733 results about "Multi-task learning" patented technology

Provided in the present application is an intelligent question answering method based on a collaboration between a large language model and a knowledge graph, relating to the technical fields of artificial intelligence and natural language processing, the method comprising: decomposing a complex question into a plurality of simple questions, and analyzing the degree of association between the simple questions and a basic function so as to form a multi-hop reasoning path; automatically extracting structured information from the simple questions on the basis of a multi-task learning framework of a large model, so as to construct a knowledge graph; and constructing a cumulative reasoning learning framework on the basis of a logic reasoning large model, and performing iterative verification on a process result formed by the knowledge graph on the basis of the multi-hop reasoning path, so as to correct the reasoning path until a correct answer is inferred.

The invention discloses a system and a method for predicting postoperative recurrence risk after triple negative breast cancer neoadjuvant therapy based on multi-modal time sequence medical image data, and belongs to the field of medical image analysis. The system comprises a data processing module used for constructing a multi-modal data set; the multi-modal feature extraction and screening module is used for extracting deep learning, radiomics and tumor habitat features from the region and carrying out feature screening; the model training module is used for constructing a time sequence model based on a Transform architecture and carrying out training through a multi-task learning strategy integrated with time consistency constraint and gene association auxiliary loss; and the recurrence risk prediction module is used for loading the trained model and outputting a recurrence probability and a risk level. According to the method, the multi-modal time sequence image and gene information are fused, so that the recurrence risk of the triple negative breast cancer patient is dynamically and accurately quantified, and support is provided for clinical individualized treatment decision.

The invention relates to the technical field of power dispatching management and control, and discloses a power distribution network power dispatching method based on a virtual power plant AI large model and demand response, and the method comprises the steps: collecting the operation data of a power distribution network, and constructing a feature vector; an AI large model is adopted to calculate and predict load output, and joint uncertainty information is output; calculating a system power unbalance amount, and generating a scheduling strategy; issuing a scheduling instruction corresponding to the scheduling strategy and executing the scheduling instruction; comprehensive performance evaluation indexes are calculated, and whether a performance reduction reason diagnosis mechanism is started or not is judged; according to the method, the AI large model is adopted, the load power, the photovoltaic output and the wind power output are predicted at the same time through a multi-task learning strategy, and the correlation among multiple variables is fully utilized; by constructing a multi-objective optimization model, comprehensively considering economy, safety and reliability and adopting an improved particle swarm optimization algorithm for solving, coordinated optimization configuration of demand response resources is realized, power grid fluctuation is effectively reduced, and power supply reliability is improved.

The invention discloses an AI-driven disease diagnosis and curative effect monitoring analysis system, which comprises a data processing module used for collecting multi-source diagnosis and treatment data and constructing a multi-modal sample set; the diagnosis prediction module is used for generating a diagnosis label, a diagnosis confidence value and a prediction curative effect trend through a multi-task learning model; the curative effect comparison module is used for collecting actual curative effect data, constructing a curative effect observation sequence and generating a curative effect deviation sequence based on the curative effect observation sequence and the predicted curative effect trend; the credibility evaluation module is used for executing credibility review based on the curative effect deviation sequence and the diagnosis confidence value; and the path evolution module is used for recording continuous multi-round diagnosis correction results, generating a jump type diagnosis path and updating a diagnosis and treatment data chain. The dynamic closed-loop verification mechanism between the multi-mode diagnosis and treatment data and the predicted curative effect trend improves the accuracy of disease diagnosis, the reliability of curative effect prediction and the adaptability of the diagnosis and treatment process.

The present invention relates to the technical field of natural ventilation in buildings, and in particular to a computationally assisted decision-making method and system for climate-adaptive building cavity design. The method comprises: using a Delaunay triangulation method to generate an initial mesh, using a Laplace operator-based mesh refinement method to adaptively refine the initial mesh, so as to obtain an adaptive mesh system, wherein the adaptive mesh system is used for dynamically adjusting the mesh density of conditional PINNs; constructing a multi-task learning framework within the conditional PINNs, wherein the multi-task learning framework is used for jointly predicting a plurality of physical field variables within the conditional PINNs; and iteratively training the conditional PINNs, and using a gradient descent algorithm to minimize a loss function until a predetermined number of training iterations or loss convergence is reached, thereby generating a key physical field variable prediction model in building cavity design. The present invention can implement efficient and accurate prediction of key physical quantities in building cavity design, and can be adapted to different building layouts and functional space characteristics.

