566results about How to "Improve forecasting efficiency" patented technology

The invention provides a DCS system autonomous controllable upgrading and system fault prediction method and system, and relates to the technical field of fault prediction, and the method comprises the steps: obtaining historical operation data and real-time operation data of a DCS system, carrying out the preprocessing, and generating an autonomous controllable upgrading scheme through a deep reinforcement learning algorithm; the method comprises the following steps of: setting specified time for upgrading time, carrying out consistent backup on the state of the DCS, executing software updating, hardware configuration adjustment and system parameter optimization according to upgrading steps, analyzing indexes of the DCS in real time in the process of executing the autonomous controllable upgrading scheme, and recovering the DCS to the state before upgrading when an abnormal condition is detected. And verifying and optimizing the real-time fault prediction result based on a knowledge graph, and generating an explanatory report including a fault prediction and upgrade decision process according to the optimized fault prediction result and the autonomous controllable upgrade scheme.

The invention discloses an efficient skin disease segmentation method based on multiple scales and a mixed attention mechanism, and the method comprises the steps: firstly carrying out the preprocessing of a skin mirror image through data enhancement, and then inputting the skin mirror image into a convolutional neural network for feature extraction, thereby obtaining a skin lesion segmentation region prediction map. According to the method, the convolutional neural network is applied, multi-scale features of local information and global information can be extracted from a skin mirror image, and the feature representation capability is enhanced through feature fusion. The objective of the invention is to solve the problems of changeable lesion areas, irregular shapes and the like of skin disease images, and improve the accuracy and robustness of skin disease image segmentation.

The invention provides a landslide displacement space-time prediction method, device and system and a storage medium, and relates to the technical field of engineering geology, and the landslide displacement space-time prediction method comprises the steps: obtaining the historical landslide multi-field time sequence monitoring data of each monitoring point of a to-be-measured region, constructing a monitoring point bitmap based on the historical space related data, constructing a time sequence characteristic matrix according to the historical displacement time sequence, the historical landslide external disturbance factor time sequence and the monitoring point bitmap; inputting the time sequence characteristic matrix and the monitoring point bitmap into a trained landslide displacement space-time prediction model to obtain a landslide displacement space-time prediction result; the landslide displacement space-time prediction model is constructed based on an improved GCN network and an improved BiLSTM network; according to the method, the space-time prediction precision of landslide displacement can be remarkably improved by combining the space correlation data and the external disturbance factors and utilizing the capability of the deep learning model.

The invention relates to the technical field of chemical engineering and machine learning, and provides a method for predicting the solubility of carbon dioxide in a deep-eutectic solvent based on a machine learning model, and the method comprises the steps: collecting CO2 solubility data, carrying out the coding and feature descriptor conversion of a deep-eutectic solvent molecular structure through an open-source chemoinformatics software package RDKit, and constructing a data set. Four algorithms of XGBoost, random forest, a deep neural network and a convolutional neural network are adopted to construct a model, and hyper-parameters are optimized through grid search and k-fold cross validation. After the model is trained, the prediction performance is evaluated, and the optimal model is selected for CO2 solubility prediction. The method improves prediction efficiency and accuracy, has strong adaptability and generalization ability, and provides an effective tool for formula optimization of the eutectic solvent and improvement of CO2 capture efficiency.

The invention discloses a complex target recognition method based on a deep twin self-attention network, and relates to the technical field of target recognition methods. According to the method, a twin network based on a sliding window multi-head self-attention transformation mechanism is applied, the global modeling capability of a feature extraction network and the acquisition efficiency of long-distance semantic information are enhanced, and the bottom-layer feature extraction capability and the abstract effect of advanced semantic information are improved; the twin network personalized modeling improves the feature segmentation effect; the whole network forms a U-shaped structure, a local symmetric encoder and decoder structure is adopted, global context information is supplemented, and semantic information space association is enhanced; a residual link is added, so that the deep network is trained efficiently, and the recognition precision is enhanced; and adaptive image feature scale input processing is added, and adaptive scale transformation is performed on the input image, so that an accurate end-to-end semantic segmentation result is realized, and multi-scale input is realized to enhance the generalization ability and accuracy of a network model.

