69results about How to "Solve the scarcity" patented technology

The invention discloses a big data analysis-based early warning method for abnormal emission of pollution facilities. The method comprises the following steps of S1, collecting data and constructing a data set; s2, storing and preprocessing a data set; s3, constructing a space-time propagation network of the external events by using the graph neural network model; s4, modeling and predicting the time sequence features by using a mixed depth generation model; s5, analyzing the causal relationship between the external event and the facility emission behavior through a causal inference model; s6, adopting a Bayesian optimization algorithm based on uncertainty estimation of a strategy to dynamically adjust an emission early warning threshold value; s7, generating a new abnormal emission mode label by using a self-supervised learning model and a few-sample learning technology; and S8, adopting an interpretable artificial intelligence technology to generate an abnormal source tracing report, and providing coping suggestions and action schemes. According to the method, the early warning of the abnormal emission of the pollution facilities is realized by utilizing a cross-time-space event inference and self-supervised learning method.

The invention relates to the technical field of lithium batteries, and discloses a lithium battery life decline quantitative prediction and health state intelligent evaluation method, which comprises the following steps: S1, multi-source data acquisition: arranging strain gauge sensors at battery electrode plates and a shell to acquire stress-strain data, integrating a gas sensor in a battery module to acquire gas data, and calculating the data of the stress-strain data; battery data and environment data are acquired by a high-precision synchronous acquisition system through nanosecond clock signals and are processed and stored, and the data quality is monitored at the same time; s2, data preprocessing: generating an extended data set through data transformation and combination and GAN-based data, and processing abnormal data by using a method based on statistics and machine learning; according to the invention, through multi-source data fusion acquisition, a stress-strain sensor and a plurality of gas sensors are added to monitor the internal mechanical change and gas component concentration of the battery, so that the problem that the accuracy and practicability of the model are greatly reduced due to a traditional method based on an electrochemical model is improved.

The invention belongs to the technical field of biological feature recognition, and relates to a Transform-based gene data mining method, which comprises the following steps of: loading gene expression data from a file, and preprocessing; inputting the data into a designed model for training and evaluation; the designed model comprises a CNN (Convolutional Neural Network) and an improved Transform model; the improved Transform model comprises an encoder and a classifier; the encoder adopts a multi-head self-attention mechanism, a convolutional self-attention mechanism and a feedforward neural network; processing the data by using the trained model, and storing the fusion attention weight obtained by the coding layer in the data processing process; and finally, averaging the fusion attention weights of all batches, calculating the comprehensive attention weight of each gene at different time points, and identifying the most important gene by calculating and analyzing the attention score of each gene. According to the method, the problems of scarcity and imbalance of gene data can be solved, the risk of overfitting is reduced, and the precision of gene data analysis is improved.

The invention provides a low-resource language-oriented large language model training method and device, equipment and a medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring low-resource language data and preprocessing the low-resource language data to obtain low-resource language unsupervised training data; generating a low-resource language vocabulary and performing vocabulary expansion on the existing model; performing unsupervised pre-training on the model after word list expansion according to the low-resource language unsupervised training data in combination with a first low-rank adaptive module; performing instruction fine tuning on the pre-trained model according to the low-resource language instruction fine tuning data set in combination with a second low-rank adaptive module; and respectively inputting a high-resource language supervised corpus into the model subjected to instruction fine tuning and the existing mature model to respectively obtain negative example data and positive example data so as to generate a reinforcement learning low-resource language data set based on model feedback, and carrying out reinforcement learning training on the model subjected to instruction fine tuning in combination with a third low-rank adaptive module.

The invention provides a meta-learning-based continuous casting blank defect classification method, system and equipment. The meta-learning-based continuous casting blank defect classification method comprises the steps of 1, preprocessing an obtained public image classification data set and an obtained continuous casting blank image containing defects; 2, randomly forming a meta-task through meta-learning task allocation on the preprocessed public image classification data set, and inputting the meta-task to a preset image meta-learning classification model to obtain a trained image meta-learning classification model; step 3, performing meta-learning task allocation on the preprocessed continuous casting blank image containing defects to form a meta-task, and performing fine adjustment on the trained image meta-learning classification model by using the obtained meta-task; 4, classifying the defects of the continuous casting blank to be processed by utilizing the final image element learning classification model; according to the method, the problem of dependence on a large amount of labeled data in a traditional defect detection method can be effectively solved, and the classification capability of the model under the condition of few samples can be improved.

