227 results about "Recurrent neural network model" patented technology

The invention discloses a health risk assessment method and early warning system based on multi-source data analysis. The health risk assessment method comprises the following steps: S1, collecting and preprocessing multi-source health data through medical detection equipment; s2, extracting key health indexes, sequence features and statistical features based on the health data set; s3, adopting a recurrent neural network model to construct a health risk assessment model; s4, optimizing structural parameters of the health risk assessment model by adopting an improved dragonfly algorithm; s5, performing performance evaluation on the health risk evaluation model by using the optimal parameter set; s6, deploying the final health risk assessment model in a health risk assessment and early warning system; and S7, when the health risk assessment result exceeds a preset risk threshold, automatically generating early warning information. According to the method, the recurrent neural network model, the improved dragonfly algorithm and the multi-source health data fusion optimization technology are combined, and health risk assessment and early warning based on multi-source data analysis are realized.

The invention relates to the technical field of isolator service life prediction, and discloses an isolator remaining service life prediction method based on deep learning. The method comprises the following steps: acquiring a vibration signal and a temperature signal when the isolator operates, and constructing a multi-dimensional sensor sequence; dividing a plurality of sub-sequence units containing a fixed time window; extracting time domain and frequency domain features of each sub-sequence unit, and generating a fusion feature vector; calculating statistical distribution characteristics and variation trend characteristics of key indexes in the vector, and outputting a health state index; through a bidirectional recurrent neural network model containing an attention mechanism, taking the health state index and the historical degradation data as input, processing a time sequence dependency relationship through multi-layer residual error connection, and generating a residual service life prediction value; and updating the multi-dimensional sensor sequence according to the real-time sensor signal, and dynamically correcting the predicted value. According to the method, multi-dimensional data are integrated, degradation characteristics are deeply mined, and the accuracy and adaptability of prediction of the remaining service life of the isolator can be improved.

Provided in the present invention are a power-distribution-network self-healing method and system taking photovoltaic output into consideration. The method comprises: acquiring historical operation data of a photovoltaic power station and irradiance observation data from a meteorological station; on the basis of the historical operation data of the photovoltaic power station and the irradiance observation data from the meteorological station, predicting the generated power of the photovoltaic power station by using a convolutional long-short-term memory recurrent neural network model that takes sparrow search into consideration; on the basis of the generated power of the photovoltaic power station, a segment-switch state of a power distribution network and a network topology of the power distribution network, constructing an objective function and a constraint condition for a power-distribution-network self-healing model, and obtaining the power-distribution-network self-healing model; solving the power-distribution-network self-healing model by using a propagation search algorithm, so as to obtain an optimal recovery strategy; and executing the optimal recovery strategy by means of segmented switches and node loads. The present invention can realize self-healing of a power distribution network while ensuring the minimum power generation cost of a distributed power source, the minimum network loss and the minimum node voltage deviation.

The invention discloses a classroom environment intelligent supervision method and system based on data analysis, and the method comprises the steps: obtaining multi-source heterogeneous data in a classroom environment, eliminating the sensor noise of the multi-source heterogeneous data through employing an improved Kalman filtering algorithm, carrying out the time-space alignment of the data after noise elimination, and obtaining the aligned multi-source heterogeneous data; establishing a CRNN three-layer convolutional recurrent neural network model, and inputting the aligned multi-source heterogeneous data into the CRNN three-layer convolutional recurrent neural network model for recognition to obtain a classroom teaching environment state; and carrying out classroom risk early warning and self-adaptive classroom environment regulation and control according to the classroom teaching environment state. The classroom emergency risk can be actively prevented, automatic adjustment can be achieved through an intelligent air conditioner and an illumination system, a safe and comfortable teaching environment is created, and classroom efficiency improvement and teacher and student health guarantee are facilitated.

The invention relates to the technical field of robot control, and discloses a mechanical arm trajectory planning control method and system based on a BAFARNN model. The method comprises the steps that a mechanical arm kinematics model is established, and a trajectory tracking problem is converted into a time-varying equation; designing a bounded adaptive function to activate a recurrent neural network model, defining an error function and constructing a dynamic equation; designing a piecewise adaptive coefficient function, and dynamically adjusting the gain according to an error norm and time; setting a Lissajous curve as an expected trajectory, and initializing a simulation environment; the joint speed is solved in real time through an ODE numerical method, and the mechanical arm is driven to move; actual motion data is collected and compared with an instruction, and closed-loop feedback control is triggered when the actual motion data exceed a threshold value. According to the method, rapid convergence is achieved through the piecewise adaptive coefficient function, the bounded activation function and the negative feedback mechanism are adopted to suppress noise, and high-precision and real-time trajectory tracking of the mechanical arm in the dynamic environment is achieved.

