US 12,072,323 B2
Analyzer configured to display list of target components
Yohei Yamada, Kyoto (JP); Shinji Kanazawa, Kyoto (JP); Hiroyuki Yasuda, Kyoto (JP); Akihiro Kunisawa, Kyoto (JP); Yuzi Kanazawa, Tokyo (JP); and Yusuke Hida, Atsugi (JP)
Assigned to SHIMADZU CORPORATION, Kyoto (JP); and FUJITSU LIMITED, Kawasaki (JP)
Appl. No. 17/600,892
Filed by SHIMADZU CORPORATION, Kyoto (JP); and FUJITSU LIMITED, Kawasaki (JP)
PCT Filed May 8, 2019, PCT No. PCT/JP2019/018338
§ 371(c)(1), (2) Date Oct. 1, 2021,
PCT Pub. No. WO2020/225864, PCT Pub. Date Nov. 12, 2020.
Prior Publication US 2022/0196615 A1, Jun. 23, 2022
Int. Cl. G01N 30/86 (2006.01)
CPC G01N 30/8634 (2013.01) [G01N 30/8693 (2013.01)] 14 Claims
OG exemplary drawing
 
1. An analyzer configured to acquire a chromatogram or a spectrum by performing a predetermined analysis of a sample, and configured, based on the chromatogram or the spectrum, to perform a qualitative analysis or a quantitative analysis of target components contained in the sample,
the analyzer comprising:
a peak detection unit configured to detect a peak or peaks in the chromatogram or the spectrum acquired by the predetermined analysis of the sample corresponding to one of the target components, configured to acquire peak information regarding each of the peak or peaks, and configured to obtain confidence information for each of the peak or peaks, the confidence information being an indicative value of certainty of detecting a peak; and
a display processing unit configured to display on a display unit a list of at least a part of the target components, the list describing the target components in correspondence to the confidence information for each of the peak or peaks detected by the peak detection unit, each of the peak or peaks corresponding to one of the target components included in the list, or describing the target components in correspondence to other information obtained based on the confidence information,
wherein
the peak detection unit uses a learned model that is previously constructed by machine learning based on a plurality of chromatograms or spectrums, where a start point and an end point of the peaks are known, and presumes the peak information including at least one of a position of a start point and a position of an end point in one of or a plurality of the peaks appearing in the chromatogram or the spectrum related to the sample, and
the confidence information corresponds to an indicative value of certainty of presuming the peak information.