1864results about How to "Easy extraction" patented technology

The invention discloses a construction method and device of a multi-component data agent, and the construction method specifically comprises the following steps: obtaining sample data, and constructing a vector knowledge base; extracting a knowledge service flow according to the sample data, determining an ontology through knowledge representation, and forming a knowledge graph; training an initial language model based on the vector knowledge base, and giving a data processing model; and performing modularization arrangement and linking on the knowledge graph and the data processing model in combination with a logic tool chain and a thinking graph of the data intelligent agent, and constructing to obtain the multi-component data intelligent agent. According to the method, the knowledge graph is fused to construct the business rule engine, training data support is provided, the thinking chain process is modeled into the thinking graph of a graph structure, and the data processing model and the knowledge graph associated with the workflow node are executed, so that the accuracy of result reasoning of the data agent is enhanced, and the knowledge boundary is expanded; and particularly for financial auditing data, key information can be better extracted, and the working efficiency of power grid auditing personnel is improved.

The invention relates to the technical field of knowledge maps, and discloses a knowledge map searching method and system based on local semantics and global communitization, and the method comprises the steps: extracting entities and relationships thereof from a knowledge map to construct an undirected graph; the undirected graph is divided into multiple levels of community information, and a community report is obtained by generating a community information table; selecting an instance triple containing data source information from the knowledge graph, constructing an instance triple information source table, extracting IDs, names and attributes of entities, and generating an entity attribute table to obtain an entity attribute vector table; key entities in a to-be-queried question are extracted and subjected to vector representation, the similarity between the key entities and an entity attribute vector table is calculated, first N related entities are selected to generate contexts (including an entity context, a relation context, a data source context and a community context), and finally a search result of the to-be-queried question is obtained. According to the method, the information related to the to-be-queried question can be accurately retrieved from the knowledge graph.

The invention discloses a remote sensing surveying and mapping image enhancement processing method for an unmanned aerial vehicle, and relates to the technical field of image enhancement processing. During operation of a system, flight attitude and position information are recorded through GNSS and IMU equipment, the flight path of the unmanned aerial vehicle is controlled, and collected original images are primarily processed; calculating and obtaining a flight stability coefficient Fs, an image acquisition quality coefficient Iq and a topographic feature retention coefficient Tf, removing random noise in a remote sensing image by using an improved non-local mean NLM algorithm, optimizing and processing an edge region, improving edge definition and texture details of a topographic image through a Laplacian pyramid algorithm, strengthening landform features of mountains and hills, and obtaining a remote sensing image; according to the method, color distortion caused by complex mountain illumination conditions is corrected, image colors are enabled to truly restore topographic features, important landform information is prevented from being lost due to over-brightness or over-darkness, topographic feature extraction is optimized, a final index Zfinal is generated, and quality evaluation is performed on an enhanced and corrected image.

The invention relates to a tree neighbor context-based big language model RAG optimization method, which comprises the following steps of: reading a directory structure and content of a document, generating a corresponding directory tree, converting the directory tree into a Markdown format containing a title and a level, and automatically extracting according to a document template if no title exists; segmenting the document into knowledge blocks according to the priority; after the knowledge blocks are recalled, the context is expanded by using a tree adjacent context method, and a new knowledge block list is formed; grouping and sorting the expanded knowledge blocks according to document identifiers, splicing reference data based on different fields and confidence coefficients, and generating a character string set from the original document; and splicing prompt words by using the constructed reference data and the new knowledge block list, and sending the spliced prompt words to the large model for processing. According to the scheme, the performance and practicability of the large model in the information retrieval and answer generation process are comprehensively enhanced by optimizing context information, emphasizing key content, adapting to various document formats, improving user experience and the like.

The invention provides a virtual fitting method and device, multi-target personalized virtual fitting is realized through a multi-target and multi-mode virtual fitting model, and the virtual fitting device comprises a multi-mode feature interlaced learning attention module (MFILA) and a parallel denoising UNet module. Wherein the MFILA module realizes multi-modal condition feature coding through a multi-modal feature fusion module (MFF) and a multi-reference target texture feature extraction module (MRSTF), and the parallel denoising UNet module is mainly responsible for denoising generation. A user uploads a model clothes graph, a target fitting clothes style graph and corresponding text cues, and the system gradually generates a denoised virtual fitting result from pure noise through an MM-VTON model by taking the inputs as conditions. According to the method, the reality sense and the accuracy of virtual fitting are improved by utilizing an advanced image generation technology and multi-modal learning, meanwhile, the demand of computing resources is reduced, and the method has relatively high practical application value and a wide market prospect.