The invention provides a vision-based surface defect detection method and detection system, and relates to the technical field of data processing, and the method comprises the steps of data acquisition and processing, data addition, modeling, model training and detection and the like. The system comprises a data acquisition and processing module, a data adding module, a modeling module, a model training module and a detection module, new defect data is generated by adopting a generative adversarial network, a detection model is trained by adopting the new defect data and original historical defect data, and the accuracy of bearing surface defect detection is improved.

The invention relates to a network abnormal behavior detection method based on dynamic data balance and generation, and the method comprises the steps: obtaining original network flow data, inputting the original network flow data into a dynamic abnormal data balance model, and obtaining an enhanced data set; the method comprises the steps of marking original network flow data based on an abnormal data balance model, performing selective undersampling on marked data, adjusting a ratio of normal data to abnormal data, obtaining a balance data set, generating new abnormal data according to the balance data set, and merging the new abnormal data with the balance data set to obtain an enhanced data set; and inputting the enhanced data set into a TimeDiT noise reduction model for denoising to obtain a target data set after noise reduction, inputting the target data set into an LSTM-Transform weighted training model for network abnormal behavior detection, and weighting abnormal data in the target data set in combination with a weighted loss function to obtain a detection result. According to the invention, the network traffic abnormal behavior detection efficiency and accuracy can be improved.

The invention provides a model training method, an industrial internet anomaly detection method and a related device, and relates to the field of industrial internet. The model training method comprises the following steps: acquiring a training sample comprising a plurality of time sequence data samples; inputting the training sample into a domain projection module to perform feature extraction of a unified dimension to obtain a plurality of target features of a target dimension; inputting the plurality of target features into a feature mixing enhancement module for feature mixing enhancement processing to obtain positive features and negative features of a plurality of target dimensions; inputting the target features, the positive features and the negative features into an anomaly detection module for anomaly detection processing to obtain inter-block characterization and intra-block characterization corresponding to each feature, and characterization loss between the inter-block characterization and the intra-block characterization; and adjusting parameters of the anomaly detection model based on a first alignment loss among the plurality of target features, a second alignment loss among the plurality of in-block representations and a target loss determined by the representation loss, and obtaining the anomaly detection model with relatively good generalization ability.

The invention provides a voice synthesis method and device, and relates to the technical field of voice processing, and the method comprises the steps: obtaining a target image and a speaking manuscript, inputting the target image and the speaking manuscript into a pre-trained voice synthesis model, and obtaining a target synthesis voice; wherein the target image comprises a plurality of pieces of visual information, the target synthetic speech comprises a plurality of acoustic features, and one piece of visual information corresponds to at least one acoustic feature; the speech synthesis model is obtained by training based on a multi-modal data set, and the multi-modal data set is obtained by performing modal enhancement on a target data set. According to the method provided by the invention, modal enhancement is performed on the existing voice data set to construct the multi-modal data set, so that the problem of scarcity of the data set is solved; according to the one-to-one correspondence between the visual information in the static image and the acoustic features in the voice audio, based on the voice synthesis model obtained through multi-modal data set training, the synthesized target synthesis voice has a finer-grained voice style.

The invention discloses a protein mutation stability prediction method based on generative adversarial network data generation, and belongs to the technical field of biological information, and the method comprises the following steps: constructing a protein mutation data set; extracting protein features from the Megascall data set and the protein mutation data set; performing five-fold cross validation on the generative adversarial network, and storing a generator G; generating a mutation sample through a generator G; constructing a downstream task network model; optimizing downstream task network model parameters through an adaptive gradient method; calculating evaluation index verification model performance through the verification set; and realizing prediction through a downstream task network model. A protein mutation sample is generated by applying the generative adversarial network, so that the problem of data scarcity in protein stability research is effectively solved; the generative adversarial mechanism is combined with the cyclic consistency loss, so that the high quality of the generated data is ensured, the data set is successfully expanded, and the adaptability of the model to different mutation types is improved.

The invention discloses an end-to-end cervical cell classification integrated framework. The system mainly comprises four modules: an enhancement module for expanding and preprocessing an original data set; the fusion module is used for training an improved primary learner on the data set and fusing, outputting and generating a new data set; the purification module is used for purifying the new data set to obtain an integration result of the primary learner and retaining misclassified samples; and the relearning module is used for carrying out relearning by using a secondary learner and carrying out final classification. In addition, a self-adaptive data enhancement method is provided in the training stage of the primary learner and the secondary learner. According to the method, through stage-by-stage fine-grained optimization, the problems that existing cervical cell data sets are unbalanced in category distribution and rare in number are solved, and meanwhile, the classification precision is remarkably improved by emphatically learning easily-confused image features through an integrated framework. Experiments show that the method can effectively assist in cervical cancer screening, the workload of pathologists is greatly reduced, and the method has good application value and huge social benefits.