The invention provides a software vulnerability understanding method based on adversarial training data enhancement and multi-task learning, belongs to the technical field of software quality assurance, and solves the technical problems that vulnerability type prediction and row-level vulnerability positioning are difficult to accurately complete at the same time and code semantics are easy to damage due to sample enhancement in the existing method. According to the technical scheme, the method comprises the following steps: (1) constructing a C / C + + vulnerability data set containing vulnerability type tags and row-level vulnerability tags; (2) generating an adversarial training data enhancement method constrained by AST and PDG in the embedding space by adopting a PGD algorithm; and (3) taking the pre-training model as a shared encoder. The method has the advantages that the performance of the two tasks can be remarkably improved, and the manual workload needed in the vulnerability understanding and analysis process is effectively reduced.

The invention provides an intelligent prediction model construction method based on multi-modal data fusion, and the method comprises the following steps: collecting multi-modal data in different electric power scenes, and carrying out the preprocessing of the multi-modal data, the electric power scenes including electric power inspection, electric power transaction and electric power equipment operation and maintenance; performing feature extraction, semantic association and space-time alignment on the preprocessed multi-modal data through a cross-modal attention mechanism and association analysis; constructing an intelligent prediction model, and performing knowledge injection on the intelligent prediction model through a retrieval enhancement generation technology and a lightweight adapter; a multi-task learning framework is introduced into the intelligent prediction model, exclusive output heads are set for different power scenes, and training is carried out through multi-modal data; after training is completed, lightweight compression is carried out on the intelligent prediction model through a knowledge distillation technology, a multi-modal data fusion technology system suitable for the power industry is formed, and key technology support is provided for deepening application of the intelligent prediction model of the power system.

The invention relates to the technical field of remote sensing data processing and earth surface parameter inversion, and discloses an earth surface matrix parameter hyperspectral data inversion method and system based on machine learning. Comprising the following steps: constructing a multi-source heterogeneous hyperspectral data set; performing feature screening on the preprocessed hyperspectral data set based on an adaptive band selection algorithm, constructing a dynamic weight matrix by calculating mutual information entropy and inter-class distance measurement between spectral bands to realize intelligent screening of key feature bands, and combining spectral derivative conversion and spectral index calculation to generate an enhanced feature vector; and a multi-task transfer learning neural network model is constructed, and an output layer realizes multi-parameter collaborative inversion based on a multi-task learning architecture. And performing preprocessing and feature enhancement operation which is the same as that of the training data on the hyperspectral image data of the to-be-inverted region, inputting the trained neural network model, and outputting a surface matrix parameter inversion result.

The invention discloses a blockage prediction and self-adaptive regulation and control method for a forging press cleaning system. The method comprises the following steps: carrying out multi-sensor data acquisition based on a multi-sensor fusion mode; preprocessing the multi-sensor data to obtain a standardized data set; a deep learning model fusing the attention mechanism and multi-task learning is constructed, and the deep learning model takes an LSTM network as a basic framework and comprises a feature extraction module, an attention enhancement module and a multi-task learning module; training and optimizing the constructed deep learning model based on training data input; predicting a blockage trend, inputting the real-time fusion feature vector into a trained model, and outputting probability distribution of a blockage state and a blockage risk level by the model; and performing self-adaptive regulation and control, namely generating a self-adaptive regulation and control instruction, and controlling an execution mechanism to execute fan power adjustment or reverse blowing mode switching operation. The invention further discloses a corresponding system, electronic equipment and a computer readable storage medium.

The invention discloses a spine image key point detection algorithm based on multi-task learning. The algorithm comprises the following steps: constructing a multi-task deep learning network model comprising a segmentation branch and a key point positioning branch; a feature aggregation module based on multi-scale cavity convolution is embedded in the segmented branches, and the multi-scale cone feature extraction capability of the model is enhanced through splicing fusion of multiple cavity rate convolution branches and global pooling branches; a cross-task attention fusion module is introduced between the two branches, and bidirectional dynamic interaction and complementation between segmentation features and key point features are realized by generating and fusing first-order and second-order context attention maps; semantic alignment loss is designed in a training stage, collaborative optimization of two tasks is promoted by constraining the consistency of segmentation masks and key point heat maps in a high-level feature space, global information of segmentation and local information of key point detection are fully utilized, and the accuracy and stability of spine centrum key point positioning and the accuracy of a segmentation result are improved.

