Blood species identification method and related equipment

Abstract

The invention is applicable to the technical field of blood identification, and provides a blood species identification method and related equipment, and the method comprises the following steps: determining differential substances between blood of different species based on blood samples of different species, and obtaining content data of the differential substances in the blood samples of different species; constructing a data set according to the content data and the species corresponding to the content data, and generating a training set and a verification set from the data set through a resampling method; training each preset algorithm in a preset algorithm library according to the training set to obtain a target algorithm library composed of the trained preset algorithms; based on the verification set, selecting an algorithm meeting a preset requirement from the target algorithm library as a classification algorithm, and inputting the to-be-detected content data of the differential substances in the to-be-detected blood into the classification algorithm to obtain the species of the to-be-detected blood.

Description

Technical Field

[0001] The present application belongs to the technical field of blood identification, and in particular to a method for blood species identification. Background Art

[0002] Blood species identification in forensic medicine refers to determining the species of the main body of blood, that is, determining whether the blood comes from humans or animals. If it comes from animals, it is necessary to specify what kind of animal it is. Blood species identification is of great significance for criminal investigation, customs import and export inspection, and wildlife protection. In criminal investigation, the scene of the case, especially the scene of major criminal crimes, almost always involves blood. Identifying the species of blood can determine the nature of the case, which is conducive to the development of further work, and can provide the direction of investigation and narrow the scope of investigation. In terms of customs import and export inspection, the state has very strict biosafety control over human blood. Human blood (and products) without the approval or certificate of the Ministry of Health cannot be imported or exported. In comparison, the control over animal blood is relatively loose, and it is easy to disguise human blood as animal blood for customs clearance; and the uncontrolled influx of blood samples of unknown species into the country may cause the risk of biological invasion, causing economic losses or ecological disasters to my country's biodiversity, agricultural, forestry, animal husbandry and fishery production, and human health, and affecting the stability of my country's ecological environment. Therefore, it is necessary to identify the species of blood samples entering and leaving the country to prevent the leakage of human genetic information resources and the cross-border spread of infectious diseases. In terms of the protection and management of endangered wild animals, some rare wild animals are not effectively protected and are facing the risk of extinction. Blood species identification can provide more objective and accurate species information, further improve the species identification system, and provide forensic scientific evidence support for combating poaching and trafficking of endangered wild animals.

[0003] Among the existing blood species identification methods, although the morphological method is relatively simple and intuitive, the blood cell morphology of each species is not the same, so the application scope of this method is limited, the discrimination is low, and the method relies on the tester to distinguish the cell morphology, there is no accurate quantitative standard, and the results are greatly affected by subjectivity. The immunological method has a low detection limit, high sensitivity, and strong specificity, but the effects of different specific application methods are uneven, and it is easy to be disturbed and false positive results appear. DNA / RNA testing technology has high accuracy, good specificity, and low detection limit, but the detection cycle is long, the detection cost is high, the primer selection is inconvenient, and the dependence on the comparison library is high. Spectroscopy has the advantages of being simple, fast, and contactless, but due to the complex matrix composition and many interfering factors, the data processing is complicated, the instrument requirements are high, and the spectral method cannot be separated and analyzed, so it is impossible to find species difference substances, and the result interpretation ability is poor. Summary of the invention

[0004] The embodiments of the present application provide a blood species identification method and related equipment to address the problem of limitations of existing blood species identification methods.

[0005] The present application embodiment provides a method for identifying blood species, comprising the following steps:

[0006] Determine the difference substances between the blood of different species based on the blood samples of different species, and obtain the content data of the difference substances in the blood samples of different species;

[0007] Constructing a data set according to the content data and the species corresponding to the content data, and dividing the data set into a training set and a validation set according to a preset ratio;

[0008] According to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of trained preset algorithms;

[0009] Based on the verification set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substance to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected.

[0010] Optionally, the step of determining the difference substances between blood of different species based on blood samples of different species comprises:

[0011] Obtain VOC qualitative and quantitative data of blood samples from different species;

[0012] PLS-DA was used to analyze the VOC qualitative and quantitative data to determine the differential substances between the blood of different species.