The invention relates to the technical field of resource scheduling, in particular to a digital-intelligent non-accompanying service management scheduling system, which comprises a service baseline construction module for instantiating a service item into a standard plan event flow; the state portrait generation module is used for collecting service object data flow, establishing a dynamic time sequence signal by applying a recurrent neural network model, and quantifying the occurrence probability of a future abnormal event through multi-step prediction; when the triggering is abnormal, executing causal two-way collision positioning reasons by applying the knowledge graph; the task load calculation module is used for integrating the plan event flow into a plan task component, and generating a worker resource list in combination with the predictive risk score and the worker real-time load and space reachability analysis containing the fatigue index; the system further comprises a task distribution module, the optimal staff is determined and a closed-loop scheduling instruction is generated by minimizing a composite cost function containing predictive load cost, and digital intelligent unattended service management from prediction to scheduling is realized.

The invention discloses a household energy storage dynamic optimization method and system combined with load feature learning, which are used for reducing prediction errors caused by sudden loads and improving response efficiency and economical efficiency of a household energy storage system. The method comprises the following steps: calculating a prediction error between real-time total load data and a basic prediction result, identifying and locking one or more high-power electric appliances causing the prediction error as target electric appliances, and decomposing and extracting historical operation state data of the target electric appliances from the total load data; constructing a time sequence feature vector based on the historical operation state data, and training by using a recurrent neural network model to extract the sudden load feature of the target electric appliance; fusing the optimized sudden load characteristics with a basic prediction result to generate a total load prediction curve; and based on the total load prediction curve, combining the residual capacity and the operation health state of the household energy storage system, and adopting a multi-objective optimization method to dynamically generate a charging and discharging strategy.

The invention relates to the technical field of component strength detection, and discloses a big data-based component strength judgment system, which comprises a data acquisition module, a data preprocessing module, a single-point strength analysis module and a continuous strength evaluation module. The data acquisition module obtains multi-dimensional parameters of the component and performs standardization processing, and main body features and abnormal fluctuation areas are separated; the preprocessing module identifies the boundary and calibrates a parameter data space coordinate system; the single-point strength analysis module generates a topological network through key nodes, and judges the strength of a detection unit in combination with structural feature density and span; and the continuous strength evaluation module generates a continuous fluctuation curve based on the parameter sequence, and evaluates the strength continuity through the curvature change rate and the recurrent neural network model. The system realizes multi-dimensional data intelligent analysis, improves the comprehensiveness and accuracy of component strength detection, is suitable for complex structure strength evaluation, and provides technical support for engineering safety.

The invention discloses a low-sample neural network structure reliability evaluation system and evaluation method, and relates to the technical field of engineering structure safety monitoring, and the evaluation system comprises a cloud server which is used for constructing a recurrent neural network model containing a static variable embedding mechanism, completing model training and converting a model format; the edge calculation terminal is used for receiving and preprocessing real-time data of the sensor, executing multi-step prediction to output a future time period response sequence, and calculating a future failure probability through virtual Monte Carlo simulation; the sensor assembly is used for collecting structure state time sequence data; and the communication module is used for realizing data interaction and alarm signal transmission operation. According to the method, collaborative modeling of time-varying and static uncertainty is realized by adopting a static variable embedded recurrent neural network model, failure probability distribution is generated at an edge computing terminal in combination with a virtual Monte Carlo technology, failure risk prediction in a future time period is supported, and real-time and accurate reliability early warning can be realized in a resource limited scene.

The invention provides a self-adaptive source-load-storage coordinated optimization control method and system, and the method comprises the steps: S1, collecting multi-element load data generated during the operation of a microgrid, and forming a time series data set; s2, key variable characteristics which have the largest influence on the micro-grid load operation state in the micro-grid load requirements are recognized; s3, determining and constructing a source-load-storage cooperative control model based on the key variable characteristics, and determining an optimal decision variable value meeting a real-time load demand; and S4, making a regulation and control strategy according to the optimal decision variable value, and realizing optimal operation of the micro-grid. According to the method, the load demand of the power system is predicted based on the trained recurrent neural network model, the most critical characteristic variable is identified, the time sequence data which can most represent the power grid load operation state during the microgrid operation period is extracted and analyzed, and the unnecessary calculation amount is reduced by focusing on the most critical characteristic variable, so that the power grid load operation state is optimized. Therefore, the whole analysis process is more efficient and accurate.

