350 results about "Sample mass" patented technology

The invention relates to the technical field of deep learning and small sample learning, in particular to a small sample capacity training method based on deep learning, which comprises the steps of 1, cross-domain data adaptation and feature alignment, 2, meta-knowledge distillation and prototype enhancement, 3, attention-guided small sample fine adjustment, and 4, model uncertainty quantification and iterative optimization. According to the small sample capacity training method based on deep learning, through cross-domain feature alignment, meta-knowledge distillation, prototype enhancement and dynamic iterative optimization, the problems of model overfitting and weak generalization ability in a small sample scene are solved, high-precision model training when the sample size is less than or equal to 50 is realized, and the training efficiency is improved. The method is suitable for data scarce scenes such as medical images and minority language processing.

The invention provides a soil nutrient content prediction method and system, and relates to the technical field of soil nutrient circulation.The soil nutrient content prediction method comprises the steps that to-be-detected soil sample data are obtained, the to-be-detected soil sample data are input into a soil nutrient content prediction model, and prediction parameters of target nutrients in a to-be-detected soil sample are obtained; wherein the soil nutrient content prediction model is a model obtained after training of a joint random forest algorithm and a depth distribution function. And based on the prediction parameter of the target nutrient, obtaining a prediction result of the target nutrient in the to-be-detected soil sample data so as to evaluate change characteristics of the target nutrient in the current to-be-detected soil sample data. On the basis, the problems that in the prior art, in the aspect of deep soil nutrient prediction, the data quality is low, and the sample size is limited can be solved, the effectiveness and accuracy of deep soil nutrient prediction are improved, and the blank in the prior art is filled up.

The invention discloses a farmland soil sampling space optimization method based on local heterogeneity, and belongs to the field of soil sampling space optimizing.The method comprises the steps that the heterogeneity level of soil in a research area is calculated through a variable coefficient; according to the soil heterogeneity level of the research area, dividing the research area into spatial continuous sub-areas with similar soil heterogeneity level by using a heterogeneity change algorithm; and on the basis of the environment covariables, a method of combining a fuzzy c-mean classifier and a heterogeneity change algorithm is adopted, geographic and feature spaces are optimized, key sampling positions in continuous sub-regions of each space are identified, and farmland soil sampling space optimization is completed. According to the method, the problem that the influence of the soil local heterogeneity level on sample size distribution and spatial layout optimization is not considered in an existing method is solved.

The invention discloses a material structured data-oriented generation and screening method and device. The method comprises the steps of S1, acquiring material structured data; s2, according to the material structured data, judging whether treatment is needed or not by evaluating the ratio of the characteristic quantity to the sample quantity and the insight of a data set, and if treatment is needed, performing the step S3; s3, effectively generating the structural data of the material by using the depth generative model oriented to the structural data; s4, the generated samples are evaluated through multiple dimensions and weighted integration is carried out; and S5, according to an evaluation result, performing multi-dimensional high-quality sample screening by fusing domain knowledge. By adopting the technical scheme of the invention, effective generation of high-quality material structured data is realized.

The invention relates to a small sample HRRP radar target identification method, device, equipment and medium, after normalization processing is carried out on a one-dimensional high-resolution range profile sequence of an unknown target with a small sample size, radar scattering physical prior is utilized to construct a static adjacency matrix, then a dynamic adjacency matrix is generated through a feature enhancement network, and the dynamic adjacency matrix is obtained. And after the static adjacent matrix and the dynamic adjacent matrix are fused, a hierarchical adaptive meta-learning graph neural network is adopted to carry out target identification training, so that high-precision identification of a position target is realized under data of fewer samples.

The invention relates to the technical field of material physical property testing, and discloses an injectable hydrogel wound dressing tensile strength testing method, which comprises: establishing a correlation model of the mass and the maximum fracture load of a standard sample at different temperatures, and the correlation model of the initial rigidity and the temperature; measuring the mass and the actual maximum fracture load of the to-be-measured sample, and determining the actual initial rigidity of the to-be-measured sample; according to the method, the actual initial stiffness is calculated, the equivalent temperature of the test is converted by utilizing the actual initial stiffness, the standard theoretical maximum fracture load is calculated in combination with the sample mass and the corresponding model, and the performance is judged by comparing the two, so that the measurement of the geometric dimension of an irregular sample is avoided by constructing the correlation between the mass and the mechanical performance; the quality control problem of an in-situ forming material is solved, and the reliability of a judgment result in an industrial environment is further ensured by utilizing mechanical response data of the same test through an integrated temperature self-adaptive calibration mechanism.