The invention discloses a power transmission line lightning classification method, which comprises the following steps: acquiring an original image, and cutting by using a lightning target cutting method to obtain a lightning target image; selecting different background images in the original image, splicing the lightning target image with the different background images, and performing first preprocessing on the spliced image to obtain a background image; modeling the background image by using a Gaussian mixture model to obtain a background model, and calculating the matching degree between each pixel of the background model and each Gaussian model distribution to obtain a foreground; judging the foreground through a threshold cutting method to obtain a lightning region, and performing second preprocessing on the lightning region to obtain a first lightning region; and inputting the first lightning region into a deep learning model for training and classification reasoning to obtain a confidence score, and marking the lightning type and the hazard level according to the confidence score to obtain a lightning classification result, thereby meeting the requirements of power transmission line monitoring safety guarantee.

The invention provides a pedestrian re-identification method based on three-dimensional reconstruction and image generation, and belongs to the technical field of machine vision. According to the invention, pedestrian images in an original pedestrian image set are utilized to generate a corresponding three-dimensional human body model; selecting a specific angle of the three-dimensional human body model to generate a two-dimensional pedestrian rendering graph; generating a virtual pedestrian image in combination with the two-dimensional pedestrian rendering graph and the original pedestrian image; adding the virtual pedestrian image into the original pedestrian image set to construct an enhanced image set; training a pedestrian re-identification model based on the enhanced image set; and inputting a to-be-detected pedestrian image to the trained pedestrian re-identification model to obtain a pedestrian identification result. According to the invention, the original pedestrian image set is enriched by generating images of different angles of portraits in the original pedestrian image set, and the problem of scarcity of pedestrian re-identification data is solved; and the model is trained and updated on the enhanced data set in combination with classification loss and triple loss, so that the model can correctly learn the generated image information, and the pedestrian re-identification precision is improved.

The invention discloses a video-based self-supervised production anomaly detection and progress prediction method, device and equipment. The method comprises the following steps: mapping image features of a production process video to a potential space of a Gaussian mixture model by using an encoder; generating a space activation graph and extracting attention features related to production; reconstructing the image by using a decoder and calculating a space activation reconstruction error; training a model based on a comprehensive loss function; and performing anomaly detection and production stage prediction by using the trained model. According to the method, an auto-encoder process probability embedding technology and a space activation graph are combined, the space-time heterogeneity of the production process is effectively captured, and meanwhile background interference is minimized; abnormality detection and progress prediction tasks are integrated into a unified framework, so that the monitoring accuracy and reliability are improved; and training can be carried out under the condition that only normal production data is used, so that the problem of scarcity of abnormal data is solved, and the adaptability of the model to a complex production environment is enhanced.

The invention discloses a preparation method of dedifferentiated saussurea involucrata cells and anti-wrinkle tightening application of the dedifferentiated saussurea involucrata cells. The preparation method comprises the following specific steps: S1, transferring root tips of aseptic seedlings to an induction culture medium, and proliferating to form cell clusters; culturing the cell cluster in a culture dish containing a proliferation culture medium to obtain primary saussurea involucrata stem cells; s2, transferring the obtained primary saussurea involucrata stem cells into a liquid MS culture medium for suspension culture, and meanwhile, changing the illumination condition, and culturing to obtain the saussurea involucrata stem cells of which the total flavone content and the chlorogenic acid content are obviously increased. According to the method, large-scale production of saussurea involucrata stem cells is realized through a plant cell culture technology, the problem of scarcity of natural resources is solved, and rare and sustainable raw materials are realized; according to the method, unique culture conditions and inducer combination are adopted, so that the activity and the active ingredient content of the saussurea involucrata stem cells are improved, and process innovation is realized; meanwhile, the saussurea involucrata stem cells prepared by the method provide a safe raw material with anti-wrinkle and firming effects for the skin care product industry.