The invention discloses a power transmission corridor tree species growth prediction method, system, device and medium, and belongs to the technical field of tree growth prediction.The method comprises the steps that tree species data and environment data in a power transmission corridor area are obtained, the tree species data and the environment data are preprocessed, and a training data set is obtained; training a cascade recurrent neural network model based on the training data set to obtain a trained cascade recurrent neural network model; predicting the growth trend of the tree species according to the trained cascade recurrent neural network model to obtain a prediction result, performing error analysis on the prediction result, and optimizing the trained cascade recurrent neural network model according to an error analysis result; performing growth trend analysis according to the prediction result, and determining the growth trend of the tree species; and carrying out early warning on the growth trend of the tree species through the prediction result in combination with a preset safety threshold. According to the method, the tree growth prediction precision is improved through a cascade structure.

The invention relates to the technical field of electric digital data processing, in particular to a shock absorber data processing method and system based on digital twinning, and the method comprises the steps: obtaining a multi-channel data signal of a shock absorber, and constructing a panoramic vibration data tensor; extracting a discrete digital sequence on a panoramic vibration data tensor time dimension, executing a variational mode decomposition algorithm, and separating and extracting a transient impact feature vector flow; constructing a double-time-axis sliding mapping window, and mapping the transient impact feature vector flow to a future node of a prediction response time axis based on a front and rear wheel preview mechanism of a vehicle wheelbase; operating the time sequence recurrent neural network model, and predicting and generating a target state data matrix of future nodes; and in the numerical constraint space, a prediction type damping adjustment instruction data packet is solved and generated through a rolling optimization algorithm. Through prospective state prediction and optimization solution, the problem of data timeliness caused by calculation delay in digital twinning is solved, and real-time, predictive and safe adjustment of the shock absorber is realized.

The invention discloses a license plate recognition method and system for automatic highway toll collection, and the method comprises the steps: collecting a vehicle image through a plurality of image sensors, sequentially carrying out the noise reduction, contrast enhancement and white balance adjustment of the vehicle image, and generating an initial vehicle image; synthesizing different light source images in the initial vehicle image by using an image fusion technology; performing coarse positioning on a license plate area in the synthesized vehicle image based on an improved YOLOv7 model in combination with a Canny edge detection algorithm; and segmenting license plate characters in the license plate region image by using a semantic segmentation model of U-Net, and performing end-to-end character recognition through a lightweight CRNN convolutional recurrent neural network model to obtain a license plate recognition result. And the recognition speed is greatly improved while the recognition accuracy is ensured.

The invention relates to the technical field of power system data processing, in particular to a power system data processing method and system based on dynamic period detection, and the method comprises the steps: collecting a historical query log of a power business system, and extracting time sequence data of query features through a sliding window; training a recurrent neural network model by using the time sequence data, and predicting a current optimal query period length; on the basis of the optimal query period length, predicting an index combination required by query through a classification model, and generating a candidate index set; optimizing an execution strategy of the candidate index set by taking the minimum index construction cost and the maximum query coverage rate as targets; and obtaining query data of the power business system in real time, and updating the candidate index set and the execution strategy when the change of the business period characteristic is detected. The objective of the invention is to match the periodic change of the power system data, improve the indexing efficiency and reduce the maintenance cost.

The invention discloses a music playing intelligent evaluation system and method based on multi-mode and man-machine cooperation, and relates to the technical field of music playing intelligent evaluation, and the method comprises the steps: collecting audio signals, video images and playing motion data in a music playing process, and obtaining a multi-mode information data set; performing feature extraction on the multi-mode information data set, and analyzing the audio signal, the video image and the playing action data by applying a convolutional neural network and a recurrent neural network model to generate a basic feature set; based on the basic feature set, utilizing a deep learning algorithm to identify and analyze emotion content conveyed in the playing process, and outputting an emotion intensity value and an emotion category; analyzing intonation error, rhythm deviation and strength matching degree according to comparison between the standard music score and the playing record, evaluating action normalization of the player in combination with action characteristics extracted from the playing action data, and calculating scores of all dimensions; and adjusting the weight between the objective score and the subjective score according to the application scene.