The invention discloses a cloud top height quality inspection method and device, computing equipment and a storage medium, and belongs to the technical field of atmospheric detection and remote sensing, and the method comprises the steps: taking laser radar cloud profile data as a detection truth value, taking imaging type radiometer cloud product data as to-be-inspected data, and carrying out the quality inspection of the to-be-inspected data on the basis of the time-space matching of the two types of data; the method comprises the following steps: screening out unqualified data through a space-time uniformity test, and carrying out layer-by-layer and step-by-step analysis on qualified matching data to count a total sample size, correct detection, missing detection, false detection, a correct screening sample size and a proportion, a correct identification sample size of each cloud type including cirrus cloud and lower cloud, an error identification sample size and a corresponding cloud top height difference; therefore, complete and accurate cloud top height quality detection is realized.

The invention provides a joint optimization method for a stacking sequence and a grabbing posture of a neutron measurement system, and relates to the field of data processing. According to the method, multi-source monitoring data of a neutron measurement system are collected, shadow voxels are constructed in combination with a three-dimensional space model, a neutron resonance shadow domain is formed through clustering superposition, and a dangerous concentration cloud cluster and a safe rarefied area are marked; mapping candidate stacking positions and postures according to sample mass distribution, geometric dimensions, centroid positions and irradiation sensitive characteristics, generating a stacking mode and determining a stacking sequence; performing path risk assessment on the grabbing postures, and selecting the grabbing postures of which the crossing risk meets a threshold value; superposing micro-random jitter on the path to suppress resonance phase locking; and abnormal events are monitored in real time during operation, and a risk domain is updated to execute hierarchical unloading control, so that the instantaneous impact and damage risk is reduced. According to the technical scheme, the probability of instantaneous impact risks caused by stacking overall micro-drift and grabbing track overlapping can be effectively reduced, and therefore the safety of the system is guaranteed.

The invention discloses an index transaction monitoring method and device, electronic equipment and a storage medium, and relates to the technical field of transaction monitoring. The threshold range is dynamically generated based on the historical business data to adapt to the change of data distribution, the adaptive statistical test algorithm is selected in combination with the data sample size and the distribution characteristics to improve the accuracy of anomaly judgment, and personalized early warning output is performed according to the region and the business type of the auditing point. According to the technical scheme, data dynamic change and business scene diversity can be flexibly coped with, so that the technical problem that the reliability of an early warning result is reduced in the face of missing data, abnormal values and complex seasonal fluctuation, and then the real-time control and decision-making efficiency of an operator on a business operation state is influenced can be solved; the technical effects of improving the accuracy and reliability of business development index abnormity identification, reducing the false report and missing report rate, and enhancing the real-time control capability and decision-making efficiency of the operator for the business operation state are achieved.

The invention discloses a large-scale customization quality prediction method based on transfer learning. The invention designs a large-scale customization quality prediction method for solving the problems that structures among variables are difficult to excavate and the quality of products with few samples is difficult to predict due to modular production, customized assembly and inconsistent number of different product samples in large-scale customization production. The method comprises the following steps: firstly, mining a causal relationship among source domain variables by utilizing a PC causal discovery method aiming at source domain data with a richer sample size, carrying out structure migration on a part of fixed structures from a source domain to a target domain by utilizing mechanism knowledge in order to obtain the causal relationship among target domain variables, and carrying out target domain few-sample amplification through a generative adversarial network; a causal relationship is complemented in a target domain after variable amplification through a PC causal discovery method, a target domain variable causal graph structure is obtained, then a heterogeneous causal graph attention network is utilized to carry out source domain and target domain model training, and target domain quality prediction is carried out through an MAML transfer learning method with MMD distance weighting. Aiming at the characteristics of large-scale customized production of customized products, the transfer learning-based quality prediction method suitable for large-scale customized production is formed.

The invention relates to a port crude oil unloading speed regulation and control prediction method based on physical constraints, and belongs to the technical field of crude oil storage and transportation automation control, and the method comprises the following steps: S1, constructing a coupling equation of pipeline outlet pressure from an oil transfer arm to a reservoir area and storage tank flow speed; s2, constructing a physical constraint neural network model; s3, constructing a loss function formula of the physical constraint neural network model based on the coupling equation; and S4, performing adaptive training on the physical constraint neural network model based on historical data, and updating network parameters of the model. According to the method, the physical law of pipeline fluid movement is fused into the loss function in the form of constraint conditions in the model training stage, the degree of dependence of the model on the pure data sample size is remarkably reduced, and accurate regulation and control of the oil discharge rate under the complex working condition are achieved.