The invention provides a real clutter and wind shear simulation echo data fusion method, and belongs to the technical field of airborne meteorological radars, and the method specifically comprises the steps: building a simulation wind field according with wind shear meteorological characteristics; acquiring different types of clutters by using an airborne radar, and calculating the coordinates of the whole flight path of the aerial carrier relative to the simulated wind field by taking the flight starting point of the aerial carrier as a reference point; inputting the relative path of the aerial carrier, the radar technical parameters and the simulation wind field to echo simulation software, and calculating a simulation echo of the simulation wind field; calculating the gain of each azimuth line of the radar by adopting a system gain or system noise method; superposition of simulation echo data and real clutter data is carried out on each azimuth line and each antenna row; and the fusion effect is measured from the angles of the echo intensity, the wind speed distribution and the distance Doppler graph before and after fusion. Through the processing scheme provided by the invention, fusion of the recorded clutter data and the simulated wind field data can be well completed.

The invention relates to a high-precision steel surface defect detection method suitable for a complex industrial environment, and aims to solve the problems of feature coupling and background interference caused by data scarcity, long tail distribution and multi-defect coexistence. According to the method, a conditional generative adversarial network (CGAN) and a convolutional neural network (CNN) are combined, an SE-Net channel attention mechanism is integrated, and the method is used for automatic detection and classification of multiple defects on the steel surface. By introducing a physical constraint CGAN data generation method, a multi-defect coexistence composite image conforming to industrial reality can be generated, so that the diversity and accuracy of a training data set are effectively enhanced. The model optimizes the expression of defect features through multi-level feature extraction and an attention mechanism, and enhances the distinguishing ability and recognition precision of multiple defects. Experiments show that the method is excellent in performance in a multi-defect identification task, the accuracy rate of 98.89% and the F1 score of 99.72% are achieved, the method is remarkably superior to a traditional detection method and other deep learning models, and the method has high robustness and practical value in a complex industrial environment.

The invention relates to a frequency spectrum recommendation method based on a knowledge graph, and belongs to the field of wireless communication. The method comprises the following steps: S1, defining a knowledge system of a satellite-ground spectrum shared knowledge graph; s2, importing the satellite parameter library and the ground frequency spectrum use condition into a knowledge graph to form a satellite-ground frequency spectrum shared knowledge graph; s3, defining parameters of a Node2vec algorithm, and calculating an embedded vector; s4, carrying out embedded vector PCA dimension reduction; s5, constructing a similarity matrix S among the satellite nodes, wherein the similarity measure is Euclidean distance; s6, screening out node pairs of which the similarity S is greater than 0.9, and writing the node pairs back to the knowledge graph to create a recovery relationship; and S7, updating the knowledge graph and visualizing the recommendation list. According to the method, the frequency spectrum recommendation method is provided based on the knowledge graph and is applied to the satellite-ground integrated system, the satellite-ground frequency spectrum shares the knowledge graph to serve as graph structure input, similar satellites are found, ground frequency bands are recommended for the satellites, and therefore the frequency spectrum resource utilization rate is increased, and the frequency spectrum scarcity problem is solved.

The application discloses a water acoustic signal time-frequency spectrum line spectrum extraction method and system, and belongs to the technical field of signal processing. A noisy time domain signal is generated through simulation, and a mask label of a time-frequency spectrum of the noisy time domain signal belonging to a line spectrum is generated through a soft threshold function; a denoising model is trained according to the time-frequency spectrum and the mask label; a target water acoustic signal is acquired, the time-frequency spectrum of the target water acoustic signal is input into the denoising model, and a mask label corresponding to the time-frequency spectrum input is output through inference; the time-frequency spectrum of the denoised target water acoustic signal is acquired according to the mask label and the time-frequency spectrum; an initial candidate point set of the time-frequency spectrum of the denoised target water acoustic signal is acquired, and an initial candidate point of a current frame time-frequency spectrum in the initial candidate point set is acquired; a correlation cost matrix is constructed, the initial candidate point and a trajectory are correlated and matched with the minimum difference as a target, and a line spectrum of the trajectory and the candidate point dynamic correlation is acquired. The method can balance denoising fidelity, detection accuracy and real-time performance.

This invention belongs to the field of power system risk assessment and control technology, and provides a method for generating extreme weather load scenarios based on a conditional diffusion model. The method includes: acquiring extreme weather load samples, and performing preprocessing, sample expansion, and post-processing on these samples to obtain a normal weather sample set, a boundary weather sample set, and an extreme weather sample set; initially training a pre-constructed conditional diffusion model using the normal weather sample set to obtain first network parameters under normal weather scenarios; fine-tuning the conditional diffusion model sequentially using the boundary weather sample set and the extreme weather sample set based on the first network parameters to obtain second network parameters under extreme weather scenarios; and generating a set of extreme weather load scenarios under target extreme weather conditions using the conditional diffusion model based on the second network parameters. This scheme improves the accuracy and reliability of the extreme weather load scenario generation process.