The invention relates to the technical field of post insulator detection, and discloses a post insulator crack detection method and system based on stress wave recursion characteristics, and the method comprises the steps: S1, generating an initial stress wave through a high-energy pulse exciter, and introducing the stress wave into a post insulator; s2, collecting a dynamic response signal of insulator stress wave propagation by using a distributed fiber bragg grating sensor network; s3, carrying out preprocessing on the dynamic response signal; s4, acquiring real-time environment parameters through an environment monitoring sensor; s5, combining material attributes and geometric structures of the post insulators; and S6, outputting recursive quantization features based on the recursive neural network model. According to the method, a stress wave propagation path is dynamically tracked by constructing a recurrent neural network model, multiple reflection characteristics of waves are quantified, abnormal phase deviation is accurately captured based on material attribute physical constraints, and the energy characteristic analysis capability of tiny defects is remarkably enhanced.

The invention belongs to the technical field of sensor measurement and recognition, and particularly relates to a human body motion recognition system based on LSTM (Long Short Term Memory), which comprises a data acquisition module, a data calculation module and a data application module, and utilizes a neural network model and a wearable electronic sensor to detect a human body walking state. A new long short term memory (LSTM) recurrent neural network model, namely an LSTM-STRM model, is established, the model combines multi-task learning, an attention mechanism and spatio-temporal feature fusion to accurately classify the walking state of the human body, and the walking state is compared with the original LSTM model. The result shows that the LSTM-STRM model can be used for classifying the time sequence data collected by the measuring unit, the states of the five targets can be classified with high precision, and the recognition accuracy is higher than that of an original LSTM model. The method improves the recognition precision, is high in adaptability, is suitable for the fields of medical treatment, human-computer interaction, exercise training and the like, and has a wide application prospect.

The invention discloses a self-adaptive system data inspection and anomaly repair method for an intelligent computing center, and relates to the technical field of intelligent computing system operation and maintenance and data processing, and the method comprises the steps: collecting system operation data of a plurality of computing nodes of the intelligent computing center, and carrying out the dynamic weight standardization processing of the system operation data based on a resource consumption proportion; obtaining a weight standardization data matrix; constructing a node correlation degree matrix according to the weight standardized data matrix, and generating a system state expected value through a bidirectional recurrent neural network model; based on the deviation distribution of the system state expected value and the current weight standardized data, an adaptive interval estimation algorithm is adopted to determine an anomaly recognition boundary; and performing data reconstruction on the data exceeding the abnormal recognition boundary by adopting a multi-source cooperative compensation mechanism, and outputting repaired system operation data through inverse weight standardization processing. According to the invention, full-process intelligent inspection and accurate abnormity repair of the operation data of the intelligent calculation center system are realized.

The invention relates to the technical field of crossing of road engineering and computer vision, and discloses a densely-stacked asphalt mixture particle roundness distribution prediction method, which comprises the following steps of: performing instance segmentation on particles in an image by adopting a visual basic model to obtain a mask image of each particle in the image; analyzing each particle mask image, extracting morphological parameters including the area, the equivalent circle diameter, the equivalent ellipse long axis and the like, constructing a particle geometric feature set, constructing a distribution curve for each morphological parameter according to the number of particles, and performing equal-interval sampling on the curve to form a multi-dimensional feature vector for machine learning input; and constructing a recurrent neural network model, and training the model by taking the multi-dimensional feature vector as an input and the known particle roundness distribution as a label to realize prediction of the particle roundness number distribution in the new image. And the segmentation applicability and the roundness distribution prediction precision of the densely-stacked asphalt mixture image are obviously improved.

The invention relates to a diagnosis and treatment result prediction method fusing a time sequence and traditional Chinese medicine multi-stage diagnosis and treatment, belongs to the technical field of traditional Chinese medicine diagnosis and treatment prediction, and solves the problem of lack of accurate whole-process prediction in the prior art. The method comprises the following steps: acquiring the current doctor-seeing symptom and historical doctor-seeing time sequence data of a to-be-predicted patient; the historical treatment time sequence data comprises symptom, syndrome, therapy and prescription data of each time step; constructing a graph structure corresponding to each time step of the historical doctor-seeing time sequence data; extracting a symptom feature sequence, a syndrome feature sequence, a therapy feature sequence and a prescription feature sequence by adopting a trained graph neural network model based on the graph structure and the current treatment symptom; and based on the symptom feature sequence, the syndrome feature sequence, the therapy feature sequence and the prescription feature sequence, performing multi-stage diagnosis and treatment result prediction by adopting a trained recurrent neural network model to obtain the prediction results of the syndrome, the therapy and the prescription of the current doctor seeing of the to-be-predicted patient. And accurate whole-process prediction is realized.

