272results about How to "Strong generalization" patented technology

The invention relates to the technical field of environmental sound event detection, in particular to an environmental sound event detection method based on multi-modal data fusion, which utilizes a microphone array, a camera and a sensor to synchronously acquire audio, video and environmental data to form a multi-modal data source. And the collected multi-modal data is preprocessed, so that the data quality and the accuracy of subsequent analysis are improved. And key features are extracted from the processed data, and the features are fused to form multi-modal features. And a deep learning model is constructed, and multi-modal features are used for training, so that a model capable of identifying an environmental sound event can be obtained. And performing optimization such as pruning, quantification and knowledge distillation on the trained model, and deploying the model on edge equipment to realize real-time preliminary feature extraction and event detection. The problems that an environment sound event detection method in the prior art is poor in robustness, low in real-time performance and limited in generalization ability are solved.

The invention relates to the technical field of software reliability guarantee, in particular to a code vulnerability detection method based on efficient parameter fine tuning of a code pre-training model, which comprises the following steps: preprocessing source codes of a vulnerability data set; s2, converting the preprocessed source code, and extracting a token sequence and a code attribute graph path corresponding to the source code; s3, constructing a code vulnerability detection model, wherein the code vulnerability detection model comprises a semantic feature extractor, a structural feature extractor, a feature fusion layer and a classifier; s4, jointly training a code vulnerability detection model by using the token sequence corresponding to the extracted source code and the code attribute graph path; and S5, through the optimized code vulnerability detection model, outputting a result that whether the source code to be detected has vulnerabilities or not. According to the method, the model is finely adjusted through efficient parameter fine adjustment, training resources are saved, good performance is obtained, and the code vulnerability detection efficiency and accuracy are improved by fusing and learning semantic and structural features of source codes at the same time.

The invention discloses an anomaly detection and repair method for non-Gaussian multi-mode sensor data, and belongs to the technical field of unmanned system multi-source autonomous navigation. The method solves the problems that an existing method is poor in performance when facing non-Gaussian data, anomaly detection is difficult to carry out on high-dimensional unstructured data, the robustness of a static anomaly detection model is insufficient, and redundancy compensation is lacked when abnormal data of a sensor is repaired. The method specifically comprises the following steps: step 1, acquiring IMU, GNSS, point cloud and image data of an unmanned system, and then carrying out preprocessing and time synchronization on the acquired data; step 2, respectively extracting features of IMU, GNSS, point cloud and image data at each acquisition moment after time synchronization; step 3, fusing the data features at each acquisition moment; and 4, performing anomaly detection on the data at each acquisition moment according to a fusion result, and further performing data restoration if the data is detected to be abnormal. The method can be applied to data anomaly detection and repair.

The invention discloses a rainy day target detection method based on paired image data generation and knowledge distillation, and belongs to the technical field of automatic driving target detection. The method comprises the following steps: acquiring a real image of a road scene and a semantic segmentation mask; inputting the semantic segmentation mask and the weather condition text information into a trained improved diffusion model to obtain a road scene generation image under a rainy day condition; introducing a CoT module and an ODConv module into the target detection model for optimization, and then improving the target detection model by adopting a dynamic weighted aggregation loss function to obtain an optimized target detection model; performing knowledge distillation to obtain a rainy day target detection enhancement model; and performing target detection by using the rainy day target detection enhancement model. The method provided by the invention is excellent in performance in a rainy day scene, has good generalization ability, can provide higher-precision target detection in various complex scenes, and effectively improves the detection accuracy and stability.

The invention discloses a novel CAD model feature recognition method based on a graph and a point cloud neural network, and the method comprises the steps: creating a data set containing heterogeneous machining features, converting a B-Rep model into a surface adjacent graph with surface-edge attributes, a surface UV grid, and a surface point cloud input neural network model; the neural network model integrates a graph encoder, a point encoder and a multi-task head, and the graph encoder and the point encoder learn classifiable embedded vectors from shape primitives of different scales of points, edges and surfaces respectively; and the multi-task head converts the embedded vector into corresponding semantic segmentation, instance segmentation and bottom surface segmentation results through three meta-learners. According to the method, insights can be extracted from different representation forms of a CAD model, semantic segmentation, instance segmentation and bottom surface segmentation tasks of heterogeneous processing features are processed in parallel, and experiments prove that Gamp is a Gamp; the PCNet has effectiveness and superiority in non-heterogeneous and heterogeneous processing feature recognition, and has application potential in real industrial scenes.

