprocessing operation on the preprocessed signal when the preprocessed signal does not satisfy the other input criterion, to further generate another postprocessed signal, and the extraction unit further extracts the preprocessed signal as other extracted data when the preprocessed signal satisfies the other input criterion, and further extracts the postprocessed signal as other extracted data when the other postprocessed signal satisfies the other input criterion.
The data extraction system according to claim 1, further comprising an abnormality determination unit that determines abnormality based on the input signal, the preprocessed signal, or the postprocessed signal, and invalidates the extracted data when abnormality is detected.
The data extraction system according to claim 8, wherein the abnormality determination unit detects abnormality of a culture medium based on a decrease in dissolved oxygen amount.
The data extraction system according to claim 8, wherein the abnormality determination unit detects abnormality of electrode potential based on correlation between dissolved oxygen amount or pH and electrode potential.
A data extraction method executed by a data extraction system including at least one processor, the data extraction method comprising: a step of setting an input criterion indicating performance required for data analysis; a step of acquiring an input signal indicating a measurement result of a measurement object in bioproduction; a step of performing a preprocessing operation on the input signal for comparison with the input criterion to generate a preprocessed signal; a step of performing a postprocessing operation using another signal indicating the measurement result of the measurement object on the preprocessed signal when the preprocessed signal does not satisfy the input criterion, to generate a postprocessed signal; and a step of extracting the preprocessed signal as extracted data when the preprocessed signal satisfies the input criterion, and extracting the postprocessed signal as extracted data when the postprocessed signal satisfies the input criterion.
A data extraction program for causing a computer to execute: a step of setting an input criterion indicating performance required for data analysis; a step of acquiring an input signal indicating a measurement result of a measurement object in bioproduction; a step of performing a preprocessing operation on the input signal for comparison with the input criterion to generate a preprocessed signal; a step of performing a postprocessing operation using another signal indicating the measurement result of the measurement object on the preprocessed signal when the preprocessed signal does not satisfy the input criterion, to generate a postprocessed signal; and a step of extracting the preprocessed signal as extracted data when the preprocessed signal satisfies the input criterion, and extracting the postprocessed signal as extracted data when the postprocessed signal satisfies the input criterion.
A data extraction system that acquires an optical spectrum measured by optical spectroscopic measurement in bioproduction, and outputs a signal obtained by calculating relative intensity with a signal level of the optical spectrum in a wavelength range that does not respond to a change in a culture medium and where a transmittance does not become zero with respect to the optical spectrum.

Description

Technical Field The present disclosure relates to a data extraction system, a data extraction method, and a data extraction program. Background Art A technique for measuring a temporal change of a substance by a sensor is known. Patent Document 1 discloses a technique for detecting presence or absence of abnormality of a culture medium. The technique described in Patent Document 1 obtains a state of distribution of characteristic values of the culture medium, and sets a threshold value for abnormality determination based on the state of distribution. Patent Document 2 discloses a technique for analyzing deterioration of plastic materials and the like. The technique described in Patent Document 2 performs second-order differential processing on near-infrared spectrum data of plastic materials and the like obtained by near-infrared spectroscopy to obtain corrected spectrum data. Citation List Patent Literature [Patent Literature 1] Japanese Patent No. 6977977[Patent Literature 2] Japanese Unexamined Patent Publication No. 2022-7236 Summary of Invention Technical Problem It is desired to improve quality of data used for analysis. Solution to Problem A data extraction system according to one aspect of the present disclosure includes: a setting unit that sets an input criterion indicating performance required for data analysis; an input unit that acquires an input signal indicating a measurement result of a measurement object in bioproduction; a preprocessing unit that performs a preprocessing operation on the input signal for comparison with the input criterion to generate a preprocessed signal; a postprocessing unit that performs a postprocessing operation using another signal indicating the measurement result of the measurement object on the preprocessed signal when the preprocessed signal does not satisfy the input criterion, to generate a postprocessed signal; and an extraction unit that extracts the preprocessed signal as extracted data when the preprocessed signal satisfies the input criterion, and extracts the postprocessed signal as extracted data when the postprocessed signal satisfies the input criterion. In the data extraction system according to one aspect of the present disclosure, the preprocessing operation is performed on the input signal to generate the preprocessed signal. Then, the preprocessed signal and the input criterion indicating performance required for data analysis are compared. When the preprocessed signal satisfies the input criterion, the preprocessed signal is extracted as the extracted data. On the other hand, when the preprocessed signal does not satisfy the input criterion, the postprocessing operation is performed on the preprocessed signal to generate the postprocessed signal. Then, the postprocessed signal and the input criterion are compared. When the postprocessed signal satisfies the input criterion, the postprocessed signal is extracted as the extracted data. Thereby, the extracted data whose quality is ensured can be extracted. As a result, the quality of data used for analysis can be improved. Advantageous Effects of Invention According to the present disclosure, it is possible to provide a technique capable of improving quality of data used for analysis. Brief Description of Drawings FIG. 1 is a diagram schematically showing a configuration of a data extraction system according to a first embodiment.FIG. 2 is a schematic diagram showing an example of operation of the data extraction system.FIG. 3 is a diagram showing an example of optical spectroscopic measurement in bioproduction.FIGS. 4(a) to 4(c) are graphs exemplifying extraction of a change in organic molecule concentration in near-infrared spectroscopic measurement.FIG. 5 is a schematic diagram showing another example of operation of the data extraction system.FIG. 6 is a schematic diagram showing still another example of operation of the data extraction system.FIGS. 7(a) to 7(d) are graphs showing an example for explaining an effect by the preprocessing operation and setting of the input criterion.FIGS. 8(a) to 8(d) are graphs showing another example for explaining an effect by the preprocessing operation and setting of the input criterion.FIG. 9 is an overall diagram showing an example of application of the data extraction system according to an embodiment.FIG. 10 is a diagram showing an example of overall operation of a bioproduction system including the data extraction system.FIG. 11 is a diagram showing an example of operation of the data extraction system.FIG. 12 is a diagram showing an example of hardware configuration related to the data extraction system. Description of Embodiment Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the description of the drawings, same reference numerals are assigned to same elements, and overlapping description is omitted. [Overview] The data extraction system of the present disclosure extracts data measured by a sen