The invention discloses a thunderstorm and gale dynamic extrapolation forecasting method based on multi-task MSTA-ConvLSTM, and relates to the technical field of atmospheric sciences, and the method comprises the steps: constructing a multi-source fusion spatio-temporal data set and a gale process record file, and obtaining a data set; a thunderstorm gale nowcasting model based on an MSTA-ConvLSTM model is constructed; according to the method, a dynamic gating mechanism of lightning data is introduced, whether a lightning probability prediction task is started or not is intelligently judged according to the lightning activity intensity, thunderstorm, gale and co-evolution characteristics of the lightning process are considered, 0-3-hour high-temporal-spatial-resolution nowcasting is achieved, the limitation of traditional single-task forecasting is broken through, a multi-task learning structure is adopted, and the prediction efficiency is improved. The model is guided to recognize the lightning occurrence probability during main task gale prediction, and the overall perception capability of a severe convection system is improved; extreme sample learning is enhanced through a weighted loss function, and output is optimized in combination with a gust coefficient model, so that the forecasting precision and practicability are effectively improved.

The invention relates to the technical field of soybean plant information analysis, in particular to a soybean whole plant character analysis method based on three-dimensional point cloud. Comprising the following steps: carrying out collection, labeling and standardized pretreatment on three-dimensional point clouds by adopting a soybean pod state joint labeling method based on the three-dimensional point clouds; an improved SoftGroup multi-task learning model is constructed, all the modules work cooperatively according to preset logic, the three-dimensional point cloud of the single plant of soybean serves as input, and target task result output is achieved through point cloud feature extraction and instance clustering; performing multi-task joint training on the improved SoftGroup multi-task learning model, preprocessing the three-dimensional point cloud of the soybean plant to be tested, inputting the preprocessed three-dimensional point cloud into the trained model, performing multi-task reasoning, correcting geometric parameters through PCA fine processing, and counting the pod bearing number; removing pod point cloud from the single-plant soybean three-dimensional point cloud to obtain plant main body point cloud; and extracting a plant skeleton from the plant main body point cloud, and obtaining character data of the plant skeleton.

The invention particularly relates to a multi-task motion recognition method based on a physical constraint guide condition diffusion model, which comprises the following steps: acquiring original observation data of multi-task motion based on an inertial measurement unit and preprocessing to obtain preprocessed original observation data; constructing a conditional diffusion model, and training the conditional diffusion model by using the preprocessed original observation data based on a preset loss function to obtain a trained conditional diffusion model; performing data enhancement on a key motion state category determined based on the motion state category label corresponding to the original observation data according to the trained conditional diffusion model to obtain a key motion state category sample, and constructing a sample balance data set based on the key motion state category sample; and based on the sample balance data set and a preset multi-task learning network loss function, constructing a multi-task learning pedestrian motion recognition model and carrying out multi-task recognition. Therefore, the problems of few key state samples, unreasonable data and the like in motion recognition are solved.

The invention discloses a breast cancer recurrence risk prediction method and system based on multi-modal data missing interpolation and gene interpretability enhancement. The method comprises the following steps: firstly, dynamically generating and complementing features of a missing mode by matching a generative adversarial network with a mode missing mask matrix; then, a feature screening mechanism driven by gene information is introduced, through a multi-task learning network, image feature extraction is supervised by using a gene expression tag in a model training process, and image features highly associated with recurrence-related genes are screened out; and finally, fusing the complemented multi-modal time sequence characteristics by adopting Transform, and outputting a recurrence risk probability. According to the method, the robust prediction performance can be realized under the condition of data missing, and meanwhile, image interpretation with a molecular biology basis is provided for the feature screening process of the model, so that the reliability and clinical acceptability of the whole system are enhanced.

This invention relates to the field of hydraulic engineering, and more particularly to a method for safety assessment and optimization design of large-flow aqueduct structures. The method includes: collecting displacement, strain, and temperature monitoring sequences based on a triple probe, completing grouping, coordinate and time registration, and establishing a monitoring baseline; constructing a spatial model including support nonlinearity and fluid-structure boundary conditions, applying loading conditions, and obtaining response predictions; aligning monitoring and prediction in time and location, performing hierarchical Bayesian filtering inversion, and obtaining parameter posteriors and structural health; under the integration of in-service monitoring and accelerated degradation characteristics, using multi-task learning to generate material evolution and lifespan intervals, and automatically generating and simulating optimization schemes under reliability and maintainability constraints. This application forms a closed loop from assessment to design, effectively enhancing data comparability, traceability of uncertain information, and adaptability of the scheme to engineering projects.