The invention discloses a short text clustering method and device based on a large language model, and belongs to the technical field of natural language processing, and the method comprises the steps: converting a short text into vector representation, and carrying out the preliminary clustering of the vector representation through a clustering algorithm, and obtaining an initial category; for all the corresponding short texts in each initial category, generating an abstract by using a large language model, generating a plurality of theme titles for summarizing the core meanings of the texts according to the abstract, respectively taking the theme titles as sub-titles, inputting the plurality of sub-titles into the large language model, and carrying out theme combination to obtain a parent title, constructing the parent title and the child titles into a hierarchical theme system; the large language model allocates to-be-classified short texts to one or more categories according to the hierarchical topic system to complete short text clustering; and performing quality evaluation and error pattern analysis on a short text clustering result to optimize a clustering algorithm and a large language model. According to the method, the theme of the short text can be automatically found and classified, and the classification accuracy and efficiency are improved.

The invention relates to the technical field of subgrade settlement prediction, in particular to a subgrade settlement prediction method based on deep learning, electronic equipment and a medium, the subgrade settlement prediction method provided by the invention adopts a subgrade settlement prediction model for prediction, and the model adopts the combination of a convolutional neural network and a bidirectional long-short term memory network. Spatio-temporal features are effectively captured, and the prediction precision and stability of the model are improved; by introducing a channel attention enhancement mechanism module, dynamic weighting is performed on different feature channels, the selection ability of the model to key features is improved, and the sensitivity of the model to subtle changes in data and the capture ability of the model to global features are enhanced; the model is trained through the genetic algorithm, the efficiency is improved, and the genetic algorithm can automatically find an optimal combination in a complex hyper-parameter space, so that the model can show good generalization ability on different roadbed settlement data sets, and the prediction precision of the model is improved.

The invention provides a multi-parameter GNSS-R soil humidity inversion method based on a random forest model. The multi-parameter GNSS-R soil humidity inversion method comprises the following steps: satellite-borne GNSS-R data quality control; satellite-borne GNSS-R data observation quantity extraction and surface reflectance calculation are carried out; eliminating satellite-borne GNSS-R observation data influenced by the open water area; carrying out surface reflectance gridding; preprocessing the SMAP data; constructing an inversion model; and carrying out spaceborne GNSS-R soil humidity inversion and precision evaluation. The method has the beneficial effects that by utilizing the performance advantages of processing a non-linear relationship, good generalization performance, strong robustness and the like of the random forest, after observation data influenced by a water body is accurately eliminated, an inversion model is constructed by combining multi-parameter auxiliary data of a soil humidity active and passive remote sensing satellite; the space-time coverage, the inversion precision and the reliability of soil humidity data are remarkably improved, and powerful data support is provided for the fields of climate forecast, agricultural production, hydrological modeling and the like.

The invention provides a two-stage registration method and device suitable for a full-length image of a lower limb, a terminal and a medium. The method comprises the steps of obtaining a to-be-registered CT image and a label of the lower limb, and a target X-ray image and a label of the lower limb; inputting the to-be-registered CT image and the label, and the target X-ray film image and the label into an affine transformation network to generate an affine transformation matrix for performing rough registration on the to-be-registered CT image; and inputting the CT image and the label output in the coarse registration stage, and the target X-ray film image and the label into a deformation field registration network to generate a deformation field for fine registration based on the coarse registration result of the CT image to be registered. According to the method, the deep learning technology is utilized, a brand-new 2D / 3D medical image registration algorithm is constructed, and full-automatic cross-modal registration of lower limb full-length horizontal position CT and standing position X-ray films is achieved for the first time. The research result of the invention can provide effective assistance for preoperative accurate planning, assist the design work of an HTO operation guide plate, and improve the clinical curative effect of early and middle knee OA.

The invention relates to a lithium ion battery health state estimation method based on an MSCNN, and belongs to the technical field of lithium ion batteries. The method comprises the following steps: performing an aging cycle test on a lithium ion battery monomer, and establishing a working condition test experiment database; collecting voltage, current and temperature data of the battery in each aging cycle, respectively calculating average values, standard deviations, skewness and kurtosis of the voltage, the current and the temperature, taking the average values, the standard deviations, the skewness and the kurtosis as health factors, and screening out the health factors which are highly related to the health state of the battery; constructing an SOH estimation model, and training the model by taking the screened health factors as input; and the model is used for predicting the health state of the lithium ion battery after being trained. The method can effectively extract features from data of different scales, has higher SOH estimation precision compared with a traditional CNN, can perform accurate SOH estimation on data sets of different working conditions, and has good generalization ability.

