Laboratory information management-oriented whole-process information input and checking method

Abstract

The present application relates to the technical field of electronic digital data processing, in particular to a full-process information input and check method for laboratory information management, which determines chromatograms of different wavelengths of materials in different process links of laboratory information input, and determines historical standard chromatograms of different wavelengths of materials in several tests, extracts first feature vectors of all chromatographic peaks in the chromatograms of different wavelengths and corresponding second feature vectors of all chromatographic peaks in the historical standard chromatograms of different wavelengths in each test to determine feature difference condition values of each target chromatographic peak corresponding to different wavelengths, determines overall matching condition values of the chromatograms and the historical standard chromatograms under different wavelengths and overall feature difference values of the materials to reflect the difference conditions, reduces the interference of chromatographic peak position deviation, and is conducive to determining accurate check results according to the overall matching condition values and the overall feature difference values.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, specifically to a full-process information entry and verification method for laboratory information management. Background Technology

[0002] Traditional Laboratory Information Management Systems (LIMS) primarily focus on recording and comparing textual information such as material details, reagent batches, and operating procedures, effectively reducing manual data entry errors and traceability challenges. However, relying solely on information-level verification cannot guarantee that the materials actually used in the experiment are in a qualified state. For example, laboratory information entry is typically assigned to different testing personnel based on a designed entry process. This process may involve storage, transportation, use, post-use storage, or re-transportation, potentially leading to contamination, degradation, or leakage. These issues often cannot be detected through simple textual information verification. Currently, some solutions involve comparing the chromatographic results of materials with those of standard materials. However, chromatographic results are easily affected by instrument status and operating conditions (such as flow rate, column temperature, and gradient ratios), resulting in retention time drift. This causes deviations in the chromatographic peak positions of the same substance in different experiments. Therefore, direct chromatographic comparison can easily lead to false positives due to "peak mismatch," resulting in misjudgments of material abnormalities. Summary of the Invention

[0003] To address the aforementioned technical problems, the present invention aims to provide a full-process information entry and verification method for laboratory information management. The specific technical solution adopted is as follows:

[0004] This application provides a full-process information entry and verification method for laboratory information management, including:

[0005] In different stages of laboratory information entry, chromatograms of materials at different wavelengths were determined, as well as historical standard chromatograms of materials at different wavelengths in several tests.

[0006] The first feature vector of all chromatographic peaks in the chromatograms of different wavelengths and the second feature vector of all chromatographic peaks in the historical standard chromatograms of different wavelengths for each test are extracted respectively. Based on the first feature vector and the second feature vector of the chromatographic peaks of the same wavelength, the feature difference values ​​of each target chromatographic peak at different wavelengths are determined respectively.

[0007] Based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths, determine the overall matching value between the chromatogram and the historical standard chromatogram at different wavelengths, as well as the overall characteristic difference value of the material;

[0008] The verification result is determined based on the overall matching value and the overall feature difference value.

[0009] In one embodiment, the step of extracting the first feature vector of all chromatographic peaks in the chromatograms at different wavelengths and the corresponding second feature vector of all chromatographic peaks in the historical standard chromatograms for each test at different wavelengths, and determining the feature difference values ​​corresponding to each target chromatographic peak at different wavelengths based on the first feature vector and the second feature vector corresponding to the chromatographic peaks at the same wavelength, includes:

[0010] The retention time, peak height, and peak width features of all chromatographic peaks in the chromatograms at different wavelengths are extracted to obtain the first feature vector of each chromatographic peak. The retention time, peak height, and peak width features of all chromatographic peaks in the historical standard chromatograms at different wavelengths for each test are extracted to obtain the second feature vector of each chromatographic peak.

[0011] Based on the first characteristic vector of each chromatographic peak in the chromatogram at different wavelengths, determine the first average characteristic vector of all chromatographic peaks corresponding to each wavelength, and based on the second characteristic vector of each chromatographic peak in the historical standard chromatogram at different wavelengths for each test, determine the second average characteristic vector of all chromatographic peaks corresponding to each wavelength for each test.

[0012] Based on the first average eigenvector and the second average eigenvector, determine the stability value corresponding to each test at each wavelength;

[0013] Based on the stability values ​​and the dynamic time warping algorithm, the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths are determined.

[0014] In one implementation, determining the stability value corresponding to each test at each wavelength based on the first average eigenvector and the second average eigenvector includes:

[0015] Determine the first difference feature value between the first average feature vector at each wavelength and the second average feature vector at the same wavelength for each test;

[0016] Based on the second average eigenvector at different wavelengths in each test, determine the variance of the second average eigenvector corresponding to each wavelength;

[0017] Based on each of the first difference feature values ​​and each of the variances, the stability value corresponding to each test at each wavelength is determined.