The invention is suitable for the technical field of tumor treatment and protection, and particularly relates to an intelligent classification prediction method, system and equipment for tumor treatment and protection, and the method comprises the steps: obtaining tumor-related molecular marker detection values and clinical diagnosis and treatment features of all target patients, and comprehensively integrating the multi-dimensional medical information of the patients; according to the relevance of molecular markers and clinical features, a scientific and quantitative multi-dimensional prognosis layering index set is constructed, and an accurate layering evaluation framework is formed; inputting the medical data into a pre-trained multilayer neural network model, and generating a high-resolution tumor characterization map through a cross-modal feature fusion technology; based on the dynamic matching of the atlas and the hierarchical index set, the hierarchical contribution degree parameter and the prognosis risk score are calculated in combination with the random forest model, the precise quantitative evaluation of the condition of the patient is completed, a high-credibility quantitative basis is provided for clinical decision making, the over-treatment risk is effectively reduced, and the prognosis management effect of the patient is improved.

The invention provides an evolutionary neural architecture searching method and system based on similarity agent assistance, and the method comprises the steps: 1, initializing an architecture population, and selecting an architecture with the best performance as an initial reference architecture; 2, constructing a graph neural network variant as a feature extractor; 3, constructing an agent model, and training the agent model through a joint loss function; 4, the high-potential architecture is reserved according to the fitness value, authenticity performance evaluation is carried out on the high-potential architecture, and an evaluation result is added into the training set; combining the current population with the high-performance architecture predicted and screened by the proxy model, and updating the population through an environment selection strategy; and step 5, repeating the step 3 and the step 4 until the population performance converges, and finally outputting a global optimal architecture. According to the method, the high-performance neural network architecture can be quickly searched under limited computing resources, and an efficient and intelligent novel solution is provided for automatic design and optimization of the neural network.

The invention discloses a residual period prediction method, system and device for enhancing time sequence prediction and a medium, and aims to solve the problems of low efficiency and limited prediction precision in the prior art in a long time sequence prediction task. According to the method, the periodic residual error is predicted by explicitly modeling the periodic mode in the time sequence data and combining the prediction model, so that the prediction precision and efficiency of the time sequence prediction model are improved. The method comprises the steps of determining the period length of a data set, generating a learnable cycle period, separating a periodic component and a residual component of a time sequence, performing prediction based on a residual, and finally combining a prediction value of the residual component and the corresponding periodic component to form a final prediction result. The method can effectively capture the inherent periodicity in the time sequence, reduce the prediction error, significantly improve the precision of long-time sequence prediction, maintain the simplicity and high efficiency of the model, and is especially suitable for application scenarios with clear periodicity characteristics, such as power consumption, traffic flow, meteorological data and the like.

The invention relates to the technical field of building industry carbon emission prediction, in particular to a building industry carbon emission prediction method and system based on a random forest algorithm, and the method comprises the steps: obtaining building industry carbon emission historical data; based on a random forest regression model, carrying out influence factor importance degree sorting on historical data of carbon emission in the building industry, extracting a characteristic data set of carbon emission correlation, and dividing the characteristic data set into a training set and a test set; inputting the training set into a preset LSTM model for calculation, evaluating an LSTM prediction result through the test set, and outputting the trained LSTM model; and combining the random forest regression model with the completely trained LSTM model, and completing carbon emission prediction of the existing building through the combined model. The invention aims to improve the accuracy and reliability of building industry carbon emission prediction.

The invention discloses a distributed photovoltaic short-time output dynamic prediction method and system. The method comprises the following steps: acquiring micro-meteorological data, a cloud picture image and historical output data of a target area; calculating a building shadow shielding coefficient, and generating shadow influence factor time sequence data; obtaining cloud image occlusion index time series data based on the cloud image and a pre-constructed cloud image occlusion prediction model; fusing the data, and constructing and training a short-time output dynamic prediction model based on a long short-term memory network; predicting photovoltaic output by using real-time data and the trained model, and adjusting the model according to a prediction error and a confidence interval; according to the method provided by the invention, various factors such as microclimate, building shadow and cloud layer shielding are comprehensively considered, and the complex nonlinear relationship between the factors and the photovoltaic output is captured by using the deep learning model, so that the accuracy and robustness of distributed photovoltaic short-time output prediction are improved.