The invention discloses a microcirculation blood vessel automatic segmentation and quantification method based on enhanced feature fusion. The method comprises the following steps: step 1, data preparation and preprocessing; 2, designing an enhanced feature fusion network model; step 3, automatically segmenting microcirculation blood vessels; and 4, quantifying the diameter of the blood vessel based on the segmentation result. According to the enhanced feature fusion network model provided by the invention, accurate segmentation of microvessels is realized through fusion and enhancement of multi-scale features. The model shows good generalization ability on diversified clinical image data through effective data enhancement, and can adapt to image data with different illumination conditions, contrast ratios and resolutions. Therefore, the model has high practicability and reliability in practical application. According to the method, the diameter of the blood vessel is quantified through the segmentation result, the diameter of the microvessel can be accurately measured, and powerful support is provided for evaluation of the clinical microcirculation function.

The invention discloses a blood vessel segmentation method and device based on large model fine tuning, equipment and a medium, and the method comprises the steps: obtaining a blood vessel image, carrying out the preprocessing of the obtained blood vessel image, and obtaining a training set; performing fine tuning on a pre-trained image segmentation model by adopting the training set, so that the image segmentation model learns related features of blood vessel segmentation; wherein the low-rank adaptive fine tuning technology is adopted to perform fine tuning on the image segmentation model: two parallel low-rank matrixes are inserted into a Transform layer in the image encoder, the input is processed by the two low-rank matrixes in sequence, and the processing result and the original output are added to obtain the final output. According to the method, the defects of a large model in a blood vessel segmentation task are overcome through efficient parameter fine tuning and a multi-scale feature fusion module. Accurate blood vessel segmentation can be realized under limited annotation data, the difficulty and cost of medical image segmentation tasks are greatly reduced, and the method can be widely applied to the technical field of medical image processing.

The invention discloses a method and device for predicting the geological storage amount of carbon dioxide and a medium, and relates to the technical field of carbon dioxide capture, utilization and burying. The method comprises the steps that whether a to-be-predicted oil and gas reservoir and a control oil and gas reservoir are in the same block or not is judged; if yes, inputting the geological data, the production dynamic data and the injection parameter combination scheme of the to-be-predicted oil and gas reservoir into the optimal control oil and gas reservoir carbon dioxide geological sequestration quantity prediction model to determine the whole-area accumulated carbon dioxide geological sequestration quantity of the to-be-predicted oil and gas reservoir; if not, geological data, production data and an injection parameter value range of the to-be-predicted oil and gas reservoir are obtained, migration training is conducted on the optimal control oil and gas reservoir carbon dioxide geological sequestration quantity prediction model, and a to-be-predicted oil and gas reservoir carbon dioxide geological sequestration quantity prediction model is obtained; and determining the whole-area accumulated carbon dioxide geological sequestration amount of the to-be-predicted oil and gas reservoir. According to the invention, the precision and efficiency of carbon dioxide geological sequestration quantity prediction are improved.

The invention discloses a reinforcement learning and graph neural fusion algorithm for effectively solving flexible workshop scheduling, which comprises the following steps of: formalizing an FJSP into an MDP by setting states, actions, state conversion and rewards, and describing a scheduling process as dynamically allocating ready operation to a compatible and idle machine; in a scheduling process, firstly converting a scheduling state into a heterogeneous graph structure; carrying out two-stage embedding by adopting a heterogeneous graph attention network, and extracting features of jobs and machines from a heterogeneous graph for embedding; the decision network generates action probability distribution by using feature embedding, and samples scheduling actions from the action probability distribution; and training the deep reinforcement learning model by using a near-end strategy optimization algorithm. Compared with the traditional PDR and SOTA DRL methods, the algorithm has the advantages that a high-quality solution is obviously realized on two synthetic data sets with different distributions, and the performance and generalization ability are improved. Good generalization ability is also exhibited because the model trains large-scale or out-of-distribution instances on small-scale instances.

The invention belongs to the technical field of network security, and discloses an Internet of Things attack detection method based on deep learning, which eliminates redundant features through feature selection, enhances inter-class difference and intra-class similarity of selected feature subsets, solves the problem of class imbalance in an attack detection data set by utilizing EQLv2, and improves the attack detection efficiency. And meanwhile, constructing a space-time model to extract space-time information of the sample. According to the method, multi-classification performance evaluation is carried out on an Internet of Things attack detection reference data set NSL-KDD and a CIC-IDS-2017, the advantages of the method are verified from five indexes including the accuracy rate, the precision rate, the recall rate, the F1 score and the false alarm rate, and the effectiveness and feasibility of the method are reflected when the method is compared with a plurality of methods.