The invention discloses an LIBS rare earth multi-element quantitative detection method based on a deep learning model, and the method comprises the steps: constructing a multi-scale feature fusion deep learning architecture MSFF-Net, carrying out the weighted fusion of local features extracted by a 1D-CNN and long-range dependence features of BiLSTM modeling through a channel attention mechanism, and enhancing weak signal features in combination with a first-order derivative spectrum. Meanwhile, a synthetic data enhancement strategy based on a physical model is adopted to simulate a matrix effect and a spectral line overlapping scene, and spectral feature migration under different matrixes is achieved in cooperation with a matrix self-adaptive migration learning strategy. And after data acquisition and preprocessing, a trace element concentration prediction value is synchronously output through a multi-task learning framework. According to the method, the detection precision and the anti-interference capability of the LIBS technology on trace elements are effectively improved, and the method has remarkable application value in the industrial fields of mineral resource exploration, strategic metal recovery and the like.

The invention relates to the technical field of target behavior prediction systems based on causal inference and multi-task learning, and particularly discloses a target behavior prediction system based on causal inference and multi-task learning. The system comprises a central coordination server and a plurality of participant clients, constructs a global causal graph through a federated causal discovery algorithm in a collaborative manner, determines a causal feature subset of each prediction task, and carries out multi-task model training through a federated average algorithm under the constraint. In the process, differential privacy and homomorphic encryption technologies are comprehensively applied to protect data privacy. According to the method, more accurate causal discovery and more reliable prediction model training can be realized on the premise of protecting data privacy of all parties.

The invention discloses a false information intelligent detection and traceability method based on cross-modal consistency verification. The method specifically comprises the following steps: S1, multi-modal content feature extraction; s2, carrying out cross-modal consistency verification; s3, performing deep counterfeiting detection; s4, propagation anomaly detection; s5, checking knowledge enhancement facts; s6, information tracing and variation tracking; s7, comprehensive authenticity evaluation; s8, a model training strategy; a multi-task learning framework is adopted, and parameters of all modules are jointly optimized. According to the method, a multi-dimensional consistency verification system is constructed by fusing multi-source information such as video content, text semantics, a propagation network and an external knowledge base, and automatic identification, authenticity evaluation and information traceability of various false information are realized.

The invention discloses a multi-modal sensing fusion dam body structure state intelligent diagnosis and early warning system and method and application. The system comprises a multi-modal sensing network composed of a space deformation monitoring subsystem, an internal response monitoring subsystem and an environment quantity monitoring subsystem; a data fusion and feature extraction module based on a space-time diagram attention network, which is used for deeply mining a complex space-time coupling relationship between multiple measurement points and multiple physical quantities; the health state diagnosis module based on multi-task learning can synchronously output dam body structure health indexes and abnormal types of key areas; and a future state evolution prediction and multi-stage early warning module based on a Transform model. According to the method, digital twinning of the dam body is constructed, a physical entity and an information model are closely combined, a full-chain closed loop from multi-dimensional perception to intelligent diagnosis to prospective early warning is achieved, and the accuracy, comprehensiveness and timeliness of dam body structure state evaluation are improved.

The invention is suitable for the technical field of industrial process fault diagnosis, and relates to a hot rolling process composite fault tracing method under a variable working condition, which comprises the following steps: S10, fusing the generality and personality characteristics of a composite fault under the variable working condition by adopting multi-task learning and deep learning; s20, on the basis of extraction and fusion of generalization and personality characteristics of the composite fault under variable working conditions, adopting transfer learning and a convolutional neural network to realize intelligent diagnosis of the composite fault of working condition transfer and generalization; and S30, adopting an ensemble learning and transfer learning method to realize compound fault accurate tracing under variable working conditions. The method is simple in process and convenient to operate, and the accuracy of compound fault tracing in the hot rolling process under the variable working conditions is effectively improved.

