6133 results about "Training data sets" patented technology

In embodiments, systems and methods for improving machine-learning systems are disclosed. In embodiments, a system includes a data pool system that is configured to receive data from a plurality of different data sources and maintain a training data set that is used to train a specific machine-learning model based on the data from the plurality of different data sources. In embodiments, the system further includes a data scoring system that determines a data reliability score corresponding to the new data based on a set of intrinsic features of the new data and a data scoring model, wherein the data pool system selectively adds the new data to the training data set based on the reliability score of the new data. The system also includes a machine learning system that trains the specific machine-learning model based on the training data set.

The invention provides a road bridge crack detection method and system, and the method comprises the steps: collecting a bridge surface multi-view image, and constructing a training data set containing crack feature labeling through quality screening and standardized labeling; preprocessing the image by using a multi-scale feature fused deep convolutional neural network and carrying out semantic segmentation, initially identifying a suspected crack region and generating a segmentation mask; and constructing a BeNNS proxy model based on the mask, and establishing a mapping relationship between the detection result and the bridge structure topology, the stress flow field and the service function chain so as to evaluate the result reliability. And inputting an evaluation result into a hybrid evaluation mechanism, performing online real-time detection and offline batch verification to optimize precision, and outputting a verified crack region. Finally, morphological analysis is conducted on the area, geometric parameters and danger levels of cracks are extracted and integrated to a bridge health monitoring system, a crack evolution tracking algorithm and an early warning mechanism are established, and dynamic tracking early warning is achieved. The problem of low detection precision in a complex environment can be solved.

A method, system, and device for wind speed prediction and layout optimization in wind power generation are provided. The method includes: obtaining a basic wind resource dataset of a target region; constructing a physics-informed neural network model based on the basic wind resource dataset; obtaining wind speeds data at a specific location in a velocity field based on the physics-informed neural networks and constructing a training dataset; training the physics-informed neural network model based on the training dataset; reconstructing a wind speed distribution within the velocity field and predicting wind speeds for a next time period with a wind farm using the trained physics-informed neural network model; and optimizing a layout of a wind turbine cluster based on a reconstructed wind speed distribution within the velocity field. The present application reconstructs a two-dimensional velocity field of the wind farm by training the PINN and enables accurate ultra-short-term wind speed prediction.

The invention discloses an intelligent detection method and device for fusing a medical image learning image, and relates to the technical field of medical image processing. The method comprises the following steps: acquiring and preprocessing a bimodal medical image, and extracting a feature map through multi-scale decomposition; constructing a cross-modal correlation model, and setting a modal attention mechanism (embedding anatomical structure prior guidance feature complementation) and a morphological attention mechanism (setting lesion morphological constraint weight); the method comprises the following steps: collecting multiple types of image samples, pairing according to a focus form and an imaging mode to construct a bimodal joint data set, and correlating and labeling to generate a training data set with modal attributes; after a multi-stage iteration training model, inputting the preprocessed image to carry out feature fusion so as to obtain a fused image; and generating a lesion probability graph according to the fused image, positioning a lesion area through multi-threshold segmentation, and outputting a detection result. The system comprises a data acquisition module, a preprocessing module and the like. The method improves the accuracy and reliability of medical image detection, and is suitable for clinical multi-modal image analysis.

The invention provides a multi-modal image fusion method based on modal self-adaption and modal interaction compensation, and the method comprises the following steps: S1, obtaining a multi-modal image fusion data set, and obtaining a training data set through preprocessing; S2, analyzing the modal difference characteristics of infrared and visible light images, and evaluating the correlation characteristics of image pairs in different scenes; s3, capturing a cross-modal feature dependency relationship through a self-attention mechanism; s4, a differential feature extraction strategy is adopted, model parameters are optimized through iterative training, and multi-modal image fusion is completed; s5, a modal interaction compensation module is additionally arranged, unit dynamic balance common features and modal exclusive features are fused, feature complementation is achieved in channel and space dimensions, parameters of the modal interaction compensation module are optimized, the model is made to learn the optimal fusion weight of the multi-modal features in a self-adaptive mode, and multi-modal fusion image generation optimization is achieved through the model; according to the invention, multi-modal image fusion can be accurately and effectively carried out.