The invention relates to the technical field of electric power operation and maintenance, and particularly discloses an unmanned aerial vehicle insulator defect identification method based on improved yov8n, and the method comprises the steps: firstly, improving a down-sampling module and feature map processing, enhancing the capability of a model for extracting insulator defect features, and improving the detection accuracy; and secondly, a Focaler-SIoU loss function is introduced, the target positioning performance is optimized, and particularly, the robustness of the model is improved when samples difficult to classify are processed. In addition, the model is lightened through the LAMP algorithm, and the parameters and the calculation amount of the model are reduced, so that the model is more suitable for running on mobile equipment such as an unmanned aerial vehicle and the like. And finally, through training verification and deployment into an unmanned aerial vehicle detection system, real-time and efficient defect identification is realized, so that the problems of low efficiency, poor real-time performance and the like in the prior art are solved, the insulator defect detection precision can be improved, and meanwhile, the complexity and the calculation amount of the model are reduced so as to adapt to the real-time detection requirement of an unmanned aerial vehicle platform.

The invention discloses a coarse-to-fine cross-scale three-dimensional point cloud registration method, and the method comprises the steps: starting from an input source point cloud and a target point cloud, firstly carrying out the down-sampling of point clouds through employing a mode of combining a global voxel structure and local farthest point sampling, and maintaining the isotropy and geometric consistency of the point clouds while simplifying the point clouds; then roughly estimating a scale factor on the sampled point cloud, and transforming the source point cloud; in the coarse registration stage, point cloud coarse registration is carried out by using a guiding type three-point sampling algorithm through feature extraction and matching, and a good initial pose is provided for fine registration while the registration speed is increased; in the fine registration stage, a scale-adaptive nearest point iterative algorithm is used, translation and scaling are jointly optimized after optimal rotation is applied to each iteration, and the registration precision of the algorithm is improved. The method does not need any training process, can effectively process cross-scale point cloud data with different resolutions, and has strong generalization ability.

The invention discloses a general image evaluation method based on a hybrid expert model, which can be applied to various image evaluation scenes to automatically evaluate the quality or aesthetics of images. According to the method, a visual encoder and a text encoder are used for extracting visual and text features of an image respectively, and a quality or aesthetic score is calculated through an adapter. The visual encoder and the text encoder are integrated with a hybrid evaluation expert module, the hybrid evaluation expert module combines a shared evaluation expert and a self-adaptive evaluation expert, the shared evaluation expert is responsible for learning general evaluation knowledge, the self-adaptive evaluation expert dynamically learns specific data sets, expert contribution is adjusted through a router, and labeling deviation in multi-data-set training is effectively managed. Furthermore, a scene-based difference prompt strategy is implemented, the model adaptability is enhanced through a scene specific prompt word, the annotation deviation between data sets is reduced, and the evaluation accuracy is improved. The method not only improves generalization and adaptability of the model, but also optimizes parameter efficiency and training efficiency, and has a wide application prospect.

The invention provides a pathological section image analysis method and device based on online learning, and belongs to the field of computer vision and medical image analysis. The method comprises the following steps: inputting a pathological section image into a current pathological section analysis model to obtain a pathological section lesion segmentation result, identifying the pathological section lesion segmentation result, and selecting an area with a better identification effect from the result with a poor overall identification effect for correction, forming an online learning sample by a local image of the corrected part in the corresponding pathological section image and the corrected segmentation result; performing online learning on the current pathological section analysis model to obtain an updated pathological section analysis model; and performing weighted fusion on the models before and after updating to obtain a new current pathological section analysis model, and further generating a final pathological section lesion segmentation result of the pathological section image. According to the method, feedback and actual data in the using process are utilized, real-time retraining and optimization are carried out on the pathological section analysis model after offline training is completed, and the recognition accuracy and stability are improved.

