860 results about "Initial sample" patented technology

The invention provides a training data synthesis method and device based on error extrapolation and inference chain analysis, a medium and a program product. The method comprises the steps of obtaining an initial sample set; performing multiple sampling reasoning on the problem of each task sample by using a small language model to generate a plurality of reasoning chains; calculating an overall error score of each reasoning chain based on a preset error evaluation rule, and determining a to-be-corrected reasoning chain; the inference chain to be corrected and the corresponding question are input into the large language model together, and a corrected answer is generated; forming a new task sample by the question and the corrected answer, and finely adjusting partial parameters of the small language model; repeatedly executing the process until the performance index change rate of the model on the task evaluation set is lower than a preset threshold value, and outputting a final task sample; and forming a training sample set by a plurality of final task samples, and performing all-parameter fine tuning on the small language model. According to the method, the training data self-optimization path is constructed by taking the model error as guidance, so that the semantic consistency and the data validity are improved.

The invention discloses an electromagnetic ultrasonic transducer rapid design method based on an S-SADE algorithm, and the method comprises the steps: constructing an electromagnetic ultrasonic transducer model and a joint simulation platform, obtaining initial sample data and various parameters, and initializing a population and a sample database; using samples in the database to construct an RBF proxy model; performing variation and crossover operation on the parent population individuals according to five variation strategies to obtain a filial population; using an RBF agent model to predict fitness values of offspring individuals, transmitting parameters of an optimal individual to an electromagnetic ultrasonic transducer model for simulation evaluation, and updating a database; selecting a most expected sub-population from the five sub-populations as a next-generation population; and outputting an optimal parameter design scheme. According to the adaptive differential evolution algorithm, appropriate variation strategies and control parameters can be selected in different evolution stages, the objective function values of population individuals are predicted through the proxy model instead of expensive simulation evaluation, and computing resources can be saved to a great extent.

The invention discloses a mixed tower type fan reliability analysis method and device based on a multi-fidelity numerical model. The method comprises the following steps: establishing more than two mixed tower type fan dynamic models; respectively inputting the input data into each mixed tower type fan dynamic model to obtain extreme value response result data with different precisions; training different types of machine learning models by using the low-precision response results to obtain a plurality of first agent models; respectively inputting the high-precision response result into each first agent model to obtain a predicted value, adjusting each first agent model according to the predicted result, and synthesizing each predicted result to train to obtain a second agent model; obtaining an initial sample point and inputting the initial sample point into the second agent model to obtain an extreme value response result; and calculating the reliability according to an extreme value response result obtained by the second agent model. According to the method, reliability analysis of the mixed tower type wind turbine in the multi-failure mode can be achieved, and the analysis efficiency, accuracy and credibility are improved.

The invention discloses a polar equipment fatigue crack propagation reliability analysis method based on an improved SVM (Support Vector Machine), which comprises the following steps: acquiring uncertain parameters influencing the fatigue crack propagation of a polar equipment structure, and generating a candidate sample population by adopting a random sampling method according to the uncertain parameters of fatigue performance; generating an initial sample by adopting an orthogonal test method based on the fatigue performance uncertain parameters; evaluating the real cycle index response of the test sample; performing normalization processing on the obtained candidate sample, the test sample, the initial training sample and the cycle index response set; constructing an IBOA-LS-SVM model based on the initial sample, and obtaining a cycle index prediction value of the test sample and the candidate sample set; carrying out reverse normalization processing on the predicted value of the cycle index of the test sample point and the predicted value of the cycle index of the candidate sample point, carrying out precision test on the IBOA-LS-SVM model by adopting the true value and the predicted value of the cycle index of the test sample, and if the precision meets the requirement, calculating the failure probability of fatigue crack propagation at different polar region service environment temperatures by utilizing an MCS method; and if the precision does not meet the condition, carrying out orthogonal test design again.