[0018] In one implementation, determining the stability value corresponding to each test at each wavelength based on each of the first difference feature values ​​and each of the variances includes:

[0019] Based on the first difference feature value corresponding to each wavelength and the variance corresponding to the same wavelength in each test, the variance contribution rate corresponding to each test is determined.

[0020] The normalized value of the variance contribution rate corresponding to each test and the sum of the normalized values ​​of the variance corresponding to each wavelength of each test are determined to obtain the stability value corresponding to each test at each wavelength.

[0021] In one embodiment, determining the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths based on the stability value and the dynamic time warping algorithm includes:

[0022] By using a dynamic time warping algorithm, the first feature vector of each chromatographic peak in the chromatograms of different wavelengths and the second feature vector of each chromatographic peak in each test at different wavelengths are matched to determine each matching chromatographic peak in the historical standard chromatograms of each test at different wavelengths, and to determine the number of each matching chromatographic peak in all tests.

[0023] Based on the second feature vector of each matching chromatographic peak at different wavelengths in each test and the first feature vector corresponding to that matching chromatographic peak, the second difference feature value corresponding to each matching chromatographic peak at different wavelengths in each test is determined.

[0024] The quantitative characteristic difference corresponding to each matching chromatographic peak is determined based on the first product of each second difference characteristic value and each of the stable condition values ​​and the natural exponential function. The characteristic difference value corresponding to each matching chromatographic peak at different wavelengths is determined by summing and averaging the quantitative characteristic difference, the number of occurrences and the total number of tests. The target chromatographic peak is the matching chromatographic peak.

[0025] In one embodiment, determining the overall matching value between the chromatogram at different wavelengths and the historical standard chromatogram based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths includes:

[0026] The characteristic difference values ​​corresponding to each matching chromatographic peak at different wavelengths are compared with the characteristic difference threshold. The matching chromatographic peaks at different wavelengths corresponding to the characteristic difference values ​​that are less than the characteristic difference threshold are zeroed out to obtain updated chromatograms at different wavelengths.

[0027] Based on the stability value corresponding to each test at each wavelength, the overall stability value of the historical test corresponding to each wavelength is determined, and the summation is performed based on the second difference characteristic value corresponding to each matching chromatographic peak in the updated chromatogram to determine the total matching difference characteristic value of the historical test corresponding to each matching chromatographic peak in the updated chromatogram of each wavelength.

[0028] Based on the characteristic difference values ​​corresponding to each matching chromatographic peak, the total matching difference characteristic value corresponding to each matching chromatographic peak, and the number of matching chromatographic peaks corresponding to each wavelength in the updated chromatograms at different wavelengths, combined with the overall stability value and the total number of wavelengths, the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms is determined.

[0029] In one embodiment, determining the overall matching value between the chromatogram and the historical standard chromatogram at different wavelengths, based on the characteristic difference values ​​corresponding to each matching chromatographic peak, the total matching difference characteristic value corresponding to each matching chromatographic peak, and the number of matching chromatographic peaks corresponding to each wavelength in the updated chromatograms at different wavelengths, combined with the overall stability value and the total number of wavelengths, includes:

[0030] The overall stability value is obtained by summing the overall stability value and the total number of wavelengths, and then by calculating the second difference characteristic value corresponding to each matched chromatographic peak at different wavelengths.

[0031] In the updated chromatograms of different wavelengths, the characteristic difference value corresponding to each matching chromatographic peak and the second product of the total matching difference characteristic value corresponding to each matching chromatographic peak are determined respectively. The total characteristic difference value is obtained by summing the second products and the number of matching chromatographic peaks corresponding to each wavelength.

[0032] Based on the overall stability value and the overall characteristic difference value, the overall matching value between the chromatogram at different wavelengths and the historical standard chromatogram is determined.

[0033] In one embodiment, determining the overall characteristic difference value of the material based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths includes:

[0034] The matching value corresponding to the chromatographic peak with matching chromatographic peaks in the updated chromatograms of different wavelengths is set as the first value, and the matching value corresponding to the chromatographic peak without matching chromatographic peaks is set as the second value.

[0035] Determine the peak area and number of each chromatographic peak in the updated chromatograms at different wavelengths. Based on the peak area, number of chromatographic peaks, matching value corresponding to each chromatographic peak, and characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms at different wavelengths, determine the overall characteristic difference value of the material.

[0036] In one embodiment, determining the overall characteristic difference value of the material based on the peak area, the number of chromatographic peaks, the matching value corresponding to each chromatographic peak, and the characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms of different wavelengths includes:

[0037] The peak area of ​​each chromatographic peak, the matching value corresponding to each chromatographic peak, and the third product of the characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms of different wavelengths are determined respectively.

[0038] The overall characteristic difference value of the material is obtained by summing the third product, the number of chromatographic peaks, and the total number of wavelengths.