The invention discloses a clinical prediction method, system and equipment based on electronic health records and a medium, belongs to the technical field of natural language processing, and aims to solve the technical problem of how to individually fill EHR data and improve the clinical prediction precision of the health condition of a patient. According to the technical scheme, the method comprises the following steps: obtaining EHR data: constructing a doctor-seeing sequence matrix and a corresponding missing mask matrix, and obtaining the EHR data of a patient; performing preliminary interpolation and personalized adjustment; randomly generating a mask matrix; feature coding; carrying out PIPER feature fusion: carrying out feature fusion on the time dimension and the feature dimension of the initial feature representation through a time attention mechanism and a variable attention mechanism of a PIPER layer, and generating a patient health representation; pre-training: reconstructing the health representation of the patient, and calculating an error between a reconstruction value and a real observation value through an MIT loss function, so that the interpolation capability of a PIPER layer is optimized; and fine tuning: performing a health state prediction task through a task-specific decoder.

The invention discloses a high-voltage cable outer metal sheath grounding defect on-line monitoring method and monitoring system, which can work under the condition that a cable is not powered off, realizes on-line monitoring, and realizes on-line monitoring through the cooperation of a current sensor, a voltage sensor, a single-chip microcomputer and an upper computer. And the equipment can quickly detect when a fault occurs and is convenient for maintenance workers to timely eliminate obstacles, so that the risk of major electric power accidents is reduced. The algorithm is similar to an improved neural network algorithm and is used for diagnosing the defects of the outer metal sheath of the cable, the weight is obtained through training learning, and finally the defects of the outer metal sheath of the high-voltage cable are determined. The protection content covers each component of the technical scheme, and comprises a monitoring method, a device structure, a sensor technology, a data processing algorithm, a neural network learning algorithm and the like.

The invention belongs to the technical field of network security, and discloses an industrial control network unsupervised anomaly detection method and system based on a space-time codec, and the method comprises the following steps: 1, carrying out the data processing and sample construction of an industrial control network sensor; performing sampling and data processing on the historical sensor original data and the time sequence to obtain a sample sequence; step 2, constructing an unsupervised deep learning model based on a space-time codec and training the unsupervised deep learning model; step 3, sensor data spatio-temporal characteristic analysis, and outputting sensor data in a future predetermined time period as a predicted value; and 4, abnormal alarm: determining a confidence space by combining the predicted value output in the step 3 and the confidence coefficient, and triggering network abnormal alarm when the current actual sensor data exceeds a normal range. According to the invention, the identification rate and generalization of industrial control network anomaly detection are improved.

The invention provides a style alignment image set generation method based on a Diffusion Transform. The style alignment image set generation method based on the Diffusion Transform comprises the following steps of: firstly, generating a style alignment image set; according to the method, firstly, a text encoder is used for converting text prompts into text features, then a model is generated through a customized DiT, and a traditional multi-head self-attention layer is replaced by a style alignment attention layer. The style alignment attention layer uses text features to guide image generation, uses the first generated image as a style reference, and ensures that the styles of the generated images are consistent through an adaptive instance normalization AdaIN and displacement scaling dot product attention mechanism. Finally, according to the method, image sets with consistent styles can be efficiently generated in parallel, and the method is suitable for image generation requirements of different aspect ratios, such as posters and other non-square images.

The invention relates to the technical field of formation control of an air-sea heterogeneous cluster system, and discloses a predefined time formation control method based on a fuzzy neural network, and the method comprises the steps: building kinematics and dynamics models of a six-degree-of-freedom four-rotor unmanned plane and a three-degree-of-freedom unmanned ship; establishing a formation tracking error and a speed tracking error of the air-sea heterogeneous cluster system; constructing a preset performance function, and determining an error conversion function; determining a predefined time virtual control law; establishing a predefined time fuzzy neural network, and determining a distributed predefined time formation controller of the air-sea heterogeneous cluster system in combination with a predefined time virtual control law; and performing distributed predefined time error constraint formation control on the air-sea heterogeneous cluster system according to a distributed predefined time formation controller of the air-sea heterogeneous cluster system. According to the method, the robustness of the air-sea heterogeneous cluster is improved, so that the system can converge within the settable predefined time and does not depend on the initial value of the system.

The invention relates to a tissue pathology image analysis method without manual annotation, and the method comprises the following steps: 1, image preprocessing and image cutting; 2, multi-scale feature extraction; 3, micro-image block unsupervised clustering analysis: randomly selecting image blocks, taking a 128 * 128 region at the upper left corner from each image block, and carrying out the clustering analysis; through variance-based feature selection, UMAP algorithm dimensionality reduction and Leiden community detection algorithm clustering, a clustering category of nodes represented by each micro-graph block is finally obtained; step 4, supervised learning model training and reasoning prediction: dividing a data set into training set image blocks and test set image blocks; supervised learning model training: using an XGBoost algorithm to train a classification model; and 5, analyzing and visualizing a result. According to the method, high-resolution pathological images can be efficiently processed, non-supervision and supervised learning combined classification is carried out on the basis of realizing multi-scale feature extraction, and accurate cellular level region classification prediction, quantification and visualization results are provided.