The invention discloses a disaster intelligent Internet of Things multivariable time sequence anomaly detection method and device, and relates to the technical field of Internet of Things anomaly detection, and the method comprises the steps: S1, constructing an initial anomaly detection model; s2, acquiring a training data set; s3, performing optimization training on the initial anomaly detection model by using the training data set to obtain an optimized anomaly detection model; s4, acquiring real-time monitoring data; s5, analyzing the real-time monitoring data by using the optimized anomaly detection model to obtain a detection result; the dynamic gated expansion convolutional network DGDC solves the problems of rigid structure and parameter explosion of a traditional TCN. Dynamic expansion rate scheduling enables a receptive field to expand in an exponential level along with the number of layers, and second-level burst and week-level periodic characteristics can be captured at the same time; the parameter quantity is reduced by 60%-70% through depth separable convolution, and the efficiency and precision of local feature extraction are both superior to those of an existing convolution module by combining the suppression effect of a gated linear unit GLU on noise features.

The invention discloses a cross-cultural customer service dialogue quality automatic evaluation method in combination with sentiment analysis, and relates to the technical field of natural language processing, and the method comprises the steps: carrying out the alignment of voice and text based on a transmission matrix in real time, extracting a speech, a metaphor and polarity, and generating a speech tag; constructing an emotion channel and a polite channel, and fusing expression and shielding intensity through sharing attention; comparing and aligning with the same language prototype in a regional culture baseline library to obtain a calibration representation and updating a language offset record table; the potential upgrading probability is represented and recurred according to round aggregation calibration, and a risk vector and a high-risk position are formed; fusing risk and business indexes by a capacity integral kernel, outputting a comprehensive quality score, and giving factors and round attributions; sample recovery is triggered according to score and feedback difference, a micro-weight training data set is constructed, gradient increment training is carried out under low-rank adaptation, and cross-language consistency, early recognition of upgrading risks and interpretable evaluation are achieved through a closed loop.

The invention discloses a renewable energy power generation power prediction and power dispatching method and system, and the method comprises the steps: collecting the historical power generation data and real-time meteorological data of renewable energy power generation, carrying out the linear interpolation of the historical power generation data and the real-time meteorological data, and carrying out the missing value filling and box plot anomaly detection, obtaining a normalized training data set; constructing a hybrid prediction model by using the normalized training data set and adopting a neural symbol acceleration technology with time logic constraints, extracting medium and long term space time features, and generating a renewable energy power generation power prediction result; and according to the renewable energy power generation power prediction result and the system constraint condition, adopting a linear one-dimensional projection constrained distribution robust control method to formulate a scheduling strategy, and utilizing the scheduling strategy to solve an optimal scheduling scheme through mixed integer linear programming. According to the method, the renewable energy power generation power prediction precision and the power dispatching robustness are remarkably improved.

The invention discloses a multi-granularity visual reasoning model construction method and device based on reinforcement learning. The method comprises the following steps: constructing an'image-reasoning query-bounding box 'triple as a training data set; designing a composite reward function including positioning precision, target counting precision and format reward; training the multi-modal large language model by adopting a GRPO algorithm; the trained model can output a region-level bounding box, and a pixel-level mask is generated and a contour-level result is extracted in combination with the segmentation model. According to the method, the problems that in the prior art, a reasoning path depends on manual annotation, multi-granularity tasks cannot be expanded, and generalization is insufficient are solved, and the autonomous decision-making ability, task expansibility and generalization in a distribution offset scene of the model are improved.

The invention provides a meteorological downscaling method based on space-time fusion and physical constraint, and belongs to the technical field of meteorological downscaling, and the method comprises the steps: carrying out the preprocessing of multi-source meteorological related data and a high-resolution meteorological truth value, and constructing a training data set; an improved U-Net model is constructed, spatiotemporal features and multi-source auxiliary features are obtained through a multi-branch feature extraction unit, high-resolution information is recovered through fusion and decoding, and an attention enhancement module is embedded to highlight a key area; a model is trained through a training data set, parameters are optimized by adopting a loss function fusing topographic features and physical rules, and prediction error differentiation constraint on a complex area and violating the physical rules is achieved; and preprocessing target low-resolution data, inputting the preprocessed target low-resolution data into the model, and outputting high-resolution meteorological data and a physical attribution result. The problems that in the prior art, multi-source meteorological data fusion is insufficient, downscaling precision of a complex terrain area is insufficient, and prediction errors violating physical laws are lack of effective constraints are solved.