The invention belongs to the technical field of medical image processing, and particularly relates to a double-encoder semi-supervised heart MRI double-ventricle segmentation method based on improved SAM. A teacher model and a student model which are used both comprise double encoders, prompt encoders and mask decoders, each double encoder comprises a ViT branch and a CNN-Mama branch which are parallel, parameter fine tuning of the ViT branch is realized through a position adapter and a feature adapter, the CNN-Mama branch mainly comprises a convolution fusion Mama block and a second-order dimension attention block, and the CNN-Mama branch is used for realizing fine tuning of parameters of the CNN-Mama block. The convolution fusion Mama block introduces an enhanced convolution block on the basis of a VSS block, and the second-order dimension attention block uses a covariance matrix to mine second-order statistical information of data; carrying out weighted summation on the output features of the ViT branch and the CNN-Mama branch to obtain the output features of the double encoders; the output features of the double-encoder and the prompt encoder are input into a mask decoder to be decoded, and a segmentation result is obtained; and performing joint training on the teacher model and the student model based on interpolation consistency regularization semi-supervision, and using the trained student model as a segmentation model for double-ventricle segmentation of heart MRI. The segmentation model has strong feature extraction capability, can effectively extract the edge information of the ventricles and the boundary information of the double-ventricle connection region, and improves the segmentation precision.

The invention relates to the technical field of financial data processing, in particular to a data processing method and system based on financial information bills. The data processing method comprises the following steps: acquiring multi-modal financial information bill data; and performing bill modal decomposition on the multi-modal financial information bill data to generate financial information bill modal decomposition data. Bond information price income prediction needs a large amount of financial data, such as market interest rate, bond expiration date, face interest rate and the like, the data are similar to the data form of bill modal decomposition, and a more accurate model can be obtained through standardization and feature extraction of multi-modal data. Therefore, valuable input is provided for bond price and income prediction. According to the invention, through multi-modal data fusion, counterfeited feature comparison modeling, abnormal bill clustering analysis and dynamic risk assessment, the security and accuracy of financial bill identification are improved.

The invention provides a tool wear state prediction method and device based on multi-source feature fusion, and the method comprises the following steps: obtaining various tool wear state data to construct a multi-source feature data set, and carrying out the preprocessing of the multi-source feature data set; performing deep fusion feature learning on the preprocessed multi-source feature data set by using a multi-modal fusion auto-encoder AE to generate a fusion feature data set; performing feature extraction on the fused feature data set by using a neural network to generate a feature sequence, and inputting the feature sequence into a multi-source gating prediction model WGX for training; and utilizing the trained multi-source gating prediction model WGX to predict the wear state of the tool to be detected. According to the method, the multi-mode fusion AE is used for fusing the multi-source features of the tool wear state, key information is effectively extracted from data, a set of fusion features with more representativeness are generated, a prediction model capable of comprehensively reflecting the tool wear state is constructed, and prediction precision and generalization ability are improved.

The invention relates to a transformer voiceprint anomaly detection method based on a generative adversarial network, and the method comprises the steps: obtaining voiceprint data, and carrying out the preprocessing of the voiceprint data, and obtaining the preprocessed spectrum data; constructing an abnormal voiceprint detection model; inputting the preprocessed spectrum data into an abnormal voiceprint detection model for training; and obtaining voiceprint data to be detected and preprocessing the voiceprint data to be detected, inputting the preprocessed voiceprint data to be detected into the trained abnormal voiceprint detection model, and outputting a detection result. According to the method, unbalanced distribution of normal voiceprint data and abnormal voiceprint data can be balanced, the generalization ability of the model is enhanced, and the model can keep high detection performance when processing a small amount of abnormal data; according to the method, the distinguishing capability of the abnormal voiceprint is enhanced, the abnormal voiceprint can be effectively recognized in a complex noise environment, the influence of noise and interference factors is reduced, and the detection accuracy is improved; fine-grained features in the voiceprint signals can be captured, extraction of the features is further optimized, and therefore abnormal voiceprints can be recognized more accurately.