The invention discloses a shaft surrounding rock deformation prediction method and device based on fluid-solid coupling linkage simulation, and the method comprises the steps: 1, describing the influence of rainwater permeation on surrounding rock deformation through the change of water content, constructing and forming a permeation-surrounding rock deformation model, and constructing and forming a scouring-surrounding rock deformation model, building a vertical shaft excavation model under the action of rainwater; 2, performing multi-scale linkage simulation on the permeation-surrounding rock deformation model, the scouring-surrounding rock deformation model and the vertical shaft excavation model to obtain surrounding rock deformation data; 3, taking the surrounding rock deformation data as a training set to train a TCN-LSTM neural network model, and obtaining a shaft surrounding rock deformation prediction model under the rainwater effect; and 4, acquiring real-time surrounding rock deformation data, inputting the real-time surrounding rock deformation data into the shaft surrounding rock deformation prediction model, and outputting a prediction result. The shaft surrounding rock deformation prediction precision, efficiency and application flexibility can be improved, and meanwhile the implementation complexity and the calculation amount are reduced.

The invention provides a rapid forecasting method for environmental response of a ship sailing in an ice region. The rapid forecasting method comprises the following steps: S1, establishing a motion response mathematical model of the ship on the sea under interference of the environment with ice, wind and waves; s2, establishing a ship navigation sea area ice condition and sea condition forecasting model; s3, enriching the environmental motion and structural response database of ship navigation in the ice area or performing data assimilation according to actual measurement information; and S4, according to the planned ship route of the ship and the forecasting result of the regional ice area environmental elements, carrying out refined real-time forecasting of the ice area environmental elements on the ship route region per hour within 24 hours, adopting multi-level decomposition and forecasting in the forecasting process, decomposing the forecasting into different time scales for forecasting, and finally, carrying out the forecasting of the ice area environmental elements in the ship route region. And summing different forecasts to obtain a final forecast result. According to the invention, the motion and structural response of the ship can be quickly and accurately obtained under the influence of a complex ice region environment.

The invention discloses a regional water safety-oriented water demand prediction method, electronic equipment and a storage medium, and the method comprises the steps: firstly collecting an industrial water impact factor, a living water demand prediction impact factor, and an agricultural irrigation water demand prediction impact factor; then, a prediction equation for reflecting the future evolution trend of each influence factor is established for each influence factor, then an industrial water demand prediction model, a living water demand prediction model and an agricultural irrigation water demand prediction model are established, and the water demand prediction models are subjected to validity inspection; and finally, performing water demand prediction on a to-be-predicted area by using the inspected water demand prediction model to obtain a water demand prediction result. According to the method, economic driving, social influence, climate change and other factors are fully considered, the water demand change mechanism is researched from the internal structure of the system, the problems that in existing water demand prediction, factor selection is not comprehensive, and the simulation effect is poor are solved, and the prediction effectiveness and accuracy are improved from the two aspects of the model structure and the prediction factors.

The invention relates to the technical field of photovoltaic power generation, and discloses a photovoltaic power generation capacity time sequence prediction method based on an improved Transform model, and the method comprises the following steps: S1, carrying out the cleaning and standardization processing of environment data and power generation capacity data; s2, extracting local features from the input multivariate time sequence data by using a convolutional layer; s3, introducing a new dynamic weight adjustment module, and dynamically adjusting the attention weight according to the correlation between the environmental factors and the power generation amount; s4, proposing a staged decoding mechanism, reducing the calculation amount through preliminary prediction and refined decoding, and paying attention to important information; s5, performing end-to-end training on the model in combination with the optimized attention mechanism and the generative decoder; and S6, using the trained model to carry out generating capacity prediction on new data, and using an evaluation index to evaluate a prediction result.

The invention provides a method for predicting a submarine shallow gas escape process under a hydrodynamic action based on a random forest. The method comprises the following steps: acquiring and processing in-situ monitoring data; performing feature screening according to the correlation; carrying out standardization processing on each data subset after the data set is divided; carrying out random forest model construction, training and cross validation; predicting the target methane concentration by using the trained model; five evaluation indexes are adopted to evaluate the prediction performance; and carrying out feature importance analysis by combining the two methods. Through the technical scheme of the invention, a plurality of hydrodynamic action factors are comprehensively considered in combination with correlation analysis, the contribution degree of each element to the shallow gas escape result is quantitatively analyzed, the prediction precision is good, and the interpretability of machine learning is enhanced by analyzing the result by adopting the Shapley sum interpretation.