The invention belongs to the technical field of speech enhancement, and discloses a Schrodinger bridge-based diffusion model speech enhancement method and system, and the method comprises the steps: converting a diffusion process of a diffusion model into a solving process of a stochastic differential equation, and determining the stochastic differential equation according to the theoretical principle of a Schrodinger bridge, and the complex spectrum is directly used as the input of the diffusion model, so that the tedious work of extracting a phase spectrum and an amplitude spectrum from the complex spectrum and the memory overhead caused by inverse transformation are omitted, and meanwhile, the alignment problem between the phase spectrum and the amplitude spectrum is also avoided. According to the speech enhancement method, unique features of time sequence signals are captured through a Transformer module, multi-scale information is fused through a U-Net module, a loss function covering a time domain, a frequency domain and a time-frequency domain is matched, the difference between a prediction sample and a clean sample is gradually reduced, the nonlinear diffusion process from a noisy sample to the clean sample can be directly learned, and the speech enhancement accuracy is improved. Therefore, the structure information of more initial samples is reserved.

The invention provides a soil heavy metal pollution risk zoning and grading method based on machine learning. The method comprises the following steps: respectively acquiring heavy metal sample data and environmental covariant data in a research area as a corresponding initial sample data set of target heavy metal; and preprocessing each initial sample data set to obtain a corresponding research sample data set. And obtaining pollution risk indexes of the target heavy metals. Mixing the research sample data sets, and randomly dividing the research sample data sets into a training set and a test set; and establishing a heavy metal risk zoning and grading model based on a random forest model according to the classification labels, the training set and the test set. And according to the effective environmental influence variables corresponding to the unknown areas in the research area, identifying and partitioning the soil heavy metal pollution risk of the research area. According to the method, the soil heavy metal pollution risk is quantitatively, qualitatively and from multiple angles, and the soil heavy metal potential pollution risk area is scientifically divided.

The embodiment of the present invention discloses a method for predicting corneal reshaping parameters based on an artificial neural network, and relates to the technical field of orthokeratology lenses. The method comprises: obtaining an initial sample data set, deleting target samples that do not contain necessary parameters, and obtaining a basic sample data set; preprocessing the basic sample data set to obtain a final sample data set; training the initial artificial neural network model to obtain a preliminary model; using the preliminary model to forward propagate the input layer data of the basic sample data set to obtain a calculation result and compare it with the result of the basic sample to obtain a final sample data set, and using the final sample data set to train the preliminary model to obtain a prediction model; inputting actual eye detection data into the prediction model to obtain corresponding corneal reshaping parameters. The present invention splits the data to be predicted into multiple dimensions, constructs different prediction models according to each data to be predicted, and then performs distributed training and uses them in combination.

The invention discloses a hybrid optimization method and system assisted by incremental multi-fidelity machine learning. The method mainly comprises the steps of initial setting and initial sample acquisition, training of a global low-fidelity proxy model # imgabs0 # and a residual model # imgabs1 #, global optimization, training and optimization of a local proxy model, low-fidelity full-wave simulation, re-prediction of an updated proxy model # imgabs2 #, high-fidelity simulation and the like. According to the method, a multi-fidelity model and adaptive incremental learning are introduced in the process of training and updating the proxy model, the calculation complexity of sampling and training can be effectively reduced, meanwhile, a global multi-target and local single-target hybrid optimization algorithm is adopted in the optimization process, and the algorithm search efficiency can be improved. The method can be used in the field of optimization design of multi-target electromagnetic devices such as medium-scale antennas, arrays, filters and the like with design parameters in 20-50 dimensions.

The invention discloses an optimization design method for a control surface of a wide-speed-range large-attack-angle reusable carrier, and relates to optimization design of aerodynamic configuration of an aircraft. The method comprises the following steps: S1, setting a control surface aerodynamic configuration design variable range, and generating an initial sample library by adopting Latin hypercube sampling; s2, aerodynamic parameters are obtained through CFD simulation, and a Kriging proxy model is trained; s3, evaluating the precision of the proxy model by taking a U learning function as a criterion, and stopping adding points when the minimum U function value is smaller than a threshold value; s4, constructing an optimization model which takes maximization of the lift-drag ratio and the static stability margin under the hypersonic speed as a target and takes the condition that the aerodynamic parameters of the supersonic speed / subsonic speed are not lower than a reference value and the hinge moment as constraints; and S5, performing iterative optimization by adopting an improved multi-target particle swarm algorithm based on genetic algorithm crossover mutation operation, updating the proxy model after the optimal solution of each generation is subjected to CFD verification, and outputting an optimal solution set. The problem of wide-speed-range aerodynamic configuration contradictions is solved, and the comprehensive performance of the carrier is remarkably improved.