[0013] Optionally, the step of using PLS-DA to analyze the VOC qualitative and quantitative data to determine the difference substances between the blood of different species includes:

[0014] Performing PLS-DA analysis on the VOC qualitative and quantitative data to obtain analytical data;

[0015] Establishing a scoring model according to the analysis data, and performing a permutation test on the scoring model to obtain a predicted sample score corresponding to the VOC qualitative and quantitative data, independent variable data corresponding to the predicted sample score, and target data corresponding to the VOC qualitative and quantitative data;

[0016] Correlation coefficient data based on the predicted sample scores and the independent variable data;

[0017] Calculate the VIP value of the independent variable data based on the target data;

[0018] The differential substances between the blood of different species are determined based on the correlation coefficient data and the VIP values.

[0019] Optionally, the step of training each preset algorithm in the preset algorithm library by a resampling method according to the training set to obtain a target algorithm library consisting of trained preset algorithms includes:

[0020] The training set is sampled using a 10-fold CV resampling method repeated 5 times to obtain target data sets for different preset algorithms;

[0021] The preset algorithm is trained according to the target data set to obtain a target algorithm library consisting of the trained preset algorithms.

[0022] Optionally, the step of selecting an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set includes:

[0023] Inputting the verification set into each trained preset algorithm in the target algorithm library to obtain a prediction result;

[0024] Calculate the index data used to characterize the performance of the preset algorithm after training according to the prediction result and the actual result of the verification set;

[0025] Based on the indicator data, an algorithm that meets preset requirements is selected in the target algorithm library as a classification algorithm.

[0026] Optionally, the indicator data includes: accuracy data, prediction effect data and mean square error data.

[0027] Optionally, the preset algorithm library includes at least: DT algorithm, Gaussian kernel function SVM algorithm, polynomial kernel function SVM algorithm, KNN algorithm, MLP algorithm, MLR algorithm, NB algorithm, XGBoost algorithm and RF algorithm.

[0028] In a second aspect, the present application provides a blood species identification device, the device comprising:

[0029] A data acquisition module, used to determine the difference substances between the blood of different species based on the blood samples of different species, and obtain the content data of the difference substances in the blood samples of different species;

[0030] A partitioning module, used to construct a data set according to the content data and the species corresponding to the content data, and to partition the data set into a training set and a validation set according to a preset ratio;

[0031] A training module, used to train each preset algorithm in the preset algorithm library by a resampling method according to the training set, so as to obtain a target algorithm library composed of the trained preset algorithms;

[0032] The prediction module is used to select an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set, and input the to-be-detected content data of the differential substance in the to-be-detected blood into the classification algorithm to obtain the species of the to-be-detected blood.

[0033] In a third aspect, the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0035] Compared with the prior art, the embodiments of the present application have the following beneficial effects: by determining the differential substances between the blood of different species based on blood samples of different species, the content data of the differential substances in the blood samples of different species are obtained; a data set is constructed according to the content data and the species corresponding to the content data, and the data set is divided into a training set and a verification set according to a preset ratio; according to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of the trained preset algorithms; based on the verification set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substances to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected. Potential biomarkers (differential substances), the model performance is evaluated by accuracy (Accuracy), area under the receiver operating characteristic curve (Receiver Operating Characteristic Curve, ROC) (Area Under Curve, AUC) and Brier score (BrierScore, BS) and the optimal classification algorithm is selected, and the optimal blood volatile organic compound classification model is obtained after hyperparameter tuning to achieve accurate classification of blood species. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 This is a flow chart of a blood species identification method provided by the present invention;

[0038] Figure 2 Sample score graphs of the PLS-DA model for human, pig, cattle, sheep, chicken, duck, rabbit, and rat blood;

[0039] Figure 3 This is the 200 permutation test graph of the PLS-DA model;

[0040] Figure 4 Scatter plot of the correlation coefficient and VIP value of the sample score predicted by the PLS-DA model;

[0041] Figure 5 It is the VIP value diagram of the PLS-DA model;

[0042] Figure 6 Accuracy, AUC and BS graphs of nine classification models;

[0043] Figure 7 ROC graphs for nine classification models;

[0044] Figure 8 Apply the KNN model classification confusion matrix for the test set data;

[0045] Fig. 9 It is a schematic diagram of the structure of a blood species identification device provided in one embodiment of the present application;

[0046] Fig.10 is a structural block diagram of an electronic device in one embodiment;

[0047] Fig.11 FIG. 4 is a structural block diagram of a computer storage medium in another embodiment. DETAILED DESCRIPTION

[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0049] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0052] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0053] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0054] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0055] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0056] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0057] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]" depending on the context.