The invention belongs to the technical field of uncertainty probability characterization analysis, and discloses a thermoplastic composite material leading edge structure design allowable value probability characterization method and system under a small sample condition, and the method comprises the steps: defining a plurality of candidate probability distribution models; fitting each model based on the original sample data and calculating an AIC value and a BIC value; a dynamic weight factor alpha is calculated according to the sample size n, and then a hybrid information criterion HIC value is calculated; generating a plurality of sample sets through Bootstrap self-service sampling, recalculating the HIC value on each sample set, and counting the selected optimal frequency of each model; and determining an optimal probability distribution model according to the frequency, wherein the optimal probability distribution model is used for representing a design allowable value. According to the method, the dynamic weight factor alpha is introduced, AIC and BIC criteria are effectively unified, optimal balance between prediction precision and model complexity is achieved under the condition of small samples, and engineering practicability and robustness are remarkably improved.

The invention discloses a sample size calculation method and system for quantitative consistency evaluation. The method comprises the following steps: firstly, determining MDL and a clinical consistency boundary value, then collecting pre-test data, and determining a required sample size through iterative calculation. Then, verification samples are extracted from the overall data for consistency analysis, and the robustness of a calculation result of the verification sample size is simulated through Bootstrap; according to the method, MDL and least square regression are fused for the first time, a sample size formula for quantitative consistency evaluation is constructed, the reliability and effectiveness of clinical test data are ensured by providing a new sample size calculation method, more accurate sample size estimation is provided for clinical research, and therefore the quality of clinical decisions is improved.

The invention discloses a product production management and control method, device and equipment and a storage medium, and relates to the technical field of informatization management and optimization in the manufacturing industry, and the method comprises the steps: obtaining the quality parameters of a to-be-detected product batch, and calculating the sample size of the to-be-detected product batch based on the quality parameters, the quality parameters comprise a nominal defective rate, a maximum error and a confidence level; sampling products with the number corresponding to the sample size are extracted from the to-be-detected product batch for quality detection, so that a sampling quality detection result of the to-be-detected product batch is obtained; and outputting a production decision of the batch of products to be inspected based on the sampling quality inspection result, and updating the quality parameters based on the production decision. According to the method, the needed sample size is calculated through the quality parameters, and it is ensured that expected detection precision can be achieved with the minimum sample size in each time of detection. Therefore, not only is the unnecessary detection times reduced, but also the detection cost is reduced.

The invention discloses a rapid yield analysis method based on xgboost proxy model truncation sampling, and the method comprises the following steps: generating a first random sample point set, and obtaining a training set through simulation; constructing a proxy simulator, and training the proxy simulator by using the training set; generating a second random sample point set, and inputting the second random sample point set into the proxy simulator to obtain a pseudo data set; establishing a filter, determining two hyperspherical surfaces based on the pseudo data set, dividing a process parameter space, evaluating a safety coefficient and the probability that a sample point enters a real simulator, and simulating the sample point of the process parameter space according to the probability to obtain a real sample set; iteratively optimizing the hyper-spherical surface and the proxy simulator by using the real sample set until convergence to obtain a final safety coefficient; and generating a third random sample point set, carrying out truncation sampling and failure discrimination by combining a real simulator and an agent simulator, and carrying out statistics on the final yield. According to the method, the xgboost network is adopted as an agent model to reduce the simulation cost, the sample size is reduced through truncation sampling, and rapid and accurate prediction of the yield of the integrated circuit is realized.

The invention provides an oil-containing shale porosity evaluation method, and belongs to the technical field of shale oil-gas exploration and development, and the method comprises the steps: obtaining a plurality of samples of a target oil-containing shale; measuring the free hydrocarbon content of the first sample; measuring the total volume, the skeleton volume and the sample mass of the second sample; measuring the crude oil density of the region where the target oil shale sample is located; determining the porosity value of the target oil-containing shale when the target oil-containing shale does not contain oil according to the total volume and the skeleton volume of the second sample, and calculating the porosity value of the target oil-containing shale when the target oil-containing shale contains oil according to the crude oil density, the free hydrocarbon content of the first sample, the total volume of the second sample, the skeleton volume and the sample mass; and determining the porosity of the target oil-containing shale sample according to the porosity value when the oil is not contained and the porosity value when the oil is contained. According to the method provided by the invention, the accuracy of porosity evaluation is improved, and meanwhile, as the test equipment is easily carried to the well site, the requirement of instantly testing the porosity in the well site is met.