The invention discloses a reward model construction method and an inference model construction method, and relates to the technical field of computers, and the method comprises the steps: obtaining a reward model training data set; performing primary iteration training on a pre-constructed initial reward model by utilizing the training data set to obtain a primary reward model; grouping the reward model training data set according to a plurality of answers corresponding to each sample question and at least one evaluation index value corresponding to each answer to obtain at least two sub-training data sets; and at least utilizing the first sub-training data set and the second sub-training data set to carry out iterative training on the first-level reward model to obtain a final reward model. According to the method and the device, through three-stage iterative training, the final reward model can accurately evaluate the sample problem based on the evaluation standard, and an evaluation basis is provided for input problem evaluation.

The invention discloses a mechanical arm path planning method based on Transform and a diffusion model, and belongs to the technical field of robots, and the method comprises the following steps: collecting environment information to generate a reference path, and constructing a training data set; a conditional diffusion Transform prediction network is constructed, features are extracted, and multi-modal path prediction is realized; gaussian noise is applied to the reference path, and denoising training is carried out on the conditional diffusion Transform prediction network; in combination with a diffusion model and a cost guidance mechanism, optimizing a noise path sampled from Gaussian distribution until a smooth collision-free path is generated; the candidate paths are evaluated, and a mechanical arm joint control instruction is generated; and the mechanical arm executes the planning track and carries out real-time sensing and online re-planning. According to the method, environment perception, Transform coding and diffusion generation are organically combined, a plurality of feasible tracks which are smooth and capable of avoiding obstacles are rapidly generated in a complex obstacle scene, and the method has good generalization ability and can adapt to different scenes and dimension changes.

The invention discloses a flow field measurement method based on an event camera, and the method comprises the steps: generating a PIV data set, each time sequence sample sequence comprising a plurality of frames of continuous particle images, a corresponding velocity vector field, and particle event data at all moments; establishing a flow field data acquisition device based on an event camera and a high-speed camera, acquiring real event data and real image data which are synchronous in time so as to adjust parameters of an event simulator, and verifying and updating particle event data in the PIV data set according to the adjusted event simulator so as to obtain a flow field data acquisition result; obtaining the updated PIV data set as a training data set; building an event camera optical flow method model, and training by adopting the training data set; and on the basis of the trained event camera optical flow method model, event sequences in two adjacent time periods are used as inputs to calculate a velocity vector field corresponding to a middle moment. According to the invention, the flow field velocity field at the required moment can be obtained based on the event data within a period of time.

Examples for performing wireless sensing tasks based on foundation model are described. In one example, a described method comprises: obtaining channel information (CI) data generated based on at least one wireless channel; generating a training dataset based on the CI data, wherein the training dataset comprises: a plurality of CI pairs, original CI data and a mask; training a foundation model using the training dataset based on an aggregate of a contrastive loss function and a reconstruction loss function; training a plurality of task-specific models; and performing a plurality of wireless sensing tasks based on the foundation model and the plurality of task-specific models. Each of the plurality of task-specific models is used to perform a corresponding one of the plurality of wireless sensing tasks together with the foundation model.

The invention discloses a heterogeneous road structure cavity disease inspection method, device and equipment and a storage medium, and the method comprises the steps: constructing a highly-simulated heterogeneous road structure model, and adaptively generating an irregular cavity disease meeting the horizon geometric constraint; the problems that electromagnetic wave reflection simulation is distorted due to the fact that a traditional homogeneous simplified model cannot reflect dielectric mutation between aggregate and a cementing material, and a regularized cavity form does not conform to a real stress distribution expansion mode are solved. According to the method, radar forward modeling simulation data containing complex heterogeneous backgrounds and randomly-shaped holes can be automatically generated in batches, a rich, real and diversified training data set is provided for intelligent identification of road internal diseases based on deep learning, and the bottleneck problem of lack of real disease radar image data is relieved.