[0039] In one implementation, determining the verification result based on the overall matching value and the overall feature difference value includes:

[0040] The largest overall match value is determined from all the overall match values ​​and used as the target overall match value;

[0041] The probability value of the material being normal is determined based on the fourth product of the overall target matching value and the overall feature difference value.

[0042] When the probability value is less than the probability threshold, the verification result representing the anomaly is determined.

[0043] The present invention has the following beneficial effects:

[0044] By determining chromatograms of materials at different wavelengths at different stages of laboratory information entry, and by identifying historical standard chromatograms of materials at different wavelengths in several tests, the first feature vector of all chromatographic peaks in the chromatograms at different wavelengths and the corresponding second feature vector of all chromatographic peaks in the historical standard chromatograms at different wavelengths for each test are extracted. Based on the first and second feature vectors corresponding to chromatographic peaks at the same wavelength, the feature difference values ​​corresponding to each target chromatographic peak at different wavelengths are determined. Based on the feature difference values ​​corresponding to each target chromatographic peak at different wavelengths, the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms, as well as the overall feature difference value of the material, are determined. By analyzing the feature difference values ​​between the chromatograms at different wavelengths and the historical standard chromatograms, the overall matching value and the overall feature difference value of the material are determined to reflect the differences. This helps to reduce the interference caused by chromatographic peak position deviations, increases the robustness of comparative analysis, and thus facilitates the determination of more accurate verification results based on the overall matching value and the overall feature difference value. Attached Figure Description

[0045] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the steps of a full-process information entry and verification method for laboratory information management provided in an embodiment of the present invention. Detailed Implementation

[0047] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of the full-process information entry and verification method for laboratory information management proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0049] It should be noted that "exemplary" in the embodiments of this application refers to examples listed for ease of explanation, and other embodiments are not limited to the listed examples.

[0050] The specific solution of the full-process information entry and verification method for laboratory information management provided by the present invention will be described in detail below with reference to the accompanying drawings.

[0051] Please see Figure 1 The diagram illustrates a flowchart of a full-process information entry and verification method for laboratory information management provided by an embodiment of the present invention. This full-process information entry and verification method for laboratory information management may include at least steps S100-S400:

[0052] S100. Determine the chromatograms of materials at different wavelengths in different stages of laboratory information entry, and determine the historical standard chromatograms of materials at different wavelengths in several tests.

[0053] S200. Extract the first feature vector of all chromatographic peaks in the chromatograms of different wavelengths and the corresponding second feature vector of all chromatographic peaks in the historical standard chromatograms of different wavelengths for each test. Based on the first feature vector and the second feature vector of the chromatographic peaks at the same wavelength, determine the feature difference values ​​of each target chromatographic peak at different wavelengths.

[0054] S300. Based on the characteristic differences of each target chromatographic peak at different wavelengths, determine the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms, as well as the overall characteristic differences of the materials.

[0055] S400. Determine the verification result based on the overall matching value and the overall feature difference value.

[0056] The technical solution of this application embodiment determines the chromatograms of materials at different wavelengths in different process steps of laboratory information entry, and determines the historical standard chromatograms of materials at different wavelengths in several tests. It extracts the first feature vector of all chromatographic peaks in the chromatograms at different wavelengths and the corresponding second feature vector of all chromatographic peaks in the historical standard chromatograms at different wavelengths for each test. Based on the first and second feature vectors corresponding to the chromatographic peaks at the same wavelength, it determines the feature difference value corresponding to each target chromatographic peak at different wavelengths. Based on the feature difference value corresponding to each target chromatographic peak at different wavelengths, it determines the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms, as well as the overall feature difference value of the material. By analyzing the feature difference values ​​between the chromatograms at different wavelengths and the historical standard chromatograms, it determines the overall matching value and the overall feature difference value of the material to reflect the differences. This helps to reduce the interference caused by chromatographic peak position deviation, increases the robustness of comparative analysis, and thus helps to determine more accurate verification results based on the overall matching value and the overall feature difference value.

[0057] In one implementation, materials (such as reagents, prepared solutions, soil sediments, blood, etc.) are typically assigned to different testing personnel based on a designed data entry process during laboratory information entry. This process includes, but is not limited to, storage, transfer, use, post-use storage, or re-transfer. During final data entry, basic information such as material name, serial number, source, quantity, collection time, storage conditions, and chromatogram are usually recorded, and a traceability barcode is generated. Typically, in subsequent management, the matching between the current material's chromatogram and the standard chromatogram is compared to analyze whether the stored material has decomposed, become contaminated, or leaked, avoiding information loss due to simply verifying the material name. However, chromatogram comparisons may be affected by parameter fluctuations due to different operating conditions (such as flow rate, column temperature, gradient ratio) or environmental conditions, causing peak positions of the same substance to deviate in different experiments. Direct chromatographic comparison is prone to false positives due to "peak mismatch," therefore, results cannot be obtained directly by comparing the current material's chromatogram with the standard chromatogram.