The invention relates to the technical field of vegetable cultivation, and discloses an automatic light supplement control method and system for vegetable cultivation, and the method comprises the steps: determining the growth state of a vegetable crop based on crop image information and a crop growth model, and judging whether to execute a light supplement strategy or not according to a solar altitude, determining a backtracking light supplementing strategy or an initial light supplementing strategy according to the occurrence frequency of the growth state in the historical light supplementing database, determining target light supplementing data of the vegetable crops according to the number of the light supplementing data, and when the initial light supplementing strategy is determined, determining the target light supplementing data of the vegetable crops based on a recurrent neural network model, and analyzing the historical light supplement record to determine a light supplement swing factor of the light supplement lamp, adjusting the target light supplement data based on the light supplement swing factor, and performing light supplement on the vegetable crops according to the adjusted target light supplement data. According to the invention, the reliability of light supplement is ensured through the crop growth model and the light supplement swing factor.

The invention discloses an air conditioner energy-saving optimization method and system based on intelligent control, and the method comprises the following steps: 1, collecting temperature and humidity data and air conditioner setting parameters, carrying out the training through a residual error connection attention recurrent neural network model, and outputting a thermal inertia prediction value; 2, constructing a thermal behavior joint feature vector; 3, performing clustering operation by adopting a Dirichlet process mean value clustering algorithm, and generating a space-time microcell by setting a clustering penalty threshold value; 4, constructing a thermal comfort model by adopting an improved PMV model based on a Fanger heat balance theory, and obtaining a disturbance index value of each space-time microcell; 5, constructing a joint optimization objective function, and generating optimal control action parameters of each space-time microcell; and step 6, carrying out fusion calculation on the optimal control action parameters of all the space-time microcells to generate an overall control instruction. According to the method, thermal inertia prediction and dynamic clustering optimization methods are fused, and intelligent energy-saving control over the air conditioner is achieved.

The invention relates to the technical field of environment prediction, and discloses an environment temperature and humidity prediction method and system, electronic equipment and a computer storage medium, and the prediction method comprises the steps: obtaining the real-time temperature and humidity data of each monitoring point in a to-be-detected region, and forming an original temperature and humidity time series data set; preprocessing the original temperature and humidity time sequence data set to obtain a clean data set; based on the historical sequence of each monitoring point in the clean data set, adopting a recurrent neural network model to predict the temperature and humidity change trend of each point in a future predetermined time window, and outputting a temperature and humidity prediction sequence; taking the prediction sequence as dynamic input, and inputting the prediction sequence into a heat and mass transfer physical model; obtaining temperature and humidity distribution of any spatial position in future time by solving the physical model; and three-dimensional temperature and humidity field inversion data covering the whole area is generated based on a solving result, and refined space-time representation of the whole-space temperature and humidity distribution state is realized.

The invention belongs to the technical field of engineering structure health monitoring, and provides a concrete dam crack prediction method based on a recurrent neural network model. The problems that in the prior art, concrete dam crack prediction is limited in multi-factor coupling effect modeling capacity and lacks multi-source heterogeneous data comprehensive analysis capacity, and refined prediction of the crack expansion dynamic process needs to be improved are solved. The method comprises the steps of data acquisition and preprocessing, multi-modal feature extraction and coding, multi-scale spatial-temporal feature fusion based on Transform architecture, and enhanced recurrent neural network prediction. Through the method, multiple complex driving factors of crack formation and expansion can be effectively captured, deep learning and fusion of heterogeneous data are realized, and the long-distance dependency capture capability of the model on time series data and the nonlinear description precision of crack evolution are improved, so that refined prediction of cracks is realized.

The invention relates to an emotion calculation and information processing method based on a deep neural network, and belongs to the technical field of artificial intelligence and natural language processing (NLP). The method comprises the following steps: preprocessing input text data; word embedding is conducted on the preprocessed text data through a Word2Vec model, each word is mapped into a high-dimensional vector, and therefore the semantic relation between words is captured; and processing the word embedding representation by using a bidirectional recurrent neural network model Bi-RNN, a bidirectional long-short-term memory network Bi-LSTM or a bidirectional LSTM model Bi-LSTM CNN combined with a convolutional neural network to obtain a classification result, and realizing an emotion analysis task. According to the method, the precision and robustness of sentiment analysis are remarkably improved.