The invention relates to the technical field of oil well fault monitoring, and discloses an oil well indicator diagram real-time fault prediction method and system. The method comprises the following steps: acquiring an oil well sensor data stream, buffering and checking data integrity through a sliding window, and aligning multi-channel sensor data by applying a dynamic time warping algorithm to generate a standardized data stream; extracting time domain features based on the data stream, and comparing the time domain features with a historical feature library after principal component analysis dimension reduction to generate a feature difference index; triggering a multi-level threshold strategy according to the difference index, collecting an incremental training data set, finely tuning the model by adopting an elastic weight preserving algorithm, and generating a hot switching ready model; after the model is loaded, a fault probability value is generated through GPU accelerated reasoning, and an early warning event with a timestamp is generated; and finally analyzing the message into an early warning protocol message edge for transmission, and dynamically optimizing system resources based on logs. According to the method, the delay problem of high-frequency data flow is effectively solved, and the fault prediction accuracy and the system response speed are remarkably improved.

The invention discloses an industrial Internet of Things time sequence self-supervision anomaly detection method and a monitoring and early warning system, and relates to the field of industrial Internet of Things, and the method comprises the steps: S1, constructing an anomaly detection model, and S2, obtaining a training data set; s3, training and optimizing an anomaly detection model; s4, acquiring to-be-detected data in real time; s5, performing anomaly detection analysis on the to-be-detected data, and outputting an anomaly detection result; through a time sequence and relation learning module, a dynamic graph topological structure learning module and an enhancement module, internal characteristics of a time sequence in a time domain and a space domain are deeply mined. The time sequence and relation learning module comprehensively captures a multi-scale time pattern, and the dynamic graph topological structure learning module eliminates dependence on a predefined graph structure; the enhancement module enhances the invariant representation under noise, and improves the recognition capability of the model to a normal mode; through wide experiments, the advancement of the method in detection performance is verified, and reliable support is provided for intelligent manufacturing and infrastructure diagnosis.

The invention discloses a multi-scale and mixed attention high-robustness motor imagery recognition method, which comprises the following steps: S1, acquiring motor imagery electroencephalogram signals, preprocessing the motor imagery electroencephalogram signals, dividing a training set and a test set, segmenting the training set, recombining the training set and expanding a training data set; s2, multi-scale feature extraction is conducted on the motor imagery electroencephalogram signals through a multi-scale convolution embedding module, and time dynamic and space cooperation features of different frequency bands are captured; s3, inputting the multi-scale features into LG-KAT, and respectively modeling a local fine-grained feature and a global time sequence dependency relationship through a local attention branch and a global attention branch; s4, features output by LG-KAT and low-layer embedded features are fused and flattened, a classification layer based on GR-KAN is input for nonlinear transformation and category mapping, model parameters are trained and optimized, and motor imagery task classification is achieved. The invention further discloses a multi-scale and mixed attention high-robustness motor imagery recognition system.

The invention belongs to the technical field of machine learning and pre-stress, and discloses a pre-stress release loss value prediction method and system based on machine learning, and the method comprises the steps: carrying out the multi-working-condition modeling and simulation of a pre-stress beam through finite element numerical software, and extracting the working parameters and design parameters of the pre-stress beam, carrying out data preprocessing, distribution check and feature importance analysis to obtain an initial data set; dividing the initial data set into an initial training data set and an initial test data set, and processing the initial training data set and the initial test data set to obtain a processed training data set and a processed test data set; constructing a full-connection multi-layer perceptron neural network model, defining training, verification and monitoring functions, training the full-connection multi-layer perceptron neural network model by using the processed training data set, and testing the trained model by using the processed test data set to obtain a prediction model; real parameters of the prestressed beam are obtained, the prediction model is used for predicting the prestress release loss value, and a prediction result is obtained.

The invention discloses an artificial intelligence industrial PCB defect detection method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining PCB image data and defect labeling data; generating three types of enhanced image sets through directional enhancement, and weighting and extracting small defect samples to construct a training data set; inputting the training data set into an improved YOLOv8 model for training, and performing multi-scale feature fusion on an input image to generate initial feature data; generating filtering characteristic data according to a PCB circuit texture prior rule; the defect area features are enhanced through a Biformer attention mechanism, and enhanced feature data are generated; inputting the enhanced feature data into the detection head network to generate prediction bounding box data; a dynamic NWD loss function is adopted to calculate the distribution distance between the predicted bounding box and the real bounding box, and model parameters are optimized; performing defect reasoning on the target PCB image according to the trained model, and outputting defect position coordinates, types and confidence coefficients; according to the method, the small defect detection precision of the model can be remarkably improved, and the omission ratio is reduced.