[0058] In this embodiment, materials are sampled at each stage of the process, and diluted or pretreated as necessary to reduce interference from complex matrices. The sampled materials are then separated and detected using high-performance liquid chromatography (HPLC) or gas chromatography (GC), thereby determining chromatograms of different wavelengths for the materials at different process stages (i.e., at different times). Baseline correction, retention time alignment, and normalization are performed on the chromatograms to reduce apparent deviations caused by differences in operating conditions. This facilitates subsequent comparison with historical standard chromatograms, identifying peak position deviations and impurity peak deviations (differences), and verifying whether the materials exhibit abnormalities. It should be noted that when inputting materials of the same type from previous periods, anomaly tests are conducted at different wavelengths at different process stages. Chromatograms corresponding to different wavelengths at different process stages that show normal results (i.e., normal material chromatograms) are selected. Each process stage has at least one normal chromatogram corresponding to different wavelengths, resulting in historical standard chromatograms of the materials at different wavelengths from several (historical) tests.

[0059] It should be noted that, since the material may be a complex matrix containing multiple chromatographic peaks, and parameter fluctuations can cause temporal shifts in the obtained chromatographic peaks, it is necessary to consider the time series corresponding to the shifts of multiple chromatographic peaks at different wavelengths, i.e., chromatograms at different wavelengths at different process stages (i.e., different times) for comprehensive analysis. Furthermore, if the material is a complex matrix, direct matching may lead to poor matching results due to the high content of substances within the complex matrix. This is because complex matrices may exhibit chromatogram diversity in laboratory tests (the main component remains constant, but its subtle components may differ). This diversity will cause some variation in the chromatograms obtained from each measurement, but the chromatographic peaks of the main components should remain constant. Therefore, it is advisable to analyze the historical distribution of substances in the complex matrix and construct multi-wavelength matrix fingerprints for matching, thereby increasing the robustness of the matching.

[0060] In one implementation, step S200 includes steps S201-S204:

[0061] S201. Extract the retention time, peak height, and peak width features of all chromatographic peaks in chromatograms of different wavelengths to obtain the first feature vector of each chromatographic peak. Extract the retention time, peak height, and peak width features of all chromatographic peaks in historical standard chromatograms of different wavelengths for each test to obtain the second feature vector of each chromatographic peak.

[0062] Optionally, the retention time, peak height, and peak width features of all chromatographic peaks in chromatograms at different wavelengths are extracted to obtain the first feature vector of each chromatographic peak. Similarly, the retention time, peak height, and peak width features of all chromatographic peaks in historical standard chromatograms from each test at different wavelengths are extracted to obtain the second feature vector of each chromatographic peak. It should be noted that both the first and second feature vectors are in the form of... , For the duration of stay, For the peak height, The width of the peak.

[0063] S202. Based on the first characteristic vector of each chromatographic peak in the chromatograms of different wavelengths, determine the first average characteristic vector of all chromatographic peaks corresponding to each wavelength, and based on the second characteristic vector of each chromatographic peak in the historical standard chromatograms of different wavelengths for each test, determine the second average characteristic vector of all chromatographic peaks corresponding to each wavelength for each test.

[0064] Optionally, after determining the first eigenvector of each chromatographic peak in the chromatograms at different wavelengths, the first average eigenvector of all chromatographic peaks corresponding to each wavelength is determined by averaging. Similarly, the second average eigenvector of all chromatographic peaks corresponding to each wavelength in each test can be determined based on the second eigenvectors. Likewise, the first and second average eigenvectors have the same form, with the first average eigenvector... For example, it means the first The average eigenvector of each chromatographic peak For the first The average retention time corresponding to each chromatographic peak, For the first The average peak height corresponding to each chromatographic peak, For the first The average peak width corresponding to each chromatographic peak.

[0065] S203. Based on the first average eigenvector and the second average eigenvector, determine the stability value corresponding to each test at each wavelength.

[0066] First, determine the first difference feature value between the first average feature vector at each wavelength and the second average feature vector at the same wavelength for each test.

[0067] Optionally, differential eigenvalues The calculation can refer to the prior Euclidean distance calculation formula, the specific formula is:

[0068]

[0069] in, This represents the difference between the mean residence time in the first average eigenvector and the mean residence time in the second average eigenvector for the same wavelength. This represents the difference between the average peak height in the first average eigenvector and the average peak height in the second average eigenvector for the same wavelength. This is the difference between the average peak width of the first average eigenvector and the average peak width of the second average eigenvector at the same wavelength. Therefore, based on the principle of the above calculation formula, the first difference eigenvalue between the first average eigenvector at each wavelength and the corresponding second average eigenvector at the same wavelength for each test can be calculated. That is, the first The chromatogram at the wavelength and the corresponding wavelength The characteristic values ​​of the differences between the historical standard chromatograms of this test.