The invention provides a ship ocean route optimization forecasting method, which comprises the following steps of S1, establishing an initial route according to a voyage number task, a steering point and a route type; s2, establishing a motion response mathematical model of the ship on the sea to the environment; s3, obtaining a marine environment forecasting result of a sea area through which the ship passes; s4, calculating the motion response of the ship passing through the sea area; s5, collecting other requirement conditions in the current voyage task of the ship as other constraints; s6, performing optimization calculation to obtain an optimized route and an optimized propeller rotating speed which should be adopted by the ship under the optimization target; and S8, repeating the steps S3-S7, and executing the newly obtained route and speed optimization scheme. According to the method, the ship navigation plan elements including the ship route and the propeller rotating speed are optimized, and a navigation scheme meeting the optimization requirement of a user can be obtained on the premise of avoiding severe sea conditions to guarantee safety. The method is beneficial to intelligent construction of ship navigation.

The embodiment of the invention provides a die forging equipment hydraulic system energy consumption prediction method with a self-learning function, and belongs to the technical field of data processing, and the method specifically comprises the steps: analyzing the energy consumption characteristics of an energy conversion unit of a die forging equipment hydraulic system, and obtaining the key energy consumption characteristics of the die forging equipment hydraulic system; an energy consumption data set is extracted and preprocessed, and an energy consumption feature set corresponding to the data information is extracted in combination with the key energy consumption features; based on the key energy consumption characteristics and the energy consumption characteristic set, using different energy consumption prediction fusion algorithms to construct an energy consumption prediction sub-model of each energy conversion unit; optimizing each energy consumption prediction sub-model through an incremental learning and transfer learning algorithm; evaluating each optimized energy consumption prediction sub-model through cross validation and a preset evaluation index; and performing energy consumption prediction on the energy conversion unit of the hydraulic system of the die forging equipment by utilizing each optimized energy consumption prediction sub-model. Through the scheme disclosed by the invention, the prediction efficiency, accuracy and adaptability are improved.

The invention relates to the technical field of ocean heat wave prediction, and discloses an ocean heat wave prediction method based on a Transform network and a graph neural network, and the method comprises the steps: obtaining the ocean meteorological data of a to-be-measured ocean region; extracting long-period features and short-period features of the marine meteorological data by using a Transform network and a time convolution network respectively; performing fusion processing on the long-period features and the short-period features to obtain fusion features; and sequentially inputting the fusion features into a graph neural network and a time convolutional network for prediction processing to obtain an ocean heat wave prediction result. According to the method, the space-time correlation and dependency of the marine meteorological data under different time granularities can be better captured, the dynamic change of the time sequence is captured, the spatial modeling capability of the graph neural network is fully utilized to predict the marine heat waves, the prediction accuracy is greatly improved, and the calculation cost is reduced.

The invention discloses a time sequence prediction model generation method and device and a data processing method and device. The method comprises the steps that historical target variable data and a covariable data set corresponding to a preset prediction task are acquired, the historical target variable data are historical prediction time sequence data, and the covariable data set is a set of data related to prediction of the historical target variable data; target covariable information is determined from the covariable data set, and the target covariable information is information influencing prediction of historical target variable data; performing feature embedding and fusion processing on the historical target variable data and the target covariable information to obtain a fusion feature vector; and training a pre-training model according to the fusion feature vector to obtain a target time sequence prediction model corresponding to the preset prediction task. According to the method and the device, the technical problem of relatively low time sequence data prediction accuracy due to the fact that a time sequence prediction model is not combined with covariable information in related technologies is solved.

The invention discloses a regional air-conditioning load prediction method based on a time sequence large model. The method comprises the following steps: acquiring historical air-conditioning load data and key variables related to air-conditioning loads; the air conditioner load data and the key variables are processed through a Prompt technology, and a processed data sequence is obtained; constructing a time sequence prediction large model based on a UniTS model; training and testing the model through the processed data sequence to obtain a trained time sequence prediction large model; and regional air conditioner load prediction is carried out through the trained time sequence prediction large model. According to the method, a large time sequence prediction model based on a Prompt + UniTS model is constructed, efficient processing and intelligent analysis of multivariable data sequences among air conditioner load data and various related data related to the air conditioner load data are achieved, the accuracy and reliability of regional air conditioner short-term prediction are improved, and powerful support is provided for safe and efficient operation of a comprehensive energy system.