The invention discloses a space identification method and system based on a YOLO model, a terminal and a medium, and the method comprises the steps: obtaining a CAD drawing, carrying out the space segmentation and coordinate conversion of the CAD drawing, obtaining a PNG image corresponding to a specified space region in the CAD drawing and a label file corresponding to the PNG image, and determining a training data set based on the PNG image and the label file; building a Python operation environment, installing a YOLOv8-seg model and a related dependency library thereof, and carrying out end-to-end training on the training data set based on a training script of the YOLOv8-seg model to obtain a YOLO space segmentation model; and based on the YOLO space segmentation model, carrying out space segmentation on the building plane drawing, outputting a segmentation result, and carrying out automatic labeling on a space region. According to the method, the YOLO space segmentation model is adopted, high-precision space recognition and classification are achieved, and the generalization ability is high.

The invention discloses a mold life prediction and maintenance strategy making method based on big data analysis, and particularly relates to the field of mold life prediction and maintenance, and the method comprises the following steps: collecting and associating multi-source heterogeneous data in a mold production process; comprising process parameter time sequence data, on-line monitoring time sequence data and structured and image data of off-line inspection; performing time domain alignment and collaborative feature extraction on the data, and constructing a structured training data set taking a production cycle as a unit; inputting the data set into a dynamic evolution prediction model, outputting a mold health state score, and generating a dynamic maintenance strategy through a multi-objective optimization model in combination with production context information; and finally, visually displaying the strategy, converting the strategy into a control instruction, issuing the control instruction to a production management system, and automatically triggering maintenance execution. The method can realize high-precision life prediction, dynamically optimize the maintenance decision, significantly improve the service life and production efficiency of the mold, and reduce the maintenance cost and production risk.

Provided are a method for training a transformer fault detection model, a fault diagnosis method, and a related device. The method includes: obtaining an initial voiceprint signal of a transformer and a fault type corresponding to the initial voiceprint signal; preprocessing the initial voiceprint signal to obtain an input signal, and establishing an input signal dataset; performing feature extraction on a first input signal in the training dataset based on a preset feature extraction algorithm to obtain a first voiceprint feature; training an initial detection model based on the first voiceprint feature and a first fault type corresponding to the first input signal to obtain a first training result; determining a loss function based on the first training result and the first fault type; and iteratively adjusting a weight value of the initial detection model until the loss function converges to obtain a fault detection model.

The invention belongs to the cross technical field of artificial intelligence and marine meteorological prediction, and discloses a sea wave probability prediction method and system, and the method comprises the steps: obtaining historical wind field data and sea wave spectrum data of a target sea area, carrying out the preprocessing and organization of the data, and constructing a training data set; constructing a hybrid expert probability model, wherein the model comprises a gating network and a plurality of expert networks; the training data set is used for training the hybrid expert probability model, the trained model receives input wind field data, and hybrid probability distribution is output through the synergistic effect of the gating network and the expert network; and sampling is carried out from the mixed probability distribution to obtain a predicted sea wave spectrum set, and sea wave risk probability prediction is realized. Complete distribution information can be obtained through one-time forward calculation, a numerical mode set is not needed, the computing power and energy consumption expenditure are remarkably reduced, and high-frequency updating and quasi-real-time business application can be conveniently achieved in resource-limited environments such as shipborne, buoys and offshore stations.

The invention provides a YOLO and Transform fused nori cultivation scene detection method, belongs to the technical field of image recognition and intelligent agriculture, and solves the technical problems of low efficiency and insufficient precision of traditional nori cultivation monitoring. According to the technical scheme, the method comprises the following steps: S1, collecting and preprocessing a laver cultivation image, and constructing a labeling data set containing laver, inserted links and raft net targets; s2, a detection model fusing a YOLO module and a Transform module is constructed; s3, based on the training data set, using an optimization algorithm to iteratively train model parameters until the performance reaches the standard; and S4, pre-processing a to-be-detected image, inputting the pre-processed to-be-detected image into the trained model for detection, and filtering out an overlapping frame through a non-maximum suppression algorithm to obtain a final result. According to the invention, key targets such as laver, inserted links and raft nets can be accurately monitored, and the monitoring automation level and accuracy are improved.