The embodiment of the invention provides a data construction method, a code question-answering method, a task platform and a code question-answering system. The data construction method comprises the steps of obtaining a first code snippet and an initial sample question for the first code snippet; rewriting the initial sample problem by using a text processing model and taking directory structure information of a sample code warehouse in the code library as context information to obtain a sample problem; based on the first code snippets and the sample questions, recalling related second code snippets from a code library; the text processing model is utilized, the second code snippets serve as context information, sample answers corresponding to the sample questions are generated, the sample questions and the sample answers are sample data used for training a code question and answer model, and the code question and answer model is suitable for a code warehouse. The data construction efficiency is improved, the data construction cost is reduced, the model obtained through training is adaptive to the code warehouse, and the user experience is improved.

The invention discloses a small sample self-adaptive mixed gas sensor dynamic response modeling method, which belongs to the technical field of gas sensors, and specifically comprises the following steps: testing mixed gas through a gas sensor array, and generating a response signal; pulse signals representing gas concentration mutation characteristics are generated, the pulse signals and response signals form an initial sample set, short-time-sequence fragments are obtained through truncation separation, initial state signals are generated at a time step before a response rising point, and a short-time-sequence fragment sample set is obtained; forming an enhanced data set through non-playback extraction and carrying out normalization processing on the enhanced data set; and constructing and training to obtain gas sensor dynamic response models of different gas sensors. By simulating the complex dynamic response of the gas sensor, the data sample enhancement of the mixed gas is completed, the difficulty of training a mixed gas component identification model by using a small sample is reduced, and the model can quickly adapt to environmental change and performance difference of different sensors; and reliable and effective data enhancement support is provided for mixed gas component identification.

The invention discloses a carbon dioxide oil displacement burying multi-objective optimization method based on a self-adaptive agent model, and relates to the technical field of oil reservoir injection and production optimization. The method comprises the following steps: firstly, constructing a carbon dioxide flooding embedding injection-production optimization model, then acquiring a plurality of initial samples by adopting Latin hypercube sampling to construct a database, preferably selecting each target agent model based on the database, and then generating a Pareto leading edge by utilizing a dominating class search strategy, a decomposing class search strategy and an index class search strategy; and in the optimization stage, a preferred potential solution is searched according to a hypervolume improvement maximum strategy, numerical simulation is carried out, the database is updated until a preset number of times is reached, each iteration optimization scheme, an oil reservoir net present value and a carbon dioxide burying amount are output, and multi-target optimization of carbon dioxide flooding burying is completed. According to the method, the carbon dioxide flooding multi-objective optimization efficiency is improved, meanwhile, the search direction is dynamically adjusted through the hyper-volume evaluation index, the Pareto frontier is accelerated, and accurate prediction of the carbon dioxide flooding development scheme is achieved.

A method for calculating decision variables is configured to calculate the unconfirmed decision variables. First, the method provides a trained predictive mode obtained by machine learning through a machine learning method on a dataset. Next, the method transforms the objective function of the trained predictive model from a constrained objective function to an unconstrained objective function. The method then solves the optimization problem of the unconstrained objective function, wherein the optimizer, trained with the trained predictive model, calculates gradients to facilitate the solution process. Additionally, the samples from the dataset used to train the trained predictive model can be utilized to determine the initial samples for solving the optimization problem. The method for calculating decision variables of the invention can also add a dummy layer in front of the trained predictive model. The optimizer, starting from the initial sample, calculates the arc weight values between the dummy layer and the input layer as the unconfirmed decision variables.

The invention discloses a wind field rapid prediction method and system based on optimized Latin hypercube sampling and POD-BPNN, and the method comprises the steps: carrying out Latin hypercube sampling to generate an initial sample point set, introducing a sensitivity weight, and carrying out the iterative optimization of sample distribution through a greedy strategy; assembling the CFD numerical simulation flow field data of all sample points in the sample point set into a flow field snapshot matrix, and determining a dynamic multi-target truncation order and a corresponding POD mode and coefficient; building and training a BPNN model, packaging the trained BPNN model, the POD modal matrix, the mean field and the flow field reconstruction logic into an FMU module, obtaining the FMU module which can be called in a cross-platform manner, and achieving the real-time prediction of a wind field. The invention relates to the technical field of wind field prediction, significantly improves the precision and calculation efficiency of wind field prediction, and provides an efficient and accurate solution for the rapid prediction of a wind field.