The invention belongs to the technical field of medical data processing, and discloses a preoperative multi-complication risk prediction method and system based on structured clinical data, and the method comprises the steps: inputting the causal association between risk factors and complication nodes into the edge of a knowledge graph, calculating the statistical correlation between all complications, and supplementing the statistical correlation into the knowledge graph, and performing network embedding training on the knowledge graph to form a first-stage model, performing preliminary risk assessment on complications, modeling the knowledge graph in a graph neural network mode, and performing joint training with the first-stage model to form a second-stage model to output a final complication probability. According to the method, the interpretability and cross-domain consistency of the model can be improved through deep fusion of the medical knowledge graph and the multi-relational graph convolutional network, stability and calibration performance are still kept in a specialist with scarce sample size, and the problem that a traditional black box model cannot be interpreted is avoided; and the practical application value can be evaluated conveniently.

The invention discloses a CAD (Computer Aided Design) model gap defect detection method and device based on deep learning, which are mainly applied to the field of computer aided design and engineering. The method comprises the following six core steps: firstly, constructing a data set covering various typical gap defects, and expanding the sample size through a data amplification technology; then coding processing is carried out on geometric features of the model, and a deep convolutional neural network is built on the basis; and finally completing model training and gap defect detection. A corresponding device is composed of a data acquisition module, an amplification module, a geometric feature coding module, a detection analysis module and the like, and a matched computer readable storage medium stores program codes for realizing the method. According to the method, the gap defect detection precision is remarkably improved, the adaptability to the complex geometrical morphology is enhanced, and the model generalization ability is effectively improved. Popularization and application of the method can promote intelligent upgrading of a detection process, reduce dependence on experience of engineers, improve detection efficiency and provide technical support for automatic geometric cleaning.

The invention discloses a cognitive function screening system and method based on an MMSE (Minimum Mean Square Error) prediction model, and relates to the technical field of data analysis, the method comprises the following steps: collecting physical examination index data, removing missing records, adopting a multiple interpolation method for interpolation, and obtaining multiple sets of complete data sets; a continuous prediction model is constructed, MMSE continuous prediction values are obtained, and a sensitivity analysis report is generated; constructing a first-stage classification model, adaptively dividing an optimal threshold combination, and dividing a sample into a high-confidence region, a to-be-discriminated region and a low-confidence region; if the sample size of the to-be-discriminated region is higher than a preset training threshold value, constructing an enhanced feature set, and constructing a second-stage classification model; when the prediction probability reaches the optimal re-discrimination threshold value, the classification result in the first stage is corrected, and otherwise, the classification result is maintained; if not, maintaining the classification result; and integrating the classification results to obtain a final classification result of all the samples.

The invention discloses gynecological tumor sampling equipment capable of avoiding secondary pollution of samples, and belongs to the technical field of gynecological tumor sampling. Gynecological tumor sampling equipment capable of avoiding secondary pollution of samples comprises a positioning device, a penetrating type penetrating hole is formed in the positioning device, a clamping groove is formed in the surface of one end of the positioning device, a clamping block matched with the clamping groove is clamped in the clamping groove, and a penetrating type fixing pipe is fixedly installed on the surface of the clamping block. Compared with the traditional sampling equipment, the gynecological tumor sampling equipment capable of avoiding secondary pollution of the sample has the advantages that the arc-shaped cutter annularly cuts a to-be-cut sample tissue by adopting rotary motion, so that the to-be-cut sample is sampled at one time by the arc-shaped cutter, and the sample is prevented from falling back due to adhesion of the sampled sample and the uncut tissue; the basic requirement of pathological detection on the sample size is met, the tumor sampling speed and efficiency are improved, the real situation of the tumor is comprehensively and accurately reflected, and the illness state of a patient is accurately judged.