The invention discloses an escalator fault diagnosis method based on multi-sensor data input. The escalator fault diagnosis method comprises the four steps of escalator original data collection, data preprocessing, fault data set setting, escalator fault recognition and cloud model updating. According to the data preprocessing, escalator signal data are filtered through an improved wavelet threshold noise reduction method; the quality of escalator signal data is improved; the fault data set is set by fusing fault data of all parts and all types of the escalator, full utilization of the fault data of the escalator is achieved, and the richness of fault category signals is improved. According to fault identification, multi-sensor data is input into a CNN-GRU network, and the CNN-GRU network extracts features in the input data and obtains a final identification result. According to cloud model updating, the CNN-GRU model is optimized by using CFOA, a network model with the optimal CNN-GRU is constructed, the recognition precision is high, the generalization performance is good, and the method can be widely applied to the field of escalator fault diagnosis.

The invention discloses a transformer fault diagnosis method based on an adaptive fault attention residual network, and the method comprises the steps: employing an MEMS photoacoustic sensor with a capacitor resonator, analyzing a sound wave signal through a photoacoustic spectrum and a signal processing technology, collecting soluble gas in oil, and forming a parameter sequence; introducing an adaptive activation function and a fault index function; the feature distribution of a source domain and a target domain is adjusted by using an LMMD and a domain discriminator, the data of the source domain and the data of the target domain are from different distributions but share the same label space, and the edge distribution difference of the features and conditions is minimized through the LMMD and the domain discriminator to realize cross-domain invariant feature learning; the performance of the model is optimized by balancing hyper-parameters, and the loss meaning in all aspects is balanced to realize dynamic balance. The method can be effectively applied to the fault diagnosis of the transformer, and the diagnosis accuracy is greatly improved.

The invention discloses an organelle combination phenotype high-throughput drug screening method based on machine learning, and relates to the technical field of drug research and development biology. The method comprises the following steps of: 1, analyzing a cell image by ComOrganNet; step 2, performance evaluation of the ComOrganNet model is carried out; 3, the performance of ComOrganNet in the data set is expanded; step 4, comparing the ComOrganNet with a conventional cell parameter extraction method; 5, verifying the practicability of the ComOrganNet classification model; 6, establishing a natural product library and obtaining an active component screening result; according to the method, cell image analysis and preprocessing are carried out in combination with ComOrganNet, deep learning classification is carried out in combination with OfficientNet V2, higher classification accuracy can be achieved in high-throughput drug screening, particularly, when multi-channel image input is used, the accuracy of a model in a verification set reaches 80%, and the result is remarkably superior to that of single-channel image training.

The present invention relates to the technical field of sleep diagnosis, and in particular to a sleep staging method based on deep learning, the method comprising: collecting a number of target physiological signals, preprocessing each target physiological signal to obtain a number of standard physiological signals; synchronously aligning and integrating each standard physiological signal in turn to obtain a standard sleep data set; determining the actual correlation between each physiological signal to be integrated in the standard sleep data set, and determining an actual signal combination strategy according to the actual correlation; generating an actual sleep data set according to the actual signal combination strategy, and extracting features from the actual sleep data set to generate actual feature parameters; inputting the actual feature parameters into a deep learning model to determine the actual sleep state; analyzing the actual sleep state, and performing corresponding sleep intervention according to the analysis results. The present invention realizes low-cost non-intrusive sleep monitoring, thereby improving people's physical health.

The invention discloses a task description enhanced molecular characterization learning system, belongs to the field of molecular characterization learning in artificial intelligence in the field of computers, and particularly relates to the task description enhanced molecular characterization learning system. The method aims to solve the problems that in the prior art, general molecular characterization is difficult to capture task specific features, generalization performance is insufficient in a labeling data scarcity scene, molecular characterization learning accuracy is low, and interpretability is poor. The system comprises a task description-based multi-regression task data set construction module, a double-tower model construction module, a double-tower model training module and a prediction module. The task description-based multi-regression task data set construction module is used for constructing a task description-based multi-regression task data set; the double-tower model construction module is used for constructing a double-tower model; the double-tower model training module is used for acquiring a trained double-tower model; the prediction module is used for inputting molecules to be tested into the trained double-tower model, and the trained double-tower model outputs task-related molecular characterization.