The embodiment of the invention discloses a model training method and device applied to direct current arc discharge detection. The method comprises the steps of performing at least two times of data processing on first time sequence data and second time sequence data and forming a sample set; selecting an initial neural network model obtained by training the initial sample set as a current detection model, taking the initial sample set as a current test set, and testing the current detection model by using the current test set to obtain a current test output result; and determining a next sample set based on the current test output result, taking a next neural network model obtained by training the next sample set as a current detection model, and taking the next sample set as a current test set for model test until the current test output result meets a preset requirement. According to the technical scheme, the precision and the accuracy of the output model can be improved, so that the accurate detection of the direct current arc discharge of the photovoltaic system is realized, and the safe and stable operation of the photovoltaic power generation system is ensured.

The invention relates to the technical field of semantic communication, and provides an image semantic communication method, device and equipment and a storage medium, and the method is applied to a sending end, and comprises the steps: segmenting a to-be-sent target image into a plurality of image blocks; semantic information of each image block is extracted by using an encoder and input to a linear mapping layer for linear mapping processing, and then the semantic information is sent to a receiving end through a wireless channel; after a receiving end performs linear mapping on the semantic information, a decoder is used for performing semantic recovery and image reconstruction to obtain an output image; wherein the codec is provided with recursive variator units with the same structure, and the number of the recursive variator units is determined by performing joint training by taking calculation of time delay as an optimization target and taking similarity of an input initial sample image and a sample image reconstructed by a receiving end as a constraint. The network architecture of the codec is constructed through joint training, the terminal computing power and task performance can be balanced, and efficient semantic communication is realized under the condition that the terminal computing power is limited.

The invention discloses a parallel evolutionary solution method for search space segmentation, comprising: S1, randomly generating solution schemes via a search space sampling and segmentation module, calculating fitness values by combining initial sample schemes with an optimization objective function, statistically screening sample schemes, determining the dimension direction K of the segmented search space, and dividing the search space into subspaces; S2, executing a global search algorithm in the segmented subspaces to obtain a global initial solution scheme; S3, using the global initial solution scheme as a starting point, obtaining a precise solution scheme via a local search algorithm. This method employs evolutionary sampling of the search space, deriving fitness terrain analysis results, and guiding the division direction and step size of the search space. Multiple search subspaces are segmented to enable parallel search for subsequent evolutionary calculations.

The invention discloses a post-pumping air tank robustness collaborative design method considering hydraulic parameter time-varying characteristics, which comprises the following steps: defining a hydraulic parameter uncertainty fluctuation interval of a water delivery system in a full life cycle, and setting a body structure decision variable range of a post-pumping air tank; performing combined sampling in the water conservancy parameter uncertainty fluctuation interval and the body structure decision variable range by using a test design method to generate an initial sample set; performing steady-state and transient-state coupling simulation on the initial sample set, constructing a constant-flow operation condition of the water delivery system by using a hydraulic equation, updating a water pump working point and pipeline pressure distribution, performing transient simulation by using a characteristic line method to obtain a hydraulic response index, and training to obtain a water hammer response agent model; constructing a robustness optimization objective function based on failure probability constraint; and performing global optimization on the target function by using an intelligent optimization algorithm, calling the water hammer response agent model to perform random simulation, evaluating a failure probability, and outputting a target design scheme.

The invention relates to a sparse antenna array synthesis method based on neural network intelligent solution, and the method comprises the steps: carrying out the full-wave simulation of an antenna unit according to an array synthesis requirement, obtaining a unit active directional diagram, and constructing a unit active directional diagram database; constructing an initial sample set according to the unit active directional diagram and the array numerical simulation model; randomly dividing the initial sample set into a training set and a verification set, carrying out offline training by utilizing the training set, and carrying out array comprehensive solution on verification set data; judging whether the resolving result meets the arraying requirement or not, if not, adopting a convex optimization algorithm to assist calculation, updating the data set, and retraining; otherwise, outputting the neural network model; and through the model, according to the unit spacing constraint and the active directional diagram, sparse antenna array synthesis is carried out, and array topology is output. The method can achieve the comprehensive settlement of the antenna array, is high in speed, is high in efficiency, and better accords with a real array working environment.