The invention relates to the field of vehicle emission prediction, and discloses a gasoline vehicle emission prediction method based on an XGBoost-SVR combined model, and the method comprises the following steps: S1, collecting the instantaneous emission data of pollutants of a gasoline vehicle and vehicle driving parameters, and carrying out the time sequence calibration processing; s2, singular spectrum analysis is adopted to decompose and reconstruct the pollutant emission data; s3, dividing the processed pollutant emission data and vehicle driving parameters into a training set, a verification set and a test set; s4, establishing an XGBoost model, and predicting the instantaneous discharge amount of pollutants by inputting vehicle driving parameters; s5, calculating a residual error between a predicted value and an actual value based on the verification set; and S6, correcting the residual error by using an SVR model to obtain a final pollutant emission prediction value. According to the method, the XGBoost and SVR models are combined, so that high-precision prediction of the pollutant emission of the gasoline car is realized, data noise is effectively removed, the experiment cost is reduced, and the generalization ability and adaptability of the model under complex working conditions are improved.

The invention discloses a deep learning-based pipeline structure stress proxy model construction method, which belongs to the field of engineering mechanics, energy transmission and artificial intelligence, and comprises the following steps of: firstly, establishing a numerical model of a pipeline, simulating different environmental conditions by applying different loads, and solving to generate a large amount of simulation data; then, feature unit extraction is carried out on the simulation data so as to compress feature dimensions; then, a deep learning initial proxy model of pipeline stress is constructed, and initial training is carried out through finite element simulation data; and finally, transfer learning is carried out based on the initial agent model, the transfer learning is divided into two stages, enhanced actual measurement sample data is used for training in the pre-training stage, and accurate actual measurement samples are used for further training and fine adjustment in the strengthening stage, so that the generalization ability of the model is improved. According to the method, the stress distribution can be rapidly and accurately solved by constructing the stress agent model, the generalization ability is high, and the problem that a traditional physical modeling method is insufficient in real-time performance and precision in stress monitoring and prediction can be solved.

The invention discloses a lithium battery remaining service life prediction method based on Stacking fusion, which comprises the following steps: firstly decomposing lithium battery capacity data through robust local mean decomposition, and then reducing the number of sequences through fuzzy entropy aggregation; carrying out secondary decomposition by utilizing a modal component with the highest entropy value of time-varying filtering empirical mode decomposition, inputting the processed data into a lightweight time sequence analysis model and a non-inverse extreme learning machine for prediction, and carrying out parameter optimization on an FITS model and an IFELM model by adopting an improved wave search algorithm; the prediction values of the two models are fused by using a Stacking algorithm, then error correction is carried out, finally, the fused prediction result and the error prediction result are superposed to obtain a final lithium battery capacity prediction result, and the prediction result is obtained according to the relationship between the capacity data and the residual life. According to the method, the prediction model precision of the residual life of the lithium battery can be effectively improved, and a reliable basis is provided for safety judgment of the lithium battery.

The invention discloses a gas detection method, equipment, a medium and a product, and relates to the technical field of gas detection. The method comprises the following steps: acquiring response data of to-be-detected gas based on a sensor array; inputting the preprocessed response data into a first shared convolutional layer of a multi-task convolutional neural network model to obtain an initial feature map; inputting the initial feature map into the pooling layer for down-sampling, and inputting the down-sampled feature map into the second shared convolutional layer to obtain a target feature map; and inputting the target feature map into a plurality of task specific layers, and outputting a prediction result of the to-be-detected gas through the full connection layer. Based on the multiple task specific layers, simultaneous prediction of four tasks of gas category, gas concentration, sensor state evaluation and gas anomaly detection is realized, the prediction efficiency of the to-be-detected gas is improved, and the operation efficiency and applicability of the electronic nose system are further improved.

The invention relates to the technical field of landslide surge and data driving, and discloses a landslide surge height prediction method and system based on a gating circulation unit, and the method comprises the steps: collecting the related data of a large-scale physical model test of a landslide surge region, carrying out the data standardization and normalization preprocessing of the feature data, and obtaining the data of the large-scale physical model test; the preprocessed feature data serve as a gated cycle unit GRU model to be input, and the surge height is obtained; building a gated loop unit GRU network in a Python compiling environment by using tensor flow; training a GRU (Gated Recirculation Unit) network model, and training the GRU network model by using the historical landslide data to adjust model parameters; and deploying the trained GRU model into an actual landslide surge prediction system for real-time monitoring. The system comprises a data preprocessing module, a model building module and a model training module. According to the invention, an efficient and accurate prediction system is formed.