The invention relates to an immunotherapy prognosis evaluation system based on combined penalty likelihood modeling, and belongs to the technical field of precision medicine. Based on a generalized linear hybrid model, various types of clinical endpoints, such as objective remission rate and disease-progression-free lifetime, are effectively integrated. By introducing the random effect, the model can capture potential correlation between end points, and the statistical effectiveness of analysis is enhanced. For the colinearity between clonality mutation features, key variables are screened through a penalty likelihood method, the influence of multiple colinearity is reduced, and the explanatory property and prediction accuracy of the model are improved. In order to overcome the challenge of limited sample size, cross-subgroup data fusion likelihood modeling is introduced, the strategy not only retains the model specificity of each subgroup, but also improves the adaptability of the model to small sample data and the prediction accuracy through information sharing among the subgroups.

The invention provides a method and a system for automatically marking text data by using a large language model, and belongs to the technical field of large language models and online public opinion monitoring and marking. According to the method and the system for automatically marking the text data by using the large language model, related personnel can more effectively analyze characteristics, trends and potential risks by generating high-quality applicable scene related data and formulate accurate monitoring and intervention measures. By increasing the sample size, the generalization ability of the machine learning model can be improved, the adaptability to different application scenes can be enhanced, and the model can respond more quickly when facing diversified bad techniques in the application scenes. According to the method and the system for automatically marking the text data by using the large language model, powerful data support can be provided for identifying, early warning and fighting against bad behaviors in an applicable scene, so that the legal rights and interests of related personnel are better protected, and the stability and the safety of the market are maintained.

The invention discloses a method for rapidly determining the optimal DSC sample amount to predict the thermal safety parameter of an autocatalytic substance. The method comprises the following steps: firstly, setting more than three groups of sample masses, carrying out a thermal decomposition test on the samples under a dynamic condition by using DSC to obtain initial decomposition temperatures T0, specific heat release amounts Q and peak temperatures Tp of the samples under different sample amounts, and analyzing the correlation between T0, Tp and Q and the sample amounts according to the change ranges and change trends of three thermodynamic parameters, if the thermodynamic parameters do not change obviously, selecting the maximum sample mass as a relatively conservative thermal safety parameter for predicting the optimal sample mass, and if the thermodynamic parameters change obviously, further comparing delta Y / delta X by taking the sample mass as an X variable and the thermodynamic parameters as a Y variable, and screening out the optimal sample mass in combination with different classification conditions. The method has the advantages of simple test conditions and short time consumption, can be widely applied to various autocatalytic substances, and can obtain more conservative and accurate evaluation results.

The invention discloses a method for judging and optimizing a raw material ratio in microwave synergistic pyrolysis, and relates to the technical field of solid waste recycling and biomass energy utilization. In order to overcome the defect that in-depth research and engineering application of a microwave pyrolysis process are restricted in the prior art, the technical scheme provided by the invention comprises the following steps: preparing samples from oily sludge and palm kernel shells according to a preset mass ratio, and mixing to obtain a mixed raw material; establishing an inert atmosphere and forming a controlled reaction system; applying microwave heating and collecting a sample mass change curve and temperature change data; comparing the mass change curve with a theoretical curve formed by weighted stacking of a single raw material pyrolysis curve to obtain a difference result; judging the synergistic effect strength among the raw materials according to the difference result, and outputting a synergistic effect judgment result; and determining an optimal ratio based on a synergistic effect judgment result. The method is suitable for raw material ratio judgment and optimization work of solid waste and biomass under the microwave synergistic pyrolysis condition.

The invention belongs to the technical field of biology, and discloses a cattle SNP chip and application thereof, the detection object of the liquid phase chip comprises 7,829 SNP sites located on a common cattle reference genome AR-UCD 1.2, and the position information of the SNP sites is shown in the specification table 3. The liquid chip provided by the invention highlights the specificity of the local cattle variety in the Tibet autonomous region, and by analyzing the local cattle population structure, sites capable of effectively distinguishing the population are screened, so that the problems of strong universality and poor specificity of a commercial chip are solved. The liquid-phase chip can also realize flexible selection and upgrading of sites, and breaks through the limitation that a solid-phase chip cannot flexibly supplement or update the sites. The whole method can be stably operated on the premise of limited sample size and complex population structure, and is suitable for genetic resource protection and application scenarios of rare varieties. The method can also be expanded into a standardized typing tool, and is suitable for various applications such as local cattle germplasm registration, variety identification, region identification and the like.