[0058] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0059] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0060] like Figure 1 As shown, the embodiment of the present application provides a method for identifying blood species, comprising the following steps:

[0061] S101, determining differential substances between bloods of different species based on blood samples of different species, and obtaining content data of differential substances in blood samples of different species;

[0062] In a possible implementation, the step of determining the difference substances between blood of different species based on blood samples of different species includes:

[0063] Obtain VOC qualitative and quantitative data of blood samples from different species;

[0064] PLS-DA was used to analyze the VOC qualitative and quantitative data to determine the differential substances between the blood of different species.

[0065] Exemplary, freshly collected human, pig, cattle, sheep, chicken, duck, rabbit, rat blood was used to 2 Anticoagulation treatment was performed, and HS-SPME and GC-MS analysis were performed using bromobenzene as the internal standard. The NIST 17 spectral library was used for qualitative retrieval and the internal standard curve was used for quantitative analysis. Non-endogenous substances were excluded to obtain VOC qualitative and quantitative data for blood samples of different species.

[0066] In a possible implementation, the step of using PLS-DA to analyze the VOC qualitative and quantitative data to determine the difference substances between blood of different species includes:

[0067] Performing PLS-DA analysis on the VOC qualitative and quantitative data to obtain analytical data;

[0068] Establishing a scoring model according to the analysis data, and performing a permutation test on the scoring model to obtain a predicted sample score corresponding to the VOC qualitative and quantitative data, independent variable data corresponding to the predicted sample score, and target data corresponding to the VOC qualitative and quantitative data;

[0069] Correlation coefficient data based on the predicted sample scores and the independent variable data;

[0070] Calculate the VIP value of the independent variable data based on the target data;

[0071] The differential substances between the blood of different species are determined based on the correlation coefficient data and the VIP values.

[0072] Exemplarily, PLS-DA analysis was performed on the differential substances between the blood samples of different species, a model was established, and the model was subjected to 200 permutation tests. The p-value of the correlation coefficient between the predicted sample score and the independent variable was calculated, and the VIP value was calculated. Potential differential substances were screened with a VIP greater than 1.0 and a p-value of the correlation coefficient between the predicted sample score and the independent variable less than 0.05.

[0073] For example, Figure 2 As shown, it can be observed that the 8 types of blood are clearly divided into 4 groups, indicating that the blood VOCs of the 8 species show differences. Figure 3 It shows that the R2 and Q2 of 200 permutation tests are lower than the original values, and the model does not have overfitting. Figure 4 This is a correlation-VIP value scatter plot. Among the four areas in the figure, only the variables represented by the yellow triangle scatter points in the upper left corner are potential differential substances, whose VIP values ​​are greater than 1, and the p-value of the correlation coefficient between the predicted sample score and the variable is less than 0.05. Figure 5It was shown that the differential substances were tetradecane, 4-nonanone, naphthalene, trans-2-octen-1-ol, biphenyl, 2-ethylhexanol, cyclohexanone, 2-propylheptanol, 2-heptanone, phenylethyl alcohol, cresol, hexylcyclohexane, heptanal, benzaldehyde, 1,2,3-trimethylbenzene, 1-octen-3-ol, and nonanal.

[0074] S102, constructing a data set according to the content data and the species corresponding to the content data, and dividing the data set into a training set and a validation set according to a preset ratio;

[0075] In a possible implementation, the step of training each preset algorithm in the preset algorithm library by a resampling method according to the training set to obtain a target algorithm library composed of trained preset algorithms includes:

[0076] The training set is sampled using a 10-fold CV resampling method repeated 5 times to obtain target data sets for different preset algorithms;

[0077] The preset algorithm is trained according to the target data set to obtain a target algorithm library consisting of the trained preset algorithms.

[0078] Exemplarily, the training set is sampled and divided into a training set and a test set according to a ratio of 7:3, and 10-fold CV is repeated 5 times as a resampling method to establish DT, Gaussian Radial Basis Function Kernel (RBF) SVM, Polynomial Kernel (POLY) SVM, KNN, MLP, MLR, NB, XGBoost, and RF classification model workflows (training set and test set). Among them, the training set and test set imported into the SVM, KNN, and MLP models are standardized; the training set and test set imported into the MLR and NB models are thresholded at 70% to remove collinear data; the training set and test set imported into the DT, RF, and XGBoost models are not specially processed.

[0079] S103, training each preset algorithm in the preset algorithm library by a resampling method according to the training set, to obtain a target algorithm library consisting of trained preset algorithms;

[0080] In a possible implementation, the step of selecting an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set includes:

[0081] Inputting the verification set into each trained preset algorithm in the target algorithm library to obtain a prediction result;

[0082] Calculate the index data used to characterize the performance of the preset algorithm after training according to the prediction result and the actual result of the verification set;

[0083] Based on the indicator data, an algorithm that meets preset requirements is selected in the target algorithm library as a classification algorithm.