The invention provides a hybrid screen space global illumination method based on resampling and a probe, and relates to the technical field of global illumination, and the method comprises the steps: firstly, in an offline environment, pre-calculating a baking light field probe; rendering a geometric buffer area, and updating a light field probe; using screen space ray tracing to generate an initial sample; performing time resampling and space resampling; obtaining an indirect diffuse reflection illumination result; carrying out delayed coloring by utilizing the generated geometric buffer area, indirect diffuse reflection illumination, light source data and shadow information; and sampling indirect diffuse reflection illumination by using the screen space coordinates of the pixels, and superposing the indirect diffuse reflection illumination with a direct illumination result, thereby obtaining a final coloring result.

The embodiment of the invention provides an emotion recognition method and device, and the method comprises the steps: determining an initial sample group, and obtaining initial face data based on the initial sample group; performing data annotation on the face data, and determining annotated data; performing data preprocessing based on the annotation data, and determining target face data; performing feature extraction based on the target facial data, and determining expression features; training a deep learning model based on the expression features, and determining an emotion recognition model; and acquiring to-be-recognized face data through a camera, and determining emotion data from the to-be-recognized face data through the emotion recognition model. The method realizes automatic detection and recognition of micro-expressions by constructing a deep learning model, has high precision, high efficiency and wide application prospect, and can be applied to the fields of man-machine interaction, intelligent monitoring, mental health and the like.

The invention relates to a limestone granularity detection method based on YOLO-ADM, which comprises the following steps: firstly, collecting a raw material crushing section limestone data set, then carrying out data enhancement on an initial sample limestone data set, and dividing the initial sample limestone data set into a training set, a verification set and a test set; a deformable attention mechanism DAttention, a multi-scale sequence fusion module SSFF and a triple feature decoding module TFE are integrated in the YOLOv8 framework, and a YOLO-ADM model is obtained; on this basis, a training loss function is improved, and a loss function MioU based on the auxiliary frame and the minimum point distance is designed; and training the YOLO-ADM model through the training set and testing the performance of the network model through the test set. According to the method, the deformable attention DAttention is introduced into the YOLOv8 network, the YOLOv8 neck network is redesigned based on the multi-scale sequence fusion module SSFF and the triple feature decoding module TFE, the designed loss function MioU is combined, the excellent performance is shown in limestone detection, and the generalization performance is good.

The invention relates to the technical field of deep learning, in particular to a migration attack resisting method based on a regularization constraint feature layer, which comprises the following steps: data preprocessing and regularization constraint are carried out, an initial sample is prepared, and regularization constraint is applied to remove low-frequency components; generating an initial confrontation sample, and generating the initial confrontation sample by using an existing iterative attack algorithm; dividing a neural network feature layer, and identifying and dividing the feature layer of the neural network model; feature layer regularization loss function design: designing a regularization loss function for each feature layer; feature layer confrontation sample generation: generating a confrontation sample on each feature layer; evaluating the mobility of the adversarial samples, and evaluating the mobility of the adversarial samples of each feature layer on other models; according to the anti-migration attack algorithm based on the regularization constraint feature layer, disturbance is added to the optimal migration level of the statistical result, and then an anti-migration sample with better mobility is generated.

The invention relates to the technical field of component analysis, and discloses an X-ray fluorescence spectrum-based rock and ore silicate component analysis method, which comprises the following steps: S1, sample collection and pretreatment: collecting, crushing and drying an initial sample, S2, sample tabletting preparation, S3, standard sample preparation, S4, X-ray fluorescence spectrum analysis, and S5, data processing and result analysis. According to the method, a complex interference characteristic mode between elements can be automatically captured through an established deep learning model and learning of a large number of known components and fluorescence spectrum data, and in an example of correcting interference between multiple elements in rocks and mines, the model can utilize a network structure of the model and comprises an established convolutional layer, a pooling layer and a full-connection layer. Effective information is extracted from multiple groups of sample data, the interference relation between elements is accurately learned, and compared with a traditional method, the precision of analyzing the content of silicate components in rock ore is remarkably improved, so that a measurement result is closer to a real value.

The invention discloses a fault detection method for a persistent memory server, and relates to the technical field of fault detection and persistent memories, and the method comprises the following steps: collecting various historical index data from a persistent memory during the operation of a system, carrying out the preprocessing, and constructing an initial sample set; expanding the initial sample set by using a generative adversarial network to obtain an expanded sample set; a CNN-LSTM model is constructed, the expanded sample set is used for model training until network convergence, and a trained persistent memory fault prediction model is obtained; and monitoring the running state of the system in real time by using the trained persistent memory fault prediction model, predicting potential faults of the persistent memory, and determining whether to send out fault early warning or not by setting a threshold value. According to the method, the fault detection accuracy can be improved, memory faults can be found in time, measures are taken for repairing, and stable operation of the system is ensured.