[0070] It should be noted that, for ease of calculation, all indicator data involved in the calculation in this embodiment of the invention have undergone data preprocessing to eliminate the influence of dimensions. The specific methods for eliminating the influence of dimensions are well known to those skilled in the art and are not limited here.

[0071] Secondly, based on the second average eigenvector at different wavelengths in each test, the variance of the second average eigenvector corresponding to each wavelength is determined. That is, in multiple tests, the first The variance of the second average eigenvector corresponding to each wavelength.

[0072] Then, based on each first difference eigenvalue In addition to the variances, the stable values ​​corresponding to each test at each wavelength are determined.

[0073] Specifically, based on the first difference characteristic value corresponding to each wavelength And the variance corresponding to each test at the same wavelength The ratio is used to determine the variance contribution rate for each test. That is, the first The variance contribution rate of the differential eigenvalues ​​in each test to the overall variance; determine the variance contribution rate for each test. The normalized value and the variance corresponding to each wavelength in each test The sum of the normalized values ​​yields the stable condition value for each test at each wavelength:

[0074]

[0075] in, For the first The first wavelength The stability value corresponding to this test, in some embodiments, can be used if comparing multiple materials. It means, that is, the first The material in the first The first wavelength The stability values ​​corresponding to this test are based on a single material in this application embodiment. The processing principle is the same for multiple materials, and will not be repeated here. It should be noted that the above analysis is of the overall characteristic changes of the chromatographic peaks at each wavelength. When there are influencing substances in the obtained complex matrix that cause baseline drift, it will affect the size of the chromatographic peak. For example, the peak value will decrease and the width will also become smaller, but the residence time may remain unchanged.

[0076] Here, norm represents linear normalization, specifically maximum and minimum value normalization, which is used to further eliminate the influence of dimensions in the addition calculation process.

[0077] S204. Based on the stable condition value and the dynamic time warping algorithm, determine the characteristic difference value corresponding to each target chromatographic peak at different wavelengths.

[0078] First, using the Dynamic Time Warping (DTW) algorithm, the first feature vectors of each chromatographic peak in the chromatograms of different wavelengths are matched with the second feature vectors of each chromatographic peak in each test at different wavelengths. This identifies the matching chromatographic peaks present in the historical standard chromatograms of each test at different wavelengths, and determines the number of each matching chromatographic peak present in all tests. That is, the first The number of matching chromatographic peaks present in all tests is considered, as there may be cases where a chromatographic peak disappears in historical tests. In the embodiments of this application, the target chromatographic peak is a matching chromatographic peak.

[0079] Secondly, based on the second eigenvector of each matching chromatographic peak at different wavelengths in each test and the first eigenvector corresponding to that matching chromatographic peak, the second difference eigenvalue corresponding to each matching chromatographic peak at different wavelengths in each test is determined. It can be understood that, similarly based on the difference eigenvalue... The formula principle is used to calculate and determine the second difference characteristic value. That is, the first The first wavelength of the chromatogram The matching chromatographic peak and its corresponding first peak The first historical standard chromatogram of the test The difference characteristic values ​​between the matched chromatographic peaks.

[0080] Then, based on each second difference eigenvalue... With each steady-state value The first product and the natural exponential function Determine the quantitative characteristic differences corresponding to each matched chromatographic peak. And based on the differences in quantitative characteristics Quantity and the total number of tests By summing and averaging, the characteristic differences of each target chromatographic peak (matching chromatographic peak) at different wavelengths are determined:

[0081]

[0082] in, For the first The first wavelength The larger the characteristic difference value corresponding to each matching chromatographic peak, the greater the deviation. When the characteristic difference value is small, it indicates that the matching chromatographic peak is relatively stable in historical tests. Therefore, more matching information needs to be provided when matching the chromatographic peak in subsequent tests.

[0083] In one embodiment, step S300 determines the overall matching value between the chromatograms at different wavelengths and historical standard chromatograms based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths, including steps S301-S303:

[0084] S301. Compare the characteristic difference values ​​corresponding to each matching chromatographic peak at different wavelengths with the characteristic difference threshold. For each matching chromatographic peak at different wavelengths with a characteristic difference value less than the characteristic difference threshold, zero out the characteristic difference values ​​to obtain updated chromatograms at different wavelengths.

[0085] For example, the feature difference threshold is 0.4, which represents the feature difference values ​​corresponding to each matched chromatographic peak at different wavelengths. Compared with the feature difference threshold of 0.4, the matching chromatographic peaks at different wavelengths corresponding to feature difference values ​​less than the feature difference threshold are zeroed out to obtain updated chromatograms at different wavelengths, thus avoiding interference from matching chromatographic peaks less than the feature difference threshold during subsequent matching.