[0084] For example, according to the evaluation index, KNN is selected as the best classification algorithm, and the best hyperparameters are: the number of neighbors K is 10, the distance weighted kernel function is a three-weight function, and the Minkowski distance parameter p is 0.250. The model is used to classify the test set data, Accuracy = 0.898, AUC = 0.998, BS = 0.062, Figure 8 This is the confusion matrix. It can be seen that the classification effect of the KNN algorithm is better.

[0085] S104, selecting an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set, and inputting the to-be-detected content data of the differential substance in the to-be-detected blood into the classification algorithm to obtain the species of the to-be-detected blood.

[0086] By determining the differential substances between the blood of different species based on blood samples of different species, the content data of the differential substances in the blood samples of different species are obtained; a data set is constructed according to the content data and the species corresponding to the content data, and the data set is divided into a training set and a validation set according to a preset ratio; according to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of trained preset algorithms; based on the validation set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substances to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected. Potential biomarkers (differential substances) are evaluated by accuracy (Accuracy), area under the receiver operating characteristic curve (ROC) (Area Under Curve, AUC) and Brier score (BrierScore, BS) and selected

[0087] In a possible implementation, the indicator data includes: accuracy data, prediction effect data and mean square error data.

[0088] For example, Figure 6-Figure 7As shown, Accuracy (accuracy data), AUC (prediction effect data), and BS (mean square error data) are used to measure the performance of the classification model. First, Accuracy is used to test the ratio of the number of correct classification predictions to the total number of predictions. The returned data is between 0 and 1, where 0 indicates that there is no correct classification prediction and 1 indicates that the prediction accuracy is 100%; AUC is used to test the prediction effect of the model, and the returned data is between 0 and , and the closer to 1, the better the model prediction effect; BS is used to calculate the mean square error of the probability prediction relative to the test sample, and the returned data is between 0 and 1, where 0 indicates that the model has the highest degree of calibration and the model is optimal, and 1 indicates that the model effect is the worst. The mathematical expressions of Accuracy (accuracy data), AUC (prediction effect data), and BS (mean square error data) are:

[0089]

[0090] In a possible implementation, the preset algorithm library includes at least: DT algorithm, Gaussian kernel function SVM algorithm, polynomial kernel function SVM algorithm, KNN algorithm, MLP algorithm, MLR algorithm, NB algorithm, XGBoost algorithm and RF algorithm.

[0091] Exemplarily, the hyperparameters of each model (algorithm) are set, including tree depth and minimum sample split number for DT model; marginal error prediction cost and RBF kernel width for SVM-RBF model; marginal error prediction cost, polynomial degree and polynomial scale factor for SVM-POLY model; number of neighbors, distance weighted kernel function and Minkowski distance parameter for KNN model; number of hidden layer neurons, regularization parameter and number of training iterations for MLP model; regularization parameter for MLR model; relative smoothness of class boundary and Laplace correction value for NB model; maximum tree depth, number of trees, learning rate, minimum sample split number and minimum loss reduction required for node splitting for XGBoost model; number of trees, minimum sample split number and number of candidate split features for tree creation for RF model. Grid method is used for hyperparameter tuning.

[0092] Second, as Fig. 9 As shown, the present application provides a blood species identification device, the device comprising:

[0093] The data acquisition module 201 is used to determine the difference substances between the blood of different species based on the blood samples of different species, and obtain the content data of the difference substances in the blood samples of different species;

[0094] A division module 202 is used to construct a data set according to the content data and the species corresponding to the content data, and divide the data set into a training set and a validation set according to a preset ratio;

[0095] A training module 203 is used to train each preset algorithm in the preset algorithm library by a resampling method according to the training set to obtain a target algorithm library composed of trained preset algorithms;

[0096] The prediction module 204 is used to select an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set, and input the to-be-detected content data of the differential substance in the to-be-detected blood into the classification algorithm to obtain the species of the to-be-detected blood.

[0097] Thirdly, Fig.10 As shown, an embodiment of the present application provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: determining differential substances between bloods of different species based on blood samples of different species, and obtaining content data of differential substances in blood samples of different species;

[0098] Constructing a data set according to the content data and the species corresponding to the content data, and dividing the data set into a training set and a validation set according to a preset ratio;

[0099] According to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of trained preset algorithms;

[0100] Based on the verification set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substance to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected.