The invention discloses an intelligent asphalt pavement disease detection method based on a YOLOv5 algorithm, and relates to the technical field of intelligent expressway and road maintenance, and the method comprises the steps: obtaining video data through a vehicle-mounted or airborne pan-tilt camera, and constructing an asphalt pavement disease image data set through manual marking; a YOLOv5 target detection model is adopted, an efficient multi-scale attention mechanism is introduced, and preliminary training is carried out; detecting a real-time database on the basis of a pre-trained improved YOLOv5 target detection model, and manually checking a detection result so as to optimize the model; and performing redundant data de-duplication on continuous multi-frame image information by using a dynamic planning method, correcting the image by using a chessboard method to obtain the actual size of the target, and performing evaluation according to a disease standard. Therefore, by adopting the method, the labor cost and the calculation cost can be saved, the pressure of storage requirements can be reduced, the real-time detection effect can be realized, and the method can be widely applied to asphalt pavement disease detection.

The invention relates to a preparation method of a chlorella exosome as well as a product and application of the chlorella exosome, the preparation method comprises the following steps: (1) mixing extremely micro chlorella with a separation buffer solution, and then carrying out wall breaking treatment to obtain a cell breaking solution; (2) centrifuging the cell disruption liquid, and reserving supernate; and (3) filtering the supernate to obtain the chlorella exosome. The preparation method of the chlorella exosome, provided by the invention, is simple in steps and easy to operate, the chlorella raw material and the specific separation buffer solution are subjected to wall breaking treatment, so that active ingredients in the prepared chlorella can be better extracted, the content of protein and polysaccharide in the obtained exosome is higher, and the purity of the exosome is improved. Meanwhile, gradient centrifugation, filter membrane filtration and the like are assisted in the preparation process, so that the prepared exosome is high in purity and less in impurities.

The invention discloses an SAR sea surface wind speed inversion method based on multiple attention-global enhancement UNet, and the method comprises the following steps: (1), obtaining wind speed data observed by a buoy, carrying out the cleaning and preprocessing, and making a label data set; (2) acquiring dual-polarization ground distance multi-view SAR data collected in an interference width mode IW type; (3) preprocessing the SAR data; and selecting SAR data corresponding to the buoy data information. Dividing the preprocessed SAR data set into a training set, a test set and a verification set; (4) constructing a multiple attention-global enhancement UNet model, namely a CPA-KiTUNet model, training to obtain a sea surface wind speed inversion model, and selecting a test set to test on the trained inversion model to obtain an inversion wind speed result; according to the invention, richness of inversion data is improved, and wind speed inversion can be accurately carried out in a complex scene.

The invention relates to the technical field of paint surface detection, in particular to a UV resin coating paint surface defect detection method and system.The method comprises the steps that a paint surface image set shot by light sources at different angles is subjected to reflective point removal treatment, and a fused to-be-detected image facilitating defect detection is obtained; segmenting the to-be-detected image of the paint surface before and after cleaning, calculating a similarity index of the segmented image, and detecting whether an uncured defect exists or not according to a preset similarity threshold value; acquiring and processing data of the segmented image to obtain a segmented region uniformity index, and detecting a color non-uniformity defect according to a preset threshold value; establishing an MSF-CRA-YOLOv5 model to carry out defect detection on the paint surface to be detected, wherein the defect detection comprises a defect type and a defect position; designing a plurality of loss functions in the total loss function, and designing a loss function in a prediction stage for accurate positioning of a bounding box; and finally obtaining a detection result and generating a detection report. According to the method provided by the invention, the efficiency of detecting the paint surface defects of the UV resin coating is improved.

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

The invention belongs to the technical field of seismic signal monitoring, and discloses a micro-seismic signal spectrum analysis system and method based on DVEC, and the system comprises a data collection device, a data preprocessing module, and a depth variation code-classifier. Acquiring a plurality of original vibration signals through a data acquisition device; performing fast Fourier transform (FFT) processing on the plurality of original vibration signals by using a data preprocessing module to obtain corresponding frequency domain sequence signals; splicing the original micro-seismic signals on a plurality of time domains and the corresponding frequency domain sequence signals in a dual-channel mode to form dual-channel micro-seismic signal input data; and inputting the dual-channel micro-seismic signal input data into the depth variational coding-classifier to obtain the classification category of each original micro-seismic signal. According to the method, different types of seismic signal features can be clearly distinguished, unknown types of seismic signals can be identified, and the method is expected to be an important technical means in the field of seismic signal identification.