[0086] S302. Based on the stability value corresponding to each test at each wavelength, determine the overall stability value of the historical test corresponding to each wavelength, and sum the second difference characteristic values ​​corresponding to each matching chromatographic peak in the updated chromatogram to determine the total matching difference characteristic value of the historical test corresponding to each matching chromatographic peak in the updated chromatogram of each wavelength.

[0087] Optionally, based on the stability value corresponding to each test at each wavelength. Summation is performed to determine the overall stability value of historical tests for each wavelength. That is, the first The overall stability value of historical tests corresponding to each wavelength; based on the second difference characteristic value corresponding to each matching chromatographic peak in the updated chromatogram. Summation is performed to determine the total matching difference characteristic value of historical tests corresponding to each matching peak in the updated chromatogram of each wavelength. That is, the first The updated chromatogram of the first wavelength The total matching difference characteristic value of historical tests corresponding to each matching chromatographic peak.

[0088] It should be noted that when performing chromatogram and standard chromatogram analysis, the matching of different wavelengths should be consistent. Chromatographic peaks are related to substances, and their time series changes reflect the changes of chromatographic peaks over time. At the same time, their time changes should be consistent at different wavelengths, and wavelength changes do not affect the detection of the same substance at the current time.

[0089] S303. Based on the characteristic difference values ​​corresponding to each matching chromatographic peak, the total matching difference characteristic value corresponding to each matching chromatographic peak, and the number of matching chromatographic peaks corresponding to each wavelength in the updated chromatograms at different wavelengths, combined with the overall stability value and the total number of wavelengths, determine the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms.

[0090] First, based on the overall stability value and the total number of wavelengths Summation is performed to obtain the overall stable value. .

[0091] Secondly, the characteristic difference values ​​corresponding to each matching chromatographic peak in the updated chromatograms at different wavelengths were determined. Total matching difference characteristic value corresponding to each matching chromatographic peak The second product, and based on each second product and the number of matched chromatographic peaks corresponding to each wavelength. Perform summation to obtain the total characteristic difference value. .

[0092] Then, based on the overall stability value and the overall characteristic difference value, the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms is determined, using the following formula:

[0093]

[0094] in, This represents the overall matching value between the chromatogram and historical standard chromatograms.

[0095] In one embodiment, step S300 determines the overall characteristic difference value of the material based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths, including steps S304-S305:

[0096] S304. Set the matching value corresponding to the chromatographic peak with matching chromatographic peak in the updated chromatogram of different wavelengths as the first value, and set the matching value corresponding to the chromatographic peak without matching chromatographic peak as the second value.

[0097] Optionally, the matching values ​​corresponding to the matching peaks in the updated chromatograms of different wavelengths can be used. (i.e., the first) The updated chromatogram of the first wavelength contains the first wavelength. The matching value corresponding to each matching chromatographic peak is set to the first value (e.g., 0), and the matching value corresponding to the chromatographic peak for which there is no matching chromatographic peak is set to the second value (e.g., 1).

[0098] S305. Determine the peak area and number of each chromatographic peak in the updated chromatograms of different wavelengths. Based on the peak area, number of chromatographic peaks, matching value corresponding to each chromatographic peak, and characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms of different wavelengths, determine the overall characteristic difference value of the material.

[0099] First, determine the peak area of ​​each target chromatographic peak (i.e., the matched chromatographic peak) in the updated chromatograms at different wavelengths. (i.e., the first) The updated chromatogram of the first wavelength The peak area of ​​each matched chromatographic peak (the larger the area, the stronger the performance and the greater the influence), and the matching value corresponding to each chromatographic peak. and the characteristic differences of each target chromatographic peak The third product .

[0100] Secondly, based on each third product and the number of chromatographic peaks (i.e., the first) The number of chromatographic peaks in the updated chromatogram for each wavelength and the total number of wavelengths. Summation is performed to obtain the overall characteristic difference value of the material. , specific formula:

[0101]

[0102] In one embodiment, step S400 includes steps S401-S403:

[0103] S401. Determine the largest overall match value from all overall match values ​​and use it as the target overall match value.

[0104] Optionally, the largest overall match value is determined from all overall match values ​​and used as the target overall match value.

[0105] S402. Determine the probability value of the material being normal based on the fourth product of the overall target matching value and the overall characteristic difference value.

[0106] Optionally, the probability value of the material being normal is determined based on the fourth product of the overall target matching value and the overall feature difference value. In some embodiments of the present invention, the fourth product can be directly normalized and mapped to the range of [0,1] to obtain the probability value. The specific normalization method can be linear normalization of the maximum and minimum values, or other normalization methods can be used, and there are no restrictions on this.