Embodiments of the present description provide a target detection method, comprising: determining an image to be detected of a target domain; inputting said image into a target detection model corresponding to the target domain, to obtain a target object image corresponding to said image, wherein the target detection model is obtained by training on the basis of a source domain labeled sample in a source domain training data set, and target domain initial samples and target domain labeled samples in a target domain training data set, the target domain labeled samples are obtained by screening from among the target domain initial samples on the basis of a preset sample selection policy, the target domain training data set, and the source domain training data set. A training sample of a source domain and training samples of the target domain are considered in the training process, so that the migration of a model from the source domain to the target domain is realized, the trained target detection model is also applicable in the target domain, and the generalization performance and the task processing performance of the target detection model in various fields are further ensured.

The invention discloses a method for predicting the social distraction risk of a colorectal cancer chemotherapy patient. The method comprises the following steps: firstly, acquiring an initial sample data set of colorectal cancer chemotherapy patients, carrying out potential profile analysis and subject working characteristic curve analysis on the patients, dividing a colorectal cancer chemotherapy patient group into a group without social distraction and a group with social distraction, and defining a social distraction threshold according to group division; on the basis, performing variable screening on an initial influence factor in the initial sample data set, determining main influence factor data and a corresponding data set, and then training a constructed initial prediction model of the social distraction risk based on the main influence factor data and the corresponding data set to obtain an initial prediction model of the social distraction risk; according to the method, a fully trained social distraction risk prediction model is obtained, and the social distraction risk of the patient is accurately predicted based on the fully trained social distraction risk prediction model, so that the risk that the colorectal cancer chemotherapy patient encounters the social distraction in the treatment process can be effectively prevented in advance.

The invention belongs to a data processing method, and provides a data enhancement method, a data enhancement system, electronic equipment and a computer storage medium aiming at the technical problems that a manual annotation mode is difficult to cope with continuously changing business scenes and the timeliness and the flexibility of corresponding model training cannot be ensured when atlas construction and relation extraction technologies are utilized at present. And marking entities and relationships in the initial sample, performing classification arrangement to obtain an entity dictionary, replacing the entities of the text in the marked sample, and marking the replaced entities to obtain a first augmented sample. Constructing a relationship template and a sentence pattern template, re-expressing the text in the replaced first augmented sample through the sentence pattern template, replacing the entity and relationship of the text in the re-expressed first augmented sample in combination with the entity dictionary to obtain a second augmented sample, and then summarizing and fusing the first augmented sample and the second augmented sample to obtain a second augmented sample; and enhanced data is obtained.

The invention discloses a task issuing method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring the total quantity of tasks to be deployed and the quantity of resources required by each task; constructing an initial sample set based on the total quantity of tasks to be deployed and the quantity of resources required by each task; the initial sample set is screened, a first sample set is obtained, and each sample in the first sample set corresponds to one task issuing strategy; performing fragment splitting on samples in the first sample set to obtain a second sample set; performing sample cross exchange and recombination on the fragments in the second sample set to obtain a third sample set; and calculating an optimal solution for the third sample set based on a simulated annealing algorithm, and issuing the task according to a task issuing strategy of a sample corresponding to the optimal solution. According to the method and the device, the technical problem of how to determine the task issuing strategy and improve the efficiency under limited resources is solved.

The invention discloses a virtual power plant gateway data processing method and system based on edge computing, and relates to the field of new energy power generation prediction, and the method comprises the following steps: obtaining an initial sample set from a database, the initial sample set comprising historical meteorological data and historical power generation power; removing abnormal data in the initial sample set; carrying out meteorological correlation coefficient calculation on the historical meteorological data and the historical power generation power, and dividing the historical meteorological data into historical correlation meteorological data and historical irrelevant meteorological data based on the meteorological correlation coefficient; the new energy power generation prediction method is used for solving the problems that in an existing new energy power generation prediction technology, meteorological data are accurately selected, a power generation abnormity judgment link is lacked after prediction, and the power generation efficiency is low. And power generation prediction is not accurate and abnormal power generation is not found timely.