The invention discloses an RF-CNN-based power transmission line tree obstacle recognition and positioning method and device and a medium, and belongs to the technical field of image processing, and the method comprises the steps: collecting data through a laser radar system and an RGB image collection device, carrying out the preprocessing of the collected data, carrying out the feature fusion through an RF-CNN model, and carrying out the recognition and positioning of a tree obstacle. And training a multi-task learning model to perform three-dimensional positioning of tree types and tree positions, performing classification through fused feature data in tree identification, identifying different types of trees, positioning the position of each tree in a three-dimensional space, calculating horizontal and vertical distances between the tree and the power transmission line, and evaluating whether the tree forms a tree obstacle risk or not. According to the method, the defects of the prior art in the aspects of tree identification, positioning precision, tree obstacle risk assessment and the like are effectively overcome, the efficiency, precision and reliability of tree obstacle monitoring are improved, and a powerful technical support is provided for intelligent inspection and safety management of a power transmission line.

The invention discloses a drug combination patent intelligent identification method and device based on a large language model, and the method comprises the steps: obtaining a standard data set built based on drug combination labeling information of patent data, carrying out the data expansion of the standard data set, and generating an initial training set; a parameter efficient fine tuning technology is adopted, the initial training set is utilized to train the base large language model, and an initial recognition model is generated; screening and identifying difficult samples in the unlabeled patent data by using the initial identification model, and adding the difficult samples into the initial training set to form an enhanced training set; performing iterative training on the initial recognition model by using the enhanced training set and adopting a multi-task learning framework in combination with a comparative learning mechanism to obtain a drug combination patent recognition model; the to-be-recognized patent data is input to the drug combination patent recognition model, and a drug combination information recognition result is obtained.The accuracy, data efficiency and model interpretability of drug combination patent recognition can be remarkably improved, and the computing resource requirement and the manual review cost are reduced.

The invention belongs to the technical field of fire-fighting facility control and management, and discloses a fire-fighting facility full-life-cycle intelligent operation and maintenance management control system. Comprising the following steps: acquiring real-time field state data; in a non-fire state, executing an active excitation and response test to obtain dynamic response data; processing the field state data and the dynamic response data by adopting an end-to-end multi-task learning framework, and outputting a structured diagnosis result containing the health states of the pump set, the valve and the pipe network; establishing an initial health baseline of each key device, and dynamically generating a self-adaptive alarm threshold value; a quantitative risk level is generated in combination with the fire safety level, and an operation and maintenance strategy instruction containing pilot operation and maintenance parameters is generated; main and standby equipment switching and strong health detection are automatically executed, and the fire protection function is preferentially guaranteed when a fire alarm or a manual forcing instruction is received; and executing grading alarm according to the quantitative risk grade. And intelligent operation and maintenance management control of the whole life cycle of fire-fighting equipment is realized.

The invention belongs to the technical field of equipment intelligent fault diagnosis and predictive maintenance, and particularly relates to a bearing intelligent fault diagnosis method fusing sound and vibration signals, which is characterized in that rapid diagnosis of a bearing fault is realized based on analysis of the fused sound and vibration signals; comprising the steps of acoustic vibration signal acquisition, extraction and fusion, enhanced feature processing, model training and fault diagnosis result generation. The method has the advantages that the one-dimensional convolutional neural network is adopted for feature extraction, multi-modal attention (MMA) is utilized for feature fusion, and the complementary advantages of sound signals and vibration signals are fully utilized. And dynamically constructing a k-nearest neighbor (KNN) graph based on the fusion features, and applying a graph convolutional network (GCN). A multi-task learning (MTL) framework is introduced, fault classification is used as a main task, and modal classification is used as an auxiliary task. According to the method, more abundant bearing fault feature information can be obtained, the classification precision is high, and an effective solution is provided for bearing intelligent fault diagnosis in industrial application.

The invention relates to an aircraft flow field and aerodynamic performance joint prediction method and system based on multi-task learning. The method comprises the following steps: collecting flow field data sets of different symmetric airfoils; after data preprocessing is carried out on the flow field data set, an input and output data set is constructed; constructing a neural network model, wherein the neural network model comprises a backbone network, a branch network and a fusion network; taking the space time sequence coordinates as input of the backbone network, and outputting backbone features; taking the static input characteristics and the historical flow field time sequence data as inputs of the branch network, and correspondingly outputting flow field prediction branch characteristics and aerodynamic coefficient prediction branch characteristics respectively; outputting a predicted value through the fusion network; constructing a weighted loss function; training the neural network model; and carrying out neural network model lightweight processing, and carrying out flow field prediction. The flow field characteristic prediction of the aircraft under the flow condition is realized quickly and accurately.