The invention relates to the technical field of intelligent traffic infrastructure engineering, in particular to a roadbed settlement high polymer grouting repair grouting parameter optimization method, which comprises the following steps of: firstly, constructing a multi-source fusion training data set, and learning a prediction model based on a training machine; establishing a driving mapping relation between the grouting parameters and the road lifting effect and the maximum stress data of the repair area; then, based on the mapping relation, a multi-objective optimization model including pavement settlement repair precision, road stress, economic cost control and environmental friendliness evaluation is constructed; solving the model by adopting a Bayesian optimization algorithm to obtain an optimized grouting parameter combination; a marginal contribution of each parameter to a prediction result is calculated in combination with an SHAP interpretability analysis method, and an engineering decision basis is provided for parameter selection; constructing a transfer learning adaptation framework to adapt to different disease, geology and road types; and finally, establishing a real-time monitoring system, and realizing optimal control by combining sensor data and model feedback.

The invention provides a multi-modal large model incremental training data screening method, and relates to the technical field of data processing, and the method comprises the steps: executing modal structure analysis on newly added multi-modal data, extracting each modal vector, calculating a semantic matching degree, and removing samples lower than a preset first threshold value; calculating a multi-level semantic distance between a sample embedding vector and a historical clustering center in a unified semantic space, and dividing a core semantic region sample, a boundary semantic region sample and a discrete semantic region sample according to the change rate of the multi-level semantic distance; performing semantic fine-grained alignment on the boundary semantic region samples, when multimodal unstable distribution is detected, executing local context reconstruction to repair semantic deviation, and if the multimodal unstable distribution is still unstable, removing the semantic deviation; performing multiple rounds of small-batch reasoning, calculating a semantic stability coefficient based on a semantic prediction result, and when the semantic stability coefficient is lower than a preset second threshold value, determining that the sample is a potential drift sample and removing the potential drift sample; constructing an incremental training data set; according to the method, the autonomy and accuracy of incremental training data screening are improved.

The invention relates to the technical field of coast engineering, in particular to an estuary sandy coast erosion and deposition simulation system based on the coupling effect of flood peak runoff, waves and tide, which comprises a training data generation module, an intelligent agent model construction module, a dynamic prediction engine module and a scene evaluation module. The training data generation module is used for outputting a hydrodynamic state field, a wave characteristic field, a bed surface shear stress field and a bed surface elevation variable quantity by utilizing a traditional numerical model to construct a training data set; the intelligent agent model building module is based on a deep learning network and introduces physical constraint loss function training to obtain an intelligent agent model; the dynamic prediction engine module loads the trained deep learning network to realize bed surface elevation variation prediction and update terrain boundary conditions; and the scene evaluation module executes erosion and deposition evolution simulation according to different hydrological boundary condition combinations and extracts terrain evolution data to quantitatively evaluate the coast stability and the channel deposition risk. The invention relates to the field of estuary dynamic landform simulation and coast engineering.

The invention provides a meteorological-distributed power supply-load long-term joint prediction method, and relates to the technical field of power system load prediction, and the method comprises the steps: introducing a multi-channel attention fusion mechanism, and constructing a feature fusion layer; performing multi-source feature coding and feature weighted fusion by using a meteorological encoder, a power encoder, a load encoder and a feature fusion layer to obtain a sample training data set; based on the time weighted loss function, adopting the sample training data set to supervise and train the long-short term memory network until convergence; and executing generation power prediction and power load prediction by using the long-term trend prediction plug-in. According to the method and the device, the technical problem of insufficient coupling modeling between prediction objects in the prior art can be solved, the technical target of collaborative modeling between the weather, the distributed power supply and the load is realized, and the technical effect of improving the power prediction precision is achieved.

The invention relates to a temperature forecast correction method based on a PSD-Net and a PSD-Net, and belongs to the technical field of weather forecast, and the method comprises the steps: obtaining a dynamic meteorological variable based on the PSD-Net, and loading topographic data and a report starting time observation truth value at the same time; preprocessing the dynamic meteorological variable, the topographic data and the report starting time observation truth value; inputting the preprocessed data into a temperature forecast correction model to obtain temperature correction field data; wherein the temperature forecast correction model is obtained by training a PSD-Net model based on a training data set, and the training data set comprises historical dynamic meteorological variables, topographic data and a report starting time observation true value. Compared with the traditional numerical mode and the original output of the archaeological model, the temperature forecast MAE corrected by the method is reduced by more than 37.6%, the accuracy rate within 2 DEG C is improved by 14%-19%, and the precision advantage is more prominent especially in complex terrain areas and extreme weather events.