The invention discloses a cowshed ingestion channel management method based on AI behavior partition, and the method comprises the following steps: S1, collecting and preprocessing cattle multi-source behavior data, and constructing a behavior time series data set; s2, establishing a recurrent neural network model, and predicting a future behavior trend; s3, constructing a behavior distribution graph and generating a dynamic behavior partition graph; s4, initializing a dragonfly optimization algorithm population, and searching an optimal ingestion channel configuration scheme; s5, the optimal channel configuration parameters are issued to a guide control device, and channel guide and shunting are executed; and S6, collecting feedback data, and updating the recurrent neural network model and the optimization algorithm. According to the method, intelligent prediction, dynamic partition and channel optimization guidance of the cattle shed feeding behavior are realized, so that the feeding efficiency is improved, and congestion and conflicts are reduced.

The invention discloses a method and equipment for determining the aging degree of a power semiconductor device and a medium, and relates to the technical field of semiconductor device reliability detection, and the method comprises the steps: taking a composite data sequence as input, constructing an electrothermal bidirectional recurrent neural network model, carrying out the temperature compensation of electrical characteristic data, and generating a pure aging signal; performing time domain and frequency domain analysis on the pure aging signal, extracting a drift rate, a drift acceleration and a stable drift value, and performing vectorization processing to form an aging feature vector; comparing the aging feature vector with the multi-dimensional threshold interval one by one, and judging a corresponding aging degree grade according to a comparison result; and displaying the aging degree grade in real time, storing and generating an aging degree grade historical record, calculating an aging trend value, comparing the aging trend value with an aging warning threshold value, and triggering an early warning signal when the aging trend value exceeds the aging warning threshold value. According to the invention, the accuracy, stability and credibility of the whole aging degree determination process are improved.

The invention provides a diabetes abnormal index early warning system and method based on a recurrent neural network. The system comprises a data acquisition module which is responsible for collecting various health data including blood sugar, heart rate, blood pressure, body weight, body fat, exercise amount, sleep quality and heart rate variability from health monitoring equipment of a patient; the data preprocessing module is used for denoising and normalizing the collected health data and detecting and correcting abnormal values; the feature extraction module is used for extracting time sequence features, statistical features and principal component features from the preprocessed health data; the convolutional gating recurrent neural network model module is used for analyzing the extracted features; and the early warning generation module generates early warning information according to the prediction result. Through the system and the method, the real-time monitoring of the multi-dimensional health data of the diabetic patient and the early warning of the abnormal indexes can be realized, and the diabetes management effect and the life quality of the patient can be improved.

The present invention discloses a gas pipeline network simulation and analysis system, comprising a gas pipeline network data acquisition unit, a pipeline network topology structure construction unit, a pipeline network data value influencing factor analysis unit, a gas pipeline network data prediction model construction unit, a gas pipeline network data periodicity prediction unit, a gas pipeline network data control unit, a risk warning unit, and a gas pipeline network data storage unit. The present invention realizes gas pipeline network simulation by constructing a pipeline network topology structure in a virtual environment; at the same time, it realizes periodicity prediction of gas pipeline network data through a time recurrent neural network model, compares the real data value collected on the gas pipeline network with the gas pipeline network data periodicity prediction range value, and judges the risk of the gas pipeline network. If the real data value exceeds the gas pipeline network data periodicity prediction range value, the valves on the branches and branch nodes in each component of the virtual pipeline network are adjusted to realize the real data value of the gas pipeline network exceeding the preset threshold value and control.

The invention discloses a few-sample irregular time sequence prediction method based on a meta-learning framework. The method comprises the steps of data acquisition, time window segmentation, random sampling, establishment of a bidirectional recursive model based on self-training, training and fine adjustment of the model by using a model-independent meta-learning method, evaluation of a prediction result and visualization. According to the invention, through the self-training bidirectional recurrent neural network model strategy and the generalization adjustment and optimization of the meta-learning method irrelevant to the model, the model is finely adjusted according to the gradient, so that the optimized weight configuration can be migrated to a new task; the method effectively improves the accuracy and efficiency of time sequence prediction in a single-field or single-group irregular multivariate few-sample scene, and maintains a low calculation cost.