Application of multi-task learning technique(s) to machine logic (for example, software) used to detect financial transactions that are fraudulent or at least considered likely to be fraudulent. Some embodiments include adjustments and / or additions to conventional multi-task learning techniques in order to make the multi-task learning techniques more suitable for use in fraud detection software. One example of this is compensation for class imbalances that are to be expected as between the likely-fraud and not-likely-fraud classes of data sets (for example, training data sets, runtime data sets).

The invention discloses a traditional Chinese medicine prescription efficacy prediction system and method based on a dual-encoder Transformer, and belongs to the technical field of crossing of artificial intelligence and traditional Chinese medicine informatization. Constructing a double-layer embedding expression module comprising a drug embedding layer and a chemical component embedding layer; extracting component aggregation expression of each medicine by using a grading Transform encoder and a content gating attention mechanism; dynamically fusing the expression into the input of a drug-grade encoder through a component information injection module; a compatibility perception bias matrix is introduced into a drug-grade encoder to learn the compatibility relationship between drugs; and finally, based on prescription comprehensive representation output by a drug-grade encoder, synchronously outputting probability distribution of disease indications and targeted tissues through a multi-task prediction module. According to the method, collaborative modeling of the hierarchical structure of the traditional Chinese medicine prescription is realized, the dynamic nature of feature representation and the prediction accuracy are improved, and multi-task learning and the interpretability of a prediction result are supported.

The invention relates to the technical field of mechanical equipment intelligent operation and maintenance and state monitoring, and discloses a health monitoring method for bearing state evaluation and residual life and degradation trend prediction, which comprises the following steps of: firstly, extracting time domain, frequency domain and time-frequency domain characteristics from original vibration signals of a bearing under different working conditions; according to comprehensive evaluation indexes and known bearing degradation characteristics, features having good characterization capability and trend consistency for bearing degradation performance are screened out, a novel backbone network model is constructed, deep features are mined, effective features are enhanced, meanwhile, a time dependency relationship in a long sequence is captured, and then a multi-task learning mechanism is introduced, so that the bearing degradation performance is evaluated. Through parameter sharing and joint optimization, bearing state identification, residual life prediction and performance degradation trend prediction can be synchronously completed only by training and deploying a single model. According to the method, multi-task collaborative prediction under complex working conditions is realized, and the accuracy and robustness of bearing state recognition and service life prediction are improved.

The invention provides a hot-rolled bar mechanical property prediction method and system based on deep learning, and the method comprises the steps: obtaining and preprocessing the technological parameter data of a hot-rolled bar; inputting the effective data set into a pre-trained mechanical property prediction model, obtaining a spatial-temporal characteristic matrix of the process parameters based on a spatial-temporal attention mechanism, and multiplying the spatial-temporal characteristic matrix with original input to obtain a weighted input sequence; performing deep feature extraction on the weighted sequence through a Transform module to obtain an output vector; and synchronously outputting prediction results including the yield strength, the tensile strength and the ductility by using a multi-task learning module. According to the method, through deep fusion of a space-time attention mechanism, Transform and multi-task learning, complex space-time association among process parameters can be fully mined, high-precision and high-efficiency parallel prediction of a plurality of mechanical property indexes is realized, and the defects of a traditional mechanism model and a machine learning method in precision and generalization ability are effectively overcome.

The invention discloses a message issuing speed control method and system based on an AI large model. The method comprises the steps of collecting multi-source data in real time and constructing a multi-dimensional fusion feature vector; based on the BERT-CNN distillation architecture, detecting abnormity and executing hierarchical fusing; based on the fusion feature vector, using a reinforcement learning model to predict message issuing rates of a plurality of time windows in the future and dynamically adjusting priorities; in the offline stage, a mixed integer programming model is adopted to generate minimum cloud resource cost, and in the online stage, a deep reinforcement learning model is adopted to carry out real-time resource fine tuning; based on the node health degree, calculating a traffic allocation weight through a smooth weighted polling algorithm so as to carry out load balancing; different business scenes are adapted through domain adversarial training and multi-task learning, and different languages are adapted through multi-language BERT coding. The message rate is accurately controlled to improve the system stability and the resource utilization rate; low-cost scheduling fine tuning of cloud resources is realized; various business scenes and languages can be quickly adapted, and the development cost and time are reduced.