[0101] Fourthly, Fig.11 As shown, the embodiment of the present application provides a computer-readable storage medium 400, wherein the computer-readable storage medium stores a computer program 411, and when the computer program is executed by a processor, the following steps are implemented: determining the difference substances between the blood of different species based on the blood samples of different species, and obtaining the content data of the difference substances in the blood samples of different species;

[0102] Constructing a data set according to the content data and the species corresponding to the content data, and dividing the data set into a training set and a validation set according to a preset ratio;

[0103] According to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of trained preset algorithms;

[0104] Based on the verification set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substance to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected.

[0105] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0106] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment / terminal equipment and methods can be implemented in other ways. For example, the device / network equipment / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for identifying blood species, characterized in that: The following steps are involved: Determine the difference substances between the blood of different species based on the blood samples of different species, and obtain the content data of the difference substances in the blood samples of different species; Constructing a data set according to the content data and the species corresponding to the content data, and dividing the data set into a training set and a validation set according to a preset ratio; According to the training set, each preset algorithm in the preset algorithm library is trained by a resampling method to obtain a target algorithm library composed of trained preset algorithms; Based on the verification set, an algorithm that meets the preset requirements is selected in the target algorithm library as a classification algorithm, and the content data of the differential substance to be detected in the blood to be detected is input into the classification algorithm to obtain the species of the blood to be detected.

2. A method for identifying blood species according to claim 1, characterized in that: The step of determining the difference substances between blood of different species based on blood samples of different species comprises: Obtain VOC qualitative and quantitative data of blood samples from different species; PLS-DA was used to analyze the VOC qualitative and quantitative data to determine the differential substances between the blood of different species.

3. A method for identifying blood species according to claim 2, characterized in that: The step of using PLS-DA to analyze the VOC qualitative and quantitative data to determine the difference substances between the blood of different species includes: Performing PLS-DA analysis on the VOC qualitative and quantitative data to obtain analytical data; Establishing a scoring model according to the analysis data, and performing a permutation test on the scoring model to obtain a predicted sample score corresponding to the VOC qualitative and quantitative data, independent variable data corresponding to the predicted sample score, and target data corresponding to the VOC qualitative and quantitative data; Correlation coefficient data based on the predicted sample scores and the independent variable data; Calculate the VIP value of the independent variable data based on the target data; The differential substances between the blood of different species are determined based on the correlation coefficient data and the VIP values.

4. A method for identifying blood species according to claim 1, characterized in that: The step of training each preset algorithm in the preset algorithm library by a resampling method according to the training set to obtain a target algorithm library composed of trained preset algorithms includes: The training set is sampled using a 10-fold CV resampling method repeated 5 times to obtain target data sets for different preset algorithms; The preset algorithm is trained according to the target data set to obtain a target algorithm library consisting of the trained preset algorithms.

5. A method for identifying blood species according to claim 1, characterized in that: The step of selecting an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set includes: Inputting the verification set into each trained preset algorithm in the target algorithm library to obtain a prediction result; Calculate the index data used to characterize the performance of the preset algorithm after training according to the prediction result and the actual result of the verification set; Based on the indicator data, an algorithm that meets preset requirements is selected in the target algorithm library as a classification algorithm.

6. A method for identifying blood species according to claim 5, characterized in that: The indicator data include: accuracy data, prediction effect data and mean square error data.

7. A method for identifying blood species according to claim 1, characterized in that: The preset algorithm library includes at least: DT algorithm, Gaussian kernel function SVM algorithm, polynomial kernel function SVM algorithm, KNN algorithm, MLP algorithm, MLR algorithm, NB algorithm, XGBoost algorithm and RF algorithm.

8. A blood species identification device, characterized in that: The device comprises: A data acquisition module, used to determine the difference substances between the blood of different species based on the blood samples of different species, and obtain the content data of the difference substances in the blood samples of different species; A partitioning module, used to construct a data set according to the content data and the species corresponding to the content data, and to partition the data set into a training set and a validation set according to a preset ratio; A training module, used to train each preset algorithm in the preset algorithm library by a resampling method according to the training set, so as to obtain a target algorithm library composed of the trained preset algorithms; The prediction module is used to select an algorithm that meets preset requirements in the target algorithm library as a classification algorithm based on the verification set, and input the to-be-detected content data of the differential substance in the to-be-detected blood into the classification algorithm to obtain the species of the to-be-detected blood.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images