[0107] It should be noted that the larger the value of the fourth product, the greater the probability that the material verification is normal. In this case, the probability value of the material being normal can be compared with the probability threshold.

[0108] S403. When the probability value is less than the probability threshold, determine the verification result that represents the anomaly.

[0109] Optionally, if the probability value is less than the probability threshold, the verification result is determined to be abnormal, indicating that there is a problem with the current material, requiring a second verification operation or reporting. Understandably, if the probability value is greater than or equal to the probability threshold, the verification result is determined to be normal.

[0110] For example, the probability threshold can be specifically 0.5, and the above steps indicate that the probability value ranges from [0,1]. That is, when the probability value is less than 0.5, the verification result is determined to be abnormal, while when the probability value is greater than or equal to 0.5, the verification result is determined to be normal. When the result is abnormal, a second verification operation or reporting is required. When the result is normal, no related second verification or reporting operation is required.

[0111] The method in this application uses dynamic time warping (DTW) to match chromatograms of different wavelengths at different process stages (at different times) with historical standard chromatograms, avoiding interference caused by time and parameter fluctuations. When matching complex matrices, it analyzes the historical distribution of substances in the complex matrix (such as the matching of chromatographic peaks) and constructs multiple wavelength chromatograms as matrix fingerprints for matching, which can increase the robustness of the matching.

[0112] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for full-process information entry and verification for laboratory information management, characterized in that: The method includes: In different stages of laboratory information entry, chromatograms of materials at different wavelengths were determined, as well as historical standard chromatograms of materials at different wavelengths in several tests. The first feature vector of all chromatographic peaks in the chromatograms of different wavelengths and the second feature vector of all chromatographic peaks in the historical standard chromatograms of different wavelengths for each test are extracted respectively. Based on the first feature vector and the second feature vector of the chromatographic peaks of the same wavelength, the feature difference values ​​of each target chromatographic peak at different wavelengths are determined respectively. Based on the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths, determine the overall matching value between the chromatogram and the historical standard chromatogram at different wavelengths, as well as the overall characteristic difference value of the material; The verification result is determined based on the overall matching score and the overall feature difference score. Methods for determining the characteristic differences of each target chromatographic peak at different wavelengths include: The retention time, peak height, and peak width features of all chromatographic peaks in the chromatograms at different wavelengths are extracted to obtain the first feature vector of each chromatographic peak. The retention time, peak height, and peak width features of all chromatographic peaks in the historical standard chromatograms at different wavelengths for each test are extracted to obtain the second feature vector of each chromatographic peak. Based on the first characteristic vector of each chromatographic peak in the chromatogram at different wavelengths, determine the first average characteristic vector of all chromatographic peaks corresponding to each wavelength, and based on the second characteristic vector of each chromatographic peak in the historical standard chromatogram at different wavelengths for each test, determine the second average characteristic vector of all chromatographic peaks corresponding to each wavelength for each test. Based on the first average eigenvector and the second average eigenvector, determine the stability value corresponding to each test at each wavelength; Based on the stability values ​​and the dynamic time warping algorithm, the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths are determined.

2. The full-process information entry and verification method for laboratory information management according to claim 1, characterized in that: The step of determining the stability value corresponding to each test at each wavelength based on the first average feature vector and the second average feature vector includes: Determine the first difference feature value between the first average feature vector at each wavelength and the second average feature vector at the same wavelength for each test; Based on the second average eigenvector at different wavelengths in each test, determine the variance of the second average eigenvector corresponding to each wavelength; Based on each of the first difference feature values ​​and each of the variances, the stability value corresponding to each test at each wavelength is determined.

3. The full-process information entry and verification method for laboratory information management according to claim 2, characterized in that: The step of determining the stability value corresponding to each test at each wavelength based on each of the first difference feature values ​​and each of the variances includes: Based on the first difference feature value corresponding to each wavelength and the variance corresponding to the same wavelength in each test, the variance contribution rate corresponding to each test is determined. The normalized value of the variance contribution rate corresponding to each test and the sum of the normalized values ​​of the variance corresponding to each wavelength of each test are determined to obtain the stability value corresponding to each test at each wavelength.