The invention relates to a light high-entropy alloy yield strength machine learning prediction method, which comprises the following steps: S1, obtaining an original data set of a light high-entropy alloy sample, the original data set comprising the yield strength of the light high-entropy alloy sample and corresponding experimental process conditions; s2, extracting feature parameters for describing samples based on the original data set; s3, dividing the original data set into a training set and a test set; s4, screening an optimal feature subset from the feature parameters, and calculating a secondary feature set based on the optimal feature subset; and S5, taking the yield strength of the light high-entropy alloy sample as a target variable, taking the secondary feature set as an independent variable, and adopting XGBoost trained by the original data set to construct a quantitative prediction model of the yield strength of the light high-entropy alloy. Compared with the prior art, the method has the advantages that the physical interpretability is enhanced, the generalization ability is improved, the dependence on the sample size is reduced, and the like.

The invention discloses an iron ore composition detection method and system based on machine learning, and relates to the technical field of data processing.The method comprises the steps that iron ore feature information of target iron ore to be detected is collected, and a plurality of iron ore samples are collected; performing drying and grinding parameter optimization according to the iron ore characteristic information, drying and grinding the plurality of iron ore samples, and collecting the particle size and mass in each drying and grinding process to obtain a plurality of particle size sequence sets and a plurality of mass sequences; preparing a plurality of detection samples, and performing sample quality analysis according to the optimized drying and grinding parameters, the plurality of particle size sequence sets and the plurality of quality sequences to obtain a plurality of sample quality coefficients; and carrying out X-ray fluorescence spectrum detection on the plurality of detection samples to obtain a plurality of spectrum detection results, and carrying out component identification on the plurality of spectrum detection results according to the plurality of sample mass coefficients to obtain an iron ore component detection result. The technical problem of poor iron ore component detection accuracy in the prior art is solved.

The invention relates to the technical field of clinical test statistical design and analysis optimization, and discloses a clinical test statistical design optimization method borrowing external data, and the method comprises the steps: collecting target test data and associated external data, and dynamically evaluating the consistency of the external data and a current test, constructing a multi-model library comprising a frequency theory method, a Bayesian hierarchical model, MAP prior and EMAP prior, selecting an optimal statistical design algorithm, and dynamically borrowing external data; therefore, on the premise of controlling the class-I error rate and maximizing the test efficiency, effective utilization of external data is realized, the current test sample size is reduced, the test efficiency is improved, and the research robustness is improved. The system comprises a data acquisition and preprocessing module, a joint modeling module, an algorithm matching engine and a dynamic optimization execution module, and supports a multi-source data interface, conflict data cleaning and an abnormal result feedback mechanism.

The invention provides a laying hen feed raw material sample screening method and system based on multi-source variability, and relates to the technical field of data processing analysis, and the method comprises the steps: obtaining multi-source attribute data and conventional component content data of raw materials, mapping the attribute data into tensor modal dimensions through multi-source variability tensor construction processing, and obtaining a multi-source variation tensor model; the component data is used as a characteristic component, and a multi-source variability tensor is obtained through decoupling and compression. Variability spectrum decomposition processing is carried out, local rank spectrum decomposition is carried out along producing areas, time and component dimensions, and a variability spectrum vector set is obtained; and identifying a candidate modeling sample set through multi-scale extremum and sparsity screening. And evaluating the contribution degree and sensitivity of the sample to a standard ileum amino acid digestibility prediction equation through a leave-one-out method and sensitivity analysis, and screening out an optimal modeling sample. According to the method, the multi-source variation information of the raw materials can be integrated, the variation spectrum is comprehensively covered with the minimum sample size, and the precision and generalization ability of the prediction model are remarkably improved.

The invention discloses a liquid chromatography-tandem mass spectrometry detection method for catecholamine and metabolites thereof, which comprises the following steps: step 1, sequentially adding a sample to be detected, an internal standard solution, a derivatization buffer solution and a derivatization solution into holes in the third / ninth column of a 96-well plate, oscillating at room temperature, replenishing water, and continuing oscillating; step 2, adding an activating solution and magnetic beads into the first / seventh column of the 96-well plate; adding equilibrium liquid into the second / eighth column; a first leacheate is added into the fourth column and the tenth column; adding a second leacheate in the fifth / eleventh column; adding the eluent into the 6 / 12th column; then placing the sample on a 32-channel sample pretreatment system for magnetic solid-phase extraction; and step 3, liquid chromatography-tandem mass spectrometry detection. According to the method, the sample is firstly derivatized and then is subjected to magnetic solid-phase extraction, so that only less sample size is needed, the sensitivity is higher, and the economical efficiency is better; according to the method for directly derivatizing the sample, the sample does not need to be derivatized after being subjected to protein precipitation and supernatant removal, and the steps are simpler, more convenient and more automatic.