The application provides a rolling stock running part fault diagnosis model training method, a diagnosis method and equipment, and relates to the technical field of vehicle fault diagnosis. The method comprises the following steps: establishing a coupling system digital twin model corresponding to a rolling stock-track coupling system according to the dynamic parameters of a target rolling stock and the running monitoring data in a normal healthy state; obtaining experimental monitoring data of the target rolling stock in the normal healthy state and a set fault working condition based on a rolling stock rolling-vibration bench experiment, and obtaining simulation monitoring data of the target rolling stock in the set fault working condition based on the twin model; performing sample segmentation and labeling on the experimental monitoring data and the simulation monitoring data respectively, obtaining source domain and auxiliary domain data to generate a combined domain data set, training an initial diagnosis model to obtain a trained domain generalization model as a rolling stock running part fault diagnosis model of the target rolling stock. The application can improve the accuracy and reliability of rolling stock running part fault diagnosis.

The invention discloses a GAN-based high-remanence neodymium-iron-boron component and process optimization method, and relates to the field of high-remanence magnetic material design, and the method comprises the steps: obtaining the input characteristics and target characteristics of a sintered neodymium-iron-boron magnet; constructing a generative adversarial network, introducing a physical constraint term into a generator loss function of the generative adversarial network, carrying out data expansion on the high residual magnetism subset by using the trained generative adversarial network, and carrying out parallel training on a deep learning model and a traditional machine learning model based on the expanded data and the original data to form a hybrid prediction model; and inputting the target magnetic performance into the hybrid prediction model, and performing reverse prediction to obtain a corresponding magnet component and sintering process parameter combination. According to the method, the adversarial network introducing the physical constraint term is utilized to expand the high residual magnetism data, and the multi-dimensional feature analysis and the mixed model training are combined, so that the precise matching of the magnet component-process-magnetic performance is realized, the design accuracy is improved, the research and development period is shortened, and the experiment cost is reduced.

The present invention discloses an abnormal data monitoring method and system based on artificial intelligence, which relates to the field of data monitoring technology. The method generates a standardized feature matrix by real-time monitoring and preprocessing data from different sources, effectively reduces data noise and scale differences between features, and analyzes the deviation of each sample relative to the overall distribution, and combines the critical value of the chi-square distribution table to make abnormal judgments on the samples, thereby ensuring the accuracy of abnormal data detection. Then, artificial intelligence technology is used to enhance the abnormal samples, and by introducing distribution constraints, several groups of supplementary abnormal samples are dynamically generated, while ensuring that the generated samples are close to the real distribution, and then by identifying and screening outliers in the abnormal group, the unreasonable samples introduced by noise or deviation in the enhancement process are further reduced, thereby improving the quality of the abnormal group data.

The invention provides a science and education resource relationship prediction method and system based on large model zero sample prediction, and the method comprises the steps: obtaining unlabeled science and education resource data, dividing the unlabeled science and education resource data into simple samples and difficult samples based on the zero sample prediction and self-inspection of a large model, and forming a few-sample training set; manually marking the training set with few samples; selecting a corresponding large model instruction fine tuning algorithm according to different application scenes, and performing model training on the marked few-sample training set to obtain a trained model; and loading the trained model to perform automatic relation extraction to complete relation prediction. The method comprises the following steps: acquiring unlabeled science and education resource data, and carrying out primary processing on the data by utilizing the zero sample prediction capability of a large model; dependence on a large amount of annotated data in a traditional method is avoided, and effective relation prediction can also be carried out in the science and education field with scarce annotated data.

This application relates to the field of hyperspectral remote sensing application technology, and provides a hyperspectral methane detection method based on spatial-spectral joint analysis. First, a sample dataset is constructed, and simultaneously, a methane detection neural network is built to extract the spatial-spectral features of the methane plume from the sample dataset. Then, a preprocessing module based on fundamental laws is established to form a hard constraint mechanism, outputting standardized spatial-spectral features of the methane plume to obtain a predicted methane concentration distribution map. A physical information penalty term is constructed to form a soft physical constraint, minimizing the error between the predicted methane concentration distribution map and the pseudo-true label, thus incentivizing the network to generate a full-resolution methane concentration distribution map. Through a deeply fused spatial-spectral joint strategy, relying on the synergistic effect of the hard constraint mechanism and the soft physical constraint, effective suppression of background noise can be achieved in complex atmospheric environments and various background interference scenarios, significantly improving the accuracy and reliability of signal detection. The detection efficiency is high, making it suitable for large-scale and efficient processing of massive hyperspectral data.