The invention provides an intelligent defect detection method and an intelligent defect detection network based on S-shaped dynamic convolution and a cross-weighted feature pyramid, and the method comprises the following steps: collecting an OK sample image and a plurality of NG sample images, and employing a co-occurrence matrix matching method based on Laplacian gradient features, extracting defect labeling area images of the plurality of NG sample images; constructing a feature extraction network based on S-type dynamic convolution for extracting defect features; constructing a pyramid module based on cross-weighted features, wherein the pyramid module is used for multi-level fusion calculation; building an intelligent defect detection network based on S-type dynamic convolution and a cross-weighted feature pyramid, and training the intelligent defect detection network; performing product detection by using the defect intelligent detection network based on the S-shaped dynamic convolution and the cross-weighted feature pyramid; through the arrangement, high-precision segmentation can be better carried out on the defect area and the background area, the precision and accuracy of industrial AOI defect detection are improved, and the quality safety of industrial AOI products is guaranteed.

The invention discloses a remote sensing target detection method based on a target feature enhanced multi-scale fusion network, and the method comprises the steps: constructing a multi-layer feature aggregation module as a main feature extraction module, and better extracting the target features of each category; a multi-channel feature fusion module is constructed, the network layer parameter quantity is reduced, a cross-stage hierarchical structure is adopted to design an MCFCSP module, richer gradient combination and feature expression are realized, and the network feature fusion capability is enhanced; by adopting a top-down and bottom-up feature fusion strategy, information interaction between different levels of features is promoted; fractional Fourier transform convolution is constructed, and parameters are adjusted according to the characteristics of small targets and the change of scenes to adapt to small targets of different types, different sizes and different complexities. The method provided by the invention has the characteristics of high detection precision, low calculation complexity, strong feature representation capability and the like, can effectively improve the detection precision of the small target, and further improves the detection performance of the small target of the remote sensing image.

The invention belongs to the field of medical image processing, and particularly relates to a semi-supervised medical image segmentation method based on single-loop regularization. Comprising the following steps: learning a preprocessed labeled image by adopting a plurality of parallel sub-networks, and calculating supervised loss of a model; single-cycle consistency regularization is adopted to enable the sub-networks to share the learned information, and regularization loss of the model is calculated; selecting a pseudo label of each sub-network by adopting a pseudo label competition mechanism; each sub-network uses a pseudo label to learn the preprocessed unlabeled image, and the unsupervised loss of the model is calculated; calculating the total loss of the model according to the supervised loss, the regularized loss and the unsupervised loss; adjusting model parameters according to the total loss of the model to obtain a trained medical image segmentation model; performing image segmentation by using the trained model; according to the method, related knowledge can be better extracted from the label-free image, the influence caused by noise is avoided, and the accuracy of image segmentation is improved.

The invention belongs to the technical field of electroencephalogram signal detection, and particularly discloses an epilepsy electroencephalogram signal detection system and method based on a diffusive attention model.The system comprises an acquisition unit, a signal processing unit, a signal processing unit and a signal processing unit, the reconstruction unit is configured to be used for inputting the preprocessed electroencephalogram signals into a distraction attention model for denoising and extracting features related to epileptic seizure at the same time; wherein the distraction attention model reconstructs a signal by using a diffusion model through step-by-step denoising, and introduces an adaptive gradient correction term to iteratively optimize the signal; in the reconstruction process of each stage, the extraction of epileptic seizure related features is enhanced through a self-adaptive attention mechanism; and the detection unit is configured to use a classifier to classify the epileptic seizure related features to obtain an epileptic seizure detection result. According to the method, the feature extraction capability of the high-dimensional noise electroencephalogram signals is improved, and the accuracy of epileptic seizure detection is remarkably improved.

The invention discloses a spatial matching method and system based on natural resource monitoring and demographic data, and the method comprises the steps: obtaining residential land and house building data in regional natural resource survey monitoring data, employing a spatial position and attribute matching technology, and combining a random forest algorithm to carry out the spatial matching of the residential land and the house building, thereby achieving the spatial matching of the residential land and the house building. Extracting residential building pattern spots and attribute information thereof; establishing attribute feature mapping between a residential building pattern spot level scale and an administrative division unit scale, and converting administrative division demographic data to residential building pattern spots by using a random forest hyper-parameter search method; further integrating multi-source data in the natural resource survey monitoring data, constructing a population geographic blot index taking a water area as a mask, and correcting the population of the residential building; and finally, calculating a population distribution fitting coefficient, iteratively correcting a population distribution error, and realizing spatial accurate matching of the residential building and population distribution through a partition adjustment strategy.

The invention provides an oat green extract and a preparation method thereof, and relates to the technical field of plant extraction. The extraction method comprises the following steps: taking immature oat plants, cleaning and quickly freezing; mixing with sodium chloride, and crushing to obtain oat sections; mixing the oat sections with an ethanol solution, performing ultrasonic extraction, and performing solid-liquid separation to obtain filtrate; and filtering, purifying and freeze-drying the filtrate to obtain the oat green extract. According to the method, the immature oat plants are adopted as extraction objects, the extraction method suitable for the immature oat plants is researched, the problem of plant waste caused by the fact that oats cannot be mature in special areas is solved, local resources are effectively and reasonably utilized, and the economic value of the oat resources is maximized. According to the extraction process, effective components of immature plants are dissolved into a solvent through low-concentration ethanol, low-temperature ultrasonic and freezing wall breaking technologies, the natural activity of the effective components in the oat is not changed in the whole process, and the nutritional value of the oat green can be reserved to a greater extent.

The invention discloses a wind speed prediction method based on improved ensemble empirical mode decomposition and LSTM model series connection, and the method comprises the steps: adding grid point historical meteorological data into adaptive noise through singular spectrum analysis, carrying out the ensemble empirical mode decomposition, and carrying out the processing of an intrinsic mode function component and a residual error obtained through the decomposition; performing standardization processing on the topographic data, and extracting topographic spatial features through different spatial feature extraction schemes; and constructing the fused features into time sequence format data, inputting the time sequence format data into an LSTM model for prediction, obtaining a predicted intrinsic mode function component and a residual error, adding the intrinsic mode function component and the residual error to generate a short-time wind speed prediction result, comparing the short-time wind speed prediction result with the real-time wind speed data to calculate a model loss function, and training the LSTM model by adopting back propagation iteration to obtain a short-time wind speed prediction result. And performing rolling prediction to obtain a future wind speed prediction result. The prediction result of the method is highly consistent with the observation value in numerical value, and the method also shows high accuracy in trend prediction.

The invention relates to an airport aid-to-navigation light inspection method based on an unmanned aerial vehicle technology, and relates to the technical field of aid-to-navigation light inspection, and the method comprises the following steps: S1, setting standard parameters; s2, the unmanned aerial vehicle executes a flight task, and images are collected from multiple angles; s3, obtaining the mass center of the navigation aid lamp; s4, calculating actual geographic coordinates of the navigation aid lamp; s5, comparing the position coordinate information of the navigation aid lamp; s6, brightness attenuation detection of the navigation aid lamp; and S7, carrying out statistical feedback, and carrying out the step S2. The airport navigational light inspection method has the effects of reducing and improving the airport navigational light inspection cost and improving the airport navigational light inspection efficiency.

The invention discloses a heart disease prediction system based on an electrocardiosignal and a large model, and relates to the field of electrocardiosignal processing, and the system is characterized in that the electrocardiosignal of a user is collected by using a heart coat, and baseline offset suppression and noise processing operation are carried out on the electrocardiosignal by using a data processing center; a variability sequence is extracted from the processed electrocardiosignal, an electrocardiograph scatter diagram is drawn according to variability, and scatter points in the scatter diagram are numbered and coded in a partitioned mode to obtain the sequence information entropy of the heart rate variability sequence; segmenting the electrocardiosignal based on the sequence information entropy and the wave crest, obtaining a waveform segment of a single cardiac pulse according to a segmentation result, inputting the waveform segment into the large medical prediction model, and outputting the characteristic change of the electrocardiosignal; and comparing the feature change with a pre-stored disease feature standard and outputting a disease prediction result. According to the method, the complex characteristics of the electrocardiosignals and the prediction capacity of the large model are combined, and the diagnosis precision and the early-stage discovery rate of heart diseases can be remarkably improved.

The invention belongs to the technical field of deep processing of agricultural products, and provides royal jelly protein zymolyte with melanin inhibition activity and preparation and application of the royal jelly protein zymolyte. Performing enzymolysis on the soluble royal jelly protein solution with pepsin to obtain enzymatic hydrolysate; and carrying out ultrafiltration separation on the enzymatic hydrolysate to obtain a polypeptide solution with the molecular weight of less than 3KDa, namely royal jelly protein hydrolysate. The royal jelly is used as a raw material, the royal jelly protein hydrolysate with low molecular weight is prepared by extracting royal jelly protein and utilizing a protease enzymolysis technology and an ultrafiltration separation technology, and the royal jelly protein hydrolysate has good melanogenesis inhibition activity and can reduce generation of mouse melanoma cells and zebra fish melanin. The inhibitor is derived from natural food royal jelly, is green and safe, is controllable in conditions in the preparation process, is convenient to extract, does not need artificial synthesis, and is expected to be applied to food, medicines or cosmetics with a whitening effect.

The invention relates to an obstacle detection method, system, equipment and medium suitable for a low-speed railway, and belongs to the technical field of rail transit, and the method comprises the following steps: collecting image data and three-dimensional point cloud data of a rail in front of a train through a laser radar and a short-focus camera, and preprocessing the image data to obtain a pre-processed image; the preprocessed image data are transmitted into the trained rail-mounted area segmentation model, and a detected rail-mounted area result is output; mapping the detected image pixel points of the rail-mounted area to three-dimensional point cloud data to obtain a rail-mounted area point cloud; performing preprocessing and point cloud clustering on the point cloud data to detect non-specific obstacles; the three-dimensional space of the rail-mounted area is divided based on the point cloud of the rail-mounted area, foreign matter invasion judgment is conducted on the detected non-specific obstacle point cloud, if invasion occurs, obstacle and alarm information is sent to an automatic train protection system, autonomous obstacle detection of the train is achieved, and therefore the purpose of guaranteeing the operation safety of the train is achieved.

The invention discloses a spoken English man-machine conversation interaction training method and system, and relates to the technical field of spoken English training, spoken English audio signals of a user are monitored in real time through a microphone, and the frequency spectrum information of the audio signals is refined into each frame of spectrogram and cepstrum coefficient feature vectors by using Fourier transform and feature extraction technologies; therefore, the voice signal characteristics of the user can be completely captured; three core dimensions of semantic similarity, grammatical structure similarity and fluency are incorporated into an evaluation model, a comprehensive oral English training evaluation system is formed, a text sequence is generated by analyzing a time sequence dependency relationship through a convolutional neural network, and the oral English training evaluation model of a deep learning technology is combined, so that the oral English training evaluation accuracy is improved. According to the method, the expressions of the user in the aspects of semantics, grammar and fluency can be accurately measured, the oral training level of the user can be comprehensively judged by the system by comparing the comprehensive evaluation coefficient with the preset qualified threshold value, and a personalized learning guide is provided according to a result.

The invention relates to an automobile body-in-white welding process planning method, which comprises the following steps of: performing data acquisition through terminal equipment, collecting welding process data in a welding process, and monitoring the running state of a welding robot in real time; edge computing nodes are arranged on a welding site and are responsible for preprocessing collected welding process data and extracting knowledge in real time; the cloud constructs a welding process knowledge graph according to the existing enterprise historical data and the welding process data extracted by the edge end knowledge; and after the cloud establishes a welding process knowledge graph, optimizing body-in-white welding process parameters and carrying out optimization solution on a body-in-white welding path and a body-in-white welding spot welding sequence on the basis of an improved artificial neural network-based automobile body-in-white welding process planning method. The method can adapt to different welding scenes and requirements, the method can adapt to shapes and materials of different workpieces, and efficient and accurate welding is achieved.

The invention discloses a micro-grid typical scene generation method and system, and the method comprises the steps: forming a plurality of load-photovoltaic output two-dimensional time sequences based on the historical load data and historical photovoltaic output data of a micro-grid, considering multiple types of objects, considering the complex mutual influence relation between photovoltaic output and load, and generating a typical scene of the micro-grid. And the diversity and accuracy of the generated scene are fully improved. According to the method, coding and dimensionality reduction are carried out on the load-photovoltaic two-dimensional output time sequence, two-dimensional deep-level features are extracted, and complex features of load-photovoltaic time sequence data and correlation between the two are fully considered, so that the generated scene is closer to the actual situation, and the accuracy and reliability of the scene are improved.

The invention discloses an ENSO prediction method, system and device based on a space-time fusion neural network, and belongs to the field of deep learning model prediction. The invention designs a time-space fusion Transform network, the network designs a parallel encoder-decoder structure, and the time-space information can be effectively extracted from the ocean surface temperature data and the # imgabs0 # index at the same time, so that the prediction precision of the # imgabs1 # index is improved. Meanwhile, the network extracts global features by using an attention mechanism in an encoder of the network, and establishes a remote dependency relationship on a target. Compared with a comparison method, the method has better prediction capability in multiple prediction advance periods, the problem that an existing ENSO prediction method underestimates the ENSO event amplitude along with the increase of the prediction advance periods is solved, and the ENSO prediction precision is improved.