The invention discloses an education evaluation assisting method and system based on artificial intelligence. The method comprises the steps of data collection, data optimization, learning behavior evaluation, education feature evaluation and education evaluation assisting. The invention relates to the technical field of education management, in particular to an education evaluation auxiliary method and system based on artificial intelligence. According to the scheme, a two-way correlation analysis method combining learning behaviors and education features is adopted, preliminary analysis is conducted through learning behavior evaluation, multi-dimensional extraction is conducted through the education features, and the education evaluation accuracy is improved. The analysis depth and the analysis specificity of education evaluation are improved, and meanwhile, an effective way for assisting the education evaluation by an intelligent method is provided; performing learning behavior evaluation by adopting a method of combining a causal enlightenment enhanced graph nerve long-short-term memory integration model; and carrying out educational feature evaluation by adopting a graph neural network method combining knowledge migration and a knowledge graph.

The invention provides a laser-induced coloring temperature field prediction method, device, equipment and medium, and belongs to the technical field of laser marking coloring, and the method comprises the steps: constructing a laser-induced coloring photo-thermal response physical model; a neural network model with time and space positions as input and temperature as output is constructed, a loss function of the neural network model is constructed based on the photo-thermal response physical model, iterative optimization is performed on the neural network model based on the loss function and a training set, and a temperature prediction model with embedded physical information is obtained; and obtaining target time and a target spatial position of a laser-induced coloring process under a target process parameter combination, and determining a predicted temperature field under the target process parameter combination based on the target time, the target spatial position and the temperature prediction model embedded with the physical information. According to the method, the photo-thermal response physical model is taken as priori knowledge, so that the determination efficiency and precision of the predicted temperature field are improved.

The invention discloses a medium and long term flood forecasting method, device, equipment, medium and product, and relates to the technical field of hydrological forecasting. The method comprises the following steps: firstly, extracting a plurality of sample data from river flow time series data and climate factor time series data, then constructing a Transform model, and carrying out model training by using the plurality of sample data to obtain an intra-segment maximum river flow prediction model; and finally, importing the maximum river flow and the plurality of climate factor values of the target river section in the most recent medium-and-long-term unit periods into a prediction model to obtain a maximum river flow prediction value of the target river section in the next future medium-and-long-term unit period, and taking the maximum river flow prediction value as a medium-and-long-term flood prediction result. The long-distance dependence in the time sequence data can be processed and recognized, the problem that a traditional hydrological prediction model is difficult to cover is solved, and then the precision of medium-and-long-term flood prediction is improved.

The invention discloses an electric power monitoring system based on artificial intelligence, relates to the technical field of electric power monitoring, and solves the technical problem of low fault detection efficiency of an existing electric power system. Comprising the following steps: collecting resident electricity consumption and real-time data of power equipment through a data collection module, and preprocessing to obtain power data; the monitoring prediction module judges whether the power equipment is abnormal or not according to the power data, if yes, an early warning signal is generated, a reason is analyzed, abnormal data is marked as a sequence, the sequence is input into the power monitoring model to obtain an abnormal label, and then the abnormal reason is matched; predicting future electricity consumption according to the historical electricity consumption; and the early warning feedback module sends an early warning signal and an abnormal reason to a manager so as to dispatch a technician to check and maintain, and the user interaction interface displays related information and provides functions of checking historical records and the like, so that accurate fault detection and intelligent prediction of power consumption can be realized, and the operation efficiency and safety of a power system are improved.

The invention provides a parallel computing method for supporting real-time data stream processing in parallel programming, which comprises the following steps of: dividing a real-time data stream into fragments through a parallel pipeline, and filtering specified fields by different threads to improve the efficiency; after filtering is completed, performing local aggregation on a result by using a local aggregation function of MapReduce to reduce the data volume; a distributed memory database based on Redis Cluster is established, and data are stored in a fragmented mode according to a time window; constructing a long-short-term memory recurrent neural network model, and performing parallel training through a parameter server architecture; if the long short-term memory recurrent neural network model needs incremental learning, a parameter interface is reserved for iterative updating, and repeated training is avoided; after training is completed, the model is deployed to a GPU server, and real-time data flow is predicted; through a task scheduler of a distributed memory computing framework, cooperation between threads and processes is automatically managed, and programming work is simplified.