The invention discloses a cross-receiver radio frequency fingerprint identification method based on feature separation under a small sample condition, relates to the technical field of communication radiation source individual identification, and aims to construct a separation model to perform feature extraction and feature separation on IQ data, separate transmitter features, and identify transmitter categories by using the transmitter features. The separation model comprises a radio frequency fingerprint feature extractor, a transmitter feature extractor, a receiver feature extractor, a transmitter classifier and a receiver classifier. IQ data of different transmitters are respectively collected through different receivers, data enhancement is performed on the collected IQ data, the IQ data after data enhancement is used as a sample, and a separation model is trained by using the sample. According to the invention, the feature separation network is used to decouple transmitter features and receiver features, and radio frequency fingerprint identification across receivers can be realized; and meanwhile, through a data enhancement mode, individual identification under a small sample condition is realized, and the robustness of the identification model under different channel conditions is enhanced.

The present invention discloses the application of H5-Re11 hemagglutinin protein monoclonal antibody and its antigenic epitope, and belongs to the field of biotechnology. The present invention solves the problem that the broad-spectrum vaccine for 2.3.4.4 branch H5 subtype avian influenza virus is relatively scarce. The monoclonal antibodies 2D7 and 3C8 are secreted and produced by hybridoma cell lines with deposit numbers CGMCC No.45926 and CGMCC No.45927, respectively. Sites 131, 136 and 172 of the hemagglutinin protein are key antigenic epitopes recognized by the two monoclonal antibodies. The artificial recombinant vaccine H5-Re11+3 constructed based on the epitope has good immunogenicity, can provide broad-spectrum immune protection for 2.3.4.4 branch H5 subtype avian influenza virus, and has good development and application prospects. The monoclonal antibodies and the epitopes recognized by the present invention have high application value in the field of avian influenza vaccine preparation.

The invention discloses a collaborative lane changing scene extraction and generation method and device based on natural driving data. The method comprises the steps that a lane changing scene is extracted from the natural driving data; wherein the extracted lane changing scene data comprises track data of a lane changing vehicle and surrounding vehicles; screening a collaborative lane changing scene from all the extracted lane changing scenes based on a preset condition; wherein the lane changing vehicles in the collaborative lane changing scene and the vehicles behind the target lane are recorded as collaborative lane changing vehicle groups, and the collaborative lane changing scene data comprises trajectory data of the collaborative lane changing vehicle groups; collaborative driving features are extracted from the trajectory data of each collaborative lane changing vehicle group; training a diffusion model to obtain a collaborative lane changing scene generation model by taking the collaborative driving feature as an input feature and the collaborative lane changing scene data as an output track; and generating a new collaborative lane changing scene by using the collaborative lane changing scene generation model. According to the method, the rare collaborative lane changing driving scene can be efficiently identified and generated from the natural driving track data.

The embodiment of the application discloses a kind of equipment health assessment method and device based on multidimensional data fusion and dynamic weight, it is related to the intelligent monitoring and health assessment technology of equipment complex system in the field of equipment health management, the present application includes: respectively from the regression trend of health parameter with time, the correlation between different health parameters and the angle of health parameter data probability distribution, describe the change with the increase of equipment storage life of health parameter, accurately reflect the difference between health parameter monitoring data and baseline data.Propose storage whole process weight dynamic updating method, scientifically calculate the weight of different health parameters when calculating health index.Thereby effectively solve the problem of health parameter monitoring data scarcity caused by inability to frequently power test during actual storage and use of equipment, improve the evaluation accuracy of equipment health state under the condition of limited monitoring data.

The application discloses a small sample professional data knowledge graph growth method for low resource computing power, uses a full parameter version large model as an initial labeling tool to generate high-quality training data, solves the problems of training data scarcity and poor quality, and trains a lightweight large model based on the training data generated by the full parameter version large model and in combination with a LoRA fine-tuning method, realizes the migration of the extraction capability of the full parameter version large model to the lightweight large model, effectively overcomes the resource bottleneck caused by the full parameter version large model, and significantly reduces the computing resource requirement; meanwhile, aiming at the problem that entity relations are difficult to align, an entity alignment mode based on semantic embedding and large language model auxiliary judgment is provided, the semantic consistency of the knowledge graph is ensured, and the domain knowledge accumulation capability and the updating and expanding quality are improved.