4. The full-process information entry and verification method for laboratory information management according to claim 1, characterized in that: The step of determining the characteristic difference values ​​corresponding to each target chromatographic peak at different wavelengths based on the stability value and the dynamic time warping algorithm includes: By using a dynamic time warping algorithm, the first feature vector of each chromatographic peak in the chromatograms of different wavelengths and the second feature vector of each chromatographic peak in each test at different wavelengths are matched to determine each matching chromatographic peak in the historical standard chromatograms of each test at different wavelengths, and to determine the number of each matching chromatographic peak in all tests. Based on the second feature vector of each matching chromatographic peak at different wavelengths in each test and the first feature vector corresponding to that matching chromatographic peak, the second difference feature value corresponding to each matching chromatographic peak at different wavelengths in each test is determined. The quantitative characteristic difference corresponding to each matching chromatographic peak is determined based on the first product of each second difference characteristic value and each of the stable condition values ​​and the natural exponential function. The characteristic difference value corresponding to each matching chromatographic peak at different wavelengths is determined by summing and averaging the quantitative characteristic difference, the number of occurrences and the total number of tests. The target chromatographic peak is the matching chromatographic peak.

5. The full-process information entry and verification method for laboratory information management according to claim 4, characterized in that: Based on the characteristic differences corresponding to each target chromatographic peak at different wavelengths, the overall matching values ​​between the chromatograms at different wavelengths and the historical standard chromatograms are determined, including: The characteristic difference values ​​corresponding to each matching chromatographic peak at different wavelengths are compared with the characteristic difference threshold. The matching chromatographic peaks at different wavelengths corresponding to the characteristic difference values ​​that are less than the characteristic difference threshold are zeroed out to obtain updated chromatograms at different wavelengths. Based on the stability value corresponding to each test at each wavelength, the overall stability value of the historical test corresponding to each wavelength is determined, and the summation is performed based on the second difference characteristic value corresponding to each matching chromatographic peak in the updated chromatogram to determine the total matching difference characteristic value of the historical test corresponding to each matching chromatographic peak in the updated chromatogram of each wavelength. Based on the characteristic difference values ​​corresponding to each matching chromatographic peak, the total matching difference characteristic value corresponding to each matching chromatographic peak, and the number of matching chromatographic peaks corresponding to each wavelength in the updated chromatograms at different wavelengths, combined with the overall stability value and the total number of wavelengths, the overall matching value between the chromatograms at different wavelengths and the historical standard chromatograms is determined.

6. The full-process information entry and verification method for laboratory information management according to claim 5, characterized in that: The determination of the overall matching value between the chromatogram and the historical standard chromatogram at different wavelengths, based on the characteristic difference values ​​corresponding to each matching chromatographic peak, the total matching difference characteristic value corresponding to each matching chromatographic peak, the number of matching chromatographic peaks corresponding to each wavelength, and the overall stability value and the total number of wavelengths in the updated chromatograms at different wavelengths, includes: The overall stability value is obtained by summing the overall stability value and the total number of wavelengths, and then by calculating the second difference characteristic value corresponding to each matched chromatographic peak at different wavelengths. In the updated chromatograms of different wavelengths, the characteristic difference value corresponding to each matching chromatographic peak and the second product of the total matching difference characteristic value corresponding to each matching chromatographic peak are determined respectively. The total characteristic difference value is obtained by summing the second products and the number of matching chromatographic peaks corresponding to each wavelength. Based on the overall stability value and the overall characteristic difference value, the overall matching value between the chromatogram at different wavelengths and the historical standard chromatogram is determined.

7. The full-process information entry and verification method for laboratory information management according to claim 5, characterized in that: Based on the characteristic differences corresponding to each target chromatographic peak at different wavelengths, the overall characteristic difference value of the material is determined, including: The matching value corresponding to the chromatographic peak with matching chromatographic peaks in the updated chromatograms of different wavelengths is set as the first value, and the matching value corresponding to the chromatographic peak without matching chromatographic peaks is set as the second value. Determine the peak area and number of each chromatographic peak in the updated chromatograms at different wavelengths. Based on the peak area, number of chromatographic peaks, matching value corresponding to each chromatographic peak, and characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms at different wavelengths, determine the overall characteristic difference value of the material.

8. The full-process information entry and verification method for laboratory information management according to claim 7, characterized in that: The determination of the overall characteristic difference value of the material based on the peak area, the number of chromatographic peaks, the matching value corresponding to each chromatographic peak, and the characteristic difference value corresponding to each target chromatographic peak in the updated chromatogram of different wavelengths includes: The peak area of ​​each chromatographic peak, the matching value corresponding to each chromatographic peak, and the third product of the characteristic difference value corresponding to each target chromatographic peak in the updated chromatograms of different wavelengths are determined respectively. The overall characteristic difference value of the material is obtained by summing the third product, the number of chromatographic peaks, and the total number of wavelengths.

9. The full-process information entry and verification method for laboratory information management according to claim 1, characterized in that: The step of determining the verification result based on the overall matching value and the overall feature difference value includes: The largest overall match value is determined from all the overall match values ​​and used as the target overall match value; The probability value of the material being normal is determined based on the fourth product of the overall target matching value and the overall feature difference value. When the probability value is less than the probability threshold, the verification result representing the